UNSPEC_SBB
UNSPEC_CC_NE
UNSPEC_STC
+ UNSPEC_PUSHFL
+ UNSPEC_POPFL
;; For SSE/MMX support:
UNSPEC_FIX_NOTRUNC
;; For insn_callee_abi:
UNSPEC_CALLEE_ABI
+ ;; For APX PUSH2/POP2 support
+ UNSPEC_APXPUSH2
+ UNSPEC_APXPOP2_LOW
+ UNSPEC_APXPOP2_HIGH
+
+ ;; For APX PPX support
+ UNSPEC_APX_PPX
])
(define_c_enum "unspecv" [
;; For PREFETCHI support
UNSPECV_PREFETCHI
+
+ ;; For USER_MSR support
+ UNSPECV_URDMSR
+ UNSPECV_UWRMSR
])
;; Constants to represent rounding modes in the ROUND instruction
(MASK5_REG 73)
(MASK6_REG 74)
(MASK7_REG 75)
- (FIRST_PSEUDO_REG 76)
+ (R16_REG 76)
+ (R17_REG 77)
+ (R18_REG 78)
+ (R19_REG 79)
+ (R20_REG 80)
+ (R21_REG 81)
+ (R22_REG 82)
+ (R23_REG 83)
+ (R24_REG 84)
+ (R25_REG 85)
+ (R26_REG 86)
+ (R27_REG 87)
+ (R28_REG 88)
+ (R29_REG 89)
+ (R30_REG 90)
+ (R31_REG 91)
+ (FIRST_PSEUDO_REG 92)
])
;; Insn callee abi index.
\f
;; Processor type.
(define_attr "cpu" "none,pentium,pentiumpro,geode,k6,athlon,k8,core2,nehalem,
- atom,slm,glm,haswell,generic,lujiazui,amdfam10,bdver1,
+ atom,slm,glm,haswell,generic,lujiazui,yongfeng,amdfam10,bdver1,
bdver2,bdver3,bdver4,btver2,znver1,znver2,znver3,znver4"
(const (symbol_ref "ix86_schedule")))
(const_string "unknown")]
(const_string "integer")))
+;; Used to control the "enabled" attribute on a per-instruction basis.
+(define_attr "isa" "base,x64,nox64,x64_sse2,x64_sse4,x64_sse4_noavx,
+ x64_avx,x64_avx512bw,x64_avx512dq,aes,apx_ndd,
+ sse_noavx,sse2,sse2_noavx,sse3,sse3_noavx,sse4,sse4_noavx,
+ avx,noavx,avx2,noavx2,bmi,bmi2,fma4,fma,avx512f,avx512f_512,
+ noavx512f,avx512bw,avx512bw_512,noavx512bw,avx512dq,
+ noavx512dq,fma_or_avx512vl,avx512vl,noavx512vl,avxvnni,
+ avx512vnnivl,avx512fp16,avxifma,avx512ifmavl,avxneconvert,
+ avx512bf16vl,vpclmulqdqvl,avx_noavx512f,avx_noavx512vl"
+ (const_string "base"))
+
;; The (bounding maximum) length of an instruction immediate.
(define_attr "length_immediate" ""
(cond [(eq_attr "type" "incdec,setcc,icmov,str,lea,other,multi,idiv,leave,
bitmanip,imulx,msklog,mskmov")
(const_int 0)
+ (ior (eq_attr "type" "sse4arg")
+ (eq_attr "isa" "fma4"))
+ (const_int 1)
(eq_attr "unit" "i387,sse,mmx")
(const_int 0)
(eq_attr "type" "alu,alu1,negnot,imovx,ishift,ishiftx,ishift1,
(const_int 0)))
;; There are also additional prefixes in 3DNOW, SSSE3.
-;; ssemuladd,sse4arg default to 0f24/0f25 and DREX byte,
-;; sseiadd1,ssecvt1 to 0f7a with no DREX byte.
;; 3DNOW has 0f0f prefix, SSSE3 and SSE4_{1,2} 0f38/0f3a.
+;; While generally inapplicable to VEX/XOP/EVEX encodings, "length_vex" uses
+;; the attribute evaluating to zero to know that VEX2 encoding may be usable.
(define_attr "prefix_extra" ""
- (cond [(eq_attr "type" "ssemuladd,sse4arg")
- (const_int 2)
- (eq_attr "type" "sseiadd1,ssecvt1")
+ (cond [(eq_attr "type" "ssemuladd,sse4arg,sseiadd1,ssecvt1")
(const_int 1)
]
(const_int 0)))
(const_string "vex")
(eq_attr "mode" "XI,V16SF,V8DF")
(const_string "evex")
+ (eq_attr "type" "ssemuladd")
+ (if_then_else (eq_attr "isa" "fma4")
+ (const_string "vex")
+ (const_string "maybe_evex"))
+ (eq_attr "type" "sse4arg")
+ (const_string "vex")
]
(const_string "orig")))
;; Define attribute to indicate unaligned ssemov insns
(define_attr "movu" "0,1" (const_string "0"))
-;; Used to control the "enabled" attribute on a per-instruction basis.
-(define_attr "isa" "base,x64,nox64,x64_sse2,x64_sse4,x64_sse4_noavx,
- x64_avx,x64_avx512bw,x64_avx512dq,aes,
- sse_noavx,sse2,sse2_noavx,sse3,sse3_noavx,sse4,sse4_noavx,
- avx,noavx,avx2,noavx2,bmi,bmi2,fma4,fma,avx512f,noavx512f,
- avx512bw,noavx512bw,avx512dq,noavx512dq,fma_or_avx512vl,
- avx512vl,noavx512vl,avxvnni,avx512vnnivl,avx512fp16,avxifma,
- avx512ifmavl,avxneconvert,avx512bf16vl,vpclmulqdqvl"
- (const_string "base"))
+;; Define attribute to limit memory address register set.
+(define_attr "addr" "gpr8,gpr16,gpr32" (const_string "gpr32"))
;; Define instruction set of MMX instructions
(define_attr "mmx_isa" "base,native,sse,sse_noavx,avx"
(eq_attr "isa" "sse4_noavx")
(symbol_ref "TARGET_SSE4_1 && !TARGET_AVX")
(eq_attr "isa" "avx") (symbol_ref "TARGET_AVX")
+ (eq_attr "isa" "avx_noavx512f")
+ (symbol_ref "TARGET_AVX && !TARGET_AVX512F")
+ (eq_attr "isa" "avx_noavx512vl")
+ (symbol_ref "TARGET_AVX && !TARGET_AVX512VL")
(eq_attr "isa" "noavx") (symbol_ref "!TARGET_AVX")
(eq_attr "isa" "avx2") (symbol_ref "TARGET_AVX2")
(eq_attr "isa" "noavx2") (symbol_ref "!TARGET_AVX2")
(eq_attr "isa" "fma_or_avx512vl")
(symbol_ref "TARGET_FMA || TARGET_AVX512VL")
(eq_attr "isa" "avx512f") (symbol_ref "TARGET_AVX512F")
+ (eq_attr "isa" "avx512f_512")
+ (symbol_ref "TARGET_AVX512F && TARGET_EVEX512")
(eq_attr "isa" "noavx512f") (symbol_ref "!TARGET_AVX512F")
(eq_attr "isa" "avx512bw") (symbol_ref "TARGET_AVX512BW")
+ (eq_attr "isa" "avx512bw_512")
+ (symbol_ref "TARGET_AVX512BW && TARGET_EVEX512")
(eq_attr "isa" "noavx512bw") (symbol_ref "!TARGET_AVX512BW")
(eq_attr "isa" "avx512dq") (symbol_ref "TARGET_AVX512DQ")
(eq_attr "isa" "noavx512dq") (symbol_ref "!TARGET_AVX512DQ")
(symbol_ref "TARGET_AVX512BF16 && TARGET_AVX512VL")
(eq_attr "isa" "vpclmulqdqvl")
(symbol_ref "TARGET_VPCLMULQDQ && TARGET_AVX512VL")
+ (eq_attr "isa" "apx_ndd")
+ (symbol_ref "TARGET_APX_NDD")
(eq_attr "mmx_isa" "native")
(symbol_ref "!TARGET_MMX_WITH_SSE")
(set_attr "type" "multi")])
(define_code_iterator plusminus [plus minus])
+(define_code_iterator plusminusmult [plus minus mult])
(define_code_iterator plusminusmultdiv [plus minus mult div])
(define_code_iterator sat_plusminus [ss_plus us_plus ss_minus us_minus])
(define_code_iterator any_shift [ashift lshiftrt ashiftrt])
;; Base name for insn mnemonic.
-(define_code_attr shift [(ashift "sll") (lshiftrt "shr") (ashiftrt "sar")])
+(define_code_attr shift [(ashift "sal") (lshiftrt "shr") (ashiftrt "sar")])
(define_code_attr vshift [(ashift "sll") (lshiftrt "srl") (ashiftrt "sra")])
;; Mapping of rotate operators
(include "core2.md")
(include "haswell.md")
(include "lujiazui.md")
+(include "yongfeng.md")
\f
;; Operand and operator predicates and constraints
DONE;
})
+(define_expand "cbranchxi4"
+ [(set (reg:CC FLAGS_REG)
+ (compare:CC (match_operand:XI 1 "nonimmediate_operand")
+ (match_operand:XI 2 "nonimmediate_operand")))
+ (set (pc) (if_then_else
+ (match_operator 0 "bt_comparison_operator"
+ [(reg:CC FLAGS_REG) (const_int 0)])
+ (label_ref (match_operand 3))
+ (pc)))]
+ "TARGET_AVX512F && TARGET_EVEX512 && !TARGET_PREFER_AVX256"
+{
+ ix86_expand_branch (GET_CODE (operands[0]),
+ operands[1], operands[2], operands[3]);
+ DONE;
+})
+
(define_expand "cstore<mode>4"
[(set (reg:CC FLAGS_REG)
(compare:CC (match_operand:SDWIM 2 "nonimmediate_operand")
[(set_attr "type" "icmp")
(set_attr "mode" "<MODE>")])
-(define_insn "*cmpqi_ext<mode>_1_mem_rex64"
- [(set (reg FLAGS_REG)
- (compare
- (match_operand:QI 0 "norex_memory_operand" "Bn")
- (subreg:QI
- (match_operator:SWI248 2 "extract_operator"
- [(match_operand 1 "int248_register_operand" "Q")
- (const_int 8)
- (const_int 8)]) 0)))]
- "TARGET_64BIT && reload_completed
- && ix86_match_ccmode (insn, CCmode)"
- "cmp{b}\t{%h1, %0|%0, %h1}"
- [(set_attr "type" "icmp")
- (set_attr "mode" "QI")])
-
(define_insn "*cmpqi_ext<mode>_1"
[(set (reg FLAGS_REG)
(compare
- (match_operand:QI 0 "nonimmediate_operand" "QBc,m")
+ (match_operand:QI 0 "nonimmediate_operand" "QBn")
(subreg:QI
(match_operator:SWI248 2 "extract_operator"
- [(match_operand 1 "int248_register_operand" "Q,Q")
+ [(match_operand 1 "int248_register_operand" "Q")
(const_int 8)
(const_int 8)]) 0)))]
"ix86_match_ccmode (insn, CCmode)"
"cmp{b}\t{%h1, %0|%0, %h1}"
- [(set_attr "isa" "*,nox64")
+ [(set_attr "addr" "gpr8")
(set_attr "type" "icmp")
(set_attr "mode" "QI")])
-(define_peephole2
- [(set (match_operand:QI 0 "register_operand")
- (match_operand:QI 1 "norex_memory_operand"))
- (set (match_operand 3 "flags_reg_operand")
- (match_operator 4 "compare_operator"
- [(match_dup 0)
- (subreg:QI
- (match_operator:SWI248 5 "extract_operator"
- [(match_operand 2 "int248_register_operand")
- (const_int 8)
- (const_int 8)]) 0)]))]
- "TARGET_64BIT
- && peep2_reg_dead_p (2, operands[0])"
- [(set (match_dup 3)
- (match_op_dup 4
- [(match_dup 1)
- (subreg:QI
- (match_op_dup 5
- [(match_dup 2)
- (const_int 8)
- (const_int 8)]) 0)]))])
-
(define_insn "*cmpqi_ext<mode>_2"
[(set (reg FLAGS_REG)
(compare
(const_int 8)) 0)
(match_operand:QI 1 "const_int_operand")))])
-(define_insn "*cmpqi_ext<mode>_3_mem_rex64"
- [(set (reg FLAGS_REG)
- (compare
- (subreg:QI
- (match_operator:SWI248 2 "extract_operator"
- [(match_operand 0 "int248_register_operand" "Q")
- (const_int 8)
- (const_int 8)]) 0)
- (match_operand:QI 1 "norex_memory_operand" "Bn")))]
- "TARGET_64BIT && reload_completed
- && ix86_match_ccmode (insn, CCmode)"
- "cmp{b}\t{%1, %h0|%h0, %1}"
- [(set_attr "type" "icmp")
- (set_attr "mode" "QI")])
-
(define_insn "*cmpqi_ext<mode>_3"
[(set (reg FLAGS_REG)
(compare
(subreg:QI
(match_operator:SWI248 2 "extract_operator"
- [(match_operand 0 "int248_register_operand" "Q,Q")
+ [(match_operand 0 "int248_register_operand" "Q")
(const_int 8)
(const_int 8)]) 0)
- (match_operand:QI 1 "general_operand" "QnBc,m")))]
+ (match_operand:QI 1 "general_operand" "QnBn")))]
"ix86_match_ccmode (insn, CCmode)"
"cmp{b}\t{%1, %h0|%h0, %1}"
- [(set_attr "isa" "*,nox64")
+ [(set_attr "addr" "gpr8")
(set_attr "type" "icmp")
(set_attr "mode" "QI")])
-(define_peephole2
- [(set (match_operand:QI 0 "register_operand")
- (match_operand:QI 1 "norex_memory_operand"))
- (set (match_operand 3 "flags_reg_operand")
- (match_operator 4 "compare_operator"
- [(subreg:QI
- (match_operator:SWI248 5 "extract_operator"
- [(match_operand 2 "int248_register_operand")
- (const_int 8)
- (const_int 8)]) 0)
- (match_dup 0)]))]
- "TARGET_64BIT
- && peep2_reg_dead_p (2, operands[0])"
- [(set (match_dup 3)
- (match_op_dup 4
- [(subreg:QI
- (match_op_dup 5
- [(match_dup 2)
- (const_int 8)
- (const_int 8)]) 0)
- (match_dup 1)]))])
-
(define_insn "*cmpqi_ext<mode>_4"
[(set (reg FLAGS_REG)
(compare
[(set_attr "type" "pop")
(set_attr "mode" "<MODE>")])
-(define_insn "*pushfl<mode>2"
+(define_insn "@pushfl<mode>2"
[(set (match_operand:W 0 "push_operand" "=<")
- (match_operand:W 1 "flags_reg_operand"))]
+ (unspec:W [(match_operand:CC 1 "flags_reg_operand")]
+ UNSPEC_PUSHFL))]
""
"pushf{<imodesuffix>}"
[(set_attr "type" "push")
(set_attr "mode" "<MODE>")])
-(define_insn "*popfl<mode>1"
- [(set (match_operand:W 0 "flags_reg_operand")
- (match_operand:W 1 "pop_operand" ">"))]
+(define_insn "@popfl<mode>1"
+ [(set (match_operand:CC 0 "flags_reg_operand")
+ (unspec:CC [(match_operand:W 1 "pop_operand" ">")]
+ UNSPEC_POPFL))]
""
"popf{<imodesuffix>}"
[(set_attr "type" "pop")
(define_expand "movxi"
[(set (match_operand:XI 0 "nonimmediate_operand")
(match_operand:XI 1 "general_operand"))]
- "TARGET_AVX512F"
+ "TARGET_AVX512F && TARGET_EVEX512"
"ix86_expand_vector_move (XImode, operands); DONE;")
(define_expand "movoi"
(define_insn "*movxi_internal_avx512f"
[(set (match_operand:XI 0 "nonimmediate_operand" "=v,v ,v ,m")
(match_operand:XI 1 "nonimmediate_or_sse_const_operand" " C,BC,vm,v"))]
- "TARGET_AVX512F
+ "TARGET_AVX512F && TARGET_EVEX512
&& (register_operand (operands[0], XImode)
|| register_operand (operands[1], XImode))"
{
(set_attr "mode" "OI")])
(define_insn "*movti_internal"
- [(set (match_operand:TI 0 "nonimmediate_operand" "=!r ,o ,v,v ,v ,m,?r,?Yd")
- (match_operand:TI 1 "general_operand" "riFo,re,C,BC,vm,v,Yd,r"))]
+ [(set (match_operand:TI 0 "nonimmediate_operand" "=!r ,o ,v,v ,v ,m,?jc,?Yd")
+ (match_operand:TI 1 "general_operand" "riFo,re,C,BC,vm,v,Yd,jc"))]
"(TARGET_64BIT
&& !(MEM_P (operands[0]) && MEM_P (operands[1])))
|| (TARGET_SSE
(define_insn "*movdi_internal"
[(set (match_operand:DI 0 "nonimmediate_operand"
- "=r ,o ,r,r ,r,m ,*y,*y,?*y,?m,?r,?*y,?v,?v,?v,m ,m,?r ,?*Yd,?r,?v,?*y,?*x,*k,*k ,*r,*m,*k")
+ "=r ,o ,r,r ,r,m ,*y,*y,?*y,?m,?r,?*y,?Yv,?v,?v,m ,m,?jc,?*Yd,?r,?v,?*y,?*x,*k,*k ,*r,*m,*k")
(match_operand:DI 1 "general_operand"
- "riFo,riF,Z,rem,i,re,C ,*y,Bk ,*y,*y,r ,C ,?v,Bk,?v,v,*Yd,r ,?v,r ,*x ,*y ,*r,*kBk,*k,*k,CBC"))]
+ "riFo,riF,Z,rem,i,re,C ,*y,Bk ,*y,*y,r ,C ,?v,Bk,?v,v,*Yd,jc ,?v,r ,*x ,*y ,*r,*kBk,*k,*k,CBC"))]
"!(MEM_P (operands[0]) && MEM_P (operands[1]))
&& ix86_hardreg_mov_ok (operands[0], operands[1])"
{
(set (attr "mode")
(cond [(eq_attr "alternative" "2")
(const_string "SI")
- (eq_attr "alternative" "12,13")
+ (eq_attr "alternative" "12")
(cond [(match_test "TARGET_AVX")
(const_string "TI")
(ior (not (match_test "TARGET_SSE2"))
(const_string "V4SF")
]
(const_string "TI"))
+ (eq_attr "alternative" "13")
+ (cond [(match_test "TARGET_AVX512VL")
+ (const_string "TI")
+ (match_test "TARGET_AVX512F")
+ (const_string "DF")
+ (match_test "TARGET_AVX")
+ (const_string "TI")
+ (ior (not (match_test "TARGET_SSE2"))
+ (match_test "optimize_function_for_size_p (cfun)"))
+ (const_string "V4SF")
+ ]
+ (const_string "TI"))
(and (eq_attr "alternative" "14,15,16")
(not (match_test "TARGET_SSE2")))
(clobber (reg:CC FLAGS_REG))])]
{
int shift = ctz_hwi (UINTVAL (operands[1]));
- operands[1] = gen_int_mode (UINTVAL (operands[1]) >> shift, DImode);
+ rtx op1 = gen_int_mode (UINTVAL (operands[1]) >> shift, DImode);
+ if (ix86_endbr_immediate_operand (op1, VOIDmode))
+ FAIL;
+ operands[1] = op1;
operands[2] = gen_int_mode (shift, QImode);
})
(define_insn "*movsi_internal"
[(set (match_operand:SI 0 "nonimmediate_operand"
- "=r,m ,*y,*y,?*y,?m,?r,?*y,?v,?v,?v,m ,?r,?v,*k,*k ,*rm,*k")
+ "=r,m ,*y,*y,?*y,?m,?r,?*y,?Yv,?v,?v,m ,?r,?v,*k,*k ,*rm,*k")
(match_operand:SI 1 "general_operand"
- "g ,re,C ,*y,Bk ,*y,*y,r ,C ,?v,Bk,?v,?v,r ,*r,*kBk,*k ,CBC"))]
+ "g ,re,C ,*y,Bk ,*y,*y,r ,C ,?v,Bk,?v,?v,r ,*r,*kBk,*k ,CBC"))]
"!(MEM_P (operands[0]) && MEM_P (operands[1]))
&& ix86_hardreg_mov_ok (operands[0], operands[1])"
{
(set (attr "mode")
(cond [(eq_attr "alternative" "2,3")
(const_string "DI")
- (eq_attr "alternative" "8,9")
+ (eq_attr "alternative" "8")
(cond [(match_test "TARGET_AVX")
(const_string "TI")
(ior (not (match_test "TARGET_SSE2"))
(const_string "V4SF")
]
(const_string "TI"))
+ (eq_attr "alternative" "9")
+ (cond [(match_test "TARGET_AVX512VL")
+ (const_string "TI")
+ (match_test "TARGET_AVX512F")
+ (const_string "SF")
+ (match_test "TARGET_AVX")
+ (const_string "TI")
+ (ior (not (match_test "TARGET_SSE2"))
+ (match_test "optimize_function_for_size_p (cfun)"))
+ (const_string "V4SF")
+ ]
+ (const_string "TI"))
(and (eq_attr "alternative" "10,11")
(not (match_test "TARGET_SSE2")))
(define_insn "*movhi_internal"
[(set (match_operand:HI 0 "nonimmediate_operand"
- "=r,r,r,m ,*k,*k ,r ,m ,*k ,?r,?*v,*v,*v,*v,m")
+ "=r,r,r,m ,*k,*k ,r ,m ,*k ,?r,?*v,*Yv,*v,*v,jm,m")
(match_operand:HI 1 "general_operand"
- "r ,n,m,rn,r ,*km,*k,*k,CBC,*v,r ,C ,*v,m ,*v"))]
+ "r ,n,m,rn,r ,*km,*k,*k,CBC,*v,r ,C ,*v,m ,*x,*v"))]
"!(MEM_P (operands[0]) && MEM_P (operands[1]))
&& ix86_hardreg_mov_ok (operands[0], operands[1])"
{
(cond [(eq_attr "alternative" "9,10,11,12,13")
(const_string "sse2")
(eq_attr "alternative" "14")
- (const_string "sse4")
+ (const_string "sse4_noavx")
+ (eq_attr "alternative" "15")
+ (const_string "avx")
]
(const_string "*")))
+ (set (attr "addr")
+ (if_then_else (eq_attr "alternative" "14")
+ (const_string "gpr16")
+ (const_string "*")))
(set (attr "type")
(cond [(eq_attr "alternative" "4,5,6,7")
(const_string "mskmov")
(eq_attr "alternative" "8")
(const_string "msklog")
- (eq_attr "alternative" "13,14")
+ (eq_attr "alternative" "13,14,15")
(if_then_else (match_test "TARGET_AVX512FP16")
(const_string "ssemov")
(const_string "sselog1"))
(set (attr "prefix")
(cond [(eq_attr "alternative" "4,5,6,7,8")
(const_string "vex")
- (eq_attr "alternative" "9,10,11,12,13,14")
+ (eq_attr "alternative" "9,10,11,12,13,14,15")
(const_string "maybe_evex")
]
(const_string "orig")))
(if_then_else (match_test "TARGET_AVX512FP16")
(const_string "HI")
(const_string "SI"))
- (eq_attr "alternative" "13,14")
+ (eq_attr "alternative" "13,14,15")
(if_then_else (match_test "TARGET_AVX512FP16")
(const_string "HI")
(const_string "TI"))
]
(const_string "TI"))
(eq_attr "alternative" "12")
- (cond [(match_test "TARGET_AVX512FP16")
+ (cond [(match_test "TARGET_AVX512VL")
+ (const_string "TI")
+ (match_test "TARGET_AVX512FP16")
(const_string "HF")
+ (match_test "TARGET_AVX512F")
+ (const_string "SF")
(match_test "TARGET_AVX")
(const_string "TI")
(ior (not (match_test "TARGET_SSE2"))
(set_attr "mode" "<MODE>")
(set_attr "length_immediate" "0")])
+(define_insn "*movstrictqi_ext<mode>_1"
+ [(set (strict_low_part
+ (match_operand:QI 0 "register_operand" "+Q"))
+ (subreg:QI
+ (match_operator:SWI248 2 "extract_operator"
+ [(match_operand 1 "int248_register_operand" "Q")
+ (const_int 8)
+ (const_int 8)]) 0))]
+ "!TARGET_PARTIAL_REG_STALL || optimize_function_for_size_p (cfun)"
+ "mov{b}\t{%h1, %0|%0, %h1}"
+ [(set_attr "type" "imov")
+ (set_attr "mode" "QI")])
+
(define_expand "extv<mode>"
[(set (match_operand:SWI24 0 "register_operand")
(sign_extract:SWI24 (match_operand:SWI24 1 "register_operand")
- (match_operand:SI 2 "const_int_operand")
- (match_operand:SI 3 "const_int_operand")))]
+ (match_operand:QI 2 "const_int_operand")
+ (match_operand:QI 3 "const_int_operand")))]
""
{
/* Handle extractions from %ah et al. */
[(set_attr "type" "imovx")
(set_attr "mode" "SI")])
+;; Split sign-extension of single least significant bit as and x,$1;neg x
+(define_insn_and_split "*extv<mode>_1_0"
+ [(set (match_operand:SWI48 0 "register_operand" "=r")
+ (sign_extract:SWI48 (match_operand:SWI48 1 "register_operand" "0")
+ (const_int 1)
+ (const_int 0)))
+ (clobber (reg:CC FLAGS_REG))]
+ ""
+ "#"
+ ""
+ [(parallel [(set (match_dup 0) (and:SWI48 (match_dup 1) (const_int 1)))
+ (clobber (reg:CC FLAGS_REG))])
+ (parallel [(set (match_dup 0) (neg:SWI48 (match_dup 0)))
+ (clobber (reg:CC FLAGS_REG))])])
+
(define_expand "extzv<mode>"
[(set (match_operand:SWI248 0 "register_operand")
(zero_extract:SWI248 (match_operand:SWI248 1 "register_operand")
- (match_operand:SI 2 "const_int_operand")
- (match_operand:SI 3 "const_int_operand")))]
+ (match_operand:QI 2 "const_int_operand")
+ (match_operand:QI 3 "const_int_operand")))]
""
{
if (ix86_expand_pextr (operands))
[(set_attr "type" "imovx")
(set_attr "mode" "SI")])
-(define_insn "*extzvqi_mem_rex64"
- [(set (match_operand:QI 0 "norex_memory_operand" "=Bn")
- (subreg:QI
- (match_operator:SWI248 2 "extract_operator"
- [(match_operand 1 "int248_register_operand" "Q")
- (const_int 8)
- (const_int 8)]) 0))]
- "TARGET_64BIT && reload_completed"
- "mov{b}\t{%h1, %0|%0, %h1}"
- [(set_attr "type" "imov")
- (set_attr "mode" "QI")])
-
(define_insn "*extzvqi"
- [(set (match_operand:QI 0 "nonimmediate_operand" "=QBc,?R,m")
+ [(set (match_operand:QI 0 "nonimmediate_operand" "=QBn,?R")
(subreg:QI
(match_operator:SWI248 2 "extract_operator"
- [(match_operand 1 "int248_register_operand" "Q,Q,Q")
+ [(match_operand 1 "int248_register_operand" "Q,Q")
(const_int 8)
(const_int 8)]) 0))]
""
return "mov{b}\t{%h1, %0|%0, %h1}";
}
}
- [(set_attr "isa" "*,*,nox64")
+ [(set_attr "addr" "gpr8,*")
(set (attr "type")
(if_then_else (and (match_operand:QI 0 "register_operand")
(ior (not (match_operand:QI 0 "QIreg_operand"))
(const_string "SI")
(const_string "QI")))])
-(define_peephole2
- [(set (match_operand:QI 0 "register_operand")
- (subreg:QI
- (match_operator:SWI248 3 "extract_operator"
- [(match_operand 1 "int248_register_operand")
- (const_int 8)
- (const_int 8)]) 0))
- (set (match_operand:QI 2 "norex_memory_operand") (match_dup 0))]
- "TARGET_64BIT
- && peep2_reg_dead_p (2, operands[0])"
- [(set (match_dup 2)
- (subreg:QI
- (match_op_dup 3
- [(match_dup 1)
- (const_int 8)
- (const_int 8)]) 0))])
-
(define_expand "insv<mode>"
[(set (zero_extract:SWI248 (match_operand:SWI248 0 "register_operand")
- (match_operand:SI 1 "const_int_operand")
- (match_operand:SI 2 "const_int_operand"))
+ (match_operand:QI 1 "const_int_operand")
+ (match_operand:QI 2 "const_int_operand"))
(match_operand:SWI248 3 "register_operand"))]
""
{
DONE;
})
-(define_insn "*insvqi_1_mem_rex64"
- [(set (zero_extract:SWI248
- (match_operand 0 "int248_register_operand" "+Q")
- (const_int 8)
- (const_int 8))
- (subreg:SWI248
- (match_operand:QI 1 "norex_memory_operand" "Bn") 0))]
- "TARGET_64BIT && reload_completed"
- "mov{b}\t{%1, %h0|%h0, %1}"
- [(set_attr "type" "imov")
- (set_attr "mode" "QI")])
-
(define_insn "@insv<mode>_1"
[(set (zero_extract:SWI248
- (match_operand 0 "int248_register_operand" "+Q,Q")
+ (match_operand 0 "int248_register_operand" "+Q")
(const_int 8)
(const_int 8))
- (match_operand:SWI248 1 "general_operand" "QnBc,m"))]
+ (match_operand:SWI248 1 "general_operand" "QnBn"))]
""
{
if (CONST_INT_P (operands[1]))
operands[1] = gen_int_mode (INTVAL (operands[1]), QImode);
return "mov{b}\t{%b1, %h0|%h0, %b1}";
}
- [(set_attr "isa" "*,nox64")
+ [(set_attr "addr" "gpr8")
(set_attr "type" "imov")
(set_attr "mode" "QI")])
(define_insn "*insvqi_1"
[(set (zero_extract:SWI248
- (match_operand 0 "int248_register_operand" "+Q,Q")
+ (match_operand 0 "int248_register_operand" "+Q")
(const_int 8)
(const_int 8))
(subreg:SWI248
- (match_operand:QI 1 "general_operand" "QnBc,m") 0))]
+ (match_operand:QI 1 "general_operand" "QnBn") 0))]
""
"mov{b}\t{%1, %h0|%h0, %1}"
- [(set_attr "isa" "*,nox64")
+ [(set_attr "addr" "gpr8")
(set_attr "type" "imov")
(set_attr "mode" "QI")])
-(define_peephole2
- [(set (match_operand:QI 0 "register_operand")
- (match_operand:QI 1 "norex_memory_operand"))
- (set (zero_extract:SWI248 (match_operand 2 "int248_register_operand")
- (const_int 8)
- (const_int 8))
- (subreg:SWI248 (match_dup 0) 0))]
- "TARGET_64BIT
- && peep2_reg_dead_p (2, operands[0])"
- [(set (zero_extract:SWI248 (match_dup 2)
- (const_int 8)
- (const_int 8))
- (subreg:SWI248 (match_dup 1) 0))])
-
;; Eliminate redundant insv, e.g. xorl %eax,%eax; movb $0, %ah
(define_peephole2
[(parallel [(set (match_operand:SWI48 0 "general_reg_operand")
(set_attr "type" "push,multi")
(set_attr "mode" "SI,TI")])
+(define_insn "push2_di"
+ [(set (match_operand:TI 0 "push_operand" "=<")
+ (unspec:TI [(match_operand:DI 1 "register_operand" "r")
+ (match_operand:DI 2 "register_operand" "r")]
+ UNSPEC_APXPUSH2))]
+ "TARGET_APX_PUSH2POP2"
+ "push2\t{%2, %1|%1, %2}"
+ [(set_attr "mode" "TI")
+ (set_attr "type" "multi")
+ (set_attr "prefix" "evex")])
+
+(define_insn "pop2_di"
+ [(parallel [(set (match_operand:DI 0 "register_operand" "=r")
+ (unspec:DI [(match_operand:TI 1 "pop_operand" ">")]
+ UNSPEC_APXPOP2_LOW))
+ (set (match_operand:DI 2 "register_operand" "=r")
+ (unspec:DI [(const_int 0)] UNSPEC_APXPOP2_HIGH))])]
+ "TARGET_APX_PUSH2POP2"
+ "pop2\t{%2, %0|%0, %2}"
+ [(set_attr "mode" "TI")
+ (set_attr "prefix" "evex")])
+
+(define_insn "pushp_di"
+ [(set (match_operand:DI 0 "push_operand" "=<")
+ (match_operand:DI 1 "register_operand" "r"))
+ (unspec:DI [(const_int 0)] UNSPEC_APX_PPX)]
+ "TARGET_64BIT"
+ "pushp\t%1"
+ [(set_attr "mode" "DI")])
+
+(define_insn "popp_di"
+ [(set (match_operand:DI 0 "register_operand" "=r")
+ (match_operand:DI 1 "pop_operand" ">"))
+ (unspec:DI [(const_int 0)] UNSPEC_APX_PPX)]
+ "TARGET_APX_PPX"
+ "popp\t%0"
+ [(set_attr "mode" "DI")])
+
+(define_insn "push2p_di"
+ [(set (match_operand:TI 0 "push_operand" "=<")
+ (unspec:TI [(match_operand:DI 1 "register_operand" "r")
+ (match_operand:DI 2 "register_operand" "r")]
+ UNSPEC_APXPUSH2))
+ (unspec:DI [(const_int 0)] UNSPEC_APX_PPX)]
+ "TARGET_APX_PUSH2POP2 && TARGET_APX_PPX"
+ "push2p\t{%2, %1|%1, %2}"
+ [(set_attr "mode" "TI")
+ (set_attr "type" "multi")
+ (set_attr "prefix" "evex")])
+
+(define_insn "pop2p_di"
+ [(parallel [(set (match_operand:DI 0 "register_operand" "=r")
+ (unspec:DI [(match_operand:TI 1 "pop_operand" ">")]
+ UNSPEC_APXPOP2_LOW))
+ (set (match_operand:DI 2 "register_operand" "=r")
+ (unspec:DI [(const_int 0)] UNSPEC_APXPOP2_HIGH))
+ (unspec:DI [(const_int 0)] UNSPEC_APX_PPX)])]
+ "TARGET_APX_PUSH2POP2 && TARGET_APX_PPX"
+ "pop2p\t{%2, %0|%0, %2}"
+ [(set_attr "mode" "TI")
+ (set_attr "prefix" "evex")])
+
(define_insn "*pushsf_rex64"
[(set (match_operand:SF 0 "push_operand" "=X,X,X")
(match_operand:SF 1 "nonmemory_no_elim_operand" "f,rF,v"))]
;; Possible store forwarding (partial memory) stall in alternatives 4, 6 and 7.
(define_insn "*movdf_internal"
[(set (match_operand:DF 0 "nonimmediate_operand"
- "=Yf*f,m ,Yf*f,?r ,!o,?*r ,!o,!o,?r,?m,?r,?r,v,v,v,m,*x,*x,*x,m ,?r,?v,r ,o ,r ,m")
+ "=Yf*f,m ,Yf*f,?r ,!o,?*r ,!o,!o,?r,?m,?r,?r,Yv,v,v,m,*x,*x,*x,m ,?r,?v,r ,o ,r ,m")
(match_operand:DF 1 "general_operand"
- "Yf*fm,Yf*f,G ,roF,r ,*roF,*r,F ,rm,rC,C ,F ,C,v,m,v,C ,*x,m ,*x, v, r,roF,rF,rmF,rC"))]
+ "Yf*fm,Yf*f,G ,roF,r ,*roF,*r,F ,rm,rC,C ,F ,C ,v,m,v,C ,*x,m ,*x, v, r,roF,rF,rmF,rC"))]
"!(MEM_P (operands[0]) && MEM_P (operands[1]))
&& (lra_in_progress || reload_completed
|| !CONST_DOUBLE_P (operands[1])
/* movaps is one byte shorter for non-AVX targets. */
(eq_attr "alternative" "13,17")
- (cond [(match_test "TARGET_AVX")
+ (cond [(match_test "TARGET_AVX512VL")
+ (const_string "V2DF")
+ (match_test "TARGET_AVX512F")
(const_string "DF")
+ (match_test "TARGET_AVX")
+ (const_string "V2DF")
(ior (not (match_test "TARGET_SSE2"))
(match_test "optimize_function_for_size_p (cfun)"))
(const_string "V4SF")
(define_insn "*movsf_internal"
[(set (match_operand:SF 0 "nonimmediate_operand"
- "=Yf*f,m ,Yf*f,?r ,?m,v,v,v,m,?r,?v,!*y,!*y,!m,!r,!*y,r ,m")
+ "=Yf*f,m ,Yf*f,?r ,?m,Yv,v,v,m,?r,?v,!*y,!*y,!m,!r,!*y,r ,m")
(match_operand:SF 1 "general_operand"
- "Yf*fm,Yf*f,G ,rmF,rF,C,v,m,v,v ,r ,*y ,m ,*y,*y,r ,rmF,rF"))]
+ "Yf*fm,Yf*f,G ,rmF,rF,C ,v,m,v,v ,r ,*y ,m ,*y,*y,r ,rmF,rF"))]
"!(MEM_P (operands[0]) && MEM_P (operands[1]))
&& (lra_in_progress || reload_completed
|| !CONST_DOUBLE_P (operands[1])
(eq_attr "alternative" "11")
(const_string "DI")
(eq_attr "alternative" "5")
- (cond [(and (match_test "TARGET_AVX512F")
+ (cond [(and (match_test "TARGET_AVX512F && TARGET_EVEX512")
(not (match_test "TARGET_PREFER_AVX256")))
(const_string "V16SF")
(match_test "TARGET_AVX")
better to maintain the whole registers in single format
to avoid problems on using packed logical operations. */
(eq_attr "alternative" "6")
- (cond [(ior (match_test "TARGET_SSE_PARTIAL_REG_DEPENDENCY")
+ (cond [(match_test "TARGET_AVX512VL")
+ (const_string "V4SF")
+ (match_test "TARGET_AVX512F")
+ (const_string "SF")
+ (ior (match_test "TARGET_SSE_PARTIAL_REG_DEPENDENCY")
(match_test "TARGET_SSE_SPLIT_REGS"))
(const_string "V4SF")
]
(define_insn "*mov<mode>_internal"
[(set (match_operand:HFBF 0 "nonimmediate_operand"
- "=?r,?r,?r,?m,v,v,?r,m,?v,v")
+ "=?r,?r,?r,?m ,Yv,v,?r,jm,m,?v,v")
(match_operand:HFBF 1 "general_operand"
- "r ,F ,m ,r<hfbfconstf>,C,v, v,v,r ,m"))]
+ "r ,F ,m ,r<hfbfconstf>,C ,v, v,v ,v,r ,m"))]
"!(MEM_P (operands[0]) && MEM_P (operands[1]))
&& (lra_in_progress
|| reload_completed
}
}
[(set (attr "isa")
- (cond [(eq_attr "alternative" "4,5,6,8,9")
+ (cond [(eq_attr "alternative" "4,5,6,9,10")
(const_string "sse2")
(eq_attr "alternative" "7")
- (const_string "sse4")
+ (const_string "sse4_noavx")
+ (eq_attr "alternative" "8")
+ (const_string "avx")
]
(const_string "*")))
+ (set (attr "addr")
+ (if_then_else (eq_attr "alternative" "7")
+ (const_string "gpr16")
+ (const_string "*")))
(set (attr "type")
(cond [(eq_attr "alternative" "4")
(const_string "sselog1")
- (eq_attr "alternative" "5,6,8")
+ (eq_attr "alternative" "5,6,9")
(const_string "ssemov")
- (eq_attr "alternative" "7,9")
+ (eq_attr "alternative" "7,8,10")
(if_then_else
(match_test ("TARGET_AVX512FP16"))
(const_string "ssemov")
]
(const_string "imov")))
(set (attr "prefix")
- (cond [(eq_attr "alternative" "4,5,6,7,8,9")
+ (cond [(eq_attr "alternative" "4,5,6,7,8,9,10")
(const_string "maybe_vex")
]
(const_string "orig")))
(set (attr "mode")
(cond [(eq_attr "alternative" "4")
(const_string "V4SF")
- (eq_attr "alternative" "6,8")
+ (eq_attr "alternative" "6,9")
(if_then_else
(match_test "TARGET_AVX512FP16")
(const_string "HI")
(const_string "SI"))
- (eq_attr "alternative" "7,9")
+ (eq_attr "alternative" "7,8,10")
(if_then_else
(match_test "TARGET_AVX512FP16")
(const_string "HI")
(const_string "TI"))
(eq_attr "alternative" "5")
- (cond [(match_test "TARGET_AVX512FP16")
+ (cond [(match_test "TARGET_AVX512VL")
+ (const_string "V4SF")
+ (match_test "TARGET_AVX512FP16")
(const_string "HF")
+ (match_test "TARGET_AVX512F")
+ (const_string "SF")
+ (match_test "TARGET_AVX")
+ (const_string "V4SF")
(ior (match_test "TARGET_SSE_PARTIAL_REG_DEPENDENCY")
(match_test "TARGET_SSE_SPLIT_REGS"))
(const_string "V4SF")
/* If it is unsafe to overwrite upper half of source, we need
to move to destination and unpack there. */
if (REGNO (operands[0]) != REGNO (operands[1])
- || (EXT_REX_SSE_REG_P (operands[1])
- && !TARGET_AVX512VL))
+ || (EXT_REX_SSE_REG_P (operands[1]) && !TARGET_AVX512VL))
{
rtx tmp = lowpart_subreg (SFmode, operands[0], DFmode);
emit_move_insn (tmp, operands[1]);
(set_attr "memory" "none")
(set (attr "enabled")
(if_then_else (eq_attr "alternative" "2")
- (symbol_ref "TARGET_AVX512F && !TARGET_AVX512VL
- && !TARGET_PREFER_AVX256")
+ (symbol_ref "TARGET_AVX512F && TARGET_EVEX512
+ && !TARGET_AVX512VL && !TARGET_PREFER_AVX256")
(const_string "*")))])
(define_expand "extend<mode>xf2"
gcc_assert (TARGET_64BIT);
return "lea{l}\t{%E1, %k0|%k0, %E1}";
}
- else
+ else
return "lea{<imodesuffix>}\t{%E1, %0|%0, %E1}";
}
[(set_attr "type" "lea")
(plus:SDWIM (match_operand:SDWIM 1 "nonimmediate_operand")
(match_operand:SDWIM 2 "<general_hilo_operand>")))]
""
- "ix86_expand_binary_operator (PLUS, <MODE>mode, operands); DONE;")
+{
+ ix86_expand_binary_operator (PLUS, <MODE>mode, operands, TARGET_APX_NDD);
+ DONE;
+})
(define_insn_and_split "*add<dwi>3_doubleword"
- [(set (match_operand:<DWI> 0 "nonimmediate_operand" "=ro,r")
+ [(set (match_operand:<DWI> 0 "nonimmediate_operand" "=ro,r,&r,&r")
(plus:<DWI>
- (match_operand:<DWI> 1 "nonimmediate_operand" "%0,0")
- (match_operand:<DWI> 2 "x86_64_hilo_general_operand" "r<di>,o")))
+ (match_operand:<DWI> 1 "nonimmediate_operand" "%0,0,ro,r")
+ (match_operand:<DWI> 2 "x86_64_hilo_general_operand" "r<di>,o,r<di>,r")))
(clobber (reg:CC FLAGS_REG))]
- "ix86_binary_operator_ok (PLUS, <DWI>mode, operands)"
+ "ix86_binary_operator_ok (PLUS, <DWI>mode, operands, TARGET_APX_NDD)"
"#"
"&& reload_completed"
[(parallel [(set (reg:CCC FLAGS_REG)
split_double_mode (<DWI>mode, &operands[0], 3, &operands[0], &operands[3]);
if (operands[2] == const0_rtx)
{
+ /* Under NDD op0 and op1 may not equal, do not delete insn then. */
+ bool emit_insn_deleted_note_p = true;
+ if (!rtx_equal_p (operands[0], operands[1]))
+ {
+ emit_move_insn (operands[0], operands[1]);
+ emit_insn_deleted_note_p = false;
+ }
if (operands[5] != const0_rtx)
- ix86_expand_binary_operator (PLUS, <MODE>mode, &operands[3]);
+ ix86_expand_binary_operator (PLUS, <MODE>mode, &operands[3],
+ TARGET_APX_NDD);
else if (!rtx_equal_p (operands[3], operands[4]))
emit_move_insn (operands[3], operands[4]);
- else
+ else if (emit_insn_deleted_note_p)
emit_note (NOTE_INSN_DELETED);
DONE;
}
-})
+}
+[(set_attr "isa" "*,*,apx_ndd,apx_ndd")])
(define_insn_and_split "*add<dwi>3_doubleword_zext"
- [(set (match_operand:<DWI> 0 "nonimmediate_operand" "=r,o")
+ [(set (match_operand:<DWI> 0 "nonimmediate_operand" "=r,o,&r,&r")
(plus:<DWI>
(zero_extend:<DWI>
- (match_operand:DWIH 2 "nonimmediate_operand" "rm,r"))
- (match_operand:<DWI> 1 "nonimmediate_operand" "0,0")))
+ (match_operand:DWIH 2 "nonimmediate_operand" "rm,r,rm,r"))
+ (match_operand:<DWI> 1 "nonimmediate_operand" "0,0,r,m")))
(clobber (reg:CC FLAGS_REG))]
- "ix86_binary_operator_ok (UNKNOWN, <DWI>mode, operands)"
+ "ix86_binary_operator_ok (UNKNOWN, <DWI>mode, operands, TARGET_APX_NDD)"
"#"
"&& reload_completed"
[(parallel [(set (reg:CCC FLAGS_REG)
(match_dup 4))
(const_int 0)))
(clobber (reg:CC FLAGS_REG))])]
- "split_double_mode (<DWI>mode, &operands[0], 2, &operands[0], &operands[3]);")
+ "split_double_mode (<DWI>mode, &operands[0], 2, &operands[0], &operands[3]);"
+ [(set_attr "isa" "*,*,apx_ndd,apx_ndd")])
(define_insn_and_split "*add<dwi>3_doubleword_concat"
[(set (match_operand:<DWI> 0 "register_operand" "=&r")
"split_double_mode (<DWI>mode, &operands[0], 1, &operands[0], &operands[5]);")
(define_insn "*add<mode>_1"
- [(set (match_operand:SWI48 0 "nonimmediate_operand" "=rm,r,r,r")
+ [(set (match_operand:SWI48 0 "nonimmediate_operand" "=rm,r,r,r,r,r,r,r")
(plus:SWI48
- (match_operand:SWI48 1 "nonimmediate_operand" "%0,0,r,r")
- (match_operand:SWI48 2 "x86_64_general_operand" "re,BM,0,le")))
+ (match_operand:SWI48 1 "nonimmediate_operand" "%0,0,r,r,rm,r,m,r")
+ (match_operand:SWI48 2 "x86_64_general_operand" "re,BM,0,le,r,e,je,BM")))
(clobber (reg:CC FLAGS_REG))]
- "ix86_binary_operator_ok (PLUS, <MODE>mode, operands)"
+ "ix86_binary_operator_ok (PLUS, <MODE>mode, operands, TARGET_APX_NDD)"
{
+ bool use_ndd = get_attr_isa (insn) == ISA_APX_NDD;
switch (get_attr_type (insn))
{
case TYPE_LEA:
return "#";
case TYPE_INCDEC:
- gcc_assert (rtx_equal_p (operands[0], operands[1]));
if (operands[2] == const1_rtx)
- return "inc{<imodesuffix>}\t%0";
+ return use_ndd ? "inc{<imodesuffix>}\t{%1, %0|%0, %1}"
+ : "inc{<imodesuffix>}\t%0";
else
{
gcc_assert (operands[2] == constm1_rtx);
- return "dec{<imodesuffix>}\t%0";
+ return use_ndd ? "dec{<imodesuffix>}\t{%1, %0|%0, %1}"
+ : "dec{<imodesuffix>}\t%0";
}
default:
if (which_alternative == 2)
std::swap (operands[1], operands[2]);
- gcc_assert (rtx_equal_p (operands[0], operands[1]));
if (x86_maybe_negate_const_int (&operands[2], <MODE>mode))
- return "sub{<imodesuffix>}\t{%2, %0|%0, %2}";
+ return use_ndd ? "sub{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}"
+ : "sub{<imodesuffix>}\t{%2, %0|%0, %2}";
- return "add{<imodesuffix>}\t{%2, %0|%0, %2}";
+ return use_ndd ? "add{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}"
+ : "add{<imodesuffix>}\t{%2, %0|%0, %2}";
}
}
- [(set (attr "type")
+ [(set_attr "isa" "*,*,*,*,apx_ndd,apx_ndd,apx_ndd,apx_ndd")
+ (set (attr "type")
(cond [(eq_attr "alternative" "3")
(const_string "lea")
(match_operand:SWI48 2 "incdec_operand")
;; patterns constructed from addsi_1 to match.
(define_insn "addsi_1_zext"
- [(set (match_operand:DI 0 "register_operand" "=r,r,r")
+ [(set (match_operand:DI 0 "register_operand" "=r,r,r,r,r")
(zero_extend:DI
- (plus:SI (match_operand:SI 1 "nonimmediate_operand" "%0,r,r")
- (match_operand:SI 2 "x86_64_general_operand" "rBMe,0,le"))))
+ (plus:SI (match_operand:SI 1 "nonimmediate_operand" "%0,r,r,r,rm")
+ (match_operand:SI 2 "x86_64_general_operand" "rBMe,0,le,rBMe,re"))))
(clobber (reg:CC FLAGS_REG))]
- "TARGET_64BIT && ix86_binary_operator_ok (PLUS, SImode, operands)"
+ "TARGET_64BIT
+ && ix86_binary_operator_ok (PLUS, SImode, operands, TARGET_APX_NDD)"
{
+ bool use_ndd = get_attr_isa (insn) == ISA_APX_NDD;
switch (get_attr_type (insn))
{
case TYPE_LEA:
case TYPE_INCDEC:
if (operands[2] == const1_rtx)
- return "inc{l}\t%k0";
+ return use_ndd ? "inc{l}\t{%1, %k0|%k0, %1}"
+ : "inc{l}\t%k0";
else
{
gcc_assert (operands[2] == constm1_rtx);
- return "dec{l}\t%k0";
+ return use_ndd ? "dec{l}\t{%1, %k0|%k0, %1}"
+ : "dec{l}\t%k0";
}
default:
std::swap (operands[1], operands[2]);
if (x86_maybe_negate_const_int (&operands[2], SImode))
- return "sub{l}\t{%2, %k0|%k0, %2}";
+ return use_ndd ? "sub{l}\t{%2 ,%1, %k0|%k0, %1, %2}"
+ : "sub{l}\t{%2, %k0|%k0, %2}";
- return "add{l}\t{%2, %k0|%k0, %2}";
+ return use_ndd ? "add{l}\t{%2 ,%1, %k0|%k0, %1, %2}"
+ : "add{l}\t{%2, %k0|%k0, %2}";
}
}
- [(set (attr "type")
+ [(set_attr "isa" "*,*,*,apx_ndd,apx_ndd")
+ (set (attr "type")
(cond [(eq_attr "alternative" "2")
(const_string "lea")
(match_operand:SI 2 "incdec_operand")
(set_attr "mode" "SI")])
(define_insn "*addhi_1"
- [(set (match_operand:HI 0 "nonimmediate_operand" "=rm,r,r,Yp")
- (plus:HI (match_operand:HI 1 "nonimmediate_operand" "%0,0,r,Yp")
- (match_operand:HI 2 "general_operand" "rn,m,0,ln")))
+ [(set (match_operand:HI 0 "nonimmediate_operand" "=rm,r,r,Yp,r,r")
+ (plus:HI (match_operand:HI 1 "nonimmediate_operand" "%0,0,r,Yp,rm,r")
+ (match_operand:HI 2 "general_operand" "rn,m,0,ln,rn,m")))
(clobber (reg:CC FLAGS_REG))]
- "ix86_binary_operator_ok (PLUS, HImode, operands)"
+ "ix86_binary_operator_ok (PLUS, HImode, operands, TARGET_APX_NDD)"
{
+ bool use_ndd = get_attr_isa (insn) == ISA_APX_NDD;
switch (get_attr_type (insn))
{
case TYPE_LEA:
return "#";
case TYPE_INCDEC:
- gcc_assert (rtx_equal_p (operands[0], operands[1]));
if (operands[2] == const1_rtx)
- return "inc{w}\t%0";
+ return use_ndd ? "inc{w}\t{%1, %0|%0, %1}" : "inc{w}\t%0";
else
{
gcc_assert (operands[2] == constm1_rtx);
- return "dec{w}\t%0";
+ return use_ndd ? "dec{w}\t{%1, %0|%0, %1}" : "dec{w}\t%0";
}
default:
if (which_alternative == 2)
std::swap (operands[1], operands[2]);
- gcc_assert (rtx_equal_p (operands[0], operands[1]));
if (x86_maybe_negate_const_int (&operands[2], HImode))
- return "sub{w}\t{%2, %0|%0, %2}";
+ return use_ndd ? "sub{w}\t{%2, %1, %0|%0, %1, %2}"
+ : "sub{w}\t{%2, %0|%0, %2}";
- return "add{w}\t{%2, %0|%0, %2}";
+ return use_ndd ? "add{w}\t{%2, %1, %0|%0, %1, %2}"
+ : "add{w}\t{%2, %0|%0, %2}";
}
}
- [(set (attr "type")
+ [(set_attr "isa" "*,*,*,*,apx_ndd,apx_ndd")
+ (set (attr "type")
(cond [(eq_attr "alternative" "3")
(const_string "lea")
(match_operand:HI 2 "incdec_operand")
(and (eq_attr "type" "alu") (match_operand 2 "const128_operand"))
(const_string "1")
(const_string "*")))
- (set_attr "mode" "HI,HI,HI,SI")])
+ (set_attr "mode" "HI,HI,HI,SI,HI,HI")])
(define_insn "*addqi_1"
- [(set (match_operand:QI 0 "nonimmediate_operand" "=qm,q,q,r,r,Yp")
- (plus:QI (match_operand:QI 1 "nonimmediate_operand" "%0,0,q,0,r,Yp")
- (match_operand:QI 2 "general_operand" "qn,m,0,rn,0,ln")))
+ [(set (match_operand:QI 0 "nonimmediate_operand" "=qm,q,q,r,r,Yp,r,r")
+ (plus:QI (match_operand:QI 1 "nonimmediate_operand" "%0,0,q,0,r,Yp,rm,r")
+ (match_operand:QI 2 "general_operand" "qn,m,0,rn,0,ln,rn,m")))
(clobber (reg:CC FLAGS_REG))]
- "ix86_binary_operator_ok (PLUS, QImode, operands)"
+ "ix86_binary_operator_ok (PLUS, QImode, operands, TARGET_APX_NDD)"
{
bool widen = (get_attr_mode (insn) != MODE_QI);
-
+ bool use_ndd = get_attr_isa (insn) == ISA_APX_NDD;
switch (get_attr_type (insn))
{
case TYPE_LEA:
return "#";
case TYPE_INCDEC:
- gcc_assert (rtx_equal_p (operands[0], operands[1]));
if (operands[2] == const1_rtx)
- return widen ? "inc{l}\t%k0" : "inc{b}\t%0";
+ if (use_ndd)
+ return "inc{b}\t{%1, %0|%0, %1}";
+ else
+ return widen ? "inc{l}\t%k0" : "inc{b}\t%0";
else
{
gcc_assert (operands[2] == constm1_rtx);
- return widen ? "dec{l}\t%k0" : "dec{b}\t%0";
+ if (use_ndd)
+ return "dec{b}\t{%1, %0|%0, %1}";
+ else
+ return widen ? "dec{l}\t%k0" : "dec{b}\t%0";
}
default:
if (which_alternative == 2 || which_alternative == 4)
std::swap (operands[1], operands[2]);
- gcc_assert (rtx_equal_p (operands[0], operands[1]));
if (x86_maybe_negate_const_int (&operands[2], QImode))
{
- if (widen)
- return "sub{l}\t{%2, %k0|%k0, %2}";
+ if (use_ndd)
+ return "sub{b}\t{%2, %1, %0|%0, %1, %2}";
else
- return "sub{b}\t{%2, %0|%0, %2}";
+ return widen ? "sub{l}\t{%2, %k0|%k0, %2}"
+ : "sub{b}\t{%2, %0|%0, %2}";
}
- if (widen)
- return "add{l}\t{%k2, %k0|%k0, %k2}";
+ if (use_ndd)
+ return "add{b}\t{%2, %1, %0|%0, %1, %2}";
else
- return "add{b}\t{%2, %0|%0, %2}";
+ return widen ? "add{l}\t{%k2, %k0|%k0, %k2}"
+ : "add{b}\t{%2, %0|%0, %2}";
}
}
- [(set (attr "type")
+ [(set_attr "isa" "*,*,*,*,*,*,apx_ndd,apx_ndd")
+ (set (attr "type")
(cond [(eq_attr "alternative" "5")
(const_string "lea")
(match_operand:QI 2 "incdec_operand")
(and (eq_attr "type" "alu") (match_operand 2 "const128_operand"))
(const_string "1")
(const_string "*")))
- (set_attr "mode" "QI,QI,QI,SI,SI,SI")
+ (set_attr "mode" "QI,QI,QI,SI,SI,SI,QI,QI")
;; Potential partial reg stall on alternatives 3 and 4.
(set (attr "preferred_for_speed")
(cond [(eq_attr "alternative" "3,4")
return "add{<imodesuffix>}\t{%2, %0|%0, %2}";
}
}
- "&& reload_completed"
+ "&& reload_completed
+ && !(rtx_equal_p (operands[0], operands[1])
+ || rtx_equal_p (operands[0], operands[2]))"
[(set (strict_low_part (match_dup 0)) (match_dup 1))
(parallel
[(set (strict_low_part (match_dup 0))
(const_string "alu")))
(set_attr "mode" "<MODE>")])
+;; Alternative 1 is needed to work around LRA limitation, see PR82524.
+(define_insn_and_split "*addqi_ext<mode>_1_slp"
+ [(set (strict_low_part (match_operand:QI 0 "register_operand" "+Q,&Q"))
+ (plus:QI
+ (subreg:QI
+ (match_operator:SWI248 3 "extract_operator"
+ [(match_operand 2 "int248_register_operand" "Q,Q")
+ (const_int 8)
+ (const_int 8)]) 0)
+ (match_operand:QI 1 "nonimmediate_operand" "0,!qm")))
+ (clobber (reg:CC FLAGS_REG))]
+ "!TARGET_PARTIAL_REG_STALL || optimize_function_for_size_p (cfun)"
+ "@
+ add{b}\t{%h2, %0|%0, %h2}
+ #"
+ "&& reload_completed
+ && !rtx_equal_p (operands[0], operands[1])"
+ [(set (strict_low_part (match_dup 0)) (match_dup 1))
+ (parallel
+ [(set (strict_low_part (match_dup 0))
+ (plus:QI
+ (subreg:QI
+ (match_op_dup 3
+ [(match_dup 2) (const_int 8) (const_int 8)]) 0)
+ (match_dup 0)))
+ (clobber (reg:CC FLAGS_REG))])]
+ ""
+ [(set_attr "type" "alu")
+ (set_attr "mode" "QI")])
+
+(define_insn_and_split "*addqi_ext<mode>_2_slp"
+ [(set (strict_low_part (match_operand:QI 0 "register_operand" "+&Q"))
+ (plus:QI
+ (subreg:QI
+ (match_operator:SWI248 3 "extract_operator"
+ [(match_operand 1 "int248_register_operand" "Q")
+ (const_int 8)
+ (const_int 8)]) 0)
+ (subreg:QI
+ (match_operator:SWI248 4 "extract_operator"
+ [(match_operand 2 "int248_register_operand" "Q")
+ (const_int 8)
+ (const_int 8)]) 0)))
+ (clobber (reg:CC FLAGS_REG))]
+ "!TARGET_PARTIAL_REG_STALL || optimize_function_for_size_p (cfun)"
+ "#"
+ "&& reload_completed"
+ [(set (strict_low_part (match_dup 0))
+ (subreg:QI
+ (match_op_dup 4
+ [(match_dup 2) (const_int 8) (const_int 8)]) 0))
+ (parallel
+ [(set (strict_low_part (match_dup 0))
+ (plus:QI
+ (subreg:QI
+ (match_op_dup 3
+ [(match_dup 1) (const_int 8) (const_int 8)]) 0)
+ (match_dup 0)))
+ (clobber (reg:CC FLAGS_REG))])]
+ ""
+ [(set_attr "type" "alu")
+ (set_attr "mode" "QI")])
+
;; Split non destructive adds if we cannot use lea.
(define_split
[(set (match_operand:SWI48 0 "register_operand")
[(set (reg FLAGS_REG)
(compare
(plus:SWI
- (match_operand:SWI 1 "nonimmediate_operand" "%0,0,<r>")
- (match_operand:SWI 2 "<general_operand>" "<r><i>,<m>,0"))
+ (match_operand:SWI 1 "nonimmediate_operand" "%0,0,<r>,rm,r")
+ (match_operand:SWI 2 "<general_operand>" "<r><i>,<m>,0,r<i>,<m>"))
(const_int 0)))
- (set (match_operand:SWI 0 "nonimmediate_operand" "=<r>m,<r>,<r>")
+ (set (match_operand:SWI 0 "nonimmediate_operand" "=<r>m,<r>,<r>,r,r")
(plus:SWI (match_dup 1) (match_dup 2)))]
"ix86_match_ccmode (insn, CCGOCmode)
- && ix86_binary_operator_ok (PLUS, <MODE>mode, operands)"
+ && ix86_binary_operator_ok (PLUS, <MODE>mode, operands, TARGET_APX_NDD)"
{
+ bool use_ndd = get_attr_isa (insn) == ISA_APX_NDD;
switch (get_attr_type (insn))
{
case TYPE_INCDEC:
if (operands[2] == const1_rtx)
- return "inc{<imodesuffix>}\t%0";
+ return use_ndd ? "inc{<imodesuffix>}\t{%1, %0|%0, %1}"
+ : "inc{<imodesuffix>}\t%0";
else
{
gcc_assert (operands[2] == constm1_rtx);
- return "dec{<imodesuffix>}\t%0";
+ return use_ndd ? "dec{<imodesuffix>}\t{%1, %0|%0, %1}"
+ : "dec{<imodesuffix>}\t%0";
}
default:
if (which_alternative == 2)
std::swap (operands[1], operands[2]);
- gcc_assert (rtx_equal_p (operands[0], operands[1]));
if (x86_maybe_negate_const_int (&operands[2], <MODE>mode))
- return "sub{<imodesuffix>}\t{%2, %0|%0, %2}";
+ return use_ndd ? "sub{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}"
+ : "sub{<imodesuffix>}\t{%2, %0|%0, %2}";
- return "add{<imodesuffix>}\t{%2, %0|%0, %2}";
+ return use_ndd ? "add{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}"
+ : "add{<imodesuffix>}\t{%2, %0|%0, %2}";
}
}
- [(set (attr "type")
+ [(set_attr "isa" "*,*,*,apx_ndd,apx_ndd")
+ (set (attr "type")
(if_then_else (match_operand:SWI 2 "incdec_operand")
(const_string "incdec")
(const_string "alu")))
(define_insn "*addsi_2_zext"
[(set (reg FLAGS_REG)
(compare
- (plus:SI (match_operand:SI 1 "nonimmediate_operand" "%0,r")
- (match_operand:SI 2 "x86_64_general_operand" "rBMe,0"))
+ (plus:SI (match_operand:SI 1 "nonimmediate_operand" "%0,r,r,rm")
+ (match_operand:SI 2 "x86_64_general_operand" "rBMe,0,rBMe,re"))
(const_int 0)))
- (set (match_operand:DI 0 "register_operand" "=r,r")
+ (set (match_operand:DI 0 "register_operand" "=r,r,r,r")
(zero_extend:DI (plus:SI (match_dup 1) (match_dup 2))))]
"TARGET_64BIT && ix86_match_ccmode (insn, CCGOCmode)
- && ix86_binary_operator_ok (PLUS, SImode, operands)"
+ && ix86_binary_operator_ok (PLUS, SImode, operands, TARGET_APX_NDD)"
{
+ bool use_ndd = get_attr_isa (insn) == ISA_APX_NDD;
switch (get_attr_type (insn))
{
case TYPE_INCDEC:
if (operands[2] == const1_rtx)
- return "inc{l}\t%k0";
+ return use_ndd ? "inc{l}\t{%1, %k0|%k0, %1}"
+ : "inc{l}\t%k0";
else
{
gcc_assert (operands[2] == constm1_rtx);
- return "dec{l}\t%k0";
+ return use_ndd ? "dec{l}\t{%1, %k0|%k0, %1}"
+ : "dec{l}\t%k0";
}
default:
std::swap (operands[1], operands[2]);
if (x86_maybe_negate_const_int (&operands[2], SImode))
- return "sub{l}\t{%2, %k0|%k0, %2}";
+ return use_ndd ? "sub{l}\t{%2, %1, %k0|%k0, %1, %2}"
+ : "sub{l}\t{%2, %k0|%k0, %2}";
- return "add{l}\t{%2, %k0|%k0, %2}";
+ return use_ndd ? "add{l}\t{%2, %1, %k0|%k0, %1, %2}"
+ : "add{l}\t{%2, %k0|%k0, %2}";
}
}
- [(set (attr "type")
+ [(set_attr "isa" "*,*,apx_ndd,apx_ndd")
+ (set (attr "type")
(if_then_else (match_operand:SI 2 "incdec_operand")
(const_string "incdec")
(const_string "alu")))
(define_insn "*add<mode>_3"
[(set (reg FLAGS_REG)
(compare
- (neg:SWI (match_operand:SWI 2 "<general_operand>" "<g>,0"))
- (match_operand:SWI 1 "nonimmediate_operand" "%0,<r>")))
- (clobber (match_scratch:SWI 0 "=<r>,<r>"))]
+ (neg:SWI (match_operand:SWI 2 "<general_operand>" "<g>,0,<g>,re"))
+ (match_operand:SWI 1 "nonimmediate_operand" "%0,<r>,r,rm")))
+ (clobber (match_scratch:SWI 0 "=<r>,<r>,r,r"))]
"ix86_match_ccmode (insn, CCZmode)
&& !(MEM_P (operands[1]) && MEM_P (operands[2]))"
{
+ bool use_ndd = get_attr_isa (insn) == ISA_APX_NDD;
switch (get_attr_type (insn))
{
case TYPE_INCDEC:
if (operands[2] == const1_rtx)
- return "inc{<imodesuffix>}\t%0";
+ return use_ndd ? "inc{<imodesuffix>}\t{%1, %0|%0, %1}"
+ : "inc{<imodesuffix>}\t%0";
else
{
gcc_assert (operands[2] == constm1_rtx);
- return "dec{<imodesuffix>}\t%0";
+ return use_ndd ? "dec{<imodesuffix>}\t{%1, %0|%0, %1}"
+ : "dec{<imodesuffix>}\t%0";
}
default:
if (which_alternative == 1)
std::swap (operands[1], operands[2]);
- gcc_assert (rtx_equal_p (operands[0], operands[1]));
if (x86_maybe_negate_const_int (&operands[2], <MODE>mode))
- return "sub{<imodesuffix>}\t{%2, %0|%0, %2}";
+ return use_ndd ? "sub{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}"
+ : "sub{<imodesuffix>}\t{%2, %0|%0, %2}";
- return "add{<imodesuffix>}\t{%2, %0|%0, %2}";
+ return use_ndd ? "add{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}"
+ : "add{<imodesuffix>}\t{%2, %0|%0, %2}";
}
}
- [(set (attr "type")
+ [(set_attr "isa" "*,*,apx_ndd,apx_ndd")
+ (set (attr "type")
(if_then_else (match_operand:SWI 2 "incdec_operand")
(const_string "incdec")
(const_string "alu")))
(define_insn "*addsi_3_zext"
[(set (reg FLAGS_REG)
(compare
- (neg:SI (match_operand:SI 2 "x86_64_general_operand" "rBMe,0"))
- (match_operand:SI 1 "nonimmediate_operand" "%0,r")))
- (set (match_operand:DI 0 "register_operand" "=r,r")
+ (neg:SI (match_operand:SI 2 "x86_64_general_operand" "rBMe,0,rBMe,re"))
+ (match_operand:SI 1 "nonimmediate_operand" "%0,r,r,rm")))
+ (set (match_operand:DI 0 "register_operand" "=r,r,r,r")
(zero_extend:DI (plus:SI (match_dup 1) (match_dup 2))))]
"TARGET_64BIT && ix86_match_ccmode (insn, CCZmode)
- && ix86_binary_operator_ok (PLUS, SImode, operands)"
+ && ix86_binary_operator_ok (PLUS, SImode, operands, TARGET_APX_NDD)"
{
+ bool use_ndd = get_attr_isa (insn) == ISA_APX_NDD;
switch (get_attr_type (insn))
{
case TYPE_INCDEC:
if (operands[2] == const1_rtx)
- return "inc{l}\t%k0";
+ return use_ndd ? "inc{l}\t{%1, %k0|%k0, %1}" : "inc{l}\t%k0";
else
{
gcc_assert (operands[2] == constm1_rtx);
- return "dec{l}\t%k0";
+ return use_ndd ? "dec{l}\t{%1, %k0|%k0, %1}" : "dec{l}\t%k0";
}
default:
std::swap (operands[1], operands[2]);
if (x86_maybe_negate_const_int (&operands[2], SImode))
- return "sub{l}\t{%2, %k0|%k0, %2}";
+ return use_ndd ? "sub{l}\t{%2, %1, %k0|%k0, %1, %2}"
+ : "sub{l}\t{%2, %k0|%k0, %2}";
- return "add{l}\t{%2, %k0|%k0, %2}";
+ return use_ndd ? "add{l}\t{%2, %1, %k0|%k0, %1, %2}"
+ : "add{l}\t{%2, %k0|%k0, %2}";
}
}
- [(set (attr "type")
+ [(set_attr "isa" "*,*,apx_ndd,apx_ndd")
+ (set (attr "type")
(if_then_else (match_operand:SI 2 "incdec_operand")
(const_string "incdec")
(const_string "alu")))
(define_insn "*adddi_4"
[(set (reg FLAGS_REG)
(compare
- (match_operand:DI 1 "nonimmediate_operand" "0")
- (match_operand:DI 2 "x86_64_immediate_operand" "e")))
- (clobber (match_scratch:DI 0 "=r"))]
+ (match_operand:DI 1 "nonimmediate_operand" "0,rm")
+ (match_operand:DI 2 "x86_64_immediate_operand" "e,e")))
+ (clobber (match_scratch:DI 0 "=r,r"))]
"TARGET_64BIT
&& ix86_match_ccmode (insn, CCGCmode)"
{
+ bool use_ndd = get_attr_isa (insn) == ISA_APX_NDD;
switch (get_attr_type (insn))
{
case TYPE_INCDEC:
if (operands[2] == constm1_rtx)
- return "inc{q}\t%0";
+ return use_ndd ? "inc{q}\t{%1, %0|%0, %1}" : "inc{q}\t%0";
else
{
gcc_assert (operands[2] == const1_rtx);
- return "dec{q}\t%0";
+ return use_ndd ? "dec{q}\t{%1, %0|%0, %1}" : "dec{q}\t%0";
}
default:
if (x86_maybe_negate_const_int (&operands[2], DImode))
- return "add{q}\t{%2, %0|%0, %2}";
+ return use_ndd ? "add{q}\t{%2, %1, %0|%0, %1, %2}"
+ : "add{q}\t{%2, %0|%0, %2}";
- return "sub{q}\t{%2, %0|%0, %2}";
+ return use_ndd ? "sub{q}\t{%2, %1, %0|%0, %1, %2}"
+ : "sub{q}\t{%2, %0|%0, %2}";
}
}
- [(set (attr "type")
+ [(set_attr "isa" "*,apx_ndd")
+ (set (attr "type")
(if_then_else (match_operand:DI 2 "incdec_operand")
(const_string "incdec")
(const_string "alu")))
(define_insn "*add<mode>_4"
[(set (reg FLAGS_REG)
(compare
- (match_operand:SWI124 1 "nonimmediate_operand" "0")
+ (match_operand:SWI124 1 "nonimmediate_operand" "0,rm")
(match_operand:SWI124 2 "const_int_operand")))
- (clobber (match_scratch:SWI124 0 "=<r>"))]
+ (clobber (match_scratch:SWI124 0 "=<r>,r"))]
"ix86_match_ccmode (insn, CCGCmode)"
{
+ bool use_ndd = get_attr_isa (insn) == ISA_APX_NDD;
switch (get_attr_type (insn))
{
case TYPE_INCDEC:
if (operands[2] == constm1_rtx)
- return "inc{<imodesuffix>}\t%0";
+ return use_ndd ? "inc{<imodesuffix>}\t{%1, %0|%0, %1}"
+ : "inc{<imodesuffix>}\t%0";
else
{
gcc_assert (operands[2] == const1_rtx);
- return "dec{<imodesuffix>}\t%0";
+ return use_ndd ? "dec{<imodesuffix>}\t{%1, %0|%0, %1}"
+ : "dec{<imodesuffix>}\t%0";
}
default:
if (x86_maybe_negate_const_int (&operands[2], <MODE>mode))
- return "add{<imodesuffix>}\t{%2, %0|%0, %2}";
+ return use_ndd ? "add{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}"
+ : "add{<imodesuffix>}\t{%2, %0|%0, %2}";
- return "sub{<imodesuffix>}\t{%2, %0|%0, %2}";
+ return use_ndd ? "sub{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}"
+ : "sub{<imodesuffix>}\t{%2, %0|%0, %2}";
}
}
- [(set (attr "type")
+ [(set_attr "isa" "*,apx_ndd")
+ (set (attr "type")
(if_then_else (match_operand:<MODE> 2 "incdec_operand")
(const_string "incdec")
(const_string "alu")))
[(set (reg FLAGS_REG)
(compare
(plus:SWI
- (match_operand:SWI 1 "nonimmediate_operand" "%0,<r>")
- (match_operand:SWI 2 "<general_operand>" "<g>,0"))
+ (match_operand:SWI 1 "nonimmediate_operand" "%0,<r>,r,rm")
+ (match_operand:SWI 2 "<general_operand>" "<g>,0,<g>,re"))
(const_int 0)))
- (clobber (match_scratch:SWI 0 "=<r>,<r>"))]
+ (clobber (match_scratch:SWI 0 "=<r>,<r>,r,r"))]
"ix86_match_ccmode (insn, CCGOCmode)
&& !(MEM_P (operands[1]) && MEM_P (operands[2]))"
{
+ bool use_ndd = get_attr_isa (insn) == ISA_APX_NDD;
switch (get_attr_type (insn))
{
case TYPE_INCDEC:
if (operands[2] == const1_rtx)
- return "inc{<imodesuffix>}\t%0";
+ return use_ndd ? "inc{<imodesuffix>}\t{%1, %0|%0, %1}"
+ : "inc{<imodesuffix>}\t%0";
else
{
gcc_assert (operands[2] == constm1_rtx);
- return "dec{<imodesuffix>}\t%0";
+ return use_ndd ? "dec{<imodesuffix>}\t{%1, %0|%0, %1}"
+ : "dec{<imodesuffix>}\t%0";
}
default:
if (which_alternative == 1)
std::swap (operands[1], operands[2]);
- gcc_assert (rtx_equal_p (operands[0], operands[1]));
if (x86_maybe_negate_const_int (&operands[2], <MODE>mode))
- return "sub{<imodesuffix>}\t{%2, %0|%0, %2}";
+ return use_ndd ? "sub{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}"
+ : "sub{<imodesuffix>}\t{%2, %0|%0, %2}";
- return "add{<imodesuffix>}\t{%2, %0|%0, %2}";
+ return use_ndd ? "add{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}"
+ : "add{<imodesuffix>}\t{%2, %0|%0, %2}";
}
}
- [(set (attr "type")
+ [(set_attr "isa" "*,*,apx_ndd,apx_ndd")
+ (set (attr "type")
(if_then_else (match_operand:SWI 2 "incdec_operand")
(const_string "incdec")
(const_string "alu")))
(set_attr "mode" "<MODE>")])
(define_insn "*addqi_ext<mode>_0"
- [(set (match_operand:QI 0 "nonimm_x64constmem_operand" "=QBc,m")
+ [(set (match_operand:QI 0 "nonimmediate_operand" "=QBn")
(plus:QI
(subreg:QI
(match_operator:SWI248 3 "extract_operator"
- [(match_operand 2 "int248_register_operand" "Q,Q")
+ [(match_operand 2 "int248_register_operand" "Q")
(const_int 8)
(const_int 8)]) 0)
- (match_operand:QI 1 "nonimm_x64constmem_operand" "0,0")))
+ (match_operand:QI 1 "nonimmediate_operand" "0")))
(clobber (reg:CC FLAGS_REG))]
""
"add{b}\t{%h2, %0|%0, %h2}"
- [(set_attr "isa" "*,nox64")
+ [(set_attr "addr" "gpr8")
(set_attr "type" "alu")
(set_attr "mode" "QI")])
+(define_insn_and_split "*addqi_ext2<mode>_0"
+ [(set (match_operand:QI 0 "register_operand" "=&Q")
+ (plus:QI
+ (subreg:QI
+ (match_operator:SWI248 3 "extract_operator"
+ [(match_operand 1 "int248_register_operand" "Q")
+ (const_int 8)
+ (const_int 8)]) 0)
+ (subreg:QI
+ (match_operator:SWI248 4 "extract_operator"
+ [(match_operand 2 "int248_register_operand" "Q")
+ (const_int 8)
+ (const_int 8)]) 0)))
+ (clobber (reg:CC FLAGS_REG))]
+ ""
+ "#"
+ "&& reload_completed"
+ [(set (match_dup 0)
+ (subreg:QI
+ (match_op_dup 4
+ [(match_dup 2) (const_int 8) (const_int 8)]) 0))
+ (parallel
+ [(set (match_dup 0)
+ (plus:QI
+ (subreg:QI
+ (match_op_dup 3
+ [(match_dup 1) (const_int 8) (const_int 8)]) 0)
+ (match_dup 0)))
+ (clobber (reg:CC FLAGS_REG))])]
+ ""
+ [(set_attr "type" "alu")
+ (set_attr "mode" "QI")])
+
(define_expand "addqi_ext_1"
[(parallel
[(set (zero_extract:HI (match_operand:HI 0 "register_operand")
(match_operand:QI 2 "const_int_operand")) 0))
(clobber (reg:CC FLAGS_REG))])])
-(define_insn "*addqi_ext<mode>_1"
+;; Alternative 1 is needed to work around LRA limitation, see PR82524.
+(define_insn_and_split "*addqi_ext<mode>_1"
[(set (zero_extract:SWI248
- (match_operand 0 "int248_register_operand" "+Q,Q")
+ (match_operand 0 "int248_register_operand" "+Q,&Q")
(const_int 8)
(const_int 8))
(subreg:SWI248
(plus:QI
(subreg:QI
(match_operator:SWI248 3 "extract_operator"
- [(match_operand 1 "int248_register_operand" "0,0")
+ [(match_operand 1 "int248_register_operand" "0,!Q")
(const_int 8)
(const_int 8)]) 0)
- (match_operand:QI 2 "general_x64constmem_operand" "QnBc,m")) 0))
+ (match_operand:QI 2 "general_operand" "QnBn,QnBn")) 0))
(clobber (reg:CC FLAGS_REG))]
- "/* FIXME: without this LRA can't reload this pattern, see PR82524. */
- rtx_equal_p (operands[0], operands[1])"
+ ""
{
+ if (which_alternative)
+ return "#";
+
switch (get_attr_type (insn))
{
case TYPE_INCDEC:
if (operands[2] == const1_rtx)
return "inc{b}\t%h0";
else
- {
+ {
gcc_assert (operands[2] == constm1_rtx);
- return "dec{b}\t%h0";
- }
+ return "dec{b}\t%h0";
+ }
default:
return "add{b}\t{%2, %h0|%h0, %2}";
}
}
- [(set_attr "isa" "*,nox64")
+ "reload_completed
+ && !rtx_equal_p (operands[0], operands[1])"
+ [(set (zero_extract:SWI248
+ (match_dup 0) (const_int 8) (const_int 8))
+ (zero_extract:SWI248
+ (match_dup 1) (const_int 8) (const_int 8)))
+ (parallel
+ [(set (zero_extract:SWI248
+ (match_dup 0) (const_int 8) (const_int 8))
+ (subreg:SWI248
+ (plus:QI
+ (subreg:QI
+ (match_op_dup 3
+ [(match_dup 0) (const_int 8) (const_int 8)]) 0)
+ (match_dup 2)) 0))
+ (clobber (reg:CC FLAGS_REG))])]
+ ""
+ [(set_attr "addr" "gpr8")
(set (attr "type")
(if_then_else (match_operand:QI 2 "incdec_operand")
(const_string "incdec")
(const_string "alu")))
(set_attr "mode" "QI")])
-(define_insn "*addqi_ext<mode>_2"
+;; Alternative 1 is needed to work around LRA limitation, see PR82524.
+(define_insn_and_split "*<insn>qi_ext<mode>_2"
[(set (zero_extract:SWI248
- (match_operand 0 "int248_register_operand" "+Q")
+ (match_operand 0 "int248_register_operand" "+Q,&Q")
(const_int 8)
(const_int 8))
(subreg:SWI248
- (plus:QI
+ (plusminus:QI
(subreg:QI
(match_operator:SWI248 3 "extract_operator"
- [(match_operand 1 "int248_register_operand" "%0")
+ [(match_operand 1 "int248_register_operand" "<comm>0,!Q")
(const_int 8)
(const_int 8)]) 0)
(subreg:QI
(match_operator:SWI248 4 "extract_operator"
- [(match_operand 2 "int248_register_operand" "Q")
+ [(match_operand 2 "int248_register_operand" "Q,Q")
(const_int 8)
(const_int 8)]) 0)) 0))
- (clobber (reg:CC FLAGS_REG))]
- "/* FIXME: without this LRA can't reload this pattern, see PR82524. */
- rtx_equal_p (operands[0], operands[1])
- || rtx_equal_p (operands[0], operands[2])"
- "add{b}\t{%h2, %h0|%h0, %h2}"
+ (clobber (reg:CC FLAGS_REG))]
+ ""
+ "@
+ <insn>{b}\t{%h2, %h0|%h0, %h2}
+ #"
+ "reload_completed
+ && !(rtx_equal_p (operands[0], operands[1])
+ || (<CODE> == PLUS && rtx_equal_p (operands[0], operands[2])))"
+ [(set (zero_extract:SWI248
+ (match_dup 0) (const_int 8) (const_int 8))
+ (zero_extract:SWI248
+ (match_dup 1) (const_int 8) (const_int 8)))
+ (parallel
+ [(set (zero_extract:SWI248
+ (match_dup 0) (const_int 8) (const_int 8))
+ (subreg:SWI248
+ (plusminus:QI
+ (subreg:QI
+ (match_op_dup 3
+ [(match_dup 0) (const_int 8) (const_int 8)]) 0)
+ (subreg:QI
+ (match_op_dup 4
+ [(match_dup 2) (const_int 8) (const_int 8)]) 0)) 0))
+ (clobber (reg:CC FLAGS_REG))])]
+ ""
[(set_attr "type" "alu")
(set_attr "mode" "QI")])
[(set (reg:CCO FLAGS_REG)
(eq:CCO (plus:<DWI>
(sign_extend:<DWI>
- (match_operand:SWI 1 "nonimmediate_operand" "%0,0"))
+ (match_operand:SWI 1 "nonimmediate_operand" "%0,0,rm,r"))
(sign_extend:<DWI>
- (match_operand:SWI 2 "<general_sext_operand>" "<r>We,m")))
+ (match_operand:SWI 2 "<general_sext_operand>" "<r>We,m,rWe,m")))
(sign_extend:<DWI>
(plus:SWI (match_dup 1) (match_dup 2)))))
- (set (match_operand:SWI 0 "nonimmediate_operand" "=<r>m,<r>")
+ (set (match_operand:SWI 0 "nonimmediate_operand" "=<r>m,<r>,r,r")
(plus:SWI (match_dup 1) (match_dup 2)))]
- "ix86_binary_operator_ok (PLUS, <MODE>mode, operands)"
- "add{<imodesuffix>}\t{%2, %0|%0, %2}"
- [(set_attr "type" "alu")
+ "ix86_binary_operator_ok (PLUS, <MODE>mode, operands, TARGET_APX_NDD)"
+ "@
+ add{<imodesuffix>}\t{%2, %0|%0, %2}
+ add{<imodesuffix>}\t{%2, %0|%0, %2}
+ add{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}
+ add{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}"
+ [(set_attr "isa" "*,*,apx_ndd,apx_ndd")
+ (set_attr "type" "alu")
(set_attr "mode" "<MODE>")])
(define_insn "addv<mode>4_1"
[(set (reg:CCO FLAGS_REG)
(eq:CCO (plus:<DWI>
(sign_extend:<DWI>
- (match_operand:SWI 1 "nonimmediate_operand" "0"))
+ (match_operand:SWI 1 "nonimmediate_operand" "0,rm"))
(match_operand:<DWI> 3 "const_int_operand"))
(sign_extend:<DWI>
(plus:SWI
(match_dup 1)
- (match_operand:SWI 2 "x86_64_immediate_operand" "<i>")))))
- (set (match_operand:SWI 0 "nonimmediate_operand" "=<r>m")
+ (match_operand:SWI 2 "x86_64_immediate_operand" "<i>,<i>")))))
+ (set (match_operand:SWI 0 "nonimmediate_operand" "=<r>m,r")
(plus:SWI (match_dup 1) (match_dup 2)))]
- "ix86_binary_operator_ok (PLUS, <MODE>mode, operands)
+ "ix86_binary_operator_ok (PLUS, <MODE>mode, operands, TARGET_APX_NDD)
&& CONST_INT_P (operands[2])
&& INTVAL (operands[2]) == INTVAL (operands[3])"
- "add{<imodesuffix>}\t{%2, %0|%0, %2}"
- [(set_attr "type" "alu")
+ "@
+ add{<imodesuffix>}\t{%2, %0|%0, %2}
+ add{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}"
+ [(set_attr "isa" "*,apx_ndd")
+ (set_attr "type" "alu")
(set_attr "mode" "<MODE>")
(set (attr "length_immediate")
(cond [(match_test "IN_RANGE (INTVAL (operands[2]), -128, 127)")
(eq:CCO
(plus:<QPWI>
(sign_extend:<QPWI>
- (match_operand:<DWI> 1 "nonimmediate_operand" "%0,0"))
+ (match_operand:<DWI> 1 "nonimmediate_operand" "%0,0,ro,r"))
(sign_extend:<QPWI>
- (match_operand:<DWI> 2 "nonimmediate_operand" "r,o")))
+ (match_operand:<DWI> 2 "nonimmediate_operand" "r,o,r,o")))
(sign_extend:<QPWI>
(plus:<DWI> (match_dup 1) (match_dup 2)))))
- (set (match_operand:<DWI> 0 "nonimmediate_operand" "=ro,r")
+ (set (match_operand:<DWI> 0 "nonimmediate_operand" "=ro,r,&r,&r")
(plus:<DWI> (match_dup 1) (match_dup 2)))]
- "ix86_binary_operator_ok (PLUS, <DWI>mode, operands)"
+ "ix86_binary_operator_ok (PLUS, <DWI>mode, operands, TARGET_APX_NDD)"
"#"
"&& reload_completed"
[(parallel [(set (reg:CCC FLAGS_REG)
(match_dup 5)))])]
{
split_double_mode (<DWI>mode, &operands[0], 3, &operands[0], &operands[3]);
-})
+}
+[(set_attr "isa" "*,*,apx_ndd,apx_ndd")])
(define_insn_and_split "*addv<dwi>4_doubleword_1"
[(set (reg:CCO FLAGS_REG)
(eq:CCO
(plus:<QPWI>
(sign_extend:<QPWI>
- (match_operand:<DWI> 1 "nonimmediate_operand" "%0"))
- (match_operand:<QPWI> 3 "const_scalar_int_operand" "n"))
+ (match_operand:<DWI> 1 "nonimmediate_operand" "%0,rm"))
+ (match_operand:<QPWI> 3 "const_scalar_int_operand" "n,n"))
(sign_extend:<QPWI>
(plus:<DWI>
(match_dup 1)
- (match_operand:<DWI> 2 "x86_64_hilo_general_operand" "<di>")))))
- (set (match_operand:<DWI> 0 "nonimmediate_operand" "=ro")
+ (match_operand:<DWI> 2 "x86_64_hilo_general_operand" "<di>,<di>")))))
+ (set (match_operand:<DWI> 0 "nonimmediate_operand" "=ro,&r")
(plus:<DWI> (match_dup 1) (match_dup 2)))]
- "ix86_binary_operator_ok (PLUS, <DWI>mode, operands)
+ "ix86_binary_operator_ok (PLUS, <DWI>mode, operands, TARGET_APX_NDD)
&& CONST_SCALAR_INT_P (operands[2])
&& rtx_equal_p (operands[2], operands[3])"
"#"
split_double_mode (<DWI>mode, &operands[0], 3, &operands[0], &operands[3]);
if (operands[2] == const0_rtx)
{
+ if (!rtx_equal_p (operands[0], operands[1]))
+ emit_move_insn (operands[0], operands[1]);
emit_insn (gen_addv<mode>4_1 (operands[3], operands[4], operands[5],
operands[5]));
DONE;
}
-})
+}
+[(set_attr "isa" "*,apx_ndd")])
(define_insn "*addv<mode>4_overflow_1"
[(set (reg:CCO FLAGS_REG)
(match_operator:<DWI> 4 "ix86_carry_flag_operator"
[(match_operand 3 "flags_reg_operand") (const_int 0)])
(sign_extend:<DWI>
- (match_operand:SWI 1 "nonimmediate_operand" "%0,0")))
+ (match_operand:SWI 1 "nonimmediate_operand" "%0,0,rm,r")))
(sign_extend:<DWI>
- (match_operand:SWI 2 "<general_sext_operand>" "rWe,m")))
+ (match_operand:SWI 2 "<general_sext_operand>" "rWe,m,rWe,m")))
(sign_extend:<DWI>
(plus:SWI
(plus:SWI
[(match_dup 3) (const_int 0)])
(match_dup 1))
(match_dup 2)))))
- (set (match_operand:SWI 0 "nonimmediate_operand" "=rm,r")
+ (set (match_operand:SWI 0 "nonimmediate_operand" "=rm,r,r,r")
(plus:SWI
(plus:SWI
(match_op_dup 5 [(match_dup 3) (const_int 0)])
(match_dup 1))
(match_dup 2)))]
- "ix86_binary_operator_ok (PLUS, <MODE>mode, operands)"
- "adc{<imodesuffix>}\t{%2, %0|%0, %2}"
- [(set_attr "type" "alu")
+ "ix86_binary_operator_ok (PLUS, <MODE>mode, operands, TARGET_APX_NDD)"
+ "@
+ adc{<imodesuffix>}\t{%2, %0|%0, %2}
+ adc{<imodesuffix>}\t{%2, %0|%0, %2}
+ adc{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}
+ adc{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}"
+ [(set_attr "isa" "*,*,apx_ndd,apx_ndd")
+ (set_attr "type" "alu")
(set_attr "mode" "<MODE>")])
(define_insn "*addv<mode>4_overflow_2"
(match_operator:<DWI> 4 "ix86_carry_flag_operator"
[(match_operand 3 "flags_reg_operand") (const_int 0)])
(sign_extend:<DWI>
- (match_operand:SWI 1 "nonimmediate_operand" "%0")))
- (match_operand:<DWI> 6 "const_int_operand" "n"))
+ (match_operand:SWI 1 "nonimmediate_operand" "%0,rm")))
+ (match_operand:<DWI> 6 "const_int_operand" "n,n"))
(sign_extend:<DWI>
(plus:SWI
(plus:SWI
(match_operator:SWI 5 "ix86_carry_flag_operator"
[(match_dup 3) (const_int 0)])
(match_dup 1))
- (match_operand:SWI 2 "x86_64_immediate_operand" "e")))))
- (set (match_operand:SWI 0 "nonimmediate_operand" "=rm")
+ (match_operand:SWI 2 "x86_64_immediate_operand" "e,e")))))
+ (set (match_operand:SWI 0 "nonimmediate_operand" "=rm,r")
(plus:SWI
(plus:SWI
(match_op_dup 5 [(match_dup 3) (const_int 0)])
(match_dup 1))
(match_dup 2)))]
- "ix86_binary_operator_ok (PLUS, <MODE>mode, operands)
+ "ix86_binary_operator_ok (PLUS, <MODE>mode, operands, TARGET_APX_NDD)
&& CONST_INT_P (operands[2])
&& INTVAL (operands[2]) == INTVAL (operands[6])"
- "adc{<imodesuffix>}\t{%2, %0|%0, %2}"
- [(set_attr "type" "alu")
+ "@
+ adc{<imodesuffix>}\t{%2, %0|%0, %2}
+ adc{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}"
+ [(set_attr "isa" "*,apx_ndd")
+ (set_attr "type" "alu")
(set_attr "mode" "<MODE>")
(set (attr "length_immediate")
(if_then_else (match_test "IN_RANGE (INTVAL (operands[2]), -128, 127)")
(minus:SDWIM (match_operand:SDWIM 1 "nonimmediate_operand")
(match_operand:SDWIM 2 "<general_hilo_operand>")))]
""
- "ix86_expand_binary_operator (MINUS, <MODE>mode, operands); DONE;")
+{
+ ix86_expand_binary_operator (MINUS, <MODE>mode, operands, TARGET_APX_NDD);
+ DONE;
+})
(define_insn_and_split "*sub<dwi>3_doubleword"
- [(set (match_operand:<DWI> 0 "nonimmediate_operand" "=ro,r")
+ [(set (match_operand:<DWI> 0 "nonimmediate_operand" "=ro,r,&r,&r")
(minus:<DWI>
- (match_operand:<DWI> 1 "nonimmediate_operand" "0,0")
- (match_operand:<DWI> 2 "x86_64_hilo_general_operand" "r<di>,o")))
+ (match_operand:<DWI> 1 "nonimmediate_operand" "0,0,ro,r")
+ (match_operand:<DWI> 2 "x86_64_hilo_general_operand" "r<di>,o,r<di>,o")))
(clobber (reg:CC FLAGS_REG))]
- "ix86_binary_operator_ok (MINUS, <MODE>mode, operands)"
+ "ix86_binary_operator_ok (MINUS, <MODE>mode, operands, TARGET_APX_NDD)"
"#"
"&& reload_completed"
[(parallel [(set (reg:CC FLAGS_REG)
split_double_mode (<DWI>mode, &operands[0], 3, &operands[0], &operands[3]);
if (operands[2] == const0_rtx)
{
- ix86_expand_binary_operator (MINUS, <MODE>mode, &operands[3]);
+ if (!rtx_equal_p (operands[0], operands[1]))
+ emit_move_insn (operands[0], operands[1]);
+ ix86_expand_binary_operator (MINUS, <MODE>mode, &operands[3],
+ TARGET_APX_NDD);
DONE;
}
-})
+}
+[(set_attr "isa" "*,*,apx_ndd,apx_ndd")])
(define_insn_and_split "*sub<dwi>3_doubleword_zext"
- [(set (match_operand:<DWI> 0 "nonimmediate_operand" "=r,o")
+ [(set (match_operand:<DWI> 0 "nonimmediate_operand" "=r,o,&r,&r")
(minus:<DWI>
- (match_operand:<DWI> 1 "nonimmediate_operand" "0,0")
+ (match_operand:<DWI> 1 "nonimmediate_operand" "0,0,r,o")
(zero_extend:<DWI>
- (match_operand:DWIH 2 "nonimmediate_operand" "rm,r"))))
+ (match_operand:DWIH 2 "nonimmediate_operand" "rm,r,rm,r"))))
(clobber (reg:CC FLAGS_REG))]
- "ix86_binary_operator_ok (UNKNOWN, <DWI>mode, operands)"
+ "ix86_binary_operator_ok (UNKNOWN, <DWI>mode, operands, TARGET_APX_NDD)"
"#"
"&& reload_completed"
[(parallel [(set (reg:CC FLAGS_REG)
(ltu:DWIH (reg:CC FLAGS_REG) (const_int 0)))
(const_int 0)))
(clobber (reg:CC FLAGS_REG))])]
- "split_double_mode (<DWI>mode, &operands[0], 2, &operands[0], &operands[3]);")
+ "split_double_mode (<DWI>mode, &operands[0], 2, &operands[0], &operands[3]);"
+[(set_attr "isa" "*,*,apx_ndd,apx_ndd")])
(define_insn "*sub<mode>_1"
- [(set (match_operand:SWI 0 "nonimmediate_operand" "=<r>m,<r>")
+ [(set (match_operand:SWI 0 "nonimmediate_operand" "=<r>m,<r>,r,r")
(minus:SWI
- (match_operand:SWI 1 "nonimmediate_operand" "0,0")
- (match_operand:SWI 2 "<general_operand>" "<r><i>,<m>")))
+ (match_operand:SWI 1 "nonimmediate_operand" "0,0,rm,r")
+ (match_operand:SWI 2 "<general_operand>" "<r><i>,<m>,r<i>,<m>")))
(clobber (reg:CC FLAGS_REG))]
- "ix86_binary_operator_ok (MINUS, <MODE>mode, operands)"
- "sub{<imodesuffix>}\t{%2, %0|%0, %2}"
- [(set_attr "type" "alu")
+ "ix86_binary_operator_ok (MINUS, <MODE>mode, operands, TARGET_APX_NDD)"
+ "@
+ sub{<imodesuffix>}\t{%2, %0|%0, %2}
+ sub{<imodesuffix>}\t{%2, %0|%0, %2}
+ sub{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}
+ sub{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}"
+ [(set_attr "isa" "*,*,apx_ndd,apx_ndd")
+ (set_attr "type" "alu")
(set_attr "mode" "<MODE>")])
(define_insn "*subsi_1_zext"
- [(set (match_operand:DI 0 "register_operand" "=r")
+ [(set (match_operand:DI 0 "register_operand" "=r,r,r")
(zero_extend:DI
- (minus:SI (match_operand:SI 1 "register_operand" "0")
- (match_operand:SI 2 "x86_64_general_operand" "rBMe"))))
+ (minus:SI (match_operand:SI 1 "nonimmediate_operand" "0,r,rm")
+ (match_operand:SI 2 "x86_64_general_operand" "rBMe,rBMe,re"))))
(clobber (reg:CC FLAGS_REG))]
- "TARGET_64BIT && ix86_binary_operator_ok (MINUS, SImode, operands)"
- "sub{l}\t{%2, %k0|%k0, %2}"
- [(set_attr "type" "alu")
+ "TARGET_64BIT
+ && ix86_binary_operator_ok (MINUS, SImode, operands, TARGET_APX_NDD)"
+ "@
+ sub{l}\t{%2, %k0|%k0, %2}
+ sub{l}\t{%2, %1, %k0|%k0, %1, %2}
+ sub{l}\t{%2, %1, %k0|%k0, %1, %2}"
+ [(set_attr "isa" "*,apx_ndd,apx_ndd")
+ (set_attr "type" "alu")
(set_attr "mode" "SI")])
;; Alternative 1 is needed to work around LRA limitation, see PR82524.
"@
sub{<imodesuffix>}\t{%2, %0|%0, %2}
#"
- "&& reload_completed"
+ "&& reload_completed
+ && !(rtx_equal_p (operands[0], operands[1]))"
[(set (strict_low_part (match_dup 0)) (match_dup 1))
(parallel
[(set (strict_low_part (match_dup 0))
[(set_attr "type" "alu")
(set_attr "mode" "<MODE>")])
+;; Alternative 1 is needed to work around LRA limitation, see PR82524.
+(define_insn_and_split "*subqi_ext<mode>_1_slp"
+ [(set (strict_low_part (match_operand:QI 0 "register_operand" "+Q,&Q"))
+ (minus:QI
+ (match_operand:QI 1 "nonimmediate_operand" "0,!qm")
+ (subreg:QI
+ (match_operator:SWI248 3 "extract_operator"
+ [(match_operand 2 "int248_register_operand" "Q,Q")
+ (const_int 8)
+ (const_int 8)]) 0)))
+ (clobber (reg:CC FLAGS_REG))]
+ "!TARGET_PARTIAL_REG_STALL || optimize_function_for_size_p (cfun)"
+ "@
+ sub{b}\t{%h2, %0|%0, %h2}
+ #"
+ "&& reload_completed
+ && !rtx_equal_p (operands[0], operands[1])"
+ [(set (strict_low_part (match_dup 0)) (match_dup 1))
+ (parallel
+ [(set (strict_low_part (match_dup 0))
+ (minus:QI
+ (match_dup 0)
+ (subreg:QI
+ (match_op_dup 3
+ [(match_dup 2) (const_int 8) (const_int 8)]) 0)))
+ (clobber (reg:CC FLAGS_REG))])]
+ ""
+ [(set_attr "type" "alu")
+ (set_attr "mode" "QI")])
+
+(define_insn_and_split "*subqi_ext<mode>_2_slp"
+ [(set (strict_low_part (match_operand:QI 0 "register_operand" "+&Q"))
+ (minus:QI
+ (subreg:QI
+ (match_operator:SWI248 3 "extract_operator"
+ [(match_operand 1 "int248_register_operand" "Q")
+ (const_int 8)
+ (const_int 8)]) 0)
+ (subreg:QI
+ (match_operator:SWI248 4 "extract_operator"
+ [(match_operand 2 "int248_register_operand" "Q")
+ (const_int 8)
+ (const_int 8)]) 0)))
+ (clobber (reg:CC FLAGS_REG))]
+ "!TARGET_PARTIAL_REG_STALL || optimize_function_for_size_p (cfun)"
+ "#"
+ "&& reload_completed"
+ [(set (strict_low_part (match_dup 0))
+ (subreg:QI
+ (match_op_dup 3
+ [(match_dup 1) (const_int 8) (const_int 8)]) 0))
+ (parallel
+ [(set (strict_low_part (match_dup 0))
+ (minus:QI
+ (match_dup 0)
+ (subreg:QI
+ (match_op_dup 4
+ [(match_dup 2) (const_int 8) (const_int 8)]) 0)))
+ (clobber (reg:CC FLAGS_REG))])]
+ ""
+ [(set_attr "type" "alu")
+ (set_attr "mode" "QI")])
+
(define_insn "*sub<mode>_2"
[(set (reg FLAGS_REG)
(compare
(minus:SWI
- (match_operand:SWI 1 "nonimmediate_operand" "0,0")
- (match_operand:SWI 2 "<general_operand>" "<r><i>,<m>"))
+ (match_operand:SWI 1 "nonimmediate_operand" "0,0,rm,r")
+ (match_operand:SWI 2 "<general_operand>" "<r><i>,<m>,r<i>,<m>"))
(const_int 0)))
- (set (match_operand:SWI 0 "nonimmediate_operand" "=<r>m,<r>")
+ (set (match_operand:SWI 0 "nonimmediate_operand" "=<r>m,<r>,r,r")
(minus:SWI (match_dup 1) (match_dup 2)))]
"ix86_match_ccmode (insn, CCGOCmode)
- && ix86_binary_operator_ok (MINUS, <MODE>mode, operands)"
- "sub{<imodesuffix>}\t{%2, %0|%0, %2}"
- [(set_attr "type" "alu")
+ && ix86_binary_operator_ok (MINUS, <MODE>mode, operands, TARGET_APX_NDD)"
+ "@
+ sub{<imodesuffix>}\t{%2, %0|%0, %2}
+ sub{<imodesuffix>}\t{%2, %0|%0, %2}
+ sub{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}
+ sub{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}"
+ [(set_attr "isa" "*,*,apx_ndd,apx_ndd")
+ (set_attr "type" "alu")
(set_attr "mode" "<MODE>")])
(define_insn "*subsi_2_zext"
[(set (reg FLAGS_REG)
(compare
- (minus:SI (match_operand:SI 1 "register_operand" "0")
- (match_operand:SI 2 "x86_64_general_operand" "rBMe"))
+ (minus:SI (match_operand:SI 1 "nonimmediate_operand" "0,r,rm")
+ (match_operand:SI 2 "x86_64_general_operand" "rBMe,rBMe,re"))
(const_int 0)))
- (set (match_operand:DI 0 "register_operand" "=r")
+ (set (match_operand:DI 0 "register_operand" "=r,r,r")
(zero_extend:DI
(minus:SI (match_dup 1)
(match_dup 2))))]
"TARGET_64BIT && ix86_match_ccmode (insn, CCGOCmode)
- && ix86_binary_operator_ok (MINUS, SImode, operands)"
- "sub{l}\t{%2, %k0|%k0, %2}"
- [(set_attr "type" "alu")
+ && ix86_binary_operator_ok (MINUS, SImode, operands, TARGET_APX_NDD)"
+ "@
+ sub{l}\t{%2, %k0|%k0, %2}
+ sub{l}\t{%2, %1, %k0|%k0, %1, %2}
+ sub{l}\t{%2, %1, %k0|%k0, %1, %2}"
+ [(set_attr "isa" "*,apx_ndd,apx_ndd")
+ (set_attr "type" "alu")
(set_attr "mode" "SI")])
(define_insn "*subqi_ext<mode>_0"
- [(set (match_operand:QI 0 "nonimm_x64constmem_operand" "=QBc,m")
+ [(set (match_operand:QI 0 "nonimmediate_operand" "=QBn")
(minus:QI
- (match_operand:QI 1 "nonimm_x64constmem_operand" "0,0")
+ (match_operand:QI 1 "nonimmediate_operand" "0")
(subreg:QI
(match_operator:SWI248 3 "extract_operator"
- [(match_operand 2 "int248_register_operand" "Q,Q")
+ [(match_operand 2 "int248_register_operand" "Q")
(const_int 8)
(const_int 8)]) 0)))
(clobber (reg:CC FLAGS_REG))]
""
"sub{b}\t{%h2, %0|%0, %h2}"
- [(set_attr "isa" "*,nox64")
+ [(set_attr "addr" "gpr8")
(set_attr "type" "alu")
(set_attr "mode" "QI")])
-(define_insn "*subqi_ext<mode>_2"
+(define_insn_and_split "*subqi_ext2<mode>_0"
+ [(set (match_operand:QI 0 "register_operand" "=&Q")
+ (minus:QI
+ (subreg:QI
+ (match_operator:SWI248 3 "extract_operator"
+ [(match_operand 1 "int248_register_operand" "Q")
+ (const_int 8)
+ (const_int 8)]) 0)
+ (subreg:QI
+ (match_operator:SWI248 4 "extract_operator"
+ [(match_operand 2 "int248_register_operand" "Q")
+ (const_int 8)
+ (const_int 8)]) 0)))
+ (clobber (reg:CC FLAGS_REG))]
+ ""
+ "#"
+ "&& reload_completed"
+ [(set (match_dup 0)
+ (subreg:QI
+ (match_op_dup 3
+ [(match_dup 1) (const_int 8) (const_int 8)]) 0))
+ (parallel
+ [(set (match_dup 0)
+ (minus:QI
+ (match_dup 0)
+ (subreg:QI
+ (match_op_dup 4
+ [(match_dup 2) (const_int 8) (const_int 8)]) 0)))
+ (clobber (reg:CC FLAGS_REG))])]
+ ""
+ [(set_attr "type" "alu")
+ (set_attr "mode" "QI")])
+
+;; Alternative 1 is needed to work around LRA limitation, see PR82524.
+(define_insn_and_split "*subqi_ext<mode>_1"
[(set (zero_extract:SWI248
- (match_operand 0 "int248_register_operand" "+Q")
+ (match_operand 0 "int248_register_operand" "+Q,&Q")
(const_int 8)
(const_int 8))
(subreg:SWI248
(minus:QI
(subreg:QI
(match_operator:SWI248 3 "extract_operator"
- [(match_operand 1 "int248_register_operand" "0")
+ [(match_operand 1 "int248_register_operand" "0,!Q")
(const_int 8)
(const_int 8)]) 0)
- (subreg:QI
- (match_operator:SWI248 4 "extract_operator"
- [(match_operand 2 "int248_register_operand" "Q")
- (const_int 8)
- (const_int 8)]) 0)) 0))
- (clobber (reg:CC FLAGS_REG))]
- "/* FIXME: without this LRA can't reload this pattern, see PR82524. */
- rtx_equal_p (operands[0], operands[1])"
- "sub{b}\t{%h2, %h0|%h0, %h2}"
- [(set_attr "type" "alu")
+ (match_operand:QI 2 "general_operand" "QnBn,QnBn")) 0))
+ (clobber (reg:CC FLAGS_REG))]
+ ""
+ "@
+ sub{b}\t{%2, %h0|%h0, %2}
+ #"
+ "reload_completed
+ && !(rtx_equal_p (operands[0], operands[1]))"
+ [(set (zero_extract:SWI248
+ (match_dup 0) (const_int 8) (const_int 8))
+ (zero_extract:SWI248
+ (match_dup 1) (const_int 8) (const_int 8)))
+ (parallel
+ [(set (zero_extract:SWI248
+ (match_dup 0) (const_int 8) (const_int 8))
+ (subreg:SWI248
+ (minus:QI
+ (subreg:QI
+ (match_op_dup 3
+ [(match_dup 0) (const_int 8) (const_int 8)]) 0)
+ (match_dup 2)) 0))
+ (clobber (reg:CC FLAGS_REG))])]
+ ""
+ [(set_attr "addr" "gpr8")
+ (set_attr "type" "alu")
(set_attr "mode" "QI")])
;; Subtract with jump on overflow.
(pc)))]
""
{
- ix86_fixup_binary_operands_no_copy (MINUS, <MODE>mode, operands);
+ ix86_fixup_binary_operands_no_copy (MINUS, <MODE>mode, operands,
+ TARGET_APX_NDD);
if (CONST_SCALAR_INT_P (operands[2]))
operands[4] = operands[2];
else
[(set (reg:CCO FLAGS_REG)
(eq:CCO (minus:<DWI>
(sign_extend:<DWI>
- (match_operand:SWI 1 "nonimmediate_operand" "0,0"))
+ (match_operand:SWI 1 "nonimmediate_operand" "0,0,rm,r"))
(sign_extend:<DWI>
- (match_operand:SWI 2 "<general_sext_operand>" "<r>We,m")))
+ (match_operand:SWI 2 "<general_sext_operand>" "<r>We,m,rWe,m")))
(sign_extend:<DWI>
(minus:SWI (match_dup 1) (match_dup 2)))))
- (set (match_operand:SWI 0 "nonimmediate_operand" "=<r>m,<r>")
+ (set (match_operand:SWI 0 "nonimmediate_operand" "=<r>m,<r>,r,r")
(minus:SWI (match_dup 1) (match_dup 2)))]
- "ix86_binary_operator_ok (MINUS, <MODE>mode, operands)"
- "sub{<imodesuffix>}\t{%2, %0|%0, %2}"
- [(set_attr "type" "alu")
+ "ix86_binary_operator_ok (MINUS, <MODE>mode, operands, TARGET_APX_NDD)"
+ "@
+ sub{<imodesuffix>}\t{%2, %0|%0, %2}
+ sub{<imodesuffix>}\t{%2, %0|%0, %2}
+ sub{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}
+ sub{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}"
+ [(set_attr "isa" "*,*,apx_ndd,apx_ndd")
+ (set_attr "type" "alu")
(set_attr "mode" "<MODE>")])
(define_insn "subv<mode>4_1"
[(set (reg:CCO FLAGS_REG)
(eq:CCO (minus:<DWI>
(sign_extend:<DWI>
- (match_operand:SWI 1 "nonimmediate_operand" "0"))
+ (match_operand:SWI 1 "nonimmediate_operand" "0,rm"))
(match_operand:<DWI> 3 "const_int_operand"))
(sign_extend:<DWI>
(minus:SWI
(match_dup 1)
- (match_operand:SWI 2 "x86_64_immediate_operand" "<i>")))))
- (set (match_operand:SWI 0 "nonimmediate_operand" "=<r>m")
+ (match_operand:SWI 2 "x86_64_immediate_operand" "<i>,<i>")))))
+ (set (match_operand:SWI 0 "nonimmediate_operand" "=<r>m,r")
(minus:SWI (match_dup 1) (match_dup 2)))]
- "ix86_binary_operator_ok (MINUS, <MODE>mode, operands)
+ "ix86_binary_operator_ok (MINUS, <MODE>mode, operands, TARGET_APX_NDD)
&& CONST_INT_P (operands[2])
&& INTVAL (operands[2]) == INTVAL (operands[3])"
- "sub{<imodesuffix>}\t{%2, %0|%0, %2}"
- [(set_attr "type" "alu")
+ "@
+ sub{<imodesuffix>}\t{%2, %0|%0, %2}
+ sub{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}"
+ [(set_attr "isa" "*,apx_ndd")
+ (set_attr "type" "alu")
(set_attr "mode" "<MODE>")
(set (attr "length_immediate")
(cond [(match_test "IN_RANGE (INTVAL (operands[2]), -128, 127)")
(eq:CCO
(minus:<QPWI>
(sign_extend:<QPWI>
- (match_operand:<DWI> 1 "nonimmediate_operand" "0,0"))
+ (match_operand:<DWI> 1 "nonimmediate_operand" "0,0,ro,r"))
(sign_extend:<QPWI>
- (match_operand:<DWI> 2 "nonimmediate_operand" "r,o")))
+ (match_operand:<DWI> 2 "nonimmediate_operand" "r,o,r,o")))
(sign_extend:<QPWI>
(minus:<DWI> (match_dup 1) (match_dup 2)))))
- (set (match_operand:<DWI> 0 "nonimmediate_operand" "=ro,r")
+ (set (match_operand:<DWI> 0 "nonimmediate_operand" "=ro,r,&r,&r")
(minus:<DWI> (match_dup 1) (match_dup 2)))]
- "ix86_binary_operator_ok (MINUS, <MODE>mode, operands)"
+ "ix86_binary_operator_ok (MINUS, <MODE>mode, operands, TARGET_APX_NDD)"
"#"
"&& reload_completed"
[(parallel [(set (reg:CC FLAGS_REG)
(match_dup 5)))])]
{
split_double_mode (<DWI>mode, &operands[0], 3, &operands[0], &operands[3]);
-})
+}
+[(set_attr "isa" "*,*,apx_ndd,apx_ndd")])
(define_insn_and_split "*subv<dwi>4_doubleword_1"
[(set (reg:CCO FLAGS_REG)
(eq:CCO
(minus:<QPWI>
(sign_extend:<QPWI>
- (match_operand:<DWI> 1 "nonimmediate_operand" "0"))
+ (match_operand:<DWI> 1 "nonimmediate_operand" "0,ro"))
(match_operand:<QPWI> 3 "const_scalar_int_operand"))
(sign_extend:<QPWI>
(minus:<DWI>
(match_dup 1)
- (match_operand:<DWI> 2 "x86_64_hilo_general_operand" "<di>")))))
- (set (match_operand:<DWI> 0 "nonimmediate_operand" "=ro")
+ (match_operand:<DWI> 2 "x86_64_hilo_general_operand" "<di>,<di>")))))
+ (set (match_operand:<DWI> 0 "nonimmediate_operand" "=ro,&r")
(minus:<DWI> (match_dup 1) (match_dup 2)))]
- "ix86_binary_operator_ok (MINUS, <MODE>mode, operands)
+ "ix86_binary_operator_ok (MINUS, <MODE>mode, operands, TARGET_APX_NDD)
&& CONST_SCALAR_INT_P (operands[2])
&& rtx_equal_p (operands[2], operands[3])"
"#"
split_double_mode (<DWI>mode, &operands[0], 3, &operands[0], &operands[3]);
if (operands[2] == const0_rtx)
{
+ if (!rtx_equal_p (operands[0], operands[1]))
+ emit_move_insn (operands[0], operands[1]);
emit_insn (gen_subv<mode>4_1 (operands[3], operands[4], operands[5],
operands[5]));
DONE;
}
-})
+}
+[(set_attr "isa" "*,apx_ndd")])
(define_insn "*subv<mode>4_overflow_1"
[(set (reg:CCO FLAGS_REG)
(minus:<DWI>
(minus:<DWI>
(sign_extend:<DWI>
- (match_operand:SWI 1 "nonimmediate_operand" "%0,0"))
+ (match_operand:SWI 1 "nonimmediate_operand" "%0,0,rm,r"))
(match_operator:<DWI> 4 "ix86_carry_flag_operator"
[(match_operand 3 "flags_reg_operand") (const_int 0)]))
(sign_extend:<DWI>
- (match_operand:SWI 2 "<general_sext_operand>" "rWe,m")))
+ (match_operand:SWI 2 "<general_sext_operand>" "rWe,m,rWe,m")))
(sign_extend:<DWI>
(minus:SWI
(minus:SWI
(match_operator:SWI 5 "ix86_carry_flag_operator"
[(match_dup 3) (const_int 0)]))
(match_dup 2)))))
- (set (match_operand:SWI 0 "nonimmediate_operand" "=rm,r")
+ (set (match_operand:SWI 0 "nonimmediate_operand" "=rm,r,r,r")
(minus:SWI
(minus:SWI
(match_dup 1)
(match_op_dup 5 [(match_dup 3) (const_int 0)]))
(match_dup 2)))]
- "ix86_binary_operator_ok (MINUS, <MODE>mode, operands)"
- "sbb{<imodesuffix>}\t{%2, %0|%0, %2}"
- [(set_attr "type" "alu")
+ "ix86_binary_operator_ok (MINUS, <MODE>mode, operands, TARGET_APX_NDD)"
+ "@
+ sbb{<imodesuffix>}\t{%2, %0|%0, %2}
+ sbb{<imodesuffix>}\t{%2, %0|%0, %2}
+ sbb{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}
+ sbb{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}"
+ [(set_attr "isa" "*,*,apx_ndd,apx_ndd")
+ (set_attr "type" "alu")
(set_attr "mode" "<MODE>")])
(define_insn "*subv<mode>4_overflow_2"
(minus:<DWI>
(minus:<DWI>
(sign_extend:<DWI>
- (match_operand:SWI 1 "nonimmediate_operand" "%0"))
+ (match_operand:SWI 1 "nonimmediate_operand" "%0,rm"))
(match_operator:<DWI> 4 "ix86_carry_flag_operator"
[(match_operand 3 "flags_reg_operand") (const_int 0)]))
- (match_operand:<DWI> 6 "const_int_operand" "n"))
+ (match_operand:<DWI> 6 "const_int_operand" "n,n"))
(sign_extend:<DWI>
(minus:SWI
(minus:SWI
(match_dup 1)
(match_operator:SWI 5 "ix86_carry_flag_operator"
[(match_dup 3) (const_int 0)]))
- (match_operand:SWI 2 "x86_64_immediate_operand" "e")))))
- (set (match_operand:SWI 0 "nonimmediate_operand" "=rm")
+ (match_operand:SWI 2 "x86_64_immediate_operand" "e,e")))))
+ (set (match_operand:SWI 0 "nonimmediate_operand" "=rm,r")
(minus:SWI
(minus:SWI
(match_dup 1)
(match_op_dup 5 [(match_dup 3) (const_int 0)]))
(match_dup 2)))]
- "ix86_binary_operator_ok (MINUS, <MODE>mode, operands)
+ "ix86_binary_operator_ok (MINUS, <MODE>mode, operands, TARGET_APX_NDD)
&& CONST_INT_P (operands[2])
&& INTVAL (operands[2]) == INTVAL (operands[6])"
- "sbb{<imodesuffix>}\t{%2, %0|%0, %2}"
- [(set_attr "type" "alu")
+ "@
+ sbb{<imodesuffix>}\t{%2, %0|%0, %2}
+ sbb{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}"
+ [(set_attr "isa" "*,apx_ndd")
+ (set_attr "type" "alu")
(set_attr "mode" "<MODE>")
(set (attr "length_immediate")
(if_then_else (match_test "IN_RANGE (INTVAL (operands[2]), -128, 127)")
(label_ref (match_operand 3))
(pc)))]
""
- "ix86_fixup_binary_operands_no_copy (MINUS, <MODE>mode, operands);")
+ "ix86_fixup_binary_operands_no_copy (MINUS, <MODE>mode, operands,
+ TARGET_APX_NDD);")
(define_insn "*sub<mode>_3"
[(set (reg FLAGS_REG)
- (compare (match_operand:SWI 1 "nonimmediate_operand" "0,0")
- (match_operand:SWI 2 "<general_operand>" "<r><i>,<m>")))
- (set (match_operand:SWI 0 "nonimmediate_operand" "=<r>m,<r>")
+ (compare (match_operand:SWI 1 "nonimmediate_operand" "0,0,rm,r")
+ (match_operand:SWI 2 "<general_operand>" "<r><i>,<m>,r<i>,<m>")))
+ (set (match_operand:SWI 0 "nonimmediate_operand" "=<r>m,<r>i,r,r")
(minus:SWI (match_dup 1) (match_dup 2)))]
"ix86_match_ccmode (insn, CCmode)
- && ix86_binary_operator_ok (MINUS, <MODE>mode, operands)"
- "sub{<imodesuffix>}\t{%2, %0|%0, %2}"
- [(set_attr "type" "alu")
+ && ix86_binary_operator_ok (MINUS, <MODE>mode, operands, TARGET_APX_NDD)"
+ "@
+ sub{<imodesuffix>}\t{%2, %0|%0, %2}
+ sub{<imodesuffix>}\t{%2, %0|%0, %2}
+ sub{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}
+ sub{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}"
+ [(set_attr "isa" "*,*,apx_ndd,apx_ndd")
+ (set_attr "type" "alu")
(set_attr "mode" "<MODE>")])
(define_peephole2
(define_insn "*subsi_3_zext"
[(set (reg FLAGS_REG)
- (compare (match_operand:SI 1 "register_operand" "0")
- (match_operand:SI 2 "x86_64_general_operand" "rBMe")))
- (set (match_operand:DI 0 "register_operand" "=r")
+ (compare (match_operand:SI 1 "nonimmediate_operand" "0,r,rm")
+ (match_operand:SI 2 "x86_64_general_operand" "rBMe,rBMe,re")))
+ (set (match_operand:DI 0 "register_operand" "=r,r,r")
(zero_extend:DI
(minus:SI (match_dup 1)
(match_dup 2))))]
"TARGET_64BIT && ix86_match_ccmode (insn, CCmode)
- && ix86_binary_operator_ok (MINUS, SImode, operands)"
- "sub{l}\t{%2, %1|%1, %2}"
- [(set_attr "type" "alu")
+ && ix86_binary_operator_ok (MINUS, SImode, operands, TARGET_APX_NDD)"
+ "@
+ sub{l}\t{%2, %1|%1, %2}
+ sub{l}\t{%2, %1, %k0|%k0, %1, %2}
+ sub{l}\t{%2, %1, %k0|%k0, %1, %2}"
+ [(set_attr "isa" "*,apx_ndd,apx_ndd")
+ (set_attr "type" "alu")
(set_attr "mode" "SI")])
\f
;; Add with carry and subtract with borrow
(define_insn "@add<mode>3_carry"
- [(set (match_operand:SWI 0 "nonimmediate_operand" "=<r>m,<r>")
+ [(set (match_operand:SWI 0 "nonimmediate_operand" "=<r>m,<r>,r,r")
(plus:SWI
(plus:SWI
(match_operator:SWI 4 "ix86_carry_flag_operator"
[(match_operand 3 "flags_reg_operand") (const_int 0)])
- (match_operand:SWI 1 "nonimmediate_operand" "%0,0"))
- (match_operand:SWI 2 "<general_operand>" "<r><i>,<m>")))
+ (match_operand:SWI 1 "nonimmediate_operand" "%0,0,rm,r"))
+ (match_operand:SWI 2 "<general_operand>" "<r><i>,<m>,r<i>,<m>")))
(clobber (reg:CC FLAGS_REG))]
- "ix86_binary_operator_ok (PLUS, <MODE>mode, operands)"
- "adc{<imodesuffix>}\t{%2, %0|%0, %2}"
- [(set_attr "type" "alu")
+ "ix86_binary_operator_ok (PLUS, <MODE>mode, operands, TARGET_APX_NDD)"
+ "@
+ adc{<imodesuffix>}\t{%2, %0|%0, %2}
+ adc{<imodesuffix>}\t{%2, %0|%0, %2}
+ adc{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}
+ adc{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}"
+ [(set_attr "isa" "*,*,apx_ndd,apx_ndd")
+ (set_attr "type" "alu")
(set_attr "use_carry" "1")
(set_attr "pent_pair" "pu")
(set_attr "mode" "<MODE>")])
(set_attr "mode" "<MODE>")])
(define_insn "*addsi3_carry_zext"
- [(set (match_operand:DI 0 "register_operand" "=r")
+ [(set (match_operand:DI 0 "register_operand" "=r,r,r")
(zero_extend:DI
(plus:SI
(plus:SI (match_operator:SI 3 "ix86_carry_flag_operator"
[(reg FLAGS_REG) (const_int 0)])
- (match_operand:SI 1 "register_operand" "%0"))
- (match_operand:SI 2 "x86_64_general_operand" "rBMe"))))
+ (match_operand:SI 1 "nonimmediate_operand" "%0,r,rm"))
+ (match_operand:SI 2 "x86_64_general_operand" "rBMe,rBMe,re"))))
(clobber (reg:CC FLAGS_REG))]
- "TARGET_64BIT && ix86_binary_operator_ok (PLUS, SImode, operands)"
- "adc{l}\t{%2, %k0|%k0, %2}"
- [(set_attr "type" "alu")
+ "TARGET_64BIT
+ && ix86_binary_operator_ok (PLUS, SImode, operands, TARGET_APX_NDD)"
+ "@
+ adc{l}\t{%2, %k0|%k0, %2}
+ adc{l}\t{%2, %1, %k0|%k0, %1, %2}
+ adc{l}\t{%2, %1, %k0|%k0, %1, %2}"
+ [(set_attr "isa" "*,apx_ndd,apx_ndd")
+ (set_attr "type" "alu")
(set_attr "use_carry" "1")
(set_attr "pent_pair" "pu")
(set_attr "mode" "SI")])
(define_insn "*addsi3_carry_zext_0"
- [(set (match_operand:DI 0 "register_operand" "=r")
+ [(set (match_operand:DI 0 "register_operand" "=r,r")
(zero_extend:DI
(plus:SI (match_operator:SI 2 "ix86_carry_flag_operator"
[(reg FLAGS_REG) (const_int 0)])
- (match_operand:SI 1 "register_operand" "0"))))
+ (match_operand:SI 1 "nonimmediate_operand" "0,rm"))))
(clobber (reg:CC FLAGS_REG))]
"TARGET_64BIT"
- "adc{l}\t{$0, %k0|%k0, 0}"
- [(set_attr "type" "alu")
+ "@
+ adc{l}\t{$0, %k0|%k0, 0}
+ adc{l}\t{$0, %1, %k0|%k0, %1, 0}"
+ [(set_attr "isa" "*,apx_ndd")
+ (set_attr "type" "alu")
(set_attr "use_carry" "1")
(set_attr "pent_pair" "pu")
(set_attr "mode" "SI")])
(define_insn "*addsi3_carry_zext_0r"
- [(set (match_operand:DI 0 "register_operand" "=r")
+ [(set (match_operand:DI 0 "register_operand" "=r,r")
(zero_extend:DI
(plus:SI (match_operator:SI 2 "ix86_carry_flag_unset_operator"
[(reg FLAGS_REG) (const_int 0)])
- (match_operand:SI 1 "register_operand" "0"))))
+ (match_operand:SI 1 "nonimmediate_operand" "0,rm"))))
(clobber (reg:CC FLAGS_REG))]
"TARGET_64BIT"
- "sbb{l}\t{$-1, %k0|%k0, -1}"
- [(set_attr "type" "alu")
+ "@
+ sbb{l}\t{$-1, %k0|%k0, -1}
+ sbb{l}\t{$-1, %1, %k0|%k0, %1, -1}"
+ [(set_attr "isa" "*,apx_ndd")
+ (set_attr "type" "alu")
(set_attr "use_carry" "1")
(set_attr "pent_pair" "pu")
(set_attr "mode" "SI")])
(plus:SWI48
(match_operator:SWI48 5 "ix86_carry_flag_operator"
[(match_operand 3 "flags_reg_operand") (const_int 0)])
- (match_operand:SWI48 1 "nonimmediate_operand" "%0,0"))
- (match_operand:SWI48 2 "nonimmediate_operand" "r,rm")))
+ (match_operand:SWI48 1 "nonimmediate_operand" "%0,0,rm,r"))
+ (match_operand:SWI48 2 "nonimmediate_operand" "r,rm,r,m")))
(plus:<DWI>
(zero_extend:<DWI> (match_dup 2))
(match_operator:<DWI> 4 "ix86_carry_flag_operator"
[(match_dup 3) (const_int 0)]))))
- (set (match_operand:SWI48 0 "nonimmediate_operand" "=rm,r")
+ (set (match_operand:SWI48 0 "nonimmediate_operand" "=rm,r,r,r")
(plus:SWI48 (plus:SWI48 (match_op_dup 5
[(match_dup 3) (const_int 0)])
(match_dup 1))
(match_dup 2)))]
- "ix86_binary_operator_ok (PLUS, <MODE>mode, operands)"
- "adc{<imodesuffix>}\t{%2, %0|%0, %2}"
- [(set_attr "type" "alu")
+ "ix86_binary_operator_ok (PLUS, <MODE>mode, operands, TARGET_APX_NDD)"
+ "@
+ adc{<imodesuffix>}\t{%2, %0|%0, %2}
+ adc{<imodesuffix>}\t{%2, %0|%0, %2}
+ adc{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}
+ adc{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}"
+ [(set_attr "isa" "*,*,apx_ndd,apx_ndd")
+ (set_attr "type" "alu")
(set_attr "use_carry" "1")
(set_attr "pent_pair" "pu")
(set_attr "mode" "<MODE>")])
(match_dup 1)))
(set (match_operand:SWI48 0 "nonimmediate_operand")
(plus:SWI48 (match_dup 1) (match_dup 2)))])]
- "ix86_binary_operator_ok (PLUS, <MODE>mode, operands)")
+ "ix86_binary_operator_ok (PLUS, <MODE>mode, operands, TARGET_APX_NDD)")
(define_insn "*addcarry<mode>_1"
[(set (reg:CCC FLAGS_REG)
(plus:SWI48
(match_operator:SWI48 5 "ix86_carry_flag_operator"
[(match_operand 3 "flags_reg_operand") (const_int 0)])
- (match_operand:SWI48 1 "nonimmediate_operand" "%0"))
- (match_operand:SWI48 2 "x86_64_immediate_operand" "e")))
+ (match_operand:SWI48 1 "nonimmediate_operand" "%0,rm"))
+ (match_operand:SWI48 2 "x86_64_immediate_operand" "e,e")))
(plus:<DWI>
(match_operand:<DWI> 6 "const_scalar_int_operand")
(match_operator:<DWI> 4 "ix86_carry_flag_operator"
[(match_dup 3) (const_int 0)]))))
- (set (match_operand:SWI48 0 "nonimmediate_operand" "=rm")
+ (set (match_operand:SWI48 0 "nonimmediate_operand" "=rm,r")
(plus:SWI48 (plus:SWI48 (match_op_dup 5
[(match_dup 3) (const_int 0)])
(match_dup 1))
(match_dup 2)))]
- "ix86_binary_operator_ok (PLUS, <MODE>mode, operands)
+ "ix86_binary_operator_ok (PLUS, <MODE>mode, operands, TARGET_APX_NDD)
&& CONST_INT_P (operands[2])
/* Check that operands[6] is operands[2] zero extended from
<MODE>mode to <DWI>mode. */
&& ((unsigned HOST_WIDE_INT) CONST_WIDE_INT_ELT (operands[6], 0)
== UINTVAL (operands[2]))
&& CONST_WIDE_INT_ELT (operands[6], 1) == 0))"
- "adc{<imodesuffix>}\t{%2, %0|%0, %2}"
- [(set_attr "type" "alu")
+ "@
+ adc{<imodesuffix>}\t{%2, %0|%0, %2}
+ adc{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}"
+ [(set_attr "isa" "*,apx_ndd")
+ (set_attr "type" "alu")
(set_attr "use_carry" "1")
(set_attr "pent_pair" "pu")
(set_attr "mode" "<MODE>")
(const_string "4")))])
(define_insn "@sub<mode>3_carry"
- [(set (match_operand:SWI 0 "nonimmediate_operand" "=<r>m,<r>")
+ [(set (match_operand:SWI 0 "nonimmediate_operand" "=<r>m,<r>,r,r")
(minus:SWI
(minus:SWI
- (match_operand:SWI 1 "nonimmediate_operand" "0,0")
+ (match_operand:SWI 1 "nonimmediate_operand" "0,0,rm,r")
(match_operator:SWI 4 "ix86_carry_flag_operator"
[(match_operand 3 "flags_reg_operand") (const_int 0)]))
- (match_operand:SWI 2 "<general_operand>" "<r><i>,<m>")))
+ (match_operand:SWI 2 "<general_operand>" "<r><i>,<m>,r<i>,<m>")))
(clobber (reg:CC FLAGS_REG))]
- "ix86_binary_operator_ok (MINUS, <MODE>mode, operands)"
- "sbb{<imodesuffix>}\t{%2, %0|%0, %2}"
- [(set_attr "type" "alu")
+ "ix86_binary_operator_ok (MINUS, <MODE>mode, operands, TARGET_APX_NDD)"
+ "@
+ sbb{<imodesuffix>}\t{%2, %0|%0, %2}
+ sbb{<imodesuffix>}\t{%2, %0|%0, %2}
+ sbb{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}
+ sbb{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}"
+ [(set_attr "isa" "*,*,apx_ndd,apx_ndd")
+ (set_attr "type" "alu")
(set_attr "use_carry" "1")
(set_attr "pent_pair" "pu")
(set_attr "mode" "<MODE>")])
(set_attr "mode" "<MODE>")])
(define_insn "*subsi3_carry_zext"
- [(set (match_operand:DI 0 "register_operand" "=r")
+ [(set (match_operand:DI 0 "register_operand" "=r,r,r")
(zero_extend:DI
(minus:SI
(minus:SI
- (match_operand:SI 1 "register_operand" "0")
+ (match_operand:SI 1 "nonimmediate_operand" "0,r,rm")
(match_operator:SI 3 "ix86_carry_flag_operator"
[(reg FLAGS_REG) (const_int 0)]))
- (match_operand:SI 2 "x86_64_general_operand" "rBMe"))))
+ (match_operand:SI 2 "x86_64_general_operand" "rBMe,rBMe,re"))))
(clobber (reg:CC FLAGS_REG))]
- "TARGET_64BIT && ix86_binary_operator_ok (MINUS, SImode, operands)"
- "sbb{l}\t{%2, %k0|%k0, %2}"
- [(set_attr "type" "alu")
+ "TARGET_64BIT
+ && ix86_binary_operator_ok (MINUS, SImode, operands, TARGET_APX_NDD)"
+ "@
+ sbb{l}\t{%2, %k0|%k0, %2}
+ sbb{l}\t{%2, %1, %k0|%k0, %1, %2}
+ sbb{l}\t{%2, %1, %k0|%k0, %1, %2}"
+ [(set_attr "isa" "*,apx_ndd,apx_ndd")
+ (set_attr "type" "alu")
(set_attr "use_carry" "1")
(set_attr "pent_pair" "pu")
(set_attr "mode" "SI")])
[(set (reg:CCC FLAGS_REG)
(compare:CCC
(zero_extend:<DWI>
- (match_operand:SWI48 1 "nonimmediate_operand" "0,0"))
+ (match_operand:SWI48 1 "nonimmediate_operand" "0,0,r,rm"))
(plus:<DWI>
(match_operator:<DWI> 4 "ix86_carry_flag_operator"
[(match_operand 3 "flags_reg_operand") (const_int 0)])
(zero_extend:<DWI>
- (match_operand:SWI48 2 "nonimmediate_operand" "r,rm")))))
- (set (match_operand:SWI48 0 "nonimmediate_operand" "=rm,r")
+ (match_operand:SWI48 2 "nonimmediate_operand" "r,rm,rm,r")))))
+ (set (match_operand:SWI48 0 "nonimmediate_operand" "=rm,r,r,r")
(minus:SWI48 (minus:SWI48
(match_dup 1)
(match_operator:SWI48 5 "ix86_carry_flag_operator"
[(match_dup 3) (const_int 0)]))
(match_dup 2)))]
- "ix86_binary_operator_ok (MINUS, <MODE>mode, operands)"
- "sbb{<imodesuffix>}\t{%2, %0|%0, %2}"
- [(set_attr "type" "alu")
+ "ix86_binary_operator_ok (MINUS, <MODE>mode, operands, TARGET_APX_NDD)"
+ "@
+ sbb{<imodesuffix>}\t{%2, %0|%0, %2}
+ sbb{<imodesuffix>}\t{%2, %0|%0, %2}
+ sbb{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}
+ sbb{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}"
+ [(set_attr "isa" "*,*,apx_ndd,apx_ndd")
+ (set_attr "type" "alu")
(set_attr "use_carry" "1")
(set_attr "pent_pair" "pu")
(set_attr "mode" "<MODE>")])
(match_operand:SWI48 2 "<general_operand>")))
(set (match_operand:SWI48 0 "register_operand")
(minus:SWI48 (match_dup 1) (match_dup 2)))])]
- "ix86_binary_operator_ok (MINUS, <MODE>mode, operands)")
+ "ix86_binary_operator_ok (MINUS, <MODE>mode, operands, TARGET_APX_NDD)")
(define_expand "uaddc<mode>5"
[(match_operand:SWI48 0 "register_operand")
[(set (reg:CCC FLAGS_REG)
(compare:CCC
(plus:SWI
- (match_operand:SWI 1 "nonimmediate_operand" "%0")
- (match_operand:SWI 2 "<general_operand>" "<g>"))
+ (match_operand:SWI 1 "nonimmediate_operand" "%0,r,rm")
+ (match_operand:SWI 2 "<general_operand>" "<g>,<g>,re"))
(match_dup 1)))
- (clobber (match_scratch:SWI 0 "=<r>"))]
+ (clobber (match_scratch:SWI 0 "=<r>,r,r"))]
"!(MEM_P (operands[1]) && MEM_P (operands[2]))"
- "add{<imodesuffix>}\t{%2, %0|%0, %2}"
- [(set_attr "type" "alu")
+ "@
+ add{<imodesuffix>}\t{%2, %0|%0, %2}
+ add{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}
+ add{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}"
+ [(set_attr "isa" "*,apx_ndd,apx_ndd")
+ (set_attr "type" "alu")
(set_attr "mode" "<MODE>")])
-(define_insn "*add<mode>3_cc_overflow_1"
+(define_insn "@add<mode>3_cc_overflow_1"
[(set (reg:CCC FLAGS_REG)
(compare:CCC
(plus:SWI
- (match_operand:SWI 1 "nonimmediate_operand" "%0,0")
- (match_operand:SWI 2 "<general_operand>" "<r><i>,<m>"))
+ (match_operand:SWI 1 "nonimmediate_operand" "%0,0,rm,r")
+ (match_operand:SWI 2 "<general_operand>" "<r><i>,<m>,r<i>,<m>"))
(match_dup 1)))
- (set (match_operand:SWI 0 "nonimmediate_operand" "=<r>m,<r>")
+ (set (match_operand:SWI 0 "nonimmediate_operand" "=<r>m,<r>,r,r")
(plus:SWI (match_dup 1) (match_dup 2)))]
- "ix86_binary_operator_ok (PLUS, <MODE>mode, operands)"
- "add{<imodesuffix>}\t{%2, %0|%0, %2}"
- [(set_attr "type" "alu")
+ "ix86_binary_operator_ok (PLUS, <MODE>mode, operands, TARGET_APX_NDD)"
+ "@
+ add{<imodesuffix>}\t{%2, %0|%0, %2}
+ add{<imodesuffix>}\t{%2, %0|%0, %2}
+ add{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}
+ add{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}"
+ [(set_attr "isa" "*,*,apx_ndd,apx_ndd")
+ (set_attr "type" "alu")
(set_attr "mode" "<MODE>")])
(define_peephole2
[(set (reg:CCC FLAGS_REG)
(compare:CCC
(plus:SI
- (match_operand:SI 1 "nonimmediate_operand" "%0")
- (match_operand:SI 2 "x86_64_general_operand" "rBMe"))
+ (match_operand:SI 1 "nonimmediate_operand" "%0,r,rm")
+ (match_operand:SI 2 "x86_64_general_operand" "rBMe,rBMe,re"))
(match_dup 1)))
- (set (match_operand:DI 0 "register_operand" "=r")
+ (set (match_operand:DI 0 "register_operand" "=r,r,r")
(zero_extend:DI (plus:SI (match_dup 1) (match_dup 2))))]
- "TARGET_64BIT && ix86_binary_operator_ok (PLUS, SImode, operands)"
- "add{l}\t{%2, %k0|%k0, %2}"
- [(set_attr "type" "alu")
+ "TARGET_64BIT
+ && ix86_binary_operator_ok (PLUS, SImode, operands, TARGET_APX_NDD)"
+ "@
+ add{l}\t{%2, %k0|%k0, %2}
+ add{l}\t{%2, %1, %k0|%k0, %1, %2}
+ add{l}\t{%2, %1, %k0|%k0, %1, %2}"
+ [(set_attr "isa" "*,apx_ndd,apx_ndd")
+ (set_attr "type" "alu")
(set_attr "mode" "SI")])
(define_insn "*add<mode>3_cconly_overflow_2"
[(set (reg:CCC FLAGS_REG)
(compare:CCC
(plus:SWI
- (match_operand:SWI 1 "nonimmediate_operand" "%0")
- (match_operand:SWI 2 "<general_operand>" "<g>"))
+ (match_operand:SWI 1 "nonimmediate_operand" "%0,r,rm")
+ (match_operand:SWI 2 "<general_operand>" "<g>,<g>,re"))
(match_dup 2)))
- (clobber (match_scratch:SWI 0 "=<r>"))]
+ (clobber (match_scratch:SWI 0 "=<r>,r,r"))]
"!(MEM_P (operands[1]) && MEM_P (operands[2]))"
- "add{<imodesuffix>}\t{%2, %0|%0, %2}"
- [(set_attr "type" "alu")
+ "@
+ add{<imodesuffix>}\t{%2, %0|%0, %2}
+ add{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}
+ add{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}"
+ [(set_attr "isa" "*,apx_ndd,apx_ndd")
+ (set_attr "type" "alu")
(set_attr "mode" "<MODE>")])
(define_insn "*add<mode>3_cc_overflow_2"
[(set (reg:CCC FLAGS_REG)
(compare:CCC
(plus:SWI
- (match_operand:SWI 1 "nonimmediate_operand" "%0,0")
- (match_operand:SWI 2 "<general_operand>" "<r><i>,<m>"))
+ (match_operand:SWI 1 "nonimmediate_operand" "%0,0,rm,r")
+ (match_operand:SWI 2 "<general_operand>" "<r><i>,<m>,r<i>,<m>"))
(match_dup 2)))
- (set (match_operand:SWI 0 "nonimmediate_operand" "=<r>m,<r>")
+ (set (match_operand:SWI 0 "nonimmediate_operand" "=<r>m,<r>,r,r")
(plus:SWI (match_dup 1) (match_dup 2)))]
- "ix86_binary_operator_ok (PLUS, <MODE>mode, operands)"
- "add{<imodesuffix>}\t{%2, %0|%0, %2}"
- [(set_attr "type" "alu")
+ "ix86_binary_operator_ok (PLUS, <MODE>mode, operands, TARGET_APX_NDD)"
+ "@
+ add{<imodesuffix>}\t{%2, %0|%0, %2}
+ add{<imodesuffix>}\t{%2, %0|%0, %2}
+ add{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}
+ add{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}"
+ [(set_attr "isa" "*,*,apx_ndd,apx_ndd")
+ (set_attr "type" "alu")
(set_attr "mode" "<MODE>")])
(define_insn "*addsi3_zext_cc_overflow_2"
[(set (reg:CCC FLAGS_REG)
(compare:CCC
(plus:SI
- (match_operand:SI 1 "nonimmediate_operand" "%0")
- (match_operand:SI 2 "x86_64_general_operand" "rBMe"))
+ (match_operand:SI 1 "nonimmediate_operand" "%0,r,rm")
+ (match_operand:SI 2 "x86_64_general_operand" "rBMe,rBMe,re"))
(match_dup 2)))
- (set (match_operand:DI 0 "register_operand" "=r")
+ (set (match_operand:DI 0 "register_operand" "=r,r,r")
(zero_extend:DI (plus:SI (match_dup 1) (match_dup 2))))]
- "TARGET_64BIT && ix86_binary_operator_ok (PLUS, SImode, operands)"
- "add{l}\t{%2, %k0|%k0, %2}"
- [(set_attr "type" "alu")
+ "TARGET_64BIT
+ && ix86_binary_operator_ok (PLUS, SImode, operands, TARGET_APX_NDD)"
+ "@
+ add{l}\t{%2, %k0|%k0, %2}
+ add{l}\t{%2, %1, %k0|%k0, %1, %2}
+ add{l}\t{%2, %1, %k0|%k0, %1, %2}"
+ [(set_attr "isa" "*,apx_ndd,apx_ndd")
+ (set_attr "type" "alu")
(set_attr "mode" "SI")])
(define_insn_and_split "*add<dwi>3_doubleword_cc_overflow_1"
[(set (reg:CCC FLAGS_REG)
(compare:CCC
(plus:<DWI>
- (match_operand:<DWI> 1 "nonimmediate_operand" "%0,0")
- (match_operand:<DWI> 2 "x86_64_hilo_general_operand" "r<di>,o"))
+ (match_operand:<DWI> 1 "nonimmediate_operand" "%0,0,ro,r")
+ (match_operand:<DWI> 2 "x86_64_hilo_general_operand" "r<di>,o,r<di>,o"))
(match_dup 1)))
- (set (match_operand:<DWI> 0 "nonimmediate_operand" "=ro,r")
+ (set (match_operand:<DWI> 0 "nonimmediate_operand" "=ro,r,&r,&r")
(plus:<DWI> (match_dup 1) (match_dup 2)))]
- "ix86_binary_operator_ok (PLUS, <DWI>mode, operands)"
+ "ix86_binary_operator_ok (PLUS, <DWI>mode, operands, TARGET_APX_NDD)"
"#"
"&& reload_completed"
[(parallel [(set (reg:CCC FLAGS_REG)
split_double_mode (<DWI>mode, &operands[0], 3, &operands[0], &operands[3]);
if (operands[2] == const0_rtx)
{
+ if (!rtx_equal_p (operands[0], operands[1]))
+ emit_move_insn (operands[0], operands[1]);
emit_insn (gen_addcarry<mode>_0 (operands[3], operands[4], operands[5]));
DONE;
}
operands[5], <MODE>mode);
else
operands[6] = gen_rtx_ZERO_EXTEND (<DWI>mode, operands[5]);
-})
+}
+[(set_attr "isa" "*,*,apx_ndd,apx_ndd")])
;; x == 0 with zero flag test can be done also as x < 1U with carry flag
;; test, where the latter is preferrable if we have some carry consuming
(match_operand:SWI 1 "nonimmediate_operand"))
(match_operand:SWI 2 "<general_operand>")))
(clobber (reg:CC FLAGS_REG))]
- "ix86_binary_operator_ok (PLUS, <MODE>mode, operands)
+ "ix86_binary_operator_ok (PLUS, <MODE>mode, operands, TARGET_APX_NDD)
&& ix86_pre_reload_split ()"
"#"
"&& 1"
"CONST_INT_P (operands[2])
&& (<MODE>mode != DImode
|| INTVAL (operands[2]) != HOST_WIDE_INT_C (-0x80000000))
- && ix86_binary_operator_ok (PLUS, <MODE>mode, operands)
+ && ix86_binary_operator_ok (PLUS, <MODE>mode, operands, TARGET_APX_NDD)
&& ix86_pre_reload_split ()"
"#"
"&& 1"
(const_int 0)))
(match_operand:SWI 2 "<general_operand>")))
(clobber (reg:CC FLAGS_REG))]
- "ix86_binary_operator_ok (MINUS, <MODE>mode, operands)
+ "ix86_binary_operator_ok (MINUS, <MODE>mode, operands, TARGET_APX_NDD)
&& ix86_pre_reload_split ()"
"#"
"&& 1"
"CONST_INT_P (operands[2])
&& (<MODE>mode != DImode
|| INTVAL (operands[2]) != HOST_WIDE_INT_C (-0x80000000))
- && ix86_binary_operator_ok (MINUS, <MODE>mode, operands)
+ && ix86_binary_operator_ok (MINUS, <MODE>mode, operands, TARGET_APX_NDD)
&& ix86_pre_reload_split ()"
"#"
"&& 1"
"CONST_INT_P (operands[2])
&& (<MODE>mode != DImode
|| INTVAL (operands[2]) != HOST_WIDE_INT_C (-0x80000000))
- && ix86_binary_operator_ok (MINUS, <MODE>mode, operands)
+ && ix86_binary_operator_ok (MINUS, <MODE>mode, operands, TARGET_APX_NDD)
&& ix86_pre_reload_split ()"
"#"
"&& 1"
[(parallel [(set (match_operand:<DWI> 0 "register_operand")
(mult:<DWI>
(any_extend:<DWI>
- (match_operand:DWIH 1 "nonimmediate_operand"))
+ (match_operand:DWIH 1 "register_operand"))
(any_extend:<DWI>
- (match_operand:DWIH 2 "register_operand"))))
+ (match_operand:DWIH 2 "nonimmediate_operand"))))
(clobber (reg:CC FLAGS_REG))])])
(define_expand "<u>mulqihi3"
[(parallel [(set (match_operand:HI 0 "register_operand")
(mult:HI
(any_extend:HI
- (match_operand:QI 1 "nonimmediate_operand"))
+ (match_operand:QI 1 "register_operand"))
(any_extend:HI
- (match_operand:QI 2 "register_operand"))))
+ (match_operand:QI 2 "nonimmediate_operand"))))
(clobber (reg:CC FLAGS_REG))])]
"TARGET_QIMODE_MATH")
(define_insn "*bmi2_umul<mode><dwi>3_1"
[(set (match_operand:DWIH 0 "register_operand" "=r")
(mult:DWIH
- (match_operand:DWIH 2 "nonimmediate_operand" "%d")
+ (match_operand:DWIH 2 "register_operand" "%d")
(match_operand:DWIH 3 "nonimmediate_operand" "rm")))
(set (match_operand:DWIH 1 "register_operand" "=r")
- (truncate:DWIH
- (lshiftrt:<DWI>
- (mult:<DWI> (zero_extend:<DWI> (match_dup 2))
- (zero_extend:<DWI> (match_dup 3)))
- (match_operand:QI 4 "const_int_operand"))))]
- "TARGET_BMI2 && INTVAL (operands[4]) == <MODE_SIZE> * BITS_PER_UNIT
- && !(MEM_P (operands[2]) && MEM_P (operands[3]))"
+ (umul_highpart:DWIH (match_dup 2) (match_dup 3)))]
+ "TARGET_BMI2"
"mulx\t{%3, %0, %1|%1, %0, %3}"
[(set_attr "type" "imulx")
(set_attr "prefix" "vex")
(set_attr "mode" "<MODE>")])
+;; Tweak *bmi2_umul<mode><dwi>3_1 to eliminate following mov.
+(define_peephole2
+ [(parallel [(set (match_operand:DWIH 0 "general_reg_operand")
+ (mult:DWIH (match_operand:DWIH 2 "register_operand")
+ (match_operand:DWIH 3 "nonimmediate_operand")))
+ (set (match_operand:DWIH 1 "general_reg_operand")
+ (umul_highpart:DWIH (match_dup 2) (match_dup 3)))])
+ (set (match_operand:DWIH 4 "general_reg_operand")
+ (match_operand:DWIH 5 "general_reg_operand"))]
+ "TARGET_BMI2
+ && ((REGNO (operands[5]) == REGNO (operands[0])
+ && REGNO (operands[1]) != REGNO (operands[4]))
+ || (REGNO (operands[5]) == REGNO (operands[1])
+ && REGNO (operands[0]) != REGNO (operands[4])))
+ && peep2_reg_dead_p (2, operands[5])"
+ [(parallel [(set (match_dup 0) (mult:DWIH (match_dup 2) (match_dup 3)))
+ (set (match_dup 1)
+ (umul_highpart:DWIH (match_dup 2) (match_dup 3)))])]
+{
+ if (REGNO (operands[5]) == REGNO (operands[0]))
+ operands[0] = operands[4];
+ else
+ operands[1] = operands[4];
+})
+
(define_insn "*umul<mode><dwi>3_1"
[(set (match_operand:<DWI> 0 "register_operand" "=r,A")
(mult:<DWI>
(zero_extend:<DWI>
- (match_operand:DWIH 1 "nonimmediate_operand" "%d,0"))
+ (match_operand:DWIH 1 "register_operand" "%d,a"))
(zero_extend:<DWI>
(match_operand:DWIH 2 "nonimmediate_operand" "rm,rm"))))
(clobber (reg:CC FLAGS_REG))]
[(parallel [(set (match_dup 3)
(mult:DWIH (match_dup 1) (match_dup 2)))
(set (match_dup 4)
- (truncate:DWIH
- (lshiftrt:<DWI>
- (mult:<DWI> (zero_extend:<DWI> (match_dup 1))
- (zero_extend:<DWI> (match_dup 2)))
- (match_dup 5))))])]
+ (umul_highpart:DWIH (match_dup 1) (match_dup 2)))])]
{
split_double_mode (<DWI>mode, &operands[0], 1, &operands[3], &operands[4]);
[(set (match_operand:<DWI> 0 "register_operand" "=A")
(mult:<DWI>
(sign_extend:<DWI>
- (match_operand:DWIH 1 "nonimmediate_operand" "%0"))
+ (match_operand:DWIH 1 "register_operand" "%a"))
(sign_extend:<DWI>
(match_operand:DWIH 2 "nonimmediate_operand" "rm"))))
(clobber (reg:CC FLAGS_REG))]
[(set (match_operand:HI 0 "register_operand" "=a")
(mult:HI
(any_extend:HI
- (match_operand:QI 1 "nonimmediate_operand" "%0"))
+ (match_operand:QI 1 "register_operand" "%0"))
(any_extend:HI
(match_operand:QI 2 "nonimmediate_operand" "qm"))))
(clobber (reg:CC FLAGS_REG))]
(set_attr "bdver1_decode" "direct")
(set_attr "mode" "QI")])
+;; Widening multiplication peephole2s to tweak register allocation.
+;; mov imm,%rdx; mov %rdi,%rax; mulq %rdx -> mov imm,%rax; mulq %rdi
+(define_peephole2
+ [(set (match_operand:DWIH 0 "general_reg_operand")
+ (match_operand:DWIH 1 "immediate_operand"))
+ (set (match_operand:DWIH 2 "general_reg_operand")
+ (match_operand:DWIH 3 "general_reg_operand"))
+ (parallel [(set (match_operand:<DWI> 4 "general_reg_operand")
+ (mult:<DWI> (zero_extend:<DWI> (match_dup 2))
+ (zero_extend:<DWI> (match_dup 0))))
+ (clobber (reg:CC FLAGS_REG))])]
+ "REGNO (operands[3]) != AX_REG
+ && REGNO (operands[0]) != REGNO (operands[2])
+ && REGNO (operands[0]) != REGNO (operands[3])
+ && (REGNO (operands[0]) == REGNO (operands[4])
+ || REGNO (operands[0]) == DX_REG
+ || peep2_reg_dead_p (3, operands[0]))"
+ [(set (match_dup 2) (match_dup 1))
+ (parallel [(set (match_dup 4)
+ (mult:<DWI> (zero_extend:<DWI> (match_dup 2))
+ (zero_extend:<DWI> (match_dup 3))))
+ (clobber (reg:CC FLAGS_REG))])])
+
+;; mov imm,%rax; mov %rdi,%rdx; mulx %rax -> mov imm,%rdx; mulx %rdi
+(define_peephole2
+ [(set (match_operand:DWIH 0 "general_reg_operand")
+ (match_operand:DWIH 1 "immediate_operand"))
+ (set (match_operand:DWIH 2 "general_reg_operand")
+ (match_operand:DWIH 3 "general_reg_operand"))
+ (parallel [(set (match_operand:DWIH 4 "general_reg_operand")
+ (mult:DWIH (match_dup 2) (match_dup 0)))
+ (set (match_operand:DWIH 5 "general_reg_operand")
+ (umul_highpart:DWIH (match_dup 2) (match_dup 0)))])]
+ "REGNO (operands[3]) != DX_REG
+ && REGNO (operands[0]) != REGNO (operands[2])
+ && REGNO (operands[0]) != REGNO (operands[3])
+ && (REGNO (operands[0]) == REGNO (operands[4])
+ || REGNO (operands[0]) == REGNO (operands[5])
+ || peep2_reg_dead_p (3, operands[0]))
+ && (REGNO (operands[2]) == REGNO (operands[4])
+ || REGNO (operands[2]) == REGNO (operands[5])
+ || peep2_reg_dead_p (3, operands[2]))"
+ [(set (match_dup 2) (match_dup 1))
+ (parallel [(set (match_dup 4)
+ (mult:DWIH (match_dup 2) (match_dup 3)))
+ (set (match_dup 5)
+ (umul_highpart:DWIH (match_dup 2) (match_dup 3)))])])
+
;; Highpart multiplication patterns
(define_insn "<s>mul<mode>3_highpart"
[(set (match_operand:DWIH 0 "register_operand" "=d")
(and:QI
(subreg:QI
(match_operator:SWI248 2 "extract_operator"
- [(match_operand 0 "int248_register_operand" "Q,Q")
+ [(match_operand 0 "int248_register_operand" "Q")
(const_int 8)
(const_int 8)]) 0)
- (match_operand:QI 1 "general_x64constmem_operand" "QnBc,m"))
+ (match_operand:QI 1 "general_operand" "QnBn"))
(const_int 0)))]
"ix86_match_ccmode (insn, CCNOmode)"
"test{b}\t{%1, %h0|%h0, %1}"
- [(set_attr "isa" "*,nox64")
+ [(set_attr "addr" "gpr8")
(set_attr "type" "test")
(set_attr "mode" "QI")])
(match_operator 1 "compare_operator"
[(zero_extract:SWI248
(match_operand 2 "int_nonimmediate_operand" "rm")
- (match_operand 3 "const_int_operand")
- (match_operand 4 "const_int_operand"))
+ (match_operand:QI 3 "const_int_operand")
+ (match_operand:QI 4 "const_int_operand"))
(const_int 0)]))]
"/* Ensure that resulting mask is zero or sign extended operand. */
INTVAL (operands[4]) >= 0
operands[3] = gen_int_mode (INTVAL (operands[3]), QImode);
})
+;; Narrow test instructions with immediate operands that test
+;; memory locations for zero. E.g. testl $0x00aa0000, mem can be
+;; converted to testb $0xaa, mem+2. Reject volatile locations and
+;; targets where reading (possibly unaligned) part of memory
+;; location after a large write to the same address causes
+;; store-to-load forwarding stall.
+(define_peephole2
+ [(set (reg:CCZ FLAGS_REG)
+ (compare:CCZ
+ (and:SWI248 (match_operand:SWI248 0 "memory_operand")
+ (match_operand 1 "const_int_operand"))
+ (const_int 0)))]
+ "!TARGET_PARTIAL_MEMORY_READ_STALL && !MEM_VOLATILE_P (operands[0])"
+ [(set (reg:CCZ FLAGS_REG)
+ (compare:CCZ (match_dup 2) (const_int 0)))]
+{
+ unsigned HOST_WIDE_INT ival = UINTVAL (operands[1]);
+ int first_nonzero_byte, bitsize;
+ rtx new_addr, new_const;
+ machine_mode new_mode;
+
+ if (ival == 0)
+ FAIL;
+
+ /* Clear bits outside mode width. */
+ ival &= GET_MODE_MASK (<MODE>mode);
+
+ first_nonzero_byte = ctz_hwi (ival) / BITS_PER_UNIT;
+
+ ival >>= first_nonzero_byte * BITS_PER_UNIT;
+
+ bitsize = sizeof (ival) * BITS_PER_UNIT - clz_hwi (ival);
+
+ if (bitsize <= GET_MODE_BITSIZE (QImode))
+ new_mode = QImode;
+ else if (bitsize <= GET_MODE_BITSIZE (HImode))
+ new_mode = HImode;
+ else if (bitsize <= GET_MODE_BITSIZE (SImode))
+ new_mode = SImode;
+ else
+ new_mode = DImode;
+
+ if (GET_MODE_SIZE (new_mode) >= GET_MODE_SIZE (<MODE>mode))
+ FAIL;
+
+ new_addr = adjust_address (operands[0], new_mode, first_nonzero_byte);
+ new_const = gen_int_mode (ival, new_mode);
+
+ operands[2] = gen_rtx_AND (new_mode, new_addr, new_const);
+})
+
;; %%% This used to optimize known byte-wide and operations to memory,
;; and sometimes to QImode registers. If this is considered useful,
;; it should be done with splitters.
(operands[0], gen_lowpart (mode, operands[1]),
<MODE>mode, mode, 1));
else
- ix86_expand_binary_operator (AND, <MODE>mode, operands);
+ ix86_expand_binary_operator (AND, <MODE>mode, operands, TARGET_APX_NDD);
DONE;
})
(define_insn_and_split "*and<dwi>3_doubleword"
- [(set (match_operand:<DWI> 0 "nonimmediate_operand" "=ro,r")
+ [(set (match_operand:<DWI> 0 "nonimmediate_operand" "=ro,r,&r,&r")
(and:<DWI>
- (match_operand:<DWI> 1 "nonimmediate_operand" "%0,0")
- (match_operand:<DWI> 2 "x86_64_hilo_general_operand" "r<di>,o")))
+ (match_operand:<DWI> 1 "nonimmediate_operand" "%0,0,ro,r")
+ (match_operand:<DWI> 2 "x86_64_hilo_general_operand" "r<di>,o,r<di>,o")))
(clobber (reg:CC FLAGS_REG))]
- "ix86_binary_operator_ok (AND, <DWI>mode, operands)"
+ "ix86_binary_operator_ok (AND, <DWI>mode, operands, TARGET_APX_NDD)"
"#"
"&& reload_completed"
[(const_int:DWIH 0)]
if (operands[2] == const0_rtx)
emit_move_insn (operands[0], const0_rtx);
else if (operands[2] == constm1_rtx)
- emit_insn_deleted_note_p = true;
+ {
+ if (!rtx_equal_p (operands[0], operands[1]))
+ emit_move_insn (operands[0], operands[1]);
+ else
+ emit_insn_deleted_note_p = true;
+ }
else
- ix86_expand_binary_operator (AND, <MODE>mode, &operands[0]);
+ ix86_expand_binary_operator (AND, <MODE>mode, &operands[0], TARGET_APX_NDD);
if (operands[5] == const0_rtx)
emit_move_insn (operands[3], const0_rtx);
else if (operands[5] == constm1_rtx)
{
- if (emit_insn_deleted_note_p)
+ if (!rtx_equal_p (operands[3], operands[4]))
+ emit_move_insn (operands[3], operands[4]);
+ else if (emit_insn_deleted_note_p)
emit_note (NOTE_INSN_DELETED);
}
else
- ix86_expand_binary_operator (AND, <MODE>mode, &operands[3]);
+ ix86_expand_binary_operator (AND, <MODE>mode, &operands[3], TARGET_APX_NDD);
DONE;
-})
+}
+[(set_attr "isa" "*,*,apx_ndd,apx_ndd")])
(define_insn "*anddi_1"
- [(set (match_operand:DI 0 "nonimmediate_operand" "=r,rm,r,r,?k")
+ [(set (match_operand:DI 0 "nonimmediate_operand" "=r,r,rm,r,r,r,r,?k")
(and:DI
- (match_operand:DI 1 "nonimmediate_operand" "%0,0,0,qm,k")
- (match_operand:DI 2 "x86_64_szext_general_operand" "Z,re,m,L,k")))
+ (match_operand:DI 1 "nonimmediate_operand" "%0,r,0,0,rm,r,qm,k")
+ (match_operand:DI 2 "x86_64_szext_general_operand" "Z,Z,re,m,re,m,L,k")))
(clobber (reg:CC FLAGS_REG))]
- "TARGET_64BIT && ix86_binary_operator_ok (AND, DImode, operands)"
+ "TARGET_64BIT
+ && ix86_binary_operator_ok (AND, DImode, operands, TARGET_APX_NDD)"
"@
and{l}\t{%k2, %k0|%k0, %k2}
+ and{l}\t{%k2, %k1, %k0|%k0, %k1, %k2}
and{q}\t{%2, %0|%0, %2}
and{q}\t{%2, %0|%0, %2}
+ and{q}\t{%2, %1, %0|%0, %1, %2}
+ and{q}\t{%2, %1, %0|%0, %1, %2}
#
#"
- [(set_attr "isa" "x64,x64,x64,x64,avx512bw")
- (set_attr "type" "alu,alu,alu,imovx,msklog")
- (set_attr "length_immediate" "*,*,*,0,*")
+ [(set_attr "isa" "x64,apx_ndd,x64,x64,apx_ndd,apx_ndd,x64,avx512bw")
+ (set_attr "type" "alu,alu,alu,alu,alu,alu,imovx,msklog")
+ (set_attr "length_immediate" "*,*,*,*,*,*,0,*")
(set (attr "prefix_rex")
(if_then_else
(and (eq_attr "type" "imovx")
(match_operand 1 "ext_QIreg_operand")))
(const_string "1")
(const_string "*")))
- (set_attr "mode" "SI,DI,DI,SI,DI")])
+ (set_attr "mode" "SI,SI,DI,DI,DI,DI,SI,DI")])
(define_insn_and_split "*anddi_1_btr"
[(set (match_operand:DI 0 "nonimmediate_operand" "=rm")
;; See comment for addsi_1_zext why we do use nonimmediate_operand
(define_insn "*andsi_1_zext"
- [(set (match_operand:DI 0 "register_operand" "=r")
+ [(set (match_operand:DI 0 "register_operand" "=r,r,r")
(zero_extend:DI
- (and:SI (match_operand:SI 1 "nonimmediate_operand" "%0")
- (match_operand:SI 2 "x86_64_general_operand" "rBMe"))))
+ (and:SI (match_operand:SI 1 "nonimmediate_operand" "%0,rm,r")
+ (match_operand:SI 2 "x86_64_general_operand" "rBMe,re,BM"))))
(clobber (reg:CC FLAGS_REG))]
- "TARGET_64BIT && ix86_binary_operator_ok (AND, SImode, operands)"
- "and{l}\t{%2, %k0|%k0, %2}"
+ "TARGET_64BIT
+ && ix86_binary_operator_ok (AND, SImode, operands, TARGET_APX_NDD)"
+ "@
+ and{l}\t{%2, %k0|%k0, %2}
+ and{l}\t{%2, %1, %k0|%k0, %1, %2}
+ and{l}\t{%2, %1, %k0|%k0, %1, %2}"
[(set_attr "type" "alu")
+ (set_attr "isa" "*,apx_ndd,apx_ndd")
(set_attr "mode" "SI")])
(define_insn "*and<mode>_1"
- [(set (match_operand:SWI24 0 "nonimmediate_operand" "=rm,r,Ya,?k")
- (and:SWI24 (match_operand:SWI24 1 "nonimmediate_operand" "%0,0,qm,k")
- (match_operand:SWI24 2 "<general_operand>" "r<i>,<m>,L,k")))
+ [(set (match_operand:SWI24 0 "nonimmediate_operand" "=rm,r,r,r,Ya,?k")
+ (and:SWI24 (match_operand:SWI24 1 "nonimmediate_operand" "%0,0,rm,r,qm,k")
+ (match_operand:SWI24 2 "<general_operand>" "r<i>,<m>,r<i>,<m>,L,k")))
(clobber (reg:CC FLAGS_REG))]
- "ix86_binary_operator_ok (AND, <MODE>mode, operands)"
+ "ix86_binary_operator_ok (AND, <MODE>mode, operands, TARGET_APX_NDD)"
"@
and{<imodesuffix>}\t{%2, %0|%0, %2}
and{<imodesuffix>}\t{%2, %0|%0, %2}
+ and{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}
+ and{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}
#
#"
[(set (attr "isa")
- (cond [(eq_attr "alternative" "3")
+ (cond [(eq_attr "alternative" "2,3")
+ (const_string "apx_ndd")
+ (eq_attr "alternative" "5")
(if_then_else (eq_attr "mode" "SI")
(const_string "avx512bw")
(const_string "avx512f"))
]
(const_string "*")))
- (set_attr "type" "alu,alu,imovx,msklog")
- (set_attr "length_immediate" "*,*,0,*")
+ (set_attr "type" "alu,alu,alu,alu,imovx,msklog")
+ (set_attr "length_immediate" "*,*,*,*,0,*")
(set (attr "prefix_rex")
(if_then_else
(and (eq_attr "type" "imovx")
(match_operand 1 "ext_QIreg_operand")))
(const_string "1")
(const_string "*")))
- (set_attr "mode" "<MODE>,<MODE>,SI,<MODE>")])
+ (set_attr "mode" "<MODE>,<MODE>,<MODE>,<MODE>,SI,<MODE>")])
(define_insn "*andqi_1"
- [(set (match_operand:QI 0 "nonimmediate_operand" "=qm,q,r,?k")
- (and:QI (match_operand:QI 1 "nonimmediate_operand" "%0,0,0,k")
- (match_operand:QI 2 "general_operand" "qn,m,rn,k")))
+ [(set (match_operand:QI 0 "nonimmediate_operand" "=qm,q,r,r,r,?k")
+ (and:QI (match_operand:QI 1 "nonimmediate_operand" "%0,0,0,rm,r,k")
+ (match_operand:QI 2 "general_operand" "qn,m,rn,rn,m,k")))
(clobber (reg:CC FLAGS_REG))]
- "ix86_binary_operator_ok (AND, QImode, operands)"
+ "ix86_binary_operator_ok (AND, QImode, operands, TARGET_APX_NDD)"
"@
and{b}\t{%2, %0|%0, %2}
and{b}\t{%2, %0|%0, %2}
and{l}\t{%k2, %k0|%k0, %k2}
+ and{b}\t{%2, %1, %0|%0, %1, %2}
+ and{b}\t{%2, %1, %0|%0, %1, %2}
#"
- [(set_attr "type" "alu,alu,alu,msklog")
+ [(set_attr "type" "alu,alu,alu,alu,alu,msklog")
+ (set_attr "isa" "*,*,*,apx_ndd,apx_ndd,*")
(set (attr "mode")
(cond [(eq_attr "alternative" "2")
(const_string "SI")
- (and (eq_attr "alternative" "3")
+ (and (eq_attr "alternative" "5")
(match_test "!TARGET_AVX512DQ"))
(const_string "HI")
]
(symbol_ref "true")))])
;; Alternative 1 is needed to work around LRA limitation, see PR82524.
-(define_insn_and_split "*and<mode>_1_slp"
+(define_insn_and_split "*<code><mode>_1_slp"
[(set (strict_low_part (match_operand:SWI12 0 "register_operand" "+<r>,&<r>"))
- (and:SWI12 (match_operand:SWI12 1 "nonimmediate_operand" "%0,!<r>")
- (match_operand:SWI12 2 "general_operand" "<r>mn,<r>mn")))
+ (any_logic:SWI12 (match_operand:SWI12 1 "nonimmediate_operand" "%0,!<r>")
+ (match_operand:SWI12 2 "general_operand" "<r>mn,<r>mn")))
(clobber (reg:CC FLAGS_REG))]
"!TARGET_PARTIAL_REG_STALL || optimize_function_for_size_p (cfun)"
"@
- and{<imodesuffix>}\t{%2, %0|%0, %2}
+ <logic>{<imodesuffix>}\t{%2, %0|%0, %2}
#"
- "&& reload_completed"
+ "&& reload_completed
+ && !(rtx_equal_p (operands[0], operands[1])
+ || rtx_equal_p (operands[0], operands[2]))"
[(set (strict_low_part (match_dup 0)) (match_dup 1))
(parallel
[(set (strict_low_part (match_dup 0))
- (and:SWI12 (match_dup 0) (match_dup 2)))
+ (any_logic:SWI12 (match_dup 0) (match_dup 2)))
(clobber (reg:CC FLAGS_REG))])]
""
[(set_attr "type" "alu")
(set_attr "mode" "<MODE>")])
+;; Alternative 1 is needed to work around LRA limitation, see PR82524.
+(define_insn_and_split "*<code>qi_ext<mode>_1_slp"
+ [(set (strict_low_part (match_operand:QI 0 "register_operand" "+Q,&Q"))
+ (any_logic:QI
+ (subreg:QI
+ (match_operator:SWI248 3 "extract_operator"
+ [(match_operand 2 "int248_register_operand" "Q,Q")
+ (const_int 8)
+ (const_int 8)]) 0)
+ (match_operand:QI 1 "nonimmediate_operand" "0,!qm")))
+ (clobber (reg:CC FLAGS_REG))]
+ "!TARGET_PARTIAL_REG_STALL || optimize_function_for_size_p (cfun)"
+ "@
+ <logic>{b}\t{%h2, %0|%0, %h2}
+ #"
+ "&& reload_completed
+ && !rtx_equal_p (operands[0], operands[1])"
+ [(set (strict_low_part (match_dup 0)) (match_dup 1))
+ (parallel
+ [(set (strict_low_part (match_dup 0))
+ (any_logic:QI
+ (subreg:QI
+ (match_op_dup 3
+ [(match_dup 2) (const_int 8) (const_int 8)]) 0)
+ (match_dup 0)))
+ (clobber (reg:CC FLAGS_REG))])]
+ ""
+ [(set_attr "type" "alu")
+ (set_attr "mode" "QI")])
+
+(define_insn_and_split "*<code>qi_ext<mode>_2_slp"
+ [(set (strict_low_part (match_operand:QI 0 "register_operand" "+&Q"))
+ (any_logic:QI
+ (subreg:QI
+ (match_operator:SWI248 3 "extract_operator"
+ [(match_operand 1 "int248_register_operand" "Q")
+ (const_int 8)
+ (const_int 8)]) 0)
+ (subreg:QI
+ (match_operator:SWI248 4 "extract_operator"
+ [(match_operand 2 "int248_register_operand" "Q")
+ (const_int 8)
+ (const_int 8)]) 0)))
+ (clobber (reg:CC FLAGS_REG))]
+ "!TARGET_PARTIAL_REG_STALL || optimize_function_for_size_p (cfun)"
+ "#"
+ "&& reload_completed"
+ [(set (strict_low_part (match_dup 0))
+ (subreg:QI
+ (match_op_dup 4
+ [(match_dup 2) (const_int 8) (const_int 8)]) 0))
+ (parallel
+ [(set (strict_low_part (match_dup 0))
+ (any_logic:QI
+ (subreg:QI
+ (match_op_dup 3
+ [(match_dup 1) (const_int 8) (const_int 8)]) 0)
+ (match_dup 0)))
+ (clobber (reg:CC FLAGS_REG))])]
+ ""
+ [(set_attr "type" "alu")
+ (set_attr "mode" "QI")])
+
(define_split
[(set (match_operand:SWI248 0 "register_operand")
(and:SWI248 (match_operand:SWI248 1 "nonimmediate_operand")
(clobber (reg:CC FLAGS_REG))]
"reload_completed
&& (!REG_P (operands[1])
- || REGNO (operands[0]) != REGNO (operands[1]))"
+ || REGNO (operands[0]) != REGNO (operands[1]))
+ && (UINTVAL (operands[2]) == GET_MODE_MASK (SImode)
+ || UINTVAL (operands[2]) == GET_MODE_MASK (HImode)
+ || UINTVAL (operands[2]) == GET_MODE_MASK (QImode))"
[(const_int 0)]
{
unsigned HOST_WIDE_INT ival = UINTVAL (operands[2]);
[(set (reg FLAGS_REG)
(compare
(and:DI
- (match_operand:DI 1 "nonimmediate_operand" "%0,0,0")
- (match_operand:DI 2 "x86_64_szext_general_operand" "Z,re,m"))
+ (match_operand:DI 1 "nonimmediate_operand" "%0,0,0,r,rm,r")
+ (match_operand:DI 2 "x86_64_szext_general_operand" "Z,re,m,Z,re,m"))
(const_int 0)))
- (set (match_operand:DI 0 "nonimmediate_operand" "=r,rm,r")
+ (set (match_operand:DI 0 "nonimmediate_operand" "=r,rm,r,r,r,r")
(and:DI (match_dup 1) (match_dup 2)))]
"TARGET_64BIT
&& ix86_match_ccmode
&& (!CONST_INT_P (operands[2])
|| val_signbit_known_set_p (SImode, INTVAL (operands[2]))))
? CCZmode : CCNOmode)
- && ix86_binary_operator_ok (AND, DImode, operands)"
+ && ix86_binary_operator_ok (AND, DImode, operands, TARGET_APX_NDD)"
"@
and{l}\t{%k2, %k0|%k0, %k2}
and{q}\t{%2, %0|%0, %2}
- and{q}\t{%2, %0|%0, %2}"
+ and{q}\t{%2, %0|%0, %2}
+ and{l}\t{%k2, %k1, %k0|%k0, %k1, %k2}
+ and{q}\t{%2, %1, %0|%0, %1, %2}
+ and{q}\t{%2, %1, %0|%0, %1, %2}"
[(set_attr "type" "alu")
- (set_attr "mode" "SI,DI,DI")])
+ (set_attr "isa" "*,*,*,apx_ndd,apx_ndd,apx_ndd")
+ (set_attr "mode" "SI,DI,DI,SI,DI,DI")])
;; See comment for addsi_1_zext why we do use nonimmediate_operand
(define_insn "*andsi_2_zext"
[(set (reg FLAGS_REG)
(compare (and:SI
- (match_operand:SI 1 "nonimmediate_operand" "%0")
- (match_operand:SI 2 "x86_64_general_operand" "rBMe"))
+ (match_operand:SI 1 "nonimmediate_operand" "%0,rm,r")
+ (match_operand:SI 2 "x86_64_general_operand" "rBMe,re,BM"))
(const_int 0)))
- (set (match_operand:DI 0 "register_operand" "=r")
+ (set (match_operand:DI 0 "register_operand" "=r,r,r")
(zero_extend:DI (and:SI (match_dup 1) (match_dup 2))))]
"TARGET_64BIT && ix86_match_ccmode (insn, CCNOmode)
- && ix86_binary_operator_ok (AND, SImode, operands)"
- "and{l}\t{%2, %k0|%k0, %2}"
+ && ix86_binary_operator_ok (AND, SImode, operands, TARGET_APX_NDD)"
+ "@
+ and{l}\t{%2, %k0|%k0, %2}
+ and{l}\t{%2, %1, %k0|%k0, %1, %2}
+ and{l}\t{%2, %1, %k0|%k0, %1, %2}"
[(set_attr "type" "alu")
+ (set_attr "isa" "*,apx_ndd,apx_ndd")
(set_attr "mode" "SI")])
(define_insn "*andqi_2_maybe_si"
[(set (reg FLAGS_REG)
(compare (and:QI
- (match_operand:QI 1 "nonimmediate_operand" "%0,0,0")
- (match_operand:QI 2 "general_operand" "qn,m,n"))
+ (match_operand:QI 1 "nonimmediate_operand" "%0,0,0,rm,r")
+ (match_operand:QI 2 "general_operand" "qn,m,n,rn,m"))
(const_int 0)))
- (set (match_operand:QI 0 "nonimmediate_operand" "=qm,q,r")
+ (set (match_operand:QI 0 "nonimmediate_operand" "=qm,q,r,r,r")
(and:QI (match_dup 1) (match_dup 2)))]
- "ix86_binary_operator_ok (AND, QImode, operands)
+ "ix86_binary_operator_ok (AND, QImode, operands, TARGET_APX_NDD)
&& ix86_match_ccmode (insn,
CONST_INT_P (operands[2])
&& INTVAL (operands[2]) >= 0 ? CCNOmode : CCZmode)"
operands[2] = GEN_INT (INTVAL (operands[2]) & 0xff);
return "and{l}\t{%2, %k0|%k0, %2}";
}
+ if (which_alternative > 2)
+ return "and{b}\t{%2, %1, %0|%0, %1, %2}";
return "and{b}\t{%2, %0|%0, %2}";
}
[(set_attr "type" "alu")
+ (set_attr "isa" "*,*,*,apx_ndd,apx_ndd")
(set (attr "mode")
- (cond [(eq_attr "alternative" "2")
+ (cond [(eq_attr "alternative" "3,4")
+ (const_string "QI")
+ (eq_attr "alternative" "2")
(const_string "SI")
(and (match_test "optimize_insn_for_size_p ()")
(and (match_operand 0 "ext_QIreg_operand")
(define_insn "*and<mode>_2"
[(set (reg FLAGS_REG)
(compare (and:SWI124
- (match_operand:SWI124 1 "nonimmediate_operand" "%0,0")
- (match_operand:SWI124 2 "<general_operand>" "<r><i>,<m>"))
+ (match_operand:SWI124 1 "nonimmediate_operand" "%0,0,rm,r")
+ (match_operand:SWI124 2 "<general_operand>" "<r><i>,<m>,r<i>,<m>"))
(const_int 0)))
- (set (match_operand:SWI124 0 "nonimmediate_operand" "=<r>m,<r>")
+ (set (match_operand:SWI124 0 "nonimmediate_operand" "=<r>m,<r>,r,r")
(and:SWI124 (match_dup 1) (match_dup 2)))]
"ix86_match_ccmode (insn, CCNOmode)
- && ix86_binary_operator_ok (AND, <MODE>mode, operands)"
- "and{<imodesuffix>}\t{%2, %0|%0, %2}"
+ && ix86_binary_operator_ok (AND, <MODE>mode, operands, TARGET_APX_NDD)"
+ "@
+ and{<imodesuffix>}\t{%2, %0|%0, %2}
+ and{<imodesuffix>}\t{%2, %0|%0, %2}
+ and{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}
+ and{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}"
[(set_attr "type" "alu")
+ (set_attr "isa" "*,*,apx_ndd,apx_ndd")
(set_attr "mode" "<MODE>")])
-(define_insn "*andqi_ext<mode>_0"
- [(set (match_operand:QI 0 "nonimm_x64constmem_operand" "=QBc,m")
- (and:QI
+(define_insn "*<code>qi_ext<mode>_0"
+ [(set (match_operand:QI 0 "nonimmediate_operand" "=QBn")
+ (any_logic:QI
(subreg:QI
(match_operator:SWI248 3 "extract_operator"
- [(match_operand 2 "int248_register_operand" "Q,Q")
+ [(match_operand 2 "int248_register_operand" "Q")
(const_int 8)
(const_int 8)]) 0)
- (match_operand:QI 1 "nonimm_x64constmem_operand" "0,0")))
+ (match_operand:QI 1 "nonimmediate_operand" "0")))
(clobber (reg:CC FLAGS_REG))]
""
- "and{b}\t{%h2, %0|%0, %h2}"
- [(set_attr "isa" "*,nox64")
+ "<logic>{b}\t{%h2, %0|%0, %h2}"
+ [(set_attr "addr" "gpr8")
(set_attr "type" "alu")
(set_attr "mode" "QI")])
+(define_insn_and_split "*<code>qi_ext2<mode>_0"
+ [(set (match_operand:QI 0 "register_operand" "=&Q")
+ (any_logic:QI
+ (subreg:QI
+ (match_operator:SWI248 3 "extract_operator"
+ [(match_operand 1 "int248_register_operand" "Q")
+ (const_int 8)
+ (const_int 8)]) 0)
+ (subreg:QI
+ (match_operator:SWI248 4 "extract_operator"
+ [(match_operand 2 "int248_register_operand" "Q")
+ (const_int 8)
+ (const_int 8)]) 0)))
+ (clobber (reg:CC FLAGS_REG))]
+ ""
+ "#"
+ "&& reload_completed"
+ [(set (match_dup 0)
+ (subreg:QI
+ (match_op_dup 4
+ [(match_dup 2) (const_int 8) (const_int 8)]) 0))
+ (parallel
+ [(set (match_dup 0)
+ (any_logic:QI
+ (subreg:QI
+ (match_op_dup 3
+ [(match_dup 1) (const_int 8) (const_int 8)]) 0)
+ (match_dup 0)))
+ (clobber (reg:CC FLAGS_REG))])]
+ ""
+ [(set_attr "type" "alu")
+ (set_attr "mode" "QI")])
+
(define_expand "andqi_ext_1"
[(parallel
[(set (zero_extract:HI (match_operand:HI 0 "register_operand")
(match_operand:QI 2 "const_int_operand")) 0))
(clobber (reg:CC FLAGS_REG))])])
-(define_insn "*andqi_ext<mode>_1"
+;; Alternative 1 is needed to work around LRA limitation, see PR82524.
+(define_insn_and_split "*<code>qi_ext<mode>_1"
[(set (zero_extract:SWI248
- (match_operand 0 "int248_register_operand" "+Q,Q")
+ (match_operand 0 "int248_register_operand" "+Q,&Q")
(const_int 8)
(const_int 8))
(subreg:SWI248
- (and:QI
+ (any_logic:QI
(subreg:QI
(match_operator:SWI248 3 "extract_operator"
- [(match_operand 1 "int248_register_operand" "0,0")
+ [(match_operand 1 "int248_register_operand" "0,!Q")
(const_int 8)
(const_int 8)]) 0)
- (match_operand:QI 2 "general_x64constmem_operand" "QnBc,m")) 0))
+ (match_operand:QI 2 "general_operand" "QnBn,QnBn")) 0))
(clobber (reg:CC FLAGS_REG))]
- "/* FIXME: without this LRA can't reload this pattern, see PR82524. */
- rtx_equal_p (operands[0], operands[1])"
- "and{b}\t{%2, %h0|%h0, %2}"
- [(set_attr "isa" "*,nox64")
+ ""
+ "@
+ <logic>{b}\t{%2, %h0|%h0, %2}
+ #"
+ "reload_completed
+ && !(rtx_equal_p (operands[0], operands[1]))"
+ [(set (zero_extract:SWI248
+ (match_dup 0) (const_int 8) (const_int 8))
+ (zero_extract:SWI248
+ (match_dup 1) (const_int 8) (const_int 8)))
+ (parallel
+ [(set (zero_extract:SWI248
+ (match_dup 0) (const_int 8) (const_int 8))
+ (subreg:SWI248
+ (any_logic:QI
+ (subreg:QI
+ (match_op_dup 3
+ [(match_dup 0) (const_int 8) (const_int 8)]) 0)
+ (match_dup 2)) 0))
+ (clobber (reg:CC FLAGS_REG))])]
+ ""
+ [(set_attr "addr" "gpr8")
(set_attr "type" "alu")
(set_attr "mode" "QI")])
-;; Generated by peephole translating test to and. This shows up
-;; often in fp comparisons.
-(define_insn "*andqi_ext<mode>_1_cc"
- [(set (reg FLAGS_REG)
- (compare
- (and:QI
- (subreg:QI
- (match_operator:SWI248 3 "extract_operator"
- [(match_operand 1 "int248_register_operand" "0,0")
- (const_int 8)
- (const_int 8)]) 0)
- (match_operand:QI 2 "general_x64constmem_operand" "QnBc,m"))
- (const_int 0)))
+;; Alternative 1 is needed to work around LRA limitation, see PR82524.
+(define_insn_and_split "*<code>qi_ext<mode>_1_cc"
+ [(set (match_operand 4 "flags_reg_operand")
+ (match_operator 5 "compare_operator"
+ [(any_logic:QI
+ (subreg:QI
+ (match_operator:SWI248 3 "extract_operator"
+ [(match_operand 1 "int248_register_operand" "0,!Q")
+ (const_int 8)
+ (const_int 8)]) 0)
+ (match_operand:QI 2 "general_operand" "QnBn,QnBn"))
+ (const_int 0)]))
(set (zero_extract:SWI248
- (match_operand 0 "int248_register_operand" "+Q,Q")
+ (match_operand 0 "int248_register_operand" "+Q,&Q")
(const_int 8)
(const_int 8))
(subreg:SWI248
- (and:QI
+ (any_logic:QI
(subreg:QI
(match_op_dup 3
- [(match_dup 1)
- (const_int 8)
- (const_int 8)]) 0)
+ [(match_dup 0) (const_int 8) (const_int 8)]) 0)
(match_dup 2)) 0))]
- "ix86_match_ccmode (insn, CCNOmode)
- /* FIXME: without this LRA can't reload this pattern, see PR82524. */
- && rtx_equal_p (operands[0], operands[1])"
- "and{b}\t{%2, %h0|%h0, %2}"
- [(set_attr "isa" "*,nox64")
+ "ix86_match_ccmode (insn, CCNOmode)"
+ "@
+ <logic>{b}\t{%2, %h0|%h0, %2}
+ #"
+ "&& reload_completed
+ && !(rtx_equal_p (operands[0], operands[1]))"
+ [(set (zero_extract:SWI248
+ (match_dup 0) (const_int 8) (const_int 8))
+ (zero_extract:SWI248
+ (match_dup 1) (const_int 8) (const_int 8)))
+ (parallel
+ [(set (match_dup 4)
+ (match_op_dup 5
+ [(any_logic:QI
+ (subreg:QI
+ (match_op_dup 3
+ [(match_dup 0) (const_int 8) (const_int 8)]) 0)
+ (match_dup 2))
+ (const_int 0)]))
+ (set (zero_extract:SWI248
+ (match_dup 0) (const_int 8) (const_int 8))
+ (subreg:SWI248
+ (any_logic:QI
+ (subreg:QI
+ (match_op_dup 3
+ [(match_dup 1) (const_int 8) (const_int 8)]) 0)
+ (match_dup 2)) 0))])]
+ ""
+ [(set_attr "addr" "gpr8")
(set_attr "type" "alu")
(set_attr "mode" "QI")])
-(define_insn "*andqi_ext<mode>_2"
+;; Alternative 1 is needed to work around LRA limitation, see PR82524.
+(define_insn_and_split "*<code>qi_ext<mode>_2"
[(set (zero_extract:SWI248
- (match_operand 0 "int248_register_operand" "+Q")
+ (match_operand 0 "int248_register_operand" "+Q,&Q")
(const_int 8)
(const_int 8))
(subreg:SWI248
- (and:QI
+ (any_logic:QI
(subreg:QI
(match_operator:SWI248 3 "extract_operator"
- [(match_operand 1 "int248_register_operand" "%0")
+ [(match_operand 1 "int248_register_operand" "%0,!Q")
(const_int 8)
(const_int 8)]) 0)
(subreg:QI
(match_operator:SWI248 4 "extract_operator"
- [(match_operand 2 "int248_register_operand" "Q")
+ [(match_operand 2 "int248_register_operand" "Q,Q")
(const_int 8)
(const_int 8)]) 0)) 0))
(clobber (reg:CC FLAGS_REG))]
- "/* FIXME: without this LRA can't reload this pattern, see PR82524. */
- rtx_equal_p (operands[0], operands[1])
- || rtx_equal_p (operands[0], operands[2])"
- "and{b}\t{%h2, %h0|%h0, %h2}"
+ ""
+ "@
+ <logic>{b}\t{%h2, %h0|%h0, %h2}
+ #"
+ "reload_completed
+ && !(rtx_equal_p (operands[0], operands[1])
+ || rtx_equal_p (operands[0], operands[2]))"
+ [(set (zero_extract:SWI248
+ (match_dup 0) (const_int 8) (const_int 8))
+ (zero_extract:SWI248
+ (match_dup 1) (const_int 8) (const_int 8)))
+ (parallel
+ [(set (zero_extract:SWI248
+ (match_dup 0) (const_int 8) (const_int 8))
+ (subreg:SWI248
+ (any_logic:QI
+ (subreg:QI
+ (match_op_dup 3
+ [(match_dup 0) (const_int 8) (const_int 8)]) 0)
+ (subreg:QI
+ (match_op_dup 4
+ [(match_dup 2) (const_int 8) (const_int 8)]) 0)) 0))
+ (clobber (reg:CC FLAGS_REG))])]
+ ""
[(set_attr "type" "alu")
(set_attr "mode" "QI")])
-;; *andqi_ext<mode>_3 is defined via *<code>qi_ext<mode>_3 below.
+;; Alternative 1 is needed to work around LRA limitation, see PR82524.
+(define_insn_and_split "*<code>qi_ext<mode>_3"
+ [(set (zero_extract:SWI248
+ (match_operand 0 "int248_register_operand" "+Q,&Q")
+ (const_int 8)
+ (const_int 8))
+ (match_operator:SWI248 3 "extract_operator"
+ [(any_logic
+ (match_operand 1 "int248_register_operand" "%0,!Q")
+ (match_operand 2 "int248_register_operand" "Q,Q"))
+ (const_int 8)
+ (const_int 8)]))
+ (clobber (reg:CC FLAGS_REG))]
+ "GET_MODE (operands[1]) == GET_MODE (operands[2])"
+ "@
+ <logic>{b}\t{%h2, %h0|%h0, %h2}
+ #"
+ "&& reload_completed
+ && !(rtx_equal_p (operands[0], operands[1])
+ || rtx_equal_p (operands[0], operands[2]))"
+ [(set (zero_extract:SWI248
+ (match_dup 0) (const_int 8) (const_int 8))
+ (zero_extract:SWI248
+ (match_dup 1) (const_int 8) (const_int 8)))
+ (parallel
+ [(set (zero_extract:SWI248
+ (match_dup 0) (const_int 8) (const_int 8))
+ (match_op_dup 3
+ [(any_logic (match_dup 4) (match_dup 2))
+ (const_int 8) (const_int 8)]))
+ (clobber (reg:CC FLAGS_REG))])]
+ "operands[4] = gen_lowpart (GET_MODE (operands[1]), operands[0]);"
+ [(set_attr "type" "alu")
+ (set_attr "mode" "QI")])
;; Convert wide AND instructions with immediate operand to shorter QImode
;; equivalents when possible.
;; Don't do the splitting with memory operands, since it introduces risk
;; of memory mismatch stalls. We may want to do the splitting for optimizing
;; for size, but that can (should?) be handled by generic code instead.
+;; Don't do the splitting for APX NDD as NDD does not support *h registers.
(define_split
[(set (match_operand:SWI248 0 "QIreg_operand")
(and:SWI248 (match_operand:SWI248 1 "register_operand")
(clobber (reg:CC FLAGS_REG))]
"reload_completed
&& (!TARGET_PARTIAL_REG_STALL || optimize_function_for_size_p (cfun))
- && !(~INTVAL (operands[2]) & ~(255 << 8))"
+ && !(~INTVAL (operands[2]) & ~(255 << 8))
+ && !(TARGET_APX_NDD && REGNO (operands[0]) != REGNO (operands[1]))"
[(parallel
[(set (zero_extract:HI (match_dup 0)
(const_int 8)
"reload_completed
&& (!TARGET_PARTIAL_REG_STALL || optimize_function_for_size_p (cfun))
&& !(~INTVAL (operands[2]) & ~255)
- && !(INTVAL (operands[2]) & 128)"
+ && !(INTVAL (operands[2]) & 128)
+ && !(TARGET_APX_NDD
+ && !rtx_equal_p (operands[0], operands[1]))"
[(parallel [(set (strict_low_part (match_dup 0))
(and:QI (match_dup 1)
(match_dup 2)))
&& !x86_64_hilo_general_operand (operands[2], <MODE>mode))
operands[2] = force_reg (<MODE>mode, operands[2]);
- ix86_expand_binary_operator (<CODE>, <MODE>mode, operands);
+ ix86_expand_binary_operator (<CODE>, <MODE>mode, operands, TARGET_APX_NDD);
DONE;
})
(define_insn_and_split "*<code><dwi>3_doubleword"
- [(set (match_operand:<DWI> 0 "nonimmediate_operand" "=ro,r")
+ [(set (match_operand:<DWI> 0 "nonimmediate_operand" "=ro,r,&r,&r")
(any_or:<DWI>
- (match_operand:<DWI> 1 "nonimmediate_operand" "%0,0")
- (match_operand:<DWI> 2 "x86_64_hilo_general_operand" "r<di>,o")))
+ (match_operand:<DWI> 1 "nonimmediate_operand" "%0,0,ro,r")
+ (match_operand:<DWI> 2 "x86_64_hilo_general_operand" "r<di>,o,r<di>,o")))
(clobber (reg:CC FLAGS_REG))]
- "ix86_binary_operator_ok (<CODE>, <DWI>mode, operands)"
+ "ix86_binary_operator_ok (<CODE>, <DWI>mode, operands, TARGET_APX_NDD)"
"#"
"&& reload_completed"
[(const_int:DWIH 0)]
split_double_mode (<DWI>mode, &operands[0], 3, &operands[0], &operands[3]);
if (operands[2] == const0_rtx)
- emit_insn_deleted_note_p = true;
+ {
+ if (!rtx_equal_p (operands[0], operands[1]))
+ emit_move_insn (operands[0], operands[1]);
+ else
+ emit_insn_deleted_note_p = true;
+ }
else if (operands[2] == constm1_rtx)
{
if (<CODE> == IOR)
emit_move_insn (operands[0], constm1_rtx);
else
- ix86_expand_unary_operator (NOT, <MODE>mode, &operands[0]);
+ ix86_expand_unary_operator (NOT, <MODE>mode, &operands[0],
+ TARGET_APX_NDD);
}
else
- ix86_expand_binary_operator (<CODE>, <MODE>mode, &operands[0]);
+ ix86_expand_binary_operator (<CODE>, <MODE>mode, &operands[0],
+ TARGET_APX_NDD);
if (operands[5] == const0_rtx)
{
- if (emit_insn_deleted_note_p)
+ if (!rtx_equal_p (operands[3], operands[4]))
+ emit_move_insn (operands[3], operands[4]);
+ else if (emit_insn_deleted_note_p)
emit_note (NOTE_INSN_DELETED);
}
else if (operands[5] == constm1_rtx)
if (<CODE> == IOR)
emit_move_insn (operands[3], constm1_rtx);
else
- ix86_expand_unary_operator (NOT, <MODE>mode, &operands[3]);
+ ix86_expand_unary_operator (NOT, <MODE>mode, &operands[3],
+ TARGET_APX_NDD);
}
else
- ix86_expand_binary_operator (<CODE>, <MODE>mode, &operands[3]);
+ ix86_expand_binary_operator (<CODE>, <MODE>mode, &operands[3],
+ TARGET_APX_NDD);
DONE;
-})
+}
+[(set_attr "isa" "*,*,apx_ndd,apx_ndd")])
(define_insn "*<code><mode>_1"
- [(set (match_operand:SWI248 0 "nonimmediate_operand" "=rm,r,?k")
+ [(set (match_operand:SWI248 0 "nonimmediate_operand" "=rm,r,r,r,?k")
(any_or:SWI248
- (match_operand:SWI248 1 "nonimmediate_operand" "%0,0,k")
- (match_operand:SWI248 2 "<general_operand>" "r<i>,<m>,k")))
+ (match_operand:SWI248 1 "nonimmediate_operand" "%0,0,rm,r,k")
+ (match_operand:SWI248 2 "<general_operand>" "r<i>,<m>,r<i>,<m>,k")))
(clobber (reg:CC FLAGS_REG))]
- "ix86_binary_operator_ok (<CODE>, <MODE>mode, operands)"
+ "ix86_binary_operator_ok (<CODE>, <MODE>mode, operands, TARGET_APX_NDD)"
"@
<logic>{<imodesuffix>}\t{%2, %0|%0, %2}
<logic>{<imodesuffix>}\t{%2, %0|%0, %2}
+ <logic>{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}
+ <logic>{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}
#"
- [(set (attr "isa")
- (cond [(eq_attr "alternative" "2")
- (if_then_else (eq_attr "mode" "SI,DI")
- (const_string "avx512bw")
- (const_string "avx512f"))
- ]
- (const_string "*")))
- (set_attr "type" "alu, alu, msklog")
+ [(set_attr "isa" "*,*,apx_ndd,apx_ndd,<kmov_isa>")
+ (set_attr "type" "alu, alu, alu, alu, msklog")
(set_attr "mode" "<MODE>")])
(define_insn_and_split "*notxor<mode>_1"
- [(set (match_operand:SWI248 0 "nonimmediate_operand" "=rm,r,?k")
+ [(set (match_operand:SWI248 0 "nonimmediate_operand" "=rm,r,r,r,?k")
(not:SWI248
(xor:SWI248
- (match_operand:SWI248 1 "nonimmediate_operand" "%0,0,k")
- (match_operand:SWI248 2 "<general_operand>" "r<i>,<m>,k"))))
+ (match_operand:SWI248 1 "nonimmediate_operand" "%0,0,rm,r,k")
+ (match_operand:SWI248 2 "<general_operand>" "r<i>,<m>,r<i>,<m>,k"))))
(clobber (reg:CC FLAGS_REG))]
- "ix86_binary_operator_ok (XOR, <MODE>mode, operands)"
+ "ix86_binary_operator_ok (XOR, <MODE>mode, operands, TARGET_APX_NDD)"
"#"
"&& reload_completed"
[(parallel
DONE;
}
}
- [(set (attr "isa")
- (cond [(eq_attr "alternative" "2")
- (if_then_else (eq_attr "mode" "SI,DI")
- (const_string "avx512bw")
- (const_string "avx512f"))
- ]
- (const_string "*")))
- (set_attr "type" "alu, alu, msklog")
+ [(set_attr "isa" "*,*,apx_ndd,apx_ndd,<kmov_isa>")
+ (set_attr "type" "alu, alu, alu, alu, msklog")
(set_attr "mode" "<MODE>")])
(define_insn_and_split "*iordi_1_bts"
;; See comment for addsi_1_zext why we do use nonimmediate_operand
(define_insn "*<code>si_1_zext"
- [(set (match_operand:DI 0 "register_operand" "=r")
+ [(set (match_operand:DI 0 "register_operand" "=r,r,r")
(zero_extend:DI
- (any_or:SI (match_operand:SI 1 "nonimmediate_operand" "%0")
- (match_operand:SI 2 "x86_64_general_operand" "rBMe"))))
+ (any_or:SI (match_operand:SI 1 "nonimmediate_operand" "%0,rm,r")
+ (match_operand:SI 2 "x86_64_general_operand" "rBMe,re,BM"))))
(clobber (reg:CC FLAGS_REG))]
- "TARGET_64BIT && ix86_binary_operator_ok (<CODE>, SImode, operands)"
- "<logic>{l}\t{%2, %k0|%k0, %2}"
+ "TARGET_64BIT
+ && ix86_binary_operator_ok (<CODE>, SImode, operands, TARGET_APX_NDD)"
+ "@
+ <logic>{l}\t{%2, %k0|%k0, %2}
+ <logic>{l}\t{%2, %1, %k0|%k0, %1, %2}
+ <logic>{l}\t{%2, %1, %k0|%k0, %1, %2}"
[(set_attr "type" "alu")
+ (set_attr "isa" "*,apx_ndd,apx_ndd")
(set_attr "mode" "SI")])
(define_insn "*<code>si_1_zext_imm"
- [(set (match_operand:DI 0 "register_operand" "=r")
+ [(set (match_operand:DI 0 "register_operand" "=r,r")
(any_or:DI
- (zero_extend:DI (match_operand:SI 1 "register_operand" "%0"))
- (match_operand:DI 2 "x86_64_zext_immediate_operand" "Z")))
+ (zero_extend:DI (match_operand:SI 1 "nonimmediate_operand" "%0,rm"))
+ (match_operand:DI 2 "x86_64_zext_immediate_operand" "Z,Z")))
(clobber (reg:CC FLAGS_REG))]
- "TARGET_64BIT && ix86_binary_operator_ok (<CODE>, SImode, operands)"
- "<logic>{l}\t{%2, %k0|%k0, %2}"
+ "TARGET_64BIT
+ && ix86_binary_operator_ok (<CODE>, SImode, operands, TARGET_APX_NDD)"
+ "@
+ <logic>{l}\t{%2, %k0|%k0, %2}
+ <logic>{l}\t{%2, %1, %k0|%k0, %1, %2}"
[(set_attr "type" "alu")
+ (set_attr "isa" "*,apx_ndd")
(set_attr "mode" "SI")])
(define_insn "*<code>qi_1"
- [(set (match_operand:QI 0 "nonimmediate_operand" "=qm,q,r,?k")
- (any_or:QI (match_operand:QI 1 "nonimmediate_operand" "%0,0,0,k")
- (match_operand:QI 2 "general_operand" "qn,m,rn,k")))
+ [(set (match_operand:QI 0 "nonimmediate_operand" "=qm,q,r,r,r,?k")
+ (any_or:QI (match_operand:QI 1 "nonimmediate_operand" "%0,0,0,rm,r,k")
+ (match_operand:QI 2 "general_operand" "qn,m,rn,rn,m,k")))
(clobber (reg:CC FLAGS_REG))]
- "ix86_binary_operator_ok (<CODE>, QImode, operands)"
+ "ix86_binary_operator_ok (<CODE>, QImode, operands, TARGET_APX_NDD)"
"@
<logic>{b}\t{%2, %0|%0, %2}
<logic>{b}\t{%2, %0|%0, %2}
<logic>{l}\t{%k2, %k0|%k0, %k2}
+ <logic>{b}\t{%2, %1, %0|%0, %1, %2}
+ <logic>{b}\t{%2, %1, %0|%0, %1, %2}
#"
- [(set_attr "isa" "*,*,*,avx512f")
- (set_attr "type" "alu,alu,alu,msklog")
+ [(set_attr "isa" "*,*,*,apx_ndd,apx_ndd,avx512f")
+ (set_attr "type" "alu,alu,alu,alu,alu,msklog")
(set (attr "mode")
(cond [(eq_attr "alternative" "2")
(const_string "SI")
- (and (eq_attr "alternative" "3")
+ (and (eq_attr "alternative" "5")
(match_test "!TARGET_AVX512DQ"))
(const_string "HI")
]
(symbol_ref "true")))])
(define_insn_and_split "*notxorqi_1"
- [(set (match_operand:QI 0 "nonimmediate_operand" "=qm,q,r,?k")
+ [(set (match_operand:QI 0 "nonimmediate_operand" "=qm,q,r,r,r,?k")
(not:QI
- (xor:QI (match_operand:QI 1 "nonimmediate_operand" "%0,0,0,k")
- (match_operand:QI 2 "general_operand" "qn,m,rn,k"))))
+ (xor:QI (match_operand:QI 1 "nonimmediate_operand" "%0,0,0,rm,r,k")
+ (match_operand:QI 2 "general_operand" "qn,m,rn,rn,m,k"))))
(clobber (reg:CC FLAGS_REG))]
- "ix86_binary_operator_ok (XOR, QImode, operands)"
+ "ix86_binary_operator_ok (XOR, QImode, operands, TARGET_APX_NDD)"
"#"
"&& reload_completed"
[(parallel
DONE;
}
}
- [(set_attr "isa" "*,*,*,avx512f")
- (set_attr "type" "alu,alu,alu,msklog")
+ [(set_attr "isa" "*,*,*,apx_ndd,apx_ndd,avx512f")
+ (set_attr "type" "alu,alu,alu,alu,alu,msklog")
(set (attr "mode")
(cond [(eq_attr "alternative" "2")
(const_string "SI")
- (and (eq_attr "alternative" "3")
+ (and (eq_attr "alternative" "5")
(match_test "!TARGET_AVX512DQ"))
(const_string "HI")
]
(symbol_ref "!TARGET_PARTIAL_REG_STALL")]
(symbol_ref "true")))])
-;; Alternative 1 is needed to work around LRA limitation, see PR82524.
-(define_insn_and_split "*<code><mode>_1_slp"
- [(set (strict_low_part (match_operand:SWI12 0 "register_operand" "+<r>,&<r>"))
- (any_or:SWI12 (match_operand:SWI12 1 "nonimmediate_operand" "%0,!<r>")
- (match_operand:SWI12 2 "general_operand" "<r>mn,<r>mn")))
- (clobber (reg:CC FLAGS_REG))]
- "!TARGET_PARTIAL_REG_STALL || optimize_function_for_size_p (cfun)"
- "@
- <logic>{<imodesuffix>}\t{%2, %0|%0, %2}
- #"
- "&& reload_completed"
- [(set (strict_low_part (match_dup 0)) (match_dup 1))
- (parallel
- [(set (strict_low_part (match_dup 0))
- (any_or:SWI12 (match_dup 0) (match_dup 2)))
- (clobber (reg:CC FLAGS_REG))])]
- ""
- [(set_attr "type" "alu")
- (set_attr "mode" "<MODE>")])
-
;; convert (sign_extend:WIDE (any_logic:NARROW (memory, immediate)))
;; to (any_logic:WIDE (sign_extend (memory)), (sign_extend (immediate))).
;; This eliminates sign extension after logic operation.
(define_insn "*<code><mode>_2"
[(set (reg FLAGS_REG)
(compare (any_or:SWI
- (match_operand:SWI 1 "nonimmediate_operand" "%0,0")
- (match_operand:SWI 2 "<general_operand>" "<r><i>,<m>"))
+ (match_operand:SWI 1 "nonimmediate_operand" "%0,0,rm,r")
+ (match_operand:SWI 2 "<general_operand>" "<r><i>,<m>,r<i>,<m>"))
(const_int 0)))
- (set (match_operand:SWI 0 "nonimmediate_operand" "=<r>m,<r>")
+ (set (match_operand:SWI 0 "nonimmediate_operand" "=<r>m,<r>,r,r")
(any_or:SWI (match_dup 1) (match_dup 2)))]
"ix86_match_ccmode (insn, CCNOmode)
- && ix86_binary_operator_ok (<CODE>, <MODE>mode, operands)"
- "<logic>{<imodesuffix>}\t{%2, %0|%0, %2}"
+ && ix86_binary_operator_ok (<CODE>, <MODE>mode, operands, TARGET_APX_NDD)"
+ "@
+ <logic>{<imodesuffix>}\t{%2, %0|%0, %2}
+ <logic>{<imodesuffix>}\t{%2, %0|%0, %2}
+ <logic>{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}
+ <logic>{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}"
[(set_attr "type" "alu")
+ (set_attr "isa" "*,*,apx_ndd,apx_ndd")
(set_attr "mode" "<MODE>")])
;; See comment for addsi_1_zext why we do use nonimmediate_operand
;; ??? Special case for immediate operand is missing - it is tricky.
(define_insn "*<code>si_2_zext"
[(set (reg FLAGS_REG)
- (compare (any_or:SI (match_operand:SI 1 "nonimmediate_operand" "%0")
- (match_operand:SI 2 "x86_64_general_operand" "rBMe"))
+ (compare (any_or:SI (match_operand:SI 1 "nonimmediate_operand" "%0,rm,r")
+ (match_operand:SI 2 "x86_64_general_operand" "rBMe,re,BM"))
(const_int 0)))
- (set (match_operand:DI 0 "register_operand" "=r")
+ (set (match_operand:DI 0 "register_operand" "=r,r,r")
(zero_extend:DI (any_or:SI (match_dup 1) (match_dup 2))))]
"TARGET_64BIT && ix86_match_ccmode (insn, CCNOmode)
- && ix86_binary_operator_ok (<CODE>, SImode, operands)"
- "<logic>{l}\t{%2, %k0|%k0, %2}"
+ && ix86_binary_operator_ok (<CODE>, SImode, operands, TARGET_APX_NDD)"
+ "@
+ <logic>{l}\t{%2, %k0|%k0, %2}
+ <logic>{l}\t{%2, %1, %k0|%k0, %1, %2}
+ <logic>{l}\t{%2, %1, %k0|%k0, %1, %2}"
[(set_attr "type" "alu")
+ (set_attr "isa" "*,apx_ndd,apx_ndd")
(set_attr "mode" "SI")])
(define_insn "*<code>si_2_zext_imm"
[(set (reg FLAGS_REG)
(compare (any_or:SI
- (match_operand:SI 1 "nonimmediate_operand" "%0")
- (match_operand:SI 2 "x86_64_zext_immediate_operand" "Z"))
+ (match_operand:SI 1 "nonimmediate_operand" "%0,rm")
+ (match_operand:SI 2 "x86_64_zext_immediate_operand" "Z,Z"))
(const_int 0)))
- (set (match_operand:DI 0 "register_operand" "=r")
+ (set (match_operand:DI 0 "register_operand" "=r,r")
(any_or:DI (zero_extend:DI (match_dup 1)) (match_dup 2)))]
"TARGET_64BIT && ix86_match_ccmode (insn, CCNOmode)
- && ix86_binary_operator_ok (<CODE>, SImode, operands)"
- "<logic>{l}\t{%2, %k0|%k0, %2}"
+ && ix86_binary_operator_ok (<CODE>, SImode, operands, TARGET_APX_NDD)"
+ "@
+ <logic>{l}\t{%2, %k0|%k0, %2}
+ <logic>{l}\t{%2, %1, %k0|%k0, %1, %2}"
[(set_attr "type" "alu")
+ (set_attr "isa" "*,apx_ndd")
(set_attr "mode" "SI")])
(define_insn "*<code><mode>_3"
[(set_attr "type" "alu")
(set_attr "mode" "<MODE>")])
-(define_insn "*<code>qi_ext<mode>_0"
- [(set (match_operand:QI 0 "nonimm_x64constmem_operand" "=QBc,m")
- (any_or:QI
- (subreg:QI
- (match_operator:SWI248 3 "extract_operator"
- [(match_operand 2 "int248_register_operand" "Q,Q")
- (const_int 8)
- (const_int 8)]) 0)
- (match_operand:QI 1 "nonimm_x64constmem_operand" "0,0")))
- (clobber (reg:CC FLAGS_REG))]
- ""
- "<logic>{b}\t{%h2, %0|%0, %h2}"
- [(set_attr "isa" "*,nox64")
- (set_attr "type" "alu")
- (set_attr "mode" "QI")])
-
-(define_insn "*<code>qi_ext<mode>_1"
- [(set (zero_extract:SWI248
- (match_operand 0 "int248_register_operand" "+Q,Q")
- (const_int 8)
- (const_int 8))
- (subreg:SWI248
- (any_or:QI
- (subreg:QI
- (match_operator:SWI248 3 "extract_operator"
- [(match_operand 1 "int248_register_operand" "0,0")
- (const_int 8)
- (const_int 8)]) 0)
- (match_operand:QI 2 "general_x64constmem_operand" "QnBc,m")) 0))
- (clobber (reg:CC FLAGS_REG))]
- "(!TARGET_PARTIAL_REG_STALL || optimize_function_for_size_p (cfun))
- /* FIXME: without this LRA can't reload this pattern, see PR82524. */
- && rtx_equal_p (operands[0], operands[1])"
- "<logic>{b}\t{%2, %h0|%h0, %2}"
- [(set_attr "isa" "*,nox64")
- (set_attr "type" "alu")
- (set_attr "mode" "QI")])
-
-(define_insn "*<code>qi_ext<mode>_2"
- [(set (zero_extract:SWI248
- (match_operand 0 "int248_register_operand" "+Q")
- (const_int 8)
- (const_int 8))
- (subreg:SWI248
- (any_or:QI
- (subreg:QI
- (match_operator:SWI248 3 "extract_operator"
- [(match_operand 1 "int248_register_operand" "%0")
- (const_int 8)
- (const_int 8)]) 0)
- (subreg:QI
- (match_operator:SWI248 4 "extract_operator"
- [(match_operand 2 "int248_register_operand" "Q")
- (const_int 8)
- (const_int 8)]) 0)) 0))
- (clobber (reg:CC FLAGS_REG))]
- "(!TARGET_PARTIAL_REG_STALL || optimize_function_for_size_p (cfun))
- /* FIXME: without this LRA can't reload this pattern, see PR82524. */
- && (rtx_equal_p (operands[0], operands[1])
- || rtx_equal_p (operands[0], operands[2]))"
- "<logic>{b}\t{%h2, %h0|%h0, %h2}"
- [(set_attr "type" "alu")
- (set_attr "mode" "QI")])
-
-(define_insn "*<code>qi_ext<mode>_3"
- [(set (zero_extract:SWI248
- (match_operand 0 "int248_register_operand" "+Q")
- (const_int 8)
- (const_int 8))
- (zero_extract:SWI248
- (any_logic:SWI248
- (match_operand 1 "int248_register_operand" "%0")
- (match_operand 2 "int248_register_operand" "Q"))
- (const_int 8)
- (const_int 8)))
- (clobber (reg:CC FLAGS_REG))]
- "(!TARGET_PARTIAL_REG_STALL || optimize_function_for_size_p (cfun))
- /* FIXME: without this LRA can't reload this pattern, see PR82524. */
- && (rtx_equal_p (operands[0], operands[1])
- || rtx_equal_p (operands[0], operands[2]))"
- "<logic>{b}\t{%h2, %h0|%h0, %h2}"
- [(set_attr "type" "alu")
- (set_attr "mode" "QI")])
-
;; Convert wide OR instructions with immediate operand to shorter QImode
;; equivalents when possible.
;; Don't do the splitting with memory operands, since it introduces risk
;; of memory mismatch stalls. We may want to do the splitting for optimizing
;; for size, but that can (should?) be handled by generic code instead.
+;; Don't do the splitting for APX NDD as NDD does not support *h registers.
(define_split
[(set (match_operand:SWI248 0 "QIreg_operand")
(any_or:SWI248 (match_operand:SWI248 1 "register_operand")
(clobber (reg:CC FLAGS_REG))]
"reload_completed
&& (!TARGET_PARTIAL_REG_STALL || optimize_function_for_size_p (cfun))
- && !(INTVAL (operands[2]) & ~(255 << 8))"
+ && !(INTVAL (operands[2]) & ~(255 << 8))
+ && !(TARGET_APX_NDD && REGNO (operands[0]) != REGNO (operands[1]))"
[(parallel
[(set (zero_extract:HI (match_dup 0)
(const_int 8)
"reload_completed
&& (!TARGET_PARTIAL_REG_STALL || optimize_function_for_size_p (cfun))
&& !(INTVAL (operands[2]) & ~255)
- && (INTVAL (operands[2]) & 128)"
+ && (INTVAL (operands[2]) & 128)
+ && !(TARGET_APX_NDD
+ && !rtx_equal_p (operands[0], operands[1]))"
[(parallel [(set (strict_low_part (match_dup 0))
(any_or:QI (match_dup 1)
(match_dup 2)))
(const_int 8)) 0)
(match_dup 2)) 0))])])
-(define_insn "*xorqi_ext<mode>_1_cc"
- [(set (reg FLAGS_REG)
- (compare
- (xor:QI
- (subreg:QI
- (match_operator:SWI248 3 "extract_operator"
- [(match_operand 1 "int248_register_operand" "0,0")
- (const_int 8)
- (const_int 8)]) 0)
- (match_operand:QI 2 "general_x64constmem_operand" "QnBc,m"))
- (const_int 0)))
- (set (zero_extract:SWI248
- (match_operand 0 "int248_register_operand" "+Q,Q")
- (const_int 8)
- (const_int 8))
- (subreg:SWI248
- (xor:QI
- (subreg:QI
- (match_op_dup 3
- [(match_dup 1)
- (const_int 8)
- (const_int 8)]) 0)
- (match_dup 2)) 0))]
- "ix86_match_ccmode (insn, CCNOmode)
- /* FIXME: without this LRA can't reload this pattern, see PR82524. */
- && rtx_equal_p (operands[0], operands[1])"
- "xor{b}\t{%2, %h0|%h0, %2}"
- [(set_attr "isa" "*,nox64")
- (set_attr "type" "alu")
- (set_attr "mode" "QI")])
-
;; Peephole2 rega = 0; rega op= regb into rega = regb.
(define_peephole2
[(parallel [(set (match_operand:SWI 0 "general_reg_operand")
})
(define_insn_and_split "*concat<mode><dwi>3_3"
- [(set (match_operand:<DWI> 0 "nonimmediate_operand" "=ro,r,r,&r")
+ [(set (match_operand:<DWI> 0 "nonimmediate_operand" "=ro,r,r,&r,x")
(any_or_plus:<DWI>
(ashift:<DWI>
(zero_extend:<DWI>
- (match_operand:DWIH 1 "nonimmediate_operand" "r,m,r,m"))
+ (match_operand:DWIH 1 "nonimmediate_operand" "r,m,r,m,x"))
(match_operand:QI 2 "const_int_operand"))
(zero_extend:<DWI>
- (match_operand:DWIH 3 "nonimmediate_operand" "r,r,m,m"))))]
+ (match_operand:DWIH 3 "nonimmediate_operand" "r,r,m,m,0"))))]
"INTVAL (operands[2]) == <MODE_SIZE> * BITS_PER_UNIT"
"#"
"&& reload_completed"
[(const_int 0)]
{
- split_double_concat (<DWI>mode, operands[0], operands[3], operands[1]);
+ if (SSE_REG_P (operands[0]))
+ {
+ rtx tmp = gen_rtx_REG (V2DImode, REGNO (operands[0]));
+ emit_insn (gen_vec_concatv2di (tmp, operands[3], operands[1]));
+ }
+ else
+ split_double_concat (<DWI>mode, operands[0], operands[3], operands[1]);
DONE;
-})
+}
+ [(set_attr "isa" "*,*,*,x64,x64")])
(define_insn_and_split "*concat<mode><dwi>3_4"
[(set (match_operand:<DWI> 0 "nonimmediate_operand" "=ro,r,r,&r")
{
split_double_concat (<DWI>mode, operands[0], operands[1], operands[2]);
DONE;
-})
+}
+ [(set_attr "isa" "*,*,*,x64")])
(define_insn_and_split "*concat<half><mode>3_5"
[(set (match_operand:DWI 0 "nonimmediate_operand" "=r,o,o")
[(set (match_operand:SDWIM 0 "nonimmediate_operand")
(neg:SDWIM (match_operand:SDWIM 1 "nonimmediate_operand")))]
""
- "ix86_expand_unary_operator (NEG, <MODE>mode, operands); DONE;")
+{
+ ix86_expand_unary_operator (NEG, <MODE>mode, operands, TARGET_APX_NDD);
+ DONE;
+})
(define_insn_and_split "*neg<dwi>2_doubleword"
- [(set (match_operand:<DWI> 0 "nonimmediate_operand" "=ro")
- (neg:<DWI> (match_operand:<DWI> 1 "nonimmediate_operand" "0")))
+ [(set (match_operand:<DWI> 0 "nonimmediate_operand" "=ro,&r")
+ (neg:<DWI> (match_operand:<DWI> 1 "nonimmediate_operand" "0,ro")))
(clobber (reg:CC FLAGS_REG))]
- "ix86_unary_operator_ok (NEG, <DWI>mode, operands)"
+ "ix86_unary_operator_ok (NEG, <DWI>mode, operands, TARGET_APX_NDD)"
"#"
"&& reload_completed"
[(parallel
[(set (match_dup 2)
(neg:DWIH (match_dup 2)))
(clobber (reg:CC FLAGS_REG))])]
- "split_double_mode (<DWI>mode, &operands[0], 2, &operands[0], &operands[2]);")
+ "split_double_mode (<DWI>mode, &operands[0], 2, &operands[0], &operands[2]);"
+ [(set_attr "isa" "*,apx_ndd")])
;; Convert:
;; mov %esi, %edx
(clobber (reg:CC FLAGS_REG))])])
(define_insn "*neg<mode>_1"
- [(set (match_operand:SWI 0 "nonimmediate_operand" "=<r>m")
- (neg:SWI (match_operand:SWI 1 "nonimmediate_operand" "0")))
+ [(set (match_operand:SWI 0 "nonimmediate_operand" "=<r>m,r")
+ (neg:SWI (match_operand:SWI 1 "nonimmediate_operand" "0,rm")))
(clobber (reg:CC FLAGS_REG))]
- "ix86_unary_operator_ok (NEG, <MODE>mode, operands)"
- "neg{<imodesuffix>}\t%0"
+ "ix86_unary_operator_ok (NEG, <MODE>mode, operands, TARGET_APX_NDD)"
+ "@
+ neg{<imodesuffix>}\t%0
+ neg{<imodesuffix>}\t{%1, %0|%0, %1}"
[(set_attr "type" "negnot")
+ (set_attr "isa" "*,apx_ndd")
(set_attr "mode" "<MODE>")])
(define_insn "*negsi_1_zext"
- [(set (match_operand:DI 0 "register_operand" "=r")
+ [(set (match_operand:DI 0 "register_operand" "=r,r")
(zero_extend:DI
- (neg:SI (match_operand:SI 1 "register_operand" "0"))))
+ (neg:SI (match_operand:SI 1 "nonimmediate_operand" "0,rm"))))
(clobber (reg:CC FLAGS_REG))]
- "TARGET_64BIT && ix86_unary_operator_ok (NEG, SImode, operands)"
- "neg{l}\t%k0"
+ "TARGET_64BIT
+ && ix86_unary_operator_ok (NEG, SImode, operands, TARGET_APX_NDD)"
+ "@
+ neg{l}\t%k0
+ neg{l}\t{%k1, %k0|%k0, %k1}"
[(set_attr "type" "negnot")
+ (set_attr "isa" "*,apx_ndd")
(set_attr "mode" "SI")])
;; Alternative 1 is needed to work around LRA limitation, see PR82524.
"@
neg{<imodesuffix>}\t%0
#"
- "&& reload_completed"
+ "&& reload_completed
+ && !(rtx_equal_p (operands[0], operands[1]))"
[(set (strict_low_part (match_dup 0)) (match_dup 1))
(parallel
[(set (strict_low_part (match_dup 0))
(define_insn "*neg<mode>_2"
[(set (reg FLAGS_REG)
(compare
- (neg:SWI (match_operand:SWI 1 "nonimmediate_operand" "0"))
+ (neg:SWI (match_operand:SWI 1 "nonimmediate_operand" "0,rm"))
(const_int 0)))
- (set (match_operand:SWI 0 "nonimmediate_operand" "=<r>m")
+ (set (match_operand:SWI 0 "nonimmediate_operand" "=<r>m,r")
(neg:SWI (match_dup 1)))]
"ix86_match_ccmode (insn, CCGOCmode)
- && ix86_unary_operator_ok (NEG, <MODE>mode, operands)"
- "neg{<imodesuffix>}\t%0"
+ && ix86_unary_operator_ok (NEG, <MODE>mode, operands, TARGET_APX_NDD)"
+ "@
+ neg{<imodesuffix>}\t%0
+ neg{<imodesuffix>}\t{%1, %0|%0, %1}"
[(set_attr "type" "negnot")
+ (set_attr "isa" "*,apx_ndd")
(set_attr "mode" "<MODE>")])
(define_insn "*negsi_2_zext"
[(set (reg FLAGS_REG)
(compare
- (neg:SI (match_operand:SI 1 "register_operand" "0"))
+ (neg:SI (match_operand:SI 1 "nonimmediate_operand" "0,rm"))
(const_int 0)))
- (set (match_operand:DI 0 "register_operand" "=r")
+ (set (match_operand:DI 0 "register_operand" "=r,r")
(zero_extend:DI
(neg:SI (match_dup 1))))]
"TARGET_64BIT && ix86_match_ccmode (insn, CCGOCmode)
- && ix86_unary_operator_ok (NEG, SImode, operands)"
- "neg{l}\t%k0"
+ && ix86_unary_operator_ok (NEG, SImode, operands, TARGET_APX_NDD)"
+ "@
+ neg{l}\t%k0
+ neg{l}\t{%1, %k0|%k0, %1}"
[(set_attr "type" "negnot")
+ (set_attr "isa" "*,apx_ndd")
(set_attr "mode" "SI")])
(define_insn "*neg<mode>_ccc_1"
[(set (reg:CCC FLAGS_REG)
(unspec:CCC
- [(match_operand:SWI 1 "nonimmediate_operand" "0")
+ [(match_operand:SWI 1 "nonimmediate_operand" "0,rm")
(const_int 0)] UNSPEC_CC_NE))
- (set (match_operand:SWI 0 "nonimmediate_operand" "=<r>m")
+ (set (match_operand:SWI 0 "nonimmediate_operand" "=<r>m,r")
(neg:SWI (match_dup 1)))]
""
- "neg{<imodesuffix>}\t%0"
+ "@
+ neg{<imodesuffix>}\t%0
+ neg{<imodesuffix>}\t{%1, %0|%0, %1}"
[(set_attr "type" "negnot")
+ (set_attr "isa" "*,apx_ndd")
(set_attr "mode" "<MODE>")])
(define_insn "*neg<mode>_ccc_2"
[(set (reg:CCC FLAGS_REG)
(unspec:CCC
- [(match_operand:SWI 1 "nonimmediate_operand" "0")
+ [(match_operand:SWI 1 "nonimmediate_operand" "0,rm")
(const_int 0)] UNSPEC_CC_NE))
- (clobber (match_scratch:SWI 0 "=<r>"))]
+ (clobber (match_scratch:SWI 0 "=<r>,r"))]
""
- "neg{<imodesuffix>}\t%0"
+ "@
+ neg{<imodesuffix>}\t%0
+ neg{<imodesuffix>}\t{%1, %0|%0, %1}"
[(set_attr "type" "negnot")
+ (set_attr "isa" "*,apx_ndd")
(set_attr "mode" "<MODE>")])
(define_expand "x86_neg<mode>_ccc"
(set (match_operand:SWI48 0 "register_operand")
(neg:SWI48 (match_dup 1)))])])
-(define_insn "*negqi_ext<mode>_2"
+;; Alternative 1 is needed to work around LRA limitation, see PR82524.
+(define_insn_and_split "*negqi_ext<mode>_1"
[(set (zero_extract:SWI248
- (match_operand 0 "int248_register_operand" "+Q")
+ (match_operand 0 "int248_register_operand" "+Q,&Q")
(const_int 8)
(const_int 8))
(subreg:SWI248
(neg:QI
(subreg:QI
(match_operator:SWI248 2 "extract_operator"
- [(match_operand 1 "int248_register_operand" "0")
+ [(match_operand 1 "int248_register_operand" "0,!Q")
(const_int 8)
(const_int 8)]) 0)) 0))
(clobber (reg:CC FLAGS_REG))]
- "/* FIXME: without this LRA can't reload this pattern, see PR82524. */
- rtx_equal_p (operands[0], operands[1])"
- "neg{b}\t%h0"
+ ""
+ "@
+ neg{b}\t%h0
+ #"
+ "reload_completed
+ && !(rtx_equal_p (operands[0], operands[1]))"
+ [(set (zero_extract:SWI248
+ (match_dup 0) (const_int 8) (const_int 8))
+ (zero_extract:SWI248
+ (match_dup 1) (const_int 8) (const_int 8)))
+ (parallel
+ [(set (zero_extract:SWI248
+ (match_dup 0) (const_int 8) (const_int 8))
+ (subreg:SWI248
+ (neg:QI
+ (subreg:QI
+ (match_op_dup 2
+ [(match_dup 0) (const_int 8) (const_int 8)]) 0)) 0))
+ (clobber (reg:CC FLAGS_REG))])]
+ ""
[(set_attr "type" "negnot")
(set_attr "mode" "QI")])
[(set (match_operand:SDWIM 0 "nonimmediate_operand")
(not:SDWIM (match_operand:SDWIM 1 "nonimmediate_operand")))]
""
- "ix86_expand_unary_operator (NOT, <MODE>mode, operands); DONE;")
+{
+ ix86_expand_unary_operator (NOT, <MODE>mode, operands, TARGET_APX_NDD);
+ DONE;
+})
(define_insn_and_split "*one_cmpl<dwi>2_doubleword"
- [(set (match_operand:<DWI> 0 "nonimmediate_operand" "=ro")
- (not:<DWI> (match_operand:<DWI> 1 "nonimmediate_operand" "0")))]
- "ix86_unary_operator_ok (NOT, <DWI>mode, operands)"
+ [(set (match_operand:<DWI> 0 "nonimmediate_operand" "=ro,&r")
+ (not:<DWI> (match_operand:<DWI> 1 "nonimmediate_operand" "0,ro")))]
+ "ix86_unary_operator_ok (NOT, <DWI>mode, operands, TARGET_APX_NDD)"
"#"
"&& reload_completed"
[(set (match_dup 0)
(not:DWIH (match_dup 1)))
(set (match_dup 2)
(not:DWIH (match_dup 3)))]
- "split_double_mode (<DWI>mode, &operands[0], 2, &operands[0], &operands[2]);")
+ "split_double_mode (<DWI>mode, &operands[0], 2, &operands[0], &operands[2]);"
+ [(set_attr "isa" "*,apx_ndd")])
(define_insn "*one_cmpl<mode>2_1"
- [(set (match_operand:SWI248 0 "nonimmediate_operand" "=rm,?k")
- (not:SWI248 (match_operand:SWI248 1 "nonimmediate_operand" "0,k")))]
- "ix86_unary_operator_ok (NOT, <MODE>mode, operands)"
+ [(set (match_operand:SWI248 0 "nonimmediate_operand" "=rm,r,?k")
+ (not:SWI248 (match_operand:SWI248 1 "nonimmediate_operand" "0,rm,k")))]
+ "ix86_unary_operator_ok (NOT, <MODE>mode, operands, TARGET_APX_NDD)"
"@
not{<imodesuffix>}\t%0
+ not{<imodesuffix>}\t{%1, %0|%0, %1}
#"
- [(set (attr "isa")
- (cond [(eq_attr "alternative" "1")
- (if_then_else (eq_attr "mode" "SI,DI")
- (const_string "avx512bw")
- (const_string "avx512f"))
- ]
- (const_string "*")))
- (set_attr "type" "negnot,msklog")
+ [(set_attr "isa" "*,apx_ndd,<kmov_isa>")
+ (set_attr "type" "negnot,negnot,msklog")
(set_attr "mode" "<MODE>")])
(define_insn "*one_cmplsi2_1_zext"
- [(set (match_operand:DI 0 "register_operand" "=r,?k")
+ [(set (match_operand:DI 0 "register_operand" "=r,r,?k")
(zero_extend:DI
- (not:SI (match_operand:SI 1 "register_operand" "0,k"))))]
- "TARGET_64BIT && ix86_unary_operator_ok (NOT, SImode, operands)"
+ (not:SI (match_operand:SI 1 "nonimmediate_operand" "0,rm,k"))))]
+ "TARGET_64BIT
+ && ix86_unary_operator_ok (NOT, SImode, operands, TARGET_APX_NDD)"
"@
not{l}\t%k0
+ not{l}\t{%1, %k0|%k0, %1}
#"
- [(set_attr "isa" "x64,avx512bw")
- (set_attr "type" "negnot,msklog")
- (set_attr "mode" "SI,SI")])
+ [(set_attr "isa" "x64,apx_ndd,avx512bw")
+ (set_attr "type" "negnot,negnot,msklog")
+ (set_attr "mode" "SI,SI,SI")])
(define_insn "*one_cmplqi2_1"
- [(set (match_operand:QI 0 "nonimmediate_operand" "=qm,r,?k")
- (not:QI (match_operand:QI 1 "nonimmediate_operand" "0,0,k")))]
- "ix86_unary_operator_ok (NOT, QImode, operands)"
+ [(set (match_operand:QI 0 "nonimmediate_operand" "=qm,r,r,?k")
+ (not:QI (match_operand:QI 1 "nonimmediate_operand" "0,0,rm,k")))]
+ "ix86_unary_operator_ok (NOT, QImode, operands, TARGET_APX_NDD)"
"@
not{b}\t%0
not{l}\t%k0
+ not{b}\t{%1, %0|%0, %1}
#"
- [(set_attr "isa" "*,*,avx512f")
- (set_attr "type" "negnot,negnot,msklog")
+ [(set_attr "isa" "*,*,apx_ndd,avx512f")
+ (set_attr "type" "negnot,negnot,negnot,msklog")
(set (attr "mode")
(cond [(eq_attr "alternative" "1")
(const_string "SI")
- (and (eq_attr "alternative" "2")
+ (and (eq_attr "alternative" "3")
(match_test "!TARGET_AVX512DQ"))
(const_string "HI")
]
"@
not{<imodesuffix>}\t%0
#"
- "&& reload_completed"
+ "&& reload_completed
+ && !(rtx_equal_p (operands[0], operands[1]))"
[(set (strict_low_part (match_dup 0)) (match_dup 1))
(set (strict_low_part (match_dup 0))
(not:SWI12 (match_dup 0)))]
(define_insn "*one_cmpl<mode>2_2"
[(set (reg FLAGS_REG)
- (compare (not:SWI (match_operand:SWI 1 "nonimmediate_operand" "0"))
+ (compare (not:SWI (match_operand:SWI 1 "nonimmediate_operand" "0,rm"))
(const_int 0)))
- (set (match_operand:SWI 0 "nonimmediate_operand" "=<r>m")
+ (set (match_operand:SWI 0 "nonimmediate_operand" "=<r>m,r")
(not:SWI (match_dup 1)))]
"ix86_match_ccmode (insn, CCNOmode)
- && ix86_unary_operator_ok (NOT, <MODE>mode, operands)"
+ && ix86_unary_operator_ok (NOT, <MODE>mode, operands, TARGET_APX_NDD)"
"#"
[(set_attr "type" "alu1")
+ (set_attr "isa" "*,apx_ndd")
(set_attr "mode" "<MODE>")])
(define_split
(define_insn "*one_cmplsi2_2_zext"
[(set (reg FLAGS_REG)
- (compare (not:SI (match_operand:SI 1 "register_operand" "0"))
+ (compare (not:SI (match_operand:SI 1 "nonimmediate_operand" "0,rm"))
(const_int 0)))
- (set (match_operand:DI 0 "register_operand" "=r")
+ (set (match_operand:DI 0 "register_operand" "=r,r")
(zero_extend:DI (not:SI (match_dup 1))))]
"TARGET_64BIT && ix86_match_ccmode (insn, CCNOmode)
- && ix86_unary_operator_ok (NOT, SImode, operands)"
+ && ix86_unary_operator_ok (NOT, SImode, operands, TARGET_APX_NDD)"
"#"
[(set_attr "type" "alu1")
+ (set_attr "isa" "*,apx_ndd")
(set_attr "mode" "SI")])
(define_split
[(set (match_operand 0 "flags_reg_operand")
(match_operator 2 "compare_operator"
- [(not:SI (match_operand:SI 3 "register_operand"))
+ [(not:SI (match_operand:SI 3 "nonimmediate_operand"))
(const_int 0)]))
(set (match_operand:DI 1 "register_operand")
(zero_extend:DI (not:SI (match_dup 3))))]
(const_int 0)]))
(set (match_dup 1)
(zero_extend:DI (xor:SI (match_dup 3) (const_int -1))))])])
+
+;; Alternative 1 is needed to work around LRA limitation, see PR82524.
+(define_insn_and_split "*one_cmplqi_ext<mode>_1"
+ [(set (zero_extract:SWI248
+ (match_operand 0 "int248_register_operand" "+Q,&Q")
+ (const_int 8)
+ (const_int 8))
+ (subreg:SWI248
+ (not:QI
+ (subreg:QI
+ (match_operator:SWI248 2 "extract_operator"
+ [(match_operand 1 "int248_register_operand" "0,!Q")
+ (const_int 8)
+ (const_int 8)]) 0)) 0))]
+ ""
+ "@
+ not{b}\t%h0
+ #"
+ "reload_completed
+ && !(rtx_equal_p (operands[0], operands[1]))"
+ [(set (zero_extract:SWI248
+ (match_dup 0) (const_int 8) (const_int 8))
+ (zero_extract:SWI248
+ (match_dup 1) (const_int 8) (const_int 8)))
+ (set (zero_extract:SWI248
+ (match_dup 0) (const_int 8) (const_int 8))
+ (subreg:SWI248
+ (not:QI
+ (subreg:QI
+ (match_op_dup 2
+ [(match_dup 0) (const_int 8) (const_int 8)]) 0)) 0))]
+ ""
+ [(set_attr "type" "negnot")
+ (set_attr "mode" "QI")])
\f
;; Shift instructions
(ashift:SDWIM (match_operand:SDWIM 1 "<ashl_input_operand>")
(match_operand:QI 2 "nonmemory_operand")))]
""
- "ix86_expand_binary_operator (ASHIFT, <MODE>mode, operands); DONE;")
+{
+ ix86_expand_binary_operator (ASHIFT, <MODE>mode, operands, TARGET_APX_NDD);
+ DONE;
+})
(define_insn_and_split "*ashl<dwi>3_doubleword_mask"
[(set (match_operand:<DWI> 0 "register_operand")
})
(define_insn "ashl<mode>3_doubleword"
- [(set (match_operand:DWI 0 "register_operand" "=&r")
- (ashift:DWI (match_operand:DWI 1 "reg_or_pm1_operand" "0n")
- (match_operand:QI 2 "nonmemory_operand" "<S>c")))
+ [(set (match_operand:DWI 0 "register_operand" "=&r,&r")
+ (ashift:DWI (match_operand:DWI 1 "reg_or_pm1_operand" "0n,r")
+ (match_operand:QI 2 "nonmemory_operand" "<S>c,<S>c")))
(clobber (reg:CC FLAGS_REG))]
""
"#"
- [(set_attr "type" "multi")])
+ [(set_attr "type" "multi")
+ (set_attr "isa" "*,apx_ndd")])
(define_split
[(set (match_operand:DWI 0 "register_operand")
(clobber (reg:CC FLAGS_REG))]
"epilogue_completed"
[(const_int 0)]
- "ix86_split_ashl (operands, NULL_RTX, <MODE>mode); DONE;")
+{
+ if (TARGET_APX_NDD
+ && !rtx_equal_p (operands[0], operands[1])
+ && REG_P (operands[1]))
+ ix86_split_ashl_ndd (operands, NULL_RTX);
+ else
+ ix86_split_ashl (operands, NULL_RTX, <MODE>mode);
+ DONE;
+})
;; By default we don't ask for a scratch register, because when DWImode
;; values are manipulated, registers are already at a premium. But if
(match_dup 3)]
"TARGET_CMOVE"
[(const_int 0)]
- "ix86_split_ashl (operands, operands[3], <DWI>mode); DONE;")
+{
+ if (TARGET_APX_NDD
+ && !rtx_equal_p (operands[0], operands[1])
+ && (REG_P (operands[1])))
+ ix86_split_ashl_ndd (operands, operands[3]);
+ else
+ ix86_split_ashl (operands, operands[3], <DWI>mode);
+ DONE;
+})
(define_insn_and_split "*ashl<dwi>3_doubleword_highpart"
[(set (match_operand:<DWI> 0 "register_operand" "=r")
{
split_double_mode (<DWI>mode, &operands[0], 1, &operands[0], &operands[3]);
int bits = INTVAL (operands[2]) - (<MODE_SIZE> * BITS_PER_UNIT);
- if (!rtx_equal_p (operands[3], operands[1]))
- emit_move_insn (operands[3], operands[1]);
- if (bits > 0)
- emit_insn (gen_ashl<mode>3 (operands[3], operands[3], GEN_INT (bits)));
+ bool op_equal_p = rtx_equal_p (operands[3], operands[1]);
+ if (bits == 0)
+ {
+ if (!op_equal_p)
+ emit_move_insn (operands[3], operands[1]);
+ }
+ else
+ {
+ if (!op_equal_p && !TARGET_APX_NDD)
+ emit_move_insn (operands[3], operands[1]);
+ rtx op_tmp = TARGET_APX_NDD ? operands[1] : operands[3];
+ emit_insn (gen_ashl<mode>3 (operands[3], op_tmp, GEN_INT (bits)));
+ }
ix86_expand_clear (operands[0]);
DONE;
})
(set_attr "amdfam10_decode" "vector")
(set_attr "bdver1_decode" "vector")])
+(define_insn "x86_64_shld_ndd"
+ [(set (match_operand:DI 0 "register_operand" "=r")
+ (ior:DI (ashift:DI (match_operand:DI 1 "nonimmediate_operand" "rm")
+ (and:QI (match_operand:QI 3 "nonmemory_operand" "Jc")
+ (const_int 63)))
+ (subreg:DI
+ (lshiftrt:TI
+ (zero_extend:TI
+ (match_operand:DI 2 "register_operand" "r"))
+ (minus:QI (const_int 64)
+ (and:QI (match_dup 3) (const_int 63)))) 0)))
+ (clobber (reg:CC FLAGS_REG))]
+ "TARGET_APX_NDD"
+ "shld{q}\t{%s3%2, %1, %0|%0, %1, %2, %3}"
+ [(set_attr "type" "ishift")
+ (set_attr "mode" "DI")])
+
(define_insn "x86_64_shld_1"
[(set (match_operand:DI 0 "nonimmediate_operand" "+r*m")
(ior:DI (ashift:DI (match_dup 0)
(set_attr "amdfam10_decode" "vector")
(set_attr "bdver1_decode" "vector")])
+(define_insn "x86_64_shld_ndd_1"
+ [(set (match_operand:DI 0 "register_operand" "=r")
+ (ior:DI (ashift:DI (match_operand:DI 1 "nonimmediate_operand" "rm")
+ (match_operand:QI 3 "const_0_to_63_operand"))
+ (subreg:DI
+ (lshiftrt:TI
+ (zero_extend:TI
+ (match_operand:DI 2 "register_operand" "r"))
+ (match_operand:QI 4 "const_0_to_255_operand")) 0)))
+ (clobber (reg:CC FLAGS_REG))]
+ "TARGET_APX_NDD
+ && INTVAL (operands[4]) == 64 - INTVAL (operands[3])"
+ "shld{q}\t{%3, %2, %1, %0|%0, %1, %2, %3}"
+ [(set_attr "type" "ishift")
+ (set_attr "mode" "DI")
+ (set_attr "length_immediate" "1")])
+
+
(define_insn_and_split "*x86_64_shld_shrd_1_nozext"
[(set (match_operand:DI 0 "nonimmediate_operand")
(ior:DI (ashift:DI (match_operand:DI 4 "nonimmediate_operand")
operands[4] = force_reg (DImode, operands[4]);
emit_insn (gen_x86_64_shrd_1 (operands[0], operands[4], operands[3], operands[2]));
}
+ else if (TARGET_APX_NDD)
+ {
+ rtx tmp = gen_reg_rtx (DImode);
+ if (MEM_P (operands[4]))
+ {
+ operands[1] = force_reg (DImode, operands[1]);
+ emit_insn (gen_x86_64_shld_ndd_1 (tmp, operands[4], operands[1],
+ operands[2], operands[3]));
+ }
+ else if (MEM_P (operands[1]))
+ emit_insn (gen_x86_64_shrd_ndd_1 (tmp, operands[1], operands[4],
+ operands[3], operands[2]));
+ else
+ emit_insn (gen_x86_64_shld_ndd_1 (tmp, operands[4], operands[1],
+ operands[2], operands[3]));
+ emit_move_insn (operands[0], tmp);
+ }
else
{
operands[1] = force_reg (DImode, operands[1]);
(const_int 63)))) 0)))
(clobber (reg:CC FLAGS_REG))])])
+(define_insn_and_split "*x86_64_shld_ndd_2"
+ [(set (match_operand:DI 0 "nonimmediate_operand")
+ (ior:DI (ashift:DI (match_operand:DI 1 "nonimmediate_operand")
+ (match_operand:QI 3 "nonmemory_operand"))
+ (lshiftrt:DI (match_operand:DI 2 "register_operand")
+ (minus:QI (const_int 64) (match_dup 3)))))
+ (clobber (reg:CC FLAGS_REG))]
+ "TARGET_APX_NDD
+ && ix86_pre_reload_split ()"
+ "#"
+ "&& 1"
+ [(parallel [(set (match_dup 4)
+ (ior:DI (ashift:DI (match_dup 1)
+ (and:QI (match_dup 3) (const_int 63)))
+ (subreg:DI
+ (lshiftrt:TI
+ (zero_extend:TI (match_dup 2))
+ (minus:QI (const_int 64)
+ (and:QI (match_dup 3)
+ (const_int 63)))) 0)))
+ (clobber (reg:CC FLAGS_REG))
+ (set (match_dup 0) (match_dup 4))])]
+{
+ operands[4] = gen_reg_rtx (DImode);
+ emit_move_insn (operands[4], operands[0]);
+})
+
(define_insn "x86_shld"
[(set (match_operand:SI 0 "nonimmediate_operand" "+r*m")
(ior:SI (ashift:SI (match_dup 0)
(set_attr "amdfam10_decode" "vector")
(set_attr "bdver1_decode" "vector")])
+(define_insn "x86_shld_ndd"
+ [(set (match_operand:SI 0 "nonimmediate_operand" "=r")
+ (ior:SI (ashift:SI (match_operand:SI 1 "nonimmediate_operand" "rm")
+ (and:QI (match_operand:QI 3 "nonmemory_operand" "Ic")
+ (const_int 31)))
+ (subreg:SI
+ (lshiftrt:DI
+ (zero_extend:DI
+ (match_operand:SI 2 "register_operand" "r"))
+ (minus:QI (const_int 32)
+ (and:QI (match_dup 3) (const_int 31)))) 0)))
+ (clobber (reg:CC FLAGS_REG))]
+ "TARGET_APX_NDD"
+ "shld{l}\t{%s3%2, %1, %0|%0, %1, %2, %3}"
+ [(set_attr "type" "ishift")
+ (set_attr "mode" "SI")])
+
+
(define_insn "x86_shld_1"
[(set (match_operand:SI 0 "nonimmediate_operand" "+r*m")
(ior:SI (ashift:SI (match_dup 0)
(set_attr "amdfam10_decode" "vector")
(set_attr "bdver1_decode" "vector")])
+(define_insn "x86_shld_ndd_1"
+ [(set (match_operand:SI 0 "register_operand" "=r")
+ (ior:SI (ashift:SI (match_operand:SI 1 "nonimmediate_operand" "rm")
+ (match_operand:QI 3 "const_0_to_31_operand"))
+ (subreg:SI
+ (lshiftrt:DI
+ (zero_extend:DI
+ (match_operand:SI 2 "register_operand" "r"))
+ (match_operand:QI 4 "const_0_to_63_operand")) 0)))
+ (clobber (reg:CC FLAGS_REG))]
+ "TARGET_APX_NDD
+ && INTVAL (operands[4]) == 32 - INTVAL (operands[3])"
+ "shld{l}\t{%3, %2, %1, %0|%0, %1, %2, %3}"
+ [(set_attr "type" "ishift")
+ (set_attr "length_immediate" "1")
+ (set_attr "mode" "SI")])
+
+
(define_insn_and_split "*x86_shld_shrd_1_nozext"
[(set (match_operand:SI 0 "nonimmediate_operand")
(ior:SI (ashift:SI (match_operand:SI 4 "nonimmediate_operand")
operands[4] = force_reg (SImode, operands[4]);
emit_insn (gen_x86_shrd_1 (operands[0], operands[4], operands[3], operands[2]));
}
- else
+ else if (TARGET_APX_NDD)
+ {
+ rtx tmp = gen_reg_rtx (SImode);
+ if (MEM_P (operands[4]))
+ {
+ operands[1] = force_reg (SImode, operands[1]);
+ emit_insn (gen_x86_shld_ndd_1 (tmp, operands[4], operands[1],
+ operands[2], operands[3]));
+ }
+ else if (MEM_P (operands[1]))
+ emit_insn (gen_x86_shrd_ndd_1 (tmp, operands[1], operands[4],
+ operands[3], operands[2]));
+ else
+ emit_insn (gen_x86_shld_ndd_1 (tmp, operands[4], operands[1],
+ operands[2], operands[3]));
+ emit_move_insn (operands[0], tmp);
+ }
+ else
{
operands[1] = force_reg (SImode, operands[1]);
rtx tmp = gen_reg_rtx (SImode);
(const_int 31)))) 0)))
(clobber (reg:CC FLAGS_REG))])])
+(define_insn_and_split "*x86_shld_ndd_2"
+ [(set (match_operand:SI 0 "nonimmediate_operand")
+ (ior:SI (ashift:SI (match_operand:SI 1 "nonimmediate_operand")
+ (match_operand:QI 3 "nonmemory_operand"))
+ (lshiftrt:SI (match_operand:SI 2 "register_operand")
+ (minus:QI (const_int 32) (match_dup 3)))))
+ (clobber (reg:CC FLAGS_REG))]
+ "TARGET_APX_NDD
+ && ix86_pre_reload_split ()"
+ "#"
+ "&& 1"
+ [(parallel [(set (match_dup 4)
+ (ior:SI (ashift:SI (match_dup 1)
+ (and:QI (match_dup 3) (const_int 31)))
+ (subreg:SI
+ (lshiftrt:DI
+ (zero_extend:DI (match_dup 2))
+ (minus:QI (const_int 32)
+ (and:QI (match_dup 3)
+ (const_int 31)))) 0)))
+ (clobber (reg:CC FLAGS_REG))
+ (set (match_dup 0) (match_dup 4))])]
+{
+ operands[4] = gen_reg_rtx (SImode);
+ emit_move_insn (operands[4], operands[0]);
+})
+
(define_expand "@x86_shift<mode>_adj_1"
[(set (reg:CCZ FLAGS_REG)
(compare:CCZ (and:QI (match_operand:QI 2 "register_operand")
(set_attr "mode" "<MODE>")])
(define_insn "*ashl<mode>3_1"
- [(set (match_operand:SWI48 0 "nonimmediate_operand" "=rm,r,r,?k")
- (ashift:SWI48 (match_operand:SWI48 1 "nonimmediate_operand" "0,l,rm,k")
- (match_operand:QI 2 "nonmemory_operand" "c<S>,M,r,<KS>")))
+ [(set (match_operand:SWI48 0 "nonimmediate_operand" "=rm,r,r,?k,r")
+ (ashift:SWI48 (match_operand:SWI48 1 "nonimmediate_operand" "0,l,rm,k,rm")
+ (match_operand:QI 2 "nonmemory_operand" "c<S>,M,r,<KS>,c<S>")))
(clobber (reg:CC FLAGS_REG))]
- "ix86_binary_operator_ok (ASHIFT, <MODE>mode, operands)"
+ "ix86_binary_operator_ok (ASHIFT, <MODE>mode, operands, TARGET_APX_NDD)"
{
+ bool use_ndd = get_attr_isa (insn) == ISA_APX_NDD;
switch (get_attr_type (insn))
{
case TYPE_LEA:
default:
if (operands[2] == const1_rtx
- && (TARGET_SHIFT1 || optimize_function_for_size_p (cfun)))
+ && (TARGET_SHIFT1 || optimize_function_for_size_p (cfun))
+ /* For NDD form instructions related to TARGET_SHIFT1, the $1
+ immediate do not need to be omitted as assembler will map it
+ to use shorter encoding. */
+ && !use_ndd)
return "sal{<imodesuffix>}\t%0";
else
- return "sal{<imodesuffix>}\t{%2, %0|%0, %2}";
+ return use_ndd ? "sal{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}"
+ : "sal{<imodesuffix>}\t{%2, %0|%0, %2}";
}
}
- [(set_attr "isa" "*,*,bmi2,avx512bw")
+ [(set_attr "isa" "*,*,bmi2,avx512bw,apx_ndd")
(set (attr "type")
(cond [(eq_attr "alternative" "1")
(const_string "lea")
(eq_attr "alternative" "2")
(const_string "ishiftx")
+ (eq_attr "alternative" "4")
+ (const_string "ishift")
(and (and (match_test "TARGET_DOUBLE_WITH_ADD")
(match_operand 0 "register_operand"))
(match_operand 2 "const1_operand"))
(set_attr "mode" "SI")])
(define_insn "*ashlsi3_1_zext"
- [(set (match_operand:DI 0 "register_operand" "=r,r,r")
+ [(set (match_operand:DI 0 "register_operand" "=r,r,r,r")
(zero_extend:DI
- (ashift:SI (match_operand:SI 1 "nonimmediate_operand" "0,l,rm")
- (match_operand:QI 2 "nonmemory_operand" "cI,M,r"))))
+ (ashift:SI (match_operand:SI 1 "nonimmediate_operand" "0,l,rm,rm")
+ (match_operand:QI 2 "nonmemory_operand" "cI,M,r,cI"))))
(clobber (reg:CC FLAGS_REG))]
- "TARGET_64BIT && ix86_binary_operator_ok (ASHIFT, SImode, operands)"
+ "TARGET_64BIT
+ && ix86_binary_operator_ok (ASHIFT, SImode, operands, TARGET_APX_NDD)"
{
+ bool use_ndd = get_attr_isa (insn) == ISA_APX_NDD;
switch (get_attr_type (insn))
{
case TYPE_LEA:
default:
if (operands[2] == const1_rtx
- && (TARGET_SHIFT1 || optimize_function_for_size_p (cfun)))
+ && (TARGET_SHIFT1 || optimize_function_for_size_p (cfun))
+ && !use_ndd)
return "sal{l}\t%k0";
else
- return "sal{l}\t{%2, %k0|%k0, %2}";
+ return use_ndd ? "sal{l}\t{%2, %1, %k0|%k0, %1, %2}"
+ : "sal{l}\t{%2, %k0|%k0, %2}";
}
}
- [(set_attr "isa" "*,*,bmi2")
+ [(set_attr "isa" "*,*,bmi2,apx_ndd")
(set (attr "type")
(cond [(eq_attr "alternative" "1")
(const_string "lea")
(eq_attr "alternative" "2")
(const_string "ishiftx")
+ (eq_attr "alternative" "3")
+ (const_string "ishift")
(and (match_test "TARGET_DOUBLE_WITH_ADD")
(match_operand 2 "const1_operand"))
(const_string "alu")
"operands[2] = gen_lowpart (SImode, operands[2]);")
(define_insn "*ashlhi3_1"
- [(set (match_operand:HI 0 "nonimmediate_operand" "=rm,Yp,?k")
- (ashift:HI (match_operand:HI 1 "nonimmediate_operand" "0,l,k")
- (match_operand:QI 2 "nonmemory_operand" "cI,M,Ww")))
+ [(set (match_operand:HI 0 "nonimmediate_operand" "=rm,Yp,?k,r")
+ (ashift:HI (match_operand:HI 1 "nonimmediate_operand" "0,l,k,rm")
+ (match_operand:QI 2 "nonmemory_operand" "cI,M,Ww,cI")))
(clobber (reg:CC FLAGS_REG))]
- "ix86_binary_operator_ok (ASHIFT, HImode, operands)"
+ "ix86_binary_operator_ok (ASHIFT, HImode, operands, TARGET_APX_NDD)"
{
+ bool use_ndd = get_attr_isa (insn) == ISA_APX_NDD;
switch (get_attr_type (insn))
{
case TYPE_LEA:
default:
if (operands[2] == const1_rtx
- && (TARGET_SHIFT1 || optimize_function_for_size_p (cfun)))
+ && (TARGET_SHIFT1 || optimize_function_for_size_p (cfun))
+ && !use_ndd)
return "sal{w}\t%0";
else
- return "sal{w}\t{%2, %0|%0, %2}";
+ return use_ndd ? "sal{w}\t{%2, %1, %0|%0, %1, %2}"
+ : "sal{w}\t{%2, %0|%0, %2}";
}
}
- [(set_attr "isa" "*,*,avx512f")
+ [(set_attr "isa" "*,*,avx512f,apx_ndd")
(set (attr "type")
(cond [(eq_attr "alternative" "1")
(const_string "lea")
(eq_attr "alternative" "2")
(const_string "msklog")
+ (eq_attr "alternative" "3")
+ (const_string "ishift")
(and (and (match_test "TARGET_DOUBLE_WITH_ADD")
(match_operand 0 "register_operand"))
(match_operand 2 "const1_operand"))
(match_test "optimize_function_for_size_p (cfun)")))))
(const_string "0")
(const_string "*")))
- (set_attr "mode" "HI,SI,HI")])
+ (set_attr "mode" "HI,SI,HI,HI")])
(define_insn "*ashlqi3_1"
- [(set (match_operand:QI 0 "nonimmediate_operand" "=qm,r,Yp,?k")
- (ashift:QI (match_operand:QI 1 "nonimmediate_operand" "0,0,l,k")
- (match_operand:QI 2 "nonmemory_operand" "cI,cI,M,Wb")))
+ [(set (match_operand:QI 0 "nonimmediate_operand" "=qm,r,Yp,?k,r")
+ (ashift:QI (match_operand:QI 1 "nonimmediate_operand" "0,0,l,k,rm")
+ (match_operand:QI 2 "nonmemory_operand" "cI,cI,M,Wb,cI")))
(clobber (reg:CC FLAGS_REG))]
- "ix86_binary_operator_ok (ASHIFT, QImode, operands)"
+ "ix86_binary_operator_ok (ASHIFT, QImode, operands, TARGET_APX_NDD)"
{
+ bool use_ndd = get_attr_isa (insn) == ISA_APX_NDD;
switch (get_attr_type (insn))
{
case TYPE_LEA:
default:
if (operands[2] == const1_rtx
- && (TARGET_SHIFT1 || optimize_function_for_size_p (cfun)))
+ && (TARGET_SHIFT1 || optimize_function_for_size_p (cfun))
+ && !use_ndd)
{
if (get_attr_mode (insn) == MODE_SI)
return "sal{l}\t%k0";
if (get_attr_mode (insn) == MODE_SI)
return "sal{l}\t{%2, %k0|%k0, %2}";
else
- return "sal{b}\t{%2, %0|%0, %2}";
+ return use_ndd ? "sal{b}\t{%2, %1, %0|%0, %1, %2}"
+ : "sal{b}\t{%2, %0|%0, %2}";
}
}
}
- [(set_attr "isa" "*,*,*,avx512dq")
+ [(set_attr "isa" "*,*,*,avx512dq,apx_ndd")
(set (attr "type")
(cond [(eq_attr "alternative" "2")
(const_string "lea")
(eq_attr "alternative" "3")
(const_string "msklog")
+ (eq_attr "alternative" "4")
+ (const_string "ishift")
(and (and (match_test "TARGET_DOUBLE_WITH_ADD")
(match_operand 0 "register_operand"))
(match_operand 2 "const1_operand"))
(match_test "optimize_function_for_size_p (cfun)")))))
(const_string "0")
(const_string "*")))
- (set_attr "mode" "QI,SI,SI,QI")
+ (set_attr "mode" "QI,SI,SI,QI,QI")
;; Potential partial reg stall on alternative 1.
(set (attr "preferred_for_speed")
- (cond [(eq_attr "alternative" "1")
+ (cond [(eq_attr "alternative" "1,4")
(symbol_ref "!TARGET_PARTIAL_REG_STALL")]
(symbol_ref "true")))])
return "sal{<imodesuffix>}\t{%2, %0|%0, %2}";
}
}
- "&& reload_completed"
+ "&& reload_completed
+ && !(rtx_equal_p (operands[0], operands[1]))"
[(set (strict_low_part (match_dup 0)) (match_dup 1))
(parallel
[(set (strict_low_part (match_dup 0))
(define_insn "*ashl<mode>3_cmp"
[(set (reg FLAGS_REG)
(compare
- (ashift:SWI (match_operand:SWI 1 "nonimmediate_operand" "0")
- (match_operand:QI 2 "<shift_immediate_operand>" "<S>"))
+ (ashift:SWI (match_operand:SWI 1 "nonimmediate_operand" "0,rm")
+ (match_operand:QI 2 "<shift_immediate_operand>" "<S>,<S>"))
(const_int 0)))
- (set (match_operand:SWI 0 "nonimmediate_operand" "=<r>m")
+ (set (match_operand:SWI 0 "nonimmediate_operand" "=<r>m,r")
(ashift:SWI (match_dup 1) (match_dup 2)))]
"(optimize_function_for_size_p (cfun)
|| !TARGET_PARTIAL_FLAG_REG_STALL
&& (TARGET_SHIFT1
|| (TARGET_DOUBLE_WITH_ADD && REG_P (operands[0])))))
&& ix86_match_ccmode (insn, CCGOCmode)
- && ix86_binary_operator_ok (ASHIFT, <MODE>mode, operands)"
+ && ix86_binary_operator_ok (ASHIFT, <MODE>mode, operands, TARGET_APX_NDD)"
{
+ bool use_ndd = get_attr_isa (insn) == ISA_APX_NDD;
switch (get_attr_type (insn))
{
case TYPE_ALU:
default:
if (operands[2] == const1_rtx
- && (TARGET_SHIFT1 || optimize_function_for_size_p (cfun)))
+ && (TARGET_SHIFT1 || optimize_function_for_size_p (cfun))
+ && !use_ndd)
return "sal{<imodesuffix>}\t%0";
else
- return "sal{<imodesuffix>}\t{%2, %0|%0, %2}";
+ return use_ndd ? "sal{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}"
+ : "sal{<imodesuffix>}\t{%2, %0|%0, %2}";
}
}
- [(set (attr "type")
- (cond [(and (and (match_test "TARGET_DOUBLE_WITH_ADD")
+ [(set_attr "isa" "*,apx_ndd")
+ (set (attr "type")
+ (cond [(eq_attr "alternative" "1")
+ (const_string "ishift")
+ (and (and (match_test "TARGET_DOUBLE_WITH_ADD")
(match_operand 0 "register_operand"))
(match_operand 2 "const1_operand"))
(const_string "alu")
(define_insn "*ashlsi3_cmp_zext"
[(set (reg FLAGS_REG)
(compare
- (ashift:SI (match_operand:SI 1 "register_operand" "0")
+ (ashift:SI (match_operand:SI 1 "nonimmediate_operand" "0,rm")
(match_operand:QI 2 "const_1_to_31_operand"))
(const_int 0)))
- (set (match_operand:DI 0 "register_operand" "=r")
+ (set (match_operand:DI 0 "register_operand" "=r,r")
(zero_extend:DI (ashift:SI (match_dup 1) (match_dup 2))))]
"TARGET_64BIT
&& (optimize_function_for_size_p (cfun)
&& (TARGET_SHIFT1
|| TARGET_DOUBLE_WITH_ADD)))
&& ix86_match_ccmode (insn, CCGOCmode)
- && ix86_binary_operator_ok (ASHIFT, SImode, operands)"
+ && ix86_binary_operator_ok (ASHIFT, SImode, operands, TARGET_APX_NDD)"
{
+ bool use_ndd = get_attr_isa (insn) == ISA_APX_NDD;
switch (get_attr_type (insn))
{
case TYPE_ALU:
default:
if (operands[2] == const1_rtx
- && (TARGET_SHIFT1 || optimize_function_for_size_p (cfun)))
+ && (TARGET_SHIFT1 || optimize_function_for_size_p (cfun))
+ && !use_ndd)
return "sal{l}\t%k0";
else
- return "sal{l}\t{%2, %k0|%k0, %2}";
+ return use_ndd ? "sal{l}\t{%2, %1, %k0|%k0, %1, %2}"
+ : "sal{l}\t{%2, %k0|%k0, %2}";
}
}
- [(set (attr "type")
- (cond [(and (match_test "TARGET_DOUBLE_WITH_ADD")
+ [(set_attr "isa" "*,apx_ndd")
+ (set (attr "type")
+ (cond [(eq_attr "alternative" "1")
+ (const_string "ishift")
+ (and (match_test "TARGET_DOUBLE_WITH_ADD")
(match_operand 2 "const1_operand"))
(const_string "alu")
]
(define_insn "*ashl<mode>3_cconly"
[(set (reg FLAGS_REG)
(compare
- (ashift:SWI (match_operand:SWI 1 "register_operand" "0")
- (match_operand:QI 2 "<shift_immediate_operand>" "<S>"))
+ (ashift:SWI (match_operand:SWI 1 "nonimmediate_operand" "0,rm")
+ (match_operand:QI 2 "<shift_immediate_operand>" "<S>,<S>"))
(const_int 0)))
- (clobber (match_scratch:SWI 0 "=<r>"))]
+ (clobber (match_scratch:SWI 0 "=<r>,r"))]
"(optimize_function_for_size_p (cfun)
|| !TARGET_PARTIAL_FLAG_REG_STALL
|| (operands[2] == const1_rtx
|| TARGET_DOUBLE_WITH_ADD)))
&& ix86_match_ccmode (insn, CCGOCmode)"
{
+ bool use_ndd = get_attr_isa (insn) == ISA_APX_NDD;
switch (get_attr_type (insn))
{
case TYPE_ALU:
gcc_assert (operands[2] == const1_rtx);
return "add{<imodesuffix>}\t%0, %0";
- default:
+ default:
if (operands[2] == const1_rtx
- && (TARGET_SHIFT1 || optimize_function_for_size_p (cfun)))
+ && (TARGET_SHIFT1 || optimize_function_for_size_p (cfun))
+ && !use_ndd)
return "sal{<imodesuffix>}\t%0";
else
- return "sal{<imodesuffix>}\t{%2, %0|%0, %2}";
+ return use_ndd ? "sal{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}"
+ : "sal{<imodesuffix>}\t{%2, %0|%0, %2}";
}
}
- [(set (attr "type")
- (cond [(and (and (match_test "TARGET_DOUBLE_WITH_ADD")
+ [(set_attr "isa" "*,apx_ndd")
+ (set (attr "type")
+ (cond [(eq_attr "alternative" "1")
+ (const_string "ishift")
+ (and (and (match_test "TARGET_DOUBLE_WITH_ADD")
(match_operand 0 "register_operand"))
(match_operand 2 "const1_operand"))
(const_string "alu")
(const_string "*")))
(set_attr "mode" "<MODE>")])
-(define_insn "*ashlqi_ext<mode>_2"
+;; Alternative 1 is needed to work around LRA limitation, see PR82524.
+(define_insn_and_split "*ashlqi_ext<mode>_1"
[(set (zero_extract:SWI248
- (match_operand 0 "int248_register_operand" "+Q")
+ (match_operand 0 "int248_register_operand" "+Q,&Q")
(const_int 8)
(const_int 8))
(subreg:SWI248
(ashift:QI
(subreg:QI
(match_operator:SWI248 3 "extract_operator"
- [(match_operand 1 "int248_register_operand" "0")
+ [(match_operand 1 "int248_register_operand" "0,!Q")
(const_int 8)
(const_int 8)]) 0)
- (match_operand:QI 2 "nonmemory_operand" "cI")) 0))
- (clobber (reg:CC FLAGS_REG))]
- "/* FIXME: without this LRA can't reload this pattern, see PR82524. */
- rtx_equal_p (operands[0], operands[1])"
+ (match_operand:QI 2 "nonmemory_operand" "cI,cI")) 0))
+ (clobber (reg:CC FLAGS_REG))]
+ ""
{
+ if (which_alternative)
+ return "#";
+
switch (get_attr_type (insn))
{
case TYPE_ALU:
return "sal{b}\t{%2, %h0|%h0, %2}";
}
}
+ "reload_completed
+ && !(rtx_equal_p (operands[0], operands[1]))"
+ [(set (zero_extract:SWI248
+ (match_dup 0) (const_int 8) (const_int 8))
+ (zero_extract:SWI248
+ (match_dup 1) (const_int 8) (const_int 8)))
+ (parallel
+ [(set (zero_extract:SWI248
+ (match_dup 0) (const_int 8) (const_int 8))
+ (subreg:SWI248
+ (ashift:QI
+ (subreg:QI
+ (match_op_dup 3
+ [(match_dup 0) (const_int 8) (const_int 8)]) 0)
+ (match_dup 2)) 0))
+ (clobber (reg:CC FLAGS_REG))])]
+ ""
[(set (attr "type")
(cond [(and (match_test "TARGET_DOUBLE_WITH_ADD")
(match_operand 2 "const1_operand"))
(any_shiftrt:SDWIM (match_operand:SDWIM 1 "<shift_operand>")
(match_operand:QI 2 "nonmemory_operand")))]
""
- "ix86_expand_binary_operator (<CODE>, <MODE>mode, operands); DONE;")
+{
+ ix86_expand_binary_operator (<CODE>, <MODE>mode, operands, TARGET_APX_NDD);
+ DONE;
+})
;; Avoid useless masking of count operand.
(define_insn_and_split "*<insn><mode>3_mask"
})
(define_insn_and_split "<insn><mode>3_doubleword"
- [(set (match_operand:DWI 0 "register_operand" "=&r")
- (any_shiftrt:DWI (match_operand:DWI 1 "register_operand" "0")
- (match_operand:QI 2 "nonmemory_operand" "<S>c")))
+ [(set (match_operand:DWI 0 "register_operand" "=&r,&r")
+ (any_shiftrt:DWI (match_operand:DWI 1 "register_operand" "0,r")
+ (match_operand:QI 2 "nonmemory_operand" "<S>c,<S>c")))
(clobber (reg:CC FLAGS_REG))]
""
"#"
"epilogue_completed"
[(const_int 0)]
- "ix86_split_<insn> (operands, NULL_RTX, <MODE>mode); DONE;"
- [(set_attr "type" "multi")])
+{
+ if (TARGET_APX_NDD
+ && !rtx_equal_p (operands[0], operands[1]))
+ ix86_split_rshift_ndd (<CODE>, operands, NULL_RTX);
+ else
+ ix86_split_<insn> (operands, NULL_RTX, <MODE>mode);
+ DONE;
+}
+ [(set_attr "type" "multi")
+ (set_attr "isa" "*,apx_ndd")])
;; By default we don't ask for a scratch register, because when DWImode
;; values are manipulated, registers are already at a premium. But if
(match_dup 3)]
"TARGET_CMOVE"
[(const_int 0)]
- "ix86_split_<insn> (operands, operands[3], <DWI>mode); DONE;")
+{
+ if (TARGET_APX_NDD
+ && !rtx_equal_p (operands[0], operands[1]))
+ ix86_split_rshift_ndd (<CODE>, operands, operands[3]);
+ else
+ ix86_split_<insn> (operands, operands[3], <DWI>mode);
+ DONE;
+})
+
+;; Split truncations of double word right shifts into x86_shrd_1.
+(define_insn_and_split "<insn><dwi>3_doubleword_lowpart"
+ [(set (match_operand:DWIH 0 "register_operand" "=&r")
+ (subreg:DWIH
+ (any_shiftrt:<DWI> (match_operand:<DWI> 1 "register_operand" "r")
+ (match_operand:QI 2 "const_int_operand")) 0))
+ (clobber (reg:CC FLAGS_REG))]
+ "UINTVAL (operands[2]) < <MODE_SIZE> * BITS_PER_UNIT"
+ "#"
+ "&& reload_completed"
+ [(parallel
+ [(set (match_dup 0)
+ (ior:DWIH (lshiftrt:DWIH (match_dup 0) (match_dup 2))
+ (subreg:DWIH
+ (ashift:<DWI> (zero_extend:<DWI> (match_dup 3))
+ (match_dup 4)) 0)))
+ (clobber (reg:CC FLAGS_REG))])]
+{
+ split_double_mode (<DWI>mode, &operands[1], 1, &operands[1], &operands[3]);
+ operands[4] = GEN_INT ((<MODE_SIZE> * BITS_PER_UNIT) - INTVAL (operands[2]));
+ if (!rtx_equal_p (operands[0], operands[1]))
+ emit_move_insn (operands[0], operands[1]);
+})
(define_insn "x86_64_shrd"
[(set (match_operand:DI 0 "nonimmediate_operand" "+r*m")
(set_attr "amdfam10_decode" "vector")
(set_attr "bdver1_decode" "vector")])
+(define_insn "x86_64_shrd_ndd"
+ [(set (match_operand:DI 0 "register_operand" "=r")
+ (ior:DI (lshiftrt:DI (match_operand:DI 1 "nonimmediate_operand" "rm")
+ (and:QI (match_operand:QI 3 "nonmemory_operand" "Jc")
+ (const_int 63)))
+ (subreg:DI
+ (ashift:TI
+ (zero_extend:TI
+ (match_operand:DI 2 "register_operand" "r"))
+ (minus:QI (const_int 64)
+ (and:QI (match_dup 3) (const_int 63)))) 0)))
+ (clobber (reg:CC FLAGS_REG))]
+ "TARGET_APX_NDD"
+ "shrd{q}\t{%s3%2, %1, %0|%0, %1, %2, %3}"
+ [(set_attr "type" "ishift")
+ (set_attr "mode" "DI")])
+
+
(define_insn "x86_64_shrd_1"
[(set (match_operand:DI 0 "nonimmediate_operand" "+r*m")
(ior:DI (lshiftrt:DI (match_dup 0)
(set_attr "amdfam10_decode" "vector")
(set_attr "bdver1_decode" "vector")])
+(define_insn "x86_64_shrd_ndd_1"
+ [(set (match_operand:DI 0 "register_operand" "=r")
+ (ior:DI (lshiftrt:DI (match_operand:DI 1 "nonimmediate_operand" "rm")
+ (match_operand:QI 3 "const_0_to_63_operand"))
+ (subreg:DI
+ (ashift:TI
+ (zero_extend:TI
+ (match_operand:DI 2 "register_operand" "r"))
+ (match_operand:QI 4 "const_0_to_255_operand")) 0)))
+ (clobber (reg:CC FLAGS_REG))]
+ "TARGET_APX_NDD
+ && INTVAL (operands[4]) == 64 - INTVAL (operands[3])"
+ "shrd{q}\t{%3, %2, %1, %0|%0, %1, %2, %3}"
+ [(set_attr "type" "ishift")
+ (set_attr "length_immediate" "1")
+ (set_attr "mode" "DI")])
+
+
(define_insn_and_split "*x86_64_shrd_shld_1_nozext"
[(set (match_operand:DI 0 "nonimmediate_operand")
(ior:DI (lshiftrt:DI (match_operand:DI 4 "nonimmediate_operand")
operands[4] = force_reg (DImode, operands[4]);
emit_insn (gen_x86_64_shld_1 (operands[0], operands[4], operands[3], operands[2]));
}
+ else if (TARGET_APX_NDD)
+ {
+ rtx tmp = gen_reg_rtx (DImode);
+ if (MEM_P (operands[4]))
+ {
+ operands[1] = force_reg (DImode, operands[1]);
+ emit_insn (gen_x86_64_shrd_ndd_1 (tmp, operands[4], operands[1],
+ operands[2], operands[3]));
+ }
+ else if (MEM_P (operands[1]))
+ emit_insn (gen_x86_64_shld_ndd_1 (tmp, operands[1], operands[4],
+ operands[3], operands[2]));
+ else
+ emit_insn (gen_x86_64_shrd_ndd_1 (tmp, operands[4], operands[1],
+ operands[2], operands[3]));
+ emit_move_insn (operands[0], tmp);
+ }
else
{
operands[1] = force_reg (DImode, operands[1]);
(const_int 63)))) 0)))
(clobber (reg:CC FLAGS_REG))])])
+(define_insn_and_split "*x86_64_shrd_ndd_2"
+ [(set (match_operand:DI 0 "nonimmediate_operand")
+ (ior:DI (lshiftrt:DI (match_operand:DI 1 "nonimmediate_operand")
+ (match_operand:QI 3 "nonmemory_operand"))
+ (ashift:DI (match_operand:DI 2 "register_operand")
+ (minus:QI (const_int 64) (match_dup 2)))))
+ (clobber (reg:CC FLAGS_REG))]
+ "TARGET_APX_NDD
+ && ix86_pre_reload_split ()"
+ "#"
+ "&& 1"
+ [(parallel [(set (match_dup 4)
+ (ior:DI (lshiftrt:DI (match_dup 1)
+ (and:QI (match_dup 3) (const_int 63)))
+ (subreg:DI
+ (ashift:TI
+ (zero_extend:TI (match_dup 2))
+ (minus:QI (const_int 64)
+ (and:QI (match_dup 3)
+ (const_int 63)))) 0)))
+ (clobber (reg:CC FLAGS_REG))
+ (set (match_dup 0) (match_dup 4))])]
+{
+ operands[4] = gen_reg_rtx (DImode);
+ emit_move_insn (operands[4], operands[0]);
+})
+
(define_insn "x86_shrd"
[(set (match_operand:SI 0 "nonimmediate_operand" "+r*m")
(ior:SI (lshiftrt:SI (match_dup 0)
(set_attr "amdfam10_decode" "vector")
(set_attr "bdver1_decode" "vector")])
+(define_insn "x86_shrd_ndd"
+ [(set (match_operand:SI 0 "register_operand" "=r")
+ (ior:SI (lshiftrt:SI (match_operand:SI 1 "nonimmediate_operand" "rm")
+ (and:QI (match_operand:QI 3 "nonmemory_operand" "Ic")
+ (const_int 31)))
+ (subreg:SI
+ (ashift:DI
+ (zero_extend:DI
+ (match_operand:SI 2 "register_operand" "r"))
+ (minus:QI (const_int 32)
+ (and:QI (match_dup 3) (const_int 31)))) 0)))
+ (clobber (reg:CC FLAGS_REG))]
+ "TARGET_APX_NDD"
+ "shrd{l}\t{%s3%2, %1, %0|%0, %1, %2, %3}"
+ [(set_attr "type" "ishift")
+ (set_attr "mode" "SI")])
+
(define_insn "x86_shrd_1"
[(set (match_operand:SI 0 "nonimmediate_operand" "+r*m")
(ior:SI (lshiftrt:SI (match_dup 0)
(set_attr "amdfam10_decode" "vector")
(set_attr "bdver1_decode" "vector")])
+(define_insn "x86_shrd_ndd_1"
+ [(set (match_operand:SI 0 "register_operand" "=r")
+ (ior:SI (lshiftrt:SI (match_operand:SI 1 "nonimmediate_operand" "rm")
+ (match_operand:QI 3 "const_0_to_31_operand"))
+ (subreg:SI
+ (ashift:DI
+ (zero_extend:DI
+ (match_operand:SI 2 "register_operand" "r"))
+ (match_operand:QI 4 "const_0_to_63_operand")) 0)))
+ (clobber (reg:CC FLAGS_REG))]
+ "TARGET_APX_NDD
+ && (INTVAL (operands[4]) == 32 - INTVAL (operands[3]))"
+ "shrd{l}\t{%3, %2, %1, %0|%0, %1, %2, %3}"
+ [(set_attr "type" "ishift")
+ (set_attr "length_immediate" "1")
+ (set_attr "mode" "SI")])
+
+
(define_insn_and_split "*x86_shrd_shld_1_nozext"
[(set (match_operand:SI 0 "nonimmediate_operand")
(ior:SI (lshiftrt:SI (match_operand:SI 4 "nonimmediate_operand")
operands[4] = force_reg (SImode, operands[4]);
emit_insn (gen_x86_shld_1 (operands[0], operands[4], operands[3], operands[2]));
}
- else
+ else if (TARGET_APX_NDD)
+ {
+ rtx tmp = gen_reg_rtx (SImode);
+ if (MEM_P (operands[4]))
+ {
+ operands[1] = force_reg (SImode, operands[1]);
+ emit_insn (gen_x86_shrd_ndd_1 (tmp, operands[4], operands[1],
+ operands[2], operands[3]));
+ }
+ else if (MEM_P (operands[1]))
+ emit_insn (gen_x86_shld_ndd_1 (tmp, operands[1], operands[4],
+ operands[3], operands[2]));
+ else
+ emit_insn (gen_x86_shrd_ndd_1 (tmp, operands[4], operands[1],
+ operands[2], operands[3]));
+ emit_move_insn (operands[0], tmp);
+ }
+ else
{
operands[1] = force_reg (SImode, operands[1]);
rtx tmp = gen_reg_rtx (SImode);
(const_int 31)))) 0)))
(clobber (reg:CC FLAGS_REG))])])
+(define_insn_and_split "*x86_shrd_ndd_2"
+ [(set (match_operand:SI 0 "nonimmediate_operand")
+ (ior:SI (lshiftrt:SI (match_operand:SI 1 "nonimmediate_operand")
+ (match_operand:QI 3 "nonmemory_operand"))
+ (ashift:SI (match_operand:SI 2 "register_operand")
+ (minus:QI (const_int 32) (match_dup 3)))))
+ (clobber (reg:CC FLAGS_REG))]
+ "TARGET_APX_NDD
+ && ix86_pre_reload_split ()"
+ "#"
+ "&& 1"
+ [(parallel [(set (match_dup 4)
+ (ior:SI (lshiftrt:SI (match_dup 1)
+ (and:QI (match_dup 3) (const_int 31)))
+ (subreg:SI
+ (ashift:DI
+ (zero_extend:DI (match_dup 2))
+ (minus:QI (const_int 32)
+ (and:QI (match_dup 3)
+ (const_int 31)))) 0)))
+ (clobber (reg:CC FLAGS_REG))
+ (set (match_dup 0) (match_dup 4))])]
+{
+ operands[4] = gen_reg_rtx (SImode);
+ emit_move_insn (operands[4], operands[0]);
+})
+
;; Base name for insn mnemonic.
(define_mode_attr cvt_mnemonic
[(SI "{cltd|cdq}") (DI "{cqto|cqo}")])
(define_insn "ashr<mode>3_cvt"
- [(set (match_operand:SWI48 0 "nonimmediate_operand" "=*d,rm")
+ [(set (match_operand:SWI48 0 "nonimmediate_operand" "=*d,rm,r")
(ashiftrt:SWI48
- (match_operand:SWI48 1 "nonimmediate_operand" "*a,0")
+ (match_operand:SWI48 1 "nonimmediate_operand" "*a,0,rm")
(match_operand:QI 2 "const_int_operand")))
(clobber (reg:CC FLAGS_REG))]
"INTVAL (operands[2]) == GET_MODE_BITSIZE (<MODE>mode)-1
&& (TARGET_USE_CLTD || optimize_function_for_size_p (cfun))
- && ix86_binary_operator_ok (ASHIFTRT, <MODE>mode, operands)"
+ && ix86_binary_operator_ok (ASHIFTRT, <MODE>mode, operands, TARGET_APX_NDD)"
"@
<cvt_mnemonic>
- sar{<imodesuffix>}\t{%2, %0|%0, %2}"
- [(set_attr "type" "imovx,ishift")
- (set_attr "prefix_0f" "0,*")
- (set_attr "length_immediate" "0,*")
- (set_attr "modrm" "0,1")
+ sar{<imodesuffix>}\t{%2, %0|%0, %2}
+ sar{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}"
+ [(set_attr "isa" "*,*,apx_ndd")
+ (set_attr "type" "imovx,ishift,ishift")
+ (set_attr "prefix_0f" "0,*,*")
+ (set_attr "length_immediate" "0,*,*")
+ (set_attr "modrm" "0,1,1")
(set_attr "mode" "<MODE>")])
(define_insn "*ashrsi3_cvt_zext"
- [(set (match_operand:DI 0 "register_operand" "=*d,r")
+ [(set (match_operand:DI 0 "register_operand" "=*d,r,r")
(zero_extend:DI
- (ashiftrt:SI (match_operand:SI 1 "register_operand" "*a,0")
+ (ashiftrt:SI (match_operand:SI 1 "nonimmediate_operand" "*a,0,rm")
(match_operand:QI 2 "const_int_operand"))))
(clobber (reg:CC FLAGS_REG))]
"TARGET_64BIT && INTVAL (operands[2]) == 31
&& (TARGET_USE_CLTD || optimize_function_for_size_p (cfun))
- && ix86_binary_operator_ok (ASHIFTRT, SImode, operands)"
+ && ix86_binary_operator_ok (ASHIFTRT, SImode, operands, TARGET_APX_NDD)"
"@
{cltd|cdq}
- sar{l}\t{%2, %k0|%k0, %2}"
- [(set_attr "type" "imovx,ishift")
- (set_attr "prefix_0f" "0,*")
- (set_attr "length_immediate" "0,*")
- (set_attr "modrm" "0,1")
+ sar{l}\t{%2, %k0|%k0, %2}
+ sar{l}\t{%2, %1, %k0|%k0, %1, %2}"
+ [(set_attr "isa" "*,*,apx_ndd")
+ (set_attr "type" "imovx,ishift,ishift")
+ (set_attr "prefix_0f" "0,*,*")
+ (set_attr "length_immediate" "0,*,*")
+ (set_attr "modrm" "0,1,1")
(set_attr "mode" "SI")])
(define_expand "@x86_shift<mode>_adj_3"
(set_attr "mode" "<MODE>")])
(define_insn "*ashr<mode>3_1"
- [(set (match_operand:SWI48 0 "nonimmediate_operand" "=rm,r")
+ [(set (match_operand:SWI48 0 "nonimmediate_operand" "=rm,r,r")
(ashiftrt:SWI48
- (match_operand:SWI48 1 "nonimmediate_operand" "0,rm")
- (match_operand:QI 2 "nonmemory_operand" "c<S>,r")))
+ (match_operand:SWI48 1 "nonimmediate_operand" "0,rm,rm")
+ (match_operand:QI 2 "nonmemory_operand" "c<S>,r,c<S>")))
(clobber (reg:CC FLAGS_REG))]
- "ix86_binary_operator_ok (ASHIFTRT, <MODE>mode, operands)"
+ "ix86_binary_operator_ok (ASHIFTRT, <MODE>mode, operands, TARGET_APX_NDD)"
{
+ bool use_ndd = get_attr_isa (insn) == ISA_APX_NDD;
switch (get_attr_type (insn))
{
case TYPE_ISHIFTX:
default:
if (operands[2] == const1_rtx
- && (TARGET_SHIFT1 || optimize_function_for_size_p (cfun)))
+ && (TARGET_SHIFT1 || optimize_function_for_size_p (cfun))
+ && !use_ndd)
return "sar{<imodesuffix>}\t%0";
else
- return "sar{<imodesuffix>}\t{%2, %0|%0, %2}";
+ return use_ndd ? "sar{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}"
+ : "sar{<imodesuffix>}\t{%2, %0|%0, %2}";
}
}
- [(set_attr "isa" "*,bmi2")
- (set_attr "type" "ishift,ishiftx")
+ [(set_attr "isa" "*,bmi2,apx_ndd")
+ (set_attr "type" "ishift,ishiftx,ishift")
(set (attr "length_immediate")
(if_then_else
(and (match_operand 2 "const1_operand")
;; Specialization of *lshr<mode>3_1 below, extracting the SImode
;; highpart of a DI to be extracted, but allowing it to be clobbered.
(define_insn_and_split "*highpartdisi2"
- [(set (subreg:DI (match_operand:SI 0 "register_operand" "=r,x,?k") 0)
- (lshiftrt:DI (match_operand:DI 1 "register_operand" "0,0,k")
+ [(set (subreg:DI (match_operand:SI 0 "register_operand" "=r,x,?k,r") 0)
+ (lshiftrt:DI (match_operand:DI 1 "nonimmediate_operand" "0,0,k,rm")
(const_int 32)))
(clobber (reg:CC FLAGS_REG))]
"TARGET_64BIT"
DONE;
}
operands[0] = gen_rtx_REG (DImode, REGNO (operands[0]));
-})
+}
+[(set_attr "isa" "*,*,*,apx_ndd")])
+
(define_insn "*lshr<mode>3_1"
- [(set (match_operand:SWI48 0 "nonimmediate_operand" "=rm,r,?k")
+ [(set (match_operand:SWI48 0 "nonimmediate_operand" "=rm,r,?k,r")
(lshiftrt:SWI48
- (match_operand:SWI48 1 "nonimmediate_operand" "0,rm,k")
- (match_operand:QI 2 "nonmemory_operand" "c<S>,r,<KS>")))
+ (match_operand:SWI48 1 "nonimmediate_operand" "0,rm,k,rm")
+ (match_operand:QI 2 "nonmemory_operand" "c<S>,r,<KS>,c<S>")))
(clobber (reg:CC FLAGS_REG))]
- "ix86_binary_operator_ok (LSHIFTRT, <MODE>mode, operands)"
+ "ix86_binary_operator_ok (LSHIFTRT, <MODE>mode, operands, TARGET_APX_NDD)"
{
+ bool use_ndd = get_attr_isa (insn) == ISA_APX_NDD;
switch (get_attr_type (insn))
{
case TYPE_ISHIFTX:
default:
if (operands[2] == const1_rtx
- && (TARGET_SHIFT1 || optimize_function_for_size_p (cfun)))
+ && (TARGET_SHIFT1 || optimize_function_for_size_p (cfun))
+ && !use_ndd)
return "shr{<imodesuffix>}\t%0";
else
- return "shr{<imodesuffix>}\t{%2, %0|%0, %2}";
+ return use_ndd ? "shr{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}"
+ : "shr{<imodesuffix>}\t{%2, %0|%0, %2}";
}
}
- [(set_attr "isa" "*,bmi2,avx512bw")
- (set_attr "type" "ishift,ishiftx,msklog")
+ [(set_attr "isa" "*,bmi2,avx512bw,apx_ndd")
+ (set_attr "type" "ishift,ishiftx,msklog,ishift")
(set (attr "length_immediate")
(if_then_else
(and (and (match_operand 2 "const1_operand")
(set_attr "mode" "SI")])
(define_insn "*<insn>si3_1_zext"
- [(set (match_operand:DI 0 "register_operand" "=r,r")
+ [(set (match_operand:DI 0 "register_operand" "=r,r,r")
(zero_extend:DI
- (any_shiftrt:SI (match_operand:SI 1 "nonimmediate_operand" "0,rm")
- (match_operand:QI 2 "nonmemory_operand" "cI,r"))))
+ (any_shiftrt:SI (match_operand:SI 1 "nonimmediate_operand" "0,rm,rm")
+ (match_operand:QI 2 "nonmemory_operand" "cI,r,cI"))))
(clobber (reg:CC FLAGS_REG))]
- "TARGET_64BIT && ix86_binary_operator_ok (<CODE>, SImode, operands)"
+ "TARGET_64BIT
+ && ix86_binary_operator_ok (<CODE>, SImode, operands, TARGET_APX_NDD)"
{
+ bool use_ndd = get_attr_isa (insn) == ISA_APX_NDD;
switch (get_attr_type (insn))
{
case TYPE_ISHIFTX:
default:
if (operands[2] == const1_rtx
- && (TARGET_SHIFT1 || optimize_function_for_size_p (cfun)))
+ && (TARGET_SHIFT1 || optimize_function_for_size_p (cfun))
+ && !use_ndd)
return "<shift>{l}\t%k0";
else
- return "<shift>{l}\t{%2, %k0|%k0, %2}";
+ return use_ndd ? "<shift>{l}\t{%2, %1, %k0|%k0, %1, %2}"
+ : "<shift>{l}\t{%2, %k0|%k0, %2}";
}
}
- [(set_attr "isa" "*,bmi2")
- (set_attr "type" "ishift,ishiftx")
+ [(set_attr "isa" "*,bmi2,apx_ndd")
+ (set_attr "type" "ishift,ishiftx,ishift")
(set (attr "length_immediate")
(if_then_else
(and (match_operand 2 "const1_operand")
"operands[2] = gen_lowpart (SImode, operands[2]);")
(define_insn "*ashr<mode>3_1"
- [(set (match_operand:SWI12 0 "nonimmediate_operand" "=<r>m")
+ [(set (match_operand:SWI12 0 "nonimmediate_operand" "=<r>m, r")
(ashiftrt:SWI12
- (match_operand:SWI12 1 "nonimmediate_operand" "0")
- (match_operand:QI 2 "nonmemory_operand" "c<S>")))
+ (match_operand:SWI12 1 "nonimmediate_operand" "0, rm")
+ (match_operand:QI 2 "nonmemory_operand" "c<S>, c<S>")))
(clobber (reg:CC FLAGS_REG))]
- "ix86_binary_operator_ok (ASHIFTRT, <MODE>mode, operands)"
+ "ix86_binary_operator_ok (ASHIFTRT, <MODE>mode, operands, TARGET_APX_NDD)"
{
+ bool use_ndd = get_attr_isa (insn) == ISA_APX_NDD;
if (operands[2] == const1_rtx
- && (TARGET_SHIFT1 || optimize_function_for_size_p (cfun)))
+ && (TARGET_SHIFT1 || optimize_function_for_size_p (cfun))
+ && !use_ndd)
return "sar{<imodesuffix>}\t%0";
else
- return "sar{<imodesuffix>}\t{%2, %0|%0, %2}";
+ return use_ndd ? "sar{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}"
+ : "sar{<imodesuffix>}\t{%2, %0|%0, %2}";
}
- [(set_attr "type" "ishift")
+ [(set_attr "isa" "*, apx_ndd")
+ (set_attr "type" "ishift")
(set (attr "length_immediate")
(if_then_else
(and (match_operand 2 "const1_operand")
(set_attr "mode" "<MODE>")])
(define_insn "*lshrqi3_1"
- [(set (match_operand:QI 0 "nonimmediate_operand" "=qm,?k")
+ [(set (match_operand:QI 0 "nonimmediate_operand" "=qm,?k,r")
(lshiftrt:QI
- (match_operand:QI 1 "nonimmediate_operand" "0, k")
- (match_operand:QI 2 "nonmemory_operand" "cI,Wb")))
+ (match_operand:QI 1 "nonimmediate_operand" "0, k, rm")
+ (match_operand:QI 2 "nonmemory_operand" "cI,Wb,cI")))
(clobber (reg:CC FLAGS_REG))]
- "ix86_binary_operator_ok (LSHIFTRT, QImode, operands)"
+ "ix86_binary_operator_ok (LSHIFTRT, QImode, operands, TARGET_APX_NDD)"
{
+ bool use_ndd = get_attr_isa (insn) == ISA_APX_NDD;
switch (get_attr_type (insn))
{
case TYPE_ISHIFT:
if (operands[2] == const1_rtx
- && (TARGET_SHIFT1 || optimize_function_for_size_p (cfun)))
+ && (TARGET_SHIFT1 || optimize_function_for_size_p (cfun))
+ && !use_ndd)
return "shr{b}\t%0";
else
- return "shr{b}\t{%2, %0|%0, %2}";
+ return use_ndd ? "shr{b}\t{%2, %1, %0|%0, %1, %2}"
+ : "shr{b}\t{%2, %0|%0, %2}";
case TYPE_MSKLOG:
return "#";
default:
gcc_unreachable ();
}
}
- [(set_attr "isa" "*,avx512dq")
- (set_attr "type" "ishift,msklog")
+ [(set_attr "isa" "*,avx512dq,apx_ndd")
+ (set_attr "type" "ishift,msklog,ishift")
(set (attr "length_immediate")
(if_then_else
(and (and (match_operand 2 "const1_operand")
(set_attr "mode" "QI")])
(define_insn "*lshrhi3_1"
- [(set (match_operand:HI 0 "nonimmediate_operand" "=rm, ?k")
+ [(set (match_operand:HI 0 "nonimmediate_operand" "=rm, ?k, r")
(lshiftrt:HI
- (match_operand:HI 1 "nonimmediate_operand" "0, k")
- (match_operand:QI 2 "nonmemory_operand" "cI, Ww")))
+ (match_operand:HI 1 "nonimmediate_operand" "0, k, rm")
+ (match_operand:QI 2 "nonmemory_operand" "cI, Ww, cI")))
(clobber (reg:CC FLAGS_REG))]
- "ix86_binary_operator_ok (LSHIFTRT, HImode, operands)"
+ "ix86_binary_operator_ok (LSHIFTRT, HImode, operands, TARGET_APX_NDD)"
{
+ bool use_ndd = get_attr_isa (insn) == ISA_APX_NDD;
switch (get_attr_type (insn))
{
case TYPE_ISHIFT:
if (operands[2] == const1_rtx
- && (TARGET_SHIFT1 || optimize_function_for_size_p (cfun)))
+ && (TARGET_SHIFT1 || optimize_function_for_size_p (cfun))
+ && !use_ndd)
return "shr{w}\t%0";
else
- return "shr{w}\t{%2, %0|%0, %2}";
+ return use_ndd ? "shr{w}\t{%2, %1, %0|%0, %1, %2}"
+ : "shr{w}\t{%2, %0|%0, %2}";
case TYPE_MSKLOG:
return "#";
default:
gcc_unreachable ();
}
}
- [(set_attr "isa" "*, avx512f")
- (set_attr "type" "ishift,msklog")
+ [(set_attr "isa" "*, avx512f, apx_ndd")
+ (set_attr "type" "ishift,msklog,ishift")
(set (attr "length_immediate")
(if_then_else
(and (and (match_operand 2 "const1_operand")
else
return "<shift>{<imodesuffix>}\t{%2, %0|%0, %2}";
}
- "&& reload_completed"
+ "&& reload_completed
+ && !(rtx_equal_p (operands[0], operands[1]))"
[(set (strict_low_part (match_dup 0)) (match_dup 1))
(parallel
[(set (strict_low_part (match_dup 0))
[(set (reg FLAGS_REG)
(compare
(any_shiftrt:SWI
- (match_operand:SWI 1 "nonimmediate_operand" "0")
- (match_operand:QI 2 "<shift_immediate_operand>" "<S>"))
+ (match_operand:SWI 1 "nonimmediate_operand" "0,rm")
+ (match_operand:QI 2 "<shift_immediate_operand>" "<S>,<S>"))
(const_int 0)))
- (set (match_operand:SWI 0 "nonimmediate_operand" "=<r>m")
+ (set (match_operand:SWI 0 "nonimmediate_operand" "=<r>m,r")
(any_shiftrt:SWI (match_dup 1) (match_dup 2)))]
"(optimize_function_for_size_p (cfun)
|| !TARGET_PARTIAL_FLAG_REG_STALL
|| (operands[2] == const1_rtx
&& TARGET_SHIFT1))
&& ix86_match_ccmode (insn, CCGOCmode)
- && ix86_binary_operator_ok (<CODE>, <MODE>mode, operands)"
+ && ix86_binary_operator_ok (<CODE>, <MODE>mode, operands, TARGET_APX_NDD)"
{
+ bool use_ndd = get_attr_isa (insn) == ISA_APX_NDD;
if (operands[2] == const1_rtx
- && (TARGET_SHIFT1 || optimize_function_for_size_p (cfun)))
+ && (TARGET_SHIFT1 || optimize_function_for_size_p (cfun))
+ && !use_ndd)
return "<shift>{<imodesuffix>}\t%0";
else
- return "<shift>{<imodesuffix>}\t{%2, %0|%0, %2}";
+ return use_ndd ? "<shift>{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}"
+ : "<shift>{<imodesuffix>}\t{%2, %0|%0, %2}";
}
- [(set_attr "type" "ishift")
+ [(set_attr "isa" "*,apx_ndd")
+ (set_attr "type" "ishift")
(set (attr "length_immediate")
(if_then_else
(and (match_operand 2 "const1_operand")
(define_insn "*<insn>si3_cmp_zext"
[(set (reg FLAGS_REG)
(compare
- (any_shiftrt:SI (match_operand:SI 1 "register_operand" "0")
+ (any_shiftrt:SI (match_operand:SI 1 "nonimmediate_operand" "0,rm")
(match_operand:QI 2 "const_1_to_31_operand"))
(const_int 0)))
- (set (match_operand:DI 0 "register_operand" "=r")
+ (set (match_operand:DI 0 "register_operand" "=r,r")
(zero_extend:DI (any_shiftrt:SI (match_dup 1) (match_dup 2))))]
"TARGET_64BIT
&& (optimize_function_for_size_p (cfun)
|| (operands[2] == const1_rtx
&& TARGET_SHIFT1))
&& ix86_match_ccmode (insn, CCGOCmode)
- && ix86_binary_operator_ok (<CODE>, SImode, operands)"
+ && ix86_binary_operator_ok (<CODE>, SImode, operands, TARGET_APX_NDD)"
{
+ bool use_ndd = get_attr_isa (insn) == ISA_APX_NDD;
if (operands[2] == const1_rtx
- && (TARGET_SHIFT1 || optimize_function_for_size_p (cfun)))
+ && (TARGET_SHIFT1 || optimize_function_for_size_p (cfun))
+ && !use_ndd)
return "<shift>{l}\t%k0";
else
- return "<shift>{l}\t{%2, %k0|%k0, %2}";
+ return use_ndd ? "<shift>{l}\t{%2, %1, %k0|%k0, %1, %2}"
+ : "<shift>{l}\t{%2, %k0|%k0, %2}";
}
- [(set_attr "type" "ishift")
+ [(set_attr "isa" "*,apx_ndd")
+ (set_attr "type" "ishift")
(set (attr "length_immediate")
(if_then_else
(and (match_operand 2 "const1_operand")
[(set (reg FLAGS_REG)
(compare
(any_shiftrt:SWI
- (match_operand:SWI 1 "register_operand" "0")
- (match_operand:QI 2 "<shift_immediate_operand>" "<S>"))
+ (match_operand:SWI 1 "nonimmediate_operand" "0,rm")
+ (match_operand:QI 2 "<shift_immediate_operand>" "<S>,<S>"))
(const_int 0)))
- (clobber (match_scratch:SWI 0 "=<r>"))]
+ (clobber (match_scratch:SWI 0 "=<r>,r"))]
"(optimize_function_for_size_p (cfun)
|| !TARGET_PARTIAL_FLAG_REG_STALL
|| (operands[2] == const1_rtx
&& TARGET_SHIFT1))
&& ix86_match_ccmode (insn, CCGOCmode)"
{
+ bool use_ndd = get_attr_isa (insn) == ISA_APX_NDD;
if (operands[2] == const1_rtx
- && (TARGET_SHIFT1 || optimize_function_for_size_p (cfun)))
+ && (TARGET_SHIFT1 || optimize_function_for_size_p (cfun))
+ && !use_ndd)
return "<shift>{<imodesuffix>}\t%0";
else
- return "<shift>{<imodesuffix>}\t{%2, %0|%0, %2}";
+ return use_ndd
+ ? "<shift>{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}"
+ : "<shift>{<imodesuffix>}\t{%2, %0|%0, %2}";
}
- [(set_attr "type" "ishift")
+ [(set_attr "isa" "*,apx_ndd")
+ (set_attr "type" "ishift")
(set (attr "length_immediate")
(if_then_else
(and (match_operand 2 "const1_operand")
(const_string "*")))
(set_attr "mode" "<MODE>")])
-(define_insn "*<insn>qi_ext<mode>_2"
+;; Alternative 1 is needed to work around LRA limitation, see PR82524.
+(define_insn_and_split "*<insn>qi_ext<mode>_1"
[(set (zero_extract:SWI248
- (match_operand 0 "int248_register_operand" "+Q")
+ (match_operand 0 "int248_register_operand" "+Q,&Q")
(const_int 8)
(const_int 8))
(subreg:SWI248
(any_shiftrt:QI
(subreg:QI
(match_operator:SWI248 3 "extract_operator"
- [(match_operand 1 "int248_register_operand" "0")
+ [(match_operand 1 "int248_register_operand" "0,!Q")
(const_int 8)
(const_int 8)]) 0)
- (match_operand:QI 2 "nonmemory_operand" "cI")) 0))
- (clobber (reg:CC FLAGS_REG))]
- "/* FIXME: without this LRA can't reload this pattern, see PR82524. */
- rtx_equal_p (operands[0], operands[1])"
+ (match_operand:QI 2 "nonmemory_operand" "cI,cI")) 0))
+ (clobber (reg:CC FLAGS_REG))]
+ ""
{
+ if (which_alternative)
+ return "#";
+
if (operands[2] == const1_rtx
&& (TARGET_SHIFT1 || optimize_function_for_size_p (cfun)))
return "<shift>{b}\t%h0";
else
return "<shift>{b}\t{%2, %h0|%h0, %2}";
}
+ "reload_completed
+ && !(rtx_equal_p (operands[0], operands[1]))"
+ [(set (zero_extract:SWI248
+ (match_dup 0) (const_int 8) (const_int 8))
+ (zero_extract:SWI248
+ (match_dup 1) (const_int 8) (const_int 8)))
+ (parallel
+ [(set (zero_extract:SWI248
+ (match_dup 0) (const_int 8) (const_int 8))
+ (subreg:SWI248
+ (any_shiftrt:QI
+ (subreg:QI
+ (match_op_dup 3
+ [(match_dup 0) (const_int 8) (const_int 8)]) 0)
+ (match_dup 2)) 0))
+ (clobber (reg:CC FLAGS_REG))])]
+ ""
[(set_attr "type" "ishift")
(set (attr "length_immediate")
(if_then_else
(const_string "0")
(const_string "*")))
(set_attr "mode" "QI")])
+
+(define_insn_and_split "*extend<dwi>2_doubleword_highpart"
+ [(set (match_operand:<DWI> 0 "register_operand" "=r")
+ (ashiftrt:<DWI>
+ (ashift:<DWI> (match_operand:<DWI> 1 "nonimmediate_operand" "0")
+ (match_operand:QI 2 "const_int_operand"))
+ (match_operand:QI 3 "const_int_operand")))
+ (clobber (reg:CC FLAGS_REG))]
+ "INTVAL (operands[2]) == INTVAL (operands[3])
+ && UINTVAL (operands[2]) < <MODE_SIZE> * BITS_PER_UNIT"
+ "#"
+ "&& reload_completed"
+ [(parallel [(set (match_dup 4)
+ (ashift:DWIH (match_dup 4) (match_dup 2)))
+ (clobber (reg:CC FLAGS_REG))])
+ (parallel [(set (match_dup 4)
+ (ashiftrt:DWIH (match_dup 4) (match_dup 2)))
+ (clobber (reg:CC FLAGS_REG))])]
+ "split_double_mode (<DWI>mode, &operands[0], 1, &operands[0], &operands[4]);")
+
+(define_insn_and_split "*extendv2di2_highpart_stv"
+ [(set (match_operand:V2DI 0 "register_operand" "=v")
+ (ashiftrt:V2DI
+ (ashift:V2DI (match_operand:V2DI 1 "nonimmediate_operand" "vm")
+ (match_operand:QI 2 "const_int_operand"))
+ (match_operand:QI 3 "const_int_operand")))]
+ "!TARGET_64BIT && TARGET_STV && TARGET_AVX512VL
+ && INTVAL (operands[2]) == INTVAL (operands[3])
+ && UINTVAL (operands[2]) < 32"
+ "#"
+ "&& reload_completed"
+ [(set (match_dup 0)
+ (ashift:V2DI (match_dup 1) (match_dup 2)))
+ (set (match_dup 0)
+ (ashiftrt:V2DI (match_dup 0) (match_dup 2)))])
\f
;; Rotate instructions
emit_insn (gen_ix86_<insn>ti3_doubleword
(operands[0], operands[1], operands[2]));
else if (CONST_INT_P (operands[2]) && INTVAL (operands[2]) == 64)
- emit_insn (gen_<insn>64ti2_doubleword (operands[0], operands[1]));
+ {
+ operands[1] = force_reg (TImode, operands[1]);
+ emit_insn (gen_<insn>64ti2_doubleword (operands[0], operands[1]));
+ }
else
{
rtx amount = force_reg (QImode, operands[2]);
""
{
if (TARGET_64BIT)
- ix86_expand_binary_operator (<CODE>, DImode, operands);
+ ix86_expand_binary_operator (<CODE>, DImode, operands, TARGET_APX_NDD);
else if (const_1_to_31_operand (operands[2], VOIDmode))
emit_insn (gen_ix86_<insn>di3_doubleword
(operands[0], operands[1], operands[2]));
else if (CONST_INT_P (operands[2]) && INTVAL (operands[2]) == 32)
- emit_insn (gen_<insn>32di2_doubleword (operands[0], operands[1]));
+ {
+ operands[1] = force_reg (DImode, operands[1]);
+ emit_insn (gen_<insn>32di2_doubleword (operands[0], operands[1]));
+ }
else
FAIL;
(any_rotate:SWIM124 (match_operand:SWIM124 1 "nonimmediate_operand")
(match_operand:QI 2 "nonmemory_operand")))]
""
- "ix86_expand_binary_operator (<CODE>, <MODE>mode, operands); DONE;")
+{
+ ix86_expand_binary_operator (<CODE>, <MODE>mode, operands, TARGET_APX_NDD);
+ DONE;
+})
;; Avoid useless masking of count operand.
(define_insn_and_split "*<insn><mode>3_mask"
})
(define_insn_and_split "<insn>32di2_doubleword"
- [(set (match_operand:DI 0 "register_operand" "=r,r,r")
- (any_rotate:DI (match_operand:DI 1 "nonimmediate_operand" "0,r,o")
+ [(set (match_operand:DI 0 "register_operand" "=r,r")
+ (any_rotate:DI (match_operand:DI 1 "register_operand" "0,r")
(const_int 32)))]
"!TARGET_64BIT"
"#"
})
(define_insn_and_split "<insn>64ti2_doubleword"
- [(set (match_operand:TI 0 "register_operand" "=r,r,r")
- (any_rotate:TI (match_operand:TI 1 "nonimmediate_operand" "0,r,o")
+ [(set (match_operand:TI 0 "register_operand" "=r,r")
+ (any_rotate:TI (match_operand:TI 1 "register_operand" "0,r")
(const_int 64)))]
"TARGET_64BIT"
"#"
(set_attr "mode" "<MODE>")])
(define_insn "*<insn><mode>3_1"
- [(set (match_operand:SWI48 0 "nonimmediate_operand" "=rm,r")
+ [(set (match_operand:SWI48 0 "nonimmediate_operand" "=rm,r,r")
(any_rotate:SWI48
- (match_operand:SWI48 1 "nonimmediate_operand" "0,rm")
- (match_operand:QI 2 "nonmemory_operand" "c<S>,<S>")))
+ (match_operand:SWI48 1 "nonimmediate_operand" "0,rm,rm")
+ (match_operand:QI 2 "nonmemory_operand" "c<S>,<S>,c<S>")))
(clobber (reg:CC FLAGS_REG))]
- "ix86_binary_operator_ok (<CODE>, <MODE>mode, operands)"
+ "ix86_binary_operator_ok (<CODE>, <MODE>mode, operands, TARGET_APX_NDD)"
{
+ bool use_ndd = get_attr_isa (insn) == ISA_APX_NDD;
switch (get_attr_type (insn))
{
case TYPE_ROTATEX:
default:
if (operands[2] == const1_rtx
- && (TARGET_SHIFT1 || optimize_function_for_size_p (cfun)))
+ && (TARGET_SHIFT1 || optimize_function_for_size_p (cfun))
+ && !use_ndd)
return "<rotate>{<imodesuffix>}\t%0";
else
- return "<rotate>{<imodesuffix>}\t{%2, %0|%0, %2}";
+ return use_ndd ? "<rotate>{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}"
+ : "<rotate>{<imodesuffix>}\t{%2, %0|%0, %2}";
}
}
- [(set_attr "isa" "*,bmi2")
- (set_attr "type" "rotate,rotatex")
+ [(set_attr "isa" "*,bmi2,apx_ndd")
+ (set_attr "type" "rotate,rotatex,rotate")
(set (attr "preferred_for_size")
(cond [(eq_attr "alternative" "0")
(symbol_ref "true")]
(set_attr "mode" "SI")])
(define_insn "*<insn>si3_1_zext"
- [(set (match_operand:DI 0 "register_operand" "=r,r")
+ [(set (match_operand:DI 0 "register_operand" "=r,r,r")
(zero_extend:DI
- (any_rotate:SI (match_operand:SI 1 "nonimmediate_operand" "0,rm")
- (match_operand:QI 2 "nonmemory_operand" "cI,I"))))
+ (any_rotate:SI (match_operand:SI 1 "nonimmediate_operand" "0,rm,rm")
+ (match_operand:QI 2 "nonmemory_operand" "cI,I,cI"))))
(clobber (reg:CC FLAGS_REG))]
"TARGET_64BIT && ix86_binary_operator_ok (<CODE>, SImode, operands)"
{
+ bool use_ndd = get_attr_isa (insn) == ISA_APX_NDD;
switch (get_attr_type (insn))
{
case TYPE_ROTATEX:
default:
if (operands[2] == const1_rtx
- && (TARGET_SHIFT1 || optimize_function_for_size_p (cfun)))
+ && (TARGET_SHIFT1 || optimize_function_for_size_p (cfun))
+ && !use_ndd)
return "<rotate>{l}\t%k0";
else
- return "<rotate>{l}\t{%2, %k0|%k0, %2}";
+ return use_ndd ? "<rotate>{l}\t{%2, %1, %k0|%k0, %1, %2}"
+ : "<rotate>{l}\t{%2, %k0|%k0, %2}";
}
}
- [(set_attr "isa" "*,bmi2")
- (set_attr "type" "rotate,rotatex")
+ [(set_attr "isa" "*,bmi2,apx_ndd")
+ (set_attr "type" "rotate,rotatex,rotate")
(set (attr "preferred_for_size")
(cond [(eq_attr "alternative" "0")
(symbol_ref "true")]
(zero_extend:DI (rotatert:SI (match_dup 1) (match_dup 2))))])
(define_insn "*<insn><mode>3_1"
- [(set (match_operand:SWI12 0 "nonimmediate_operand" "=<r>m")
- (any_rotate:SWI12 (match_operand:SWI12 1 "nonimmediate_operand" "0")
- (match_operand:QI 2 "nonmemory_operand" "c<S>")))
+ [(set (match_operand:SWI12 0 "nonimmediate_operand" "=<r>m,r")
+ (any_rotate:SWI12 (match_operand:SWI12 1 "nonimmediate_operand" "0,rm")
+ (match_operand:QI 2 "nonmemory_operand" "c<S>,c<S>")))
(clobber (reg:CC FLAGS_REG))]
- "ix86_binary_operator_ok (<CODE>, <MODE>mode, operands)"
+ "ix86_binary_operator_ok (<CODE>, <MODE>mode, operands, TARGET_APX_NDD)"
{
+ bool use_ndd = get_attr_isa (insn) == ISA_APX_NDD;
if (operands[2] == const1_rtx
- && (TARGET_SHIFT1 || optimize_function_for_size_p (cfun)))
+ && (TARGET_SHIFT1 || optimize_function_for_size_p (cfun))
+ && !use_ndd)
return "<rotate>{<imodesuffix>}\t%0";
else
- return "<rotate>{<imodesuffix>}\t{%2, %0|%0, %2}";
+ return use_ndd
+ ? "<rotate>{<imodesuffix>}\t{%2, %1, %0|%0, %1, %2}"
+ : "<rotate>{<imodesuffix>}\t{%2, %0|%0, %2}";
}
- [(set_attr "type" "rotate")
+ [(set_attr "isa" "*,apx_ndd")
+ (set_attr "type" "rotate")
(set (attr "length_immediate")
(if_then_else
(and (match_operand 2 "const1_operand")
else
return "<rotate>{<imodesuffix>}\t{%2, %0|%0, %2}";
}
- "&& reload_completed"
+ "&& reload_completed
+ && !(rtx_equal_p (operands[0], operands[1]))"
[(set (strict_low_part (match_dup 0)) (match_dup 1))
(parallel
[(set (strict_low_part (match_dup 0))
[(parallel [(set (strict_low_part (match_dup 0))
(bswap:HI (match_dup 0)))
(clobber (reg:CC FLAGS_REG))])])
+
+;; Rotations through carry flag
+(define_insn "rcrsi2"
+ [(set (match_operand:SI 0 "register_operand" "=r,r")
+ (plus:SI
+ (lshiftrt:SI (match_operand:SI 1 "nonimmediate_operand" "0,rm")
+ (const_int 1))
+ (ashift:SI (ltu:SI (reg:CCC FLAGS_REG) (const_int 0))
+ (const_int 31))))
+ (clobber (reg:CC FLAGS_REG))]
+ ""
+ "@
+ rcr{l}\t%0
+ rcr{l}\t{%1, %0|%0, %1}"
+ [(set_attr "isa" "*,apx_ndd")
+ (set_attr "type" "ishift1")
+ (set_attr "memory" "none")
+ (set_attr "length_immediate" "0")
+ (set_attr "mode" "SI")])
+
+(define_insn "rcrdi2"
+ [(set (match_operand:DI 0 "register_operand" "=r,r")
+ (plus:DI
+ (lshiftrt:DI (match_operand:DI 1 "nonimmediate_operand" "0,rm")
+ (const_int 1))
+ (ashift:DI (ltu:DI (reg:CCC FLAGS_REG) (const_int 0))
+ (const_int 63))))
+ (clobber (reg:CC FLAGS_REG))]
+ "TARGET_64BIT"
+ "@
+ rcr{q}\t%0
+ rcr{q}\t{%1, %0|%0, %1}"
+ [(set_attr "isa" "*,apx_ndd")
+ (set_attr "type" "ishift1")
+ (set_attr "length_immediate" "0")
+ (set_attr "mode" "DI")])
+
+;; Versions of sar and shr that set the carry flag.
+(define_insn "<insn><mode>3_carry"
+ [(set (reg:CCC FLAGS_REG)
+ (unspec:CCC [(and:SWI48 (match_operand:SWI48 1 "nonimmediate_operand" "0,rm")
+ (const_int 1))
+ (const_int 0)] UNSPEC_CC_NE))
+ (set (match_operand:SWI48 0 "register_operand" "=r,r")
+ (any_shiftrt:SWI48 (match_dup 1) (const_int 1)))]
+ ""
+{
+ bool use_ndd = get_attr_isa (insn) == ISA_APX_NDD;
+ if ((TARGET_SHIFT1 || optimize_function_for_size_p (cfun))
+ && !use_ndd)
+ return "<shift>{<imodesuffix>}\t%0";
+ return use_ndd ? "<shift>{<imodesuffix>}\t{$1, %1, %0|%0, %1, 1}"
+ : "<shift>{<imodesuffix>}\t{$1, %0|%0, 1}";
+}
+ [(set_attr "isa" "*, apx_ndd")
+ (set_attr "type" "ishift1")
+ (set (attr "length_immediate")
+ (if_then_else
+ (ior (match_test "TARGET_SHIFT1")
+ (match_test "optimize_function_for_size_p (cfun)"))
+ (const_string "0")
+ (const_string "*")))
+ (set_attr "mode" "<MODE>")])
\f
;; Bit set / bit test instructions
[(set (zero_extract:HI
(match_operand:SWI12 0 "nonimmediate_operand")
(const_int 1)
- (zero_extend:SI (match_operand:QI 1 "register_operand")))
+ (match_operand:QI 1 "register_operand"))
(const_int 0))
(clobber (reg:CC FLAGS_REG))]
"TARGET_USE_BT && ix86_pre_reload_split ()"
[(set (zero_extract:HI
(match_operand:SWI12 0 "register_operand")
(const_int 1)
- (zero_extend:SI (match_operand:QI 1 "register_operand")))
+ (match_operand:QI 1 "register_operand"))
(const_int 0))
(clobber (reg:CC FLAGS_REG))]
"TARGET_USE_BT && ix86_pre_reload_split ()"
(define_insn "*btsq_imm"
[(set (zero_extract:DI (match_operand:DI 0 "nonimmediate_operand" "+rm")
(const_int 1)
- (match_operand 1 "const_0_to_63_operand"))
+ (match_operand:QI 1 "const_0_to_63_operand"))
(const_int 1))
(clobber (reg:CC FLAGS_REG))]
"TARGET_64BIT && (TARGET_USE_BT || reload_completed)"
(define_insn "*btrq_imm"
[(set (zero_extract:DI (match_operand:DI 0 "nonimmediate_operand" "+rm")
(const_int 1)
- (match_operand 1 "const_0_to_63_operand"))
+ (match_operand:QI 1 "const_0_to_63_operand"))
(const_int 0))
(clobber (reg:CC FLAGS_REG))]
"TARGET_64BIT && (TARGET_USE_BT || reload_completed)"
(define_insn "*btcq_imm"
[(set (zero_extract:DI (match_operand:DI 0 "nonimmediate_operand" "+rm")
(const_int 1)
- (match_operand 1 "const_0_to_63_operand"))
+ (match_operand:QI 1 "const_0_to_63_operand"))
(not:DI (zero_extract:DI (match_dup 0) (const_int 1) (match_dup 1))))
(clobber (reg:CC FLAGS_REG))]
"TARGET_64BIT && (TARGET_USE_BT || reload_completed)"
(parallel [(set (zero_extract:DI
(match_operand:DI 0 "nonimmediate_operand")
(const_int 1)
- (match_operand 1 "const_0_to_63_operand"))
+ (match_operand:QI 1 "const_0_to_63_operand"))
(const_int 1))
(clobber (reg:CC FLAGS_REG))])]
"TARGET_64BIT && !TARGET_USE_BT"
(parallel [(set (zero_extract:DI
(match_operand:DI 0 "nonimmediate_operand")
(const_int 1)
- (match_operand 1 "const_0_to_63_operand"))
+ (match_operand:QI 1 "const_0_to_63_operand"))
(const_int 0))
(clobber (reg:CC FLAGS_REG))])]
"TARGET_64BIT && !TARGET_USE_BT"
(parallel [(set (zero_extract:DI
(match_operand:DI 0 "nonimmediate_operand")
(const_int 1)
- (match_operand 1 "const_0_to_63_operand"))
+ (match_operand:QI 1 "const_0_to_63_operand"))
(not:DI (zero_extract:DI
(match_dup 0) (const_int 1) (match_dup 1))))
(clobber (reg:CC FLAGS_REG))])]
(zero_extract:SWI48
(match_operand:SWI48 0 "nonimmediate_operand" "r,m")
(const_int 1)
- (match_operand:SI 1 "nonmemory_operand" "r<S>,<S>"))
+ (match_operand:QI 1 "nonmemory_operand" "q<S>,<S>"))
(const_int 0)))]
""
{
switch (get_attr_mode (insn))
{
case MODE_SI:
- return "bt{l}\t{%1, %k0|%k0, %1}";
+ return "bt{l}\t{%k1, %k0|%k0, %k1}";
case MODE_DI:
return "bt{q}\t{%q1, %0|%0, %q1}";
(const_string "SI")
(const_string "<MODE>")))])
+(define_insn_and_split "*bt<SWI48:mode>_mask"
+ [(set (reg:CCC FLAGS_REG)
+ (compare:CCC
+ (zero_extract:SWI48
+ (match_operand:SWI48 0 "nonimmediate_operand" "r,m")
+ (const_int 1)
+ (subreg:QI
+ (and:SWI248
+ (match_operand:SWI248 1 "register_operand")
+ (match_operand 2 "const_int_operand")) 0))
+ (const_int 0)))]
+ "TARGET_USE_BT
+ && (INTVAL (operands[2]) & (GET_MODE_BITSIZE (<SWI48:MODE>mode)-1))
+ == GET_MODE_BITSIZE (<SWI48:MODE>mode)-1
+ && ix86_pre_reload_split ()"
+ "#"
+ "&& 1"
+ [(set (reg:CCC FLAGS_REG)
+ (compare:CCC
+ (zero_extract:SWI48 (match_dup 0) (const_int 1) (match_dup 1))
+ (const_int 0)))]
+ "operands[1] = gen_lowpart (QImode, operands[1]);")
+
(define_insn_and_split "*jcc_bt<mode>"
[(set (pc)
(if_then_else (match_operator 0 "bt_comparison_operator"
[(zero_extract:SWI48
(match_operand:SWI48 1 "nonimmediate_operand")
(const_int 1)
- (match_operand:SI 2 "nonmemory_operand"))
+ (match_operand:QI 2 "nonmemory_operand"))
(const_int 0)])
(label_ref (match_operand 3))
(pc)))
PUT_CODE (operands[0], reverse_condition (GET_CODE (operands[0])));
})
-(define_insn_and_split "*jcc_bt<mode>_1"
- [(set (pc)
- (if_then_else (match_operator 0 "bt_comparison_operator"
- [(zero_extract:SWI48
- (match_operand:SWI48 1 "register_operand")
- (const_int 1)
- (zero_extend:SI
- (match_operand:QI 2 "register_operand")))
- (const_int 0)])
- (label_ref (match_operand 3))
- (pc)))
- (clobber (reg:CC FLAGS_REG))]
- "(TARGET_USE_BT || optimize_function_for_size_p (cfun))
- && ix86_pre_reload_split ()"
- "#"
- "&& 1"
- [(set (reg:CCC FLAGS_REG)
- (compare:CCC
- (zero_extract:SWI48
- (match_dup 1)
- (const_int 1)
- (match_dup 2))
- (const_int 0)))
- (set (pc)
- (if_then_else (match_op_dup 0 [(reg:CCC FLAGS_REG) (const_int 0)])
- (label_ref (match_dup 3))
- (pc)))]
-{
- operands[2] = lowpart_subreg (SImode, operands[2], QImode);
- operands[0] = shallow_copy_rtx (operands[0]);
- PUT_CODE (operands[0], reverse_condition (GET_CODE (operands[0])));
-})
-
;; Avoid useless masking of bit offset operand.
(define_insn_and_split "*jcc_bt<mode>_mask"
[(set (pc)
[(zero_extract:SWI48
(match_operand:SWI48 1 "register_operand")
(const_int 1)
- (and:SI
- (match_operand:SI 2 "register_operand")
- (match_operand 3 "const_int_operand")))])
+ (and:QI
+ (match_operand:QI 2 "register_operand")
+ (match_operand 3 "const_int_operand")))
+ (const_int 0)])
(label_ref (match_operand 4))
(pc)))
(clobber (reg:CC FLAGS_REG))]
PUT_CODE (operands[0], reverse_condition (GET_CODE (operands[0])));
})
-(define_insn_and_split "*jcc_bt<mode>_mask_1"
+;; Avoid useless masking of bit offset operand.
+(define_insn_and_split "*jcc_bt<SWI48:mode>_mask_1"
[(set (pc)
- (if_then_else (match_operator 0 "bt_comparison_operator"
+ (if_then_else (match_operator 0 "bt_comparison_operator"
[(zero_extract:SWI48
(match_operand:SWI48 1 "register_operand")
(const_int 1)
- (zero_extend:SI
- (subreg:QI
- (and
- (match_operand 2 "int248_register_operand")
- (match_operand 3 "const_int_operand")) 0)))])
+ (subreg:QI
+ (and:SWI248
+ (match_operand:SWI248 2 "register_operand")
+ (match_operand 3 "const_int_operand")) 0))
+ (const_int 0)])
(label_ref (match_operand 4))
(pc)))
(clobber (reg:CC FLAGS_REG))]
"(TARGET_USE_BT || optimize_function_for_size_p (cfun))
- && (INTVAL (operands[3]) & (GET_MODE_BITSIZE (<MODE>mode)-1))
- == GET_MODE_BITSIZE (<MODE>mode)-1
+ && (INTVAL (operands[3]) & (GET_MODE_BITSIZE (<SWI48:MODE>mode)-1))
+ == GET_MODE_BITSIZE (<SWI48:MODE>mode)-1
&& ix86_pre_reload_split ()"
"#"
"&& 1"
(label_ref (match_dup 4))
(pc)))]
{
- operands[2] = force_reg (GET_MODE (operands[2]), operands[2]);
- operands[2] = gen_lowpart (SImode, operands[2]);
operands[0] = shallow_copy_rtx (operands[0]);
PUT_CODE (operands[0], reverse_condition (GET_CODE (operands[0])));
+ operands[2] = gen_lowpart (QImode, operands[2]);
})
;; Help combine recognize bt followed by cmov
[(zero_extract:SWI48
(match_operand:SWI48 1 "register_operand")
(const_int 1)
- (zero_extend:SI (match_operand:QI 2 "register_operand")))
+ (match_operand:QI 2 "register_operand"))
(const_int 0)])
(match_operand:SWI248 3 "nonimmediate_operand")
(match_operand:SWI248 4 "nonimmediate_operand")))]
{
if (GET_CODE (operands[5]) == EQ)
std::swap (operands[3], operands[4]);
- operands[2] = lowpart_subreg (SImode, operands[2], QImode);
})
;; Help combine recognize bt followed by setc
(zero_extract:SWI48
(match_operand:SWI48 1 "register_operand")
(const_int 1)
- (zero_extend:SI (match_operand:QI 2 "register_operand"))))
+ (match_operand:QI 2 "register_operand")))
(clobber (reg:CC FLAGS_REG))]
"TARGET_USE_BT && ix86_pre_reload_split ()"
"#"
(zero_extract:SWI48 (match_dup 1) (const_int 1) (match_dup 2))
(const_int 0)))
(set (match_dup 0)
- (eq:QI (reg:CCC FLAGS_REG) (const_int 0)))]
-{
- operands[2] = lowpart_subreg (SImode, operands[2], QImode);
-})
+ (eq:QI (reg:CCC FLAGS_REG) (const_int 0)))])
+
+;; Help combine recognize bt followed by setnc
+(define_insn_and_split "*bt<mode>_setncqi"
+ [(set (match_operand:QI 0 "register_operand")
+ (and:QI
+ (not:QI
+ (subreg:QI
+ (lshiftrt:SWI48 (match_operand:SWI48 1 "register_operand")
+ (match_operand:QI 2 "register_operand")) 0))
+ (const_int 1)))
+ (clobber (reg:CC FLAGS_REG))]
+ "TARGET_USE_BT && ix86_pre_reload_split ()"
+ "#"
+ "&& 1"
+ [(set (reg:CCC FLAGS_REG)
+ (compare:CCC
+ (zero_extract:SWI48 (match_dup 1) (const_int 1) (match_dup 2))
+ (const_int 0)))
+ (set (match_dup 0)
+ (ne:QI (reg:CCC FLAGS_REG) (const_int 0)))])
+
+(define_insn_and_split "*bt<mode>_setnc<mode>"
+ [(set (match_operand:SWI48 0 "register_operand")
+ (and:SWI48
+ (not:SWI48
+ (lshiftrt:SWI48 (match_operand:SWI48 1 "register_operand")
+ (match_operand:QI 2 "register_operand")))
+ (const_int 1)))
+ (clobber (reg:CC FLAGS_REG))]
+ "TARGET_USE_BT && ix86_pre_reload_split ()"
+ "#"
+ "&& 1"
+ [(set (reg:CCC FLAGS_REG)
+ (compare:CCC
+ (zero_extract:SWI48 (match_dup 1) (const_int 1) (match_dup 2))
+ (const_int 0)))
+ (set (match_dup 3)
+ (ne:QI (reg:CCC FLAGS_REG) (const_int 0)))
+ (set (match_dup 0) (zero_extend:SWI48 (match_dup 3)))]
+ "operands[3] = gen_reg_rtx (QImode);")
-;; Help combine recognize bt followed by setnc
-(define_insn_and_split "*bt<mode>_setncqi"
+;; Help combine recognize bt followed by setnc (PR target/110588)
+(define_insn_and_split "*bt<mode>_setncqi_2"
[(set (match_operand:QI 0 "register_operand")
- (and:QI
- (not:QI
- (subreg:QI
- (lshiftrt:SWI48 (match_operand:SWI48 1 "register_operand")
- (match_operand:QI 2 "register_operand")) 0))
- (const_int 1)))
+ (eq:QI
+ (zero_extract:SWI48
+ (match_operand:SWI48 1 "register_operand")
+ (const_int 1)
+ (match_operand:QI 2 "register_operand"))
+ (const_int 0)))
(clobber (reg:CC FLAGS_REG))]
"TARGET_USE_BT && ix86_pre_reload_split ()"
"#"
(zero_extract:SWI48 (match_dup 1) (const_int 1) (match_dup 2))
(const_int 0)))
(set (match_dup 0)
- (ne:QI (reg:CCC FLAGS_REG) (const_int 0)))]
-{
- operands[2] = lowpart_subreg (SImode, operands[2], QImode);
-})
+ (ne:QI (reg:CCC FLAGS_REG) (const_int 0)))])
-(define_insn_and_split "*bt<mode>_setnc<mode>"
+;; Help combine recognize bt followed by setc
+(define_insn_and_split "*bt<mode>_setc<mode>_mask"
[(set (match_operand:SWI48 0 "register_operand")
- (and:SWI48
- (not:SWI48
- (lshiftrt:SWI48 (match_operand:SWI48 1 "register_operand")
- (match_operand:QI 2 "register_operand")))
- (const_int 1)))
+ (zero_extract:SWI48
+ (match_operand:SWI48 1 "register_operand")
+ (const_int 1)
+ (subreg:QI
+ (and:SWI48
+ (match_operand:SWI48 2 "register_operand")
+ (match_operand 3 "const_int_operand")) 0)))
(clobber (reg:CC FLAGS_REG))]
- "TARGET_USE_BT && ix86_pre_reload_split ()"
+ "TARGET_USE_BT
+ && (INTVAL (operands[3]) & (GET_MODE_BITSIZE (<MODE>mode)-1))
+ == GET_MODE_BITSIZE (<MODE>mode)-1
+ && ix86_pre_reload_split ()"
"#"
"&& 1"
[(set (reg:CCC FLAGS_REG)
(zero_extract:SWI48 (match_dup 1) (const_int 1) (match_dup 2))
(const_int 0)))
(set (match_dup 3)
- (ne:QI (reg:CCC FLAGS_REG) (const_int 0)))
+ (eq:QI (reg:CCC FLAGS_REG) (const_int 0)))
(set (match_dup 0) (zero_extend:SWI48 (match_dup 3)))]
{
- operands[2] = lowpart_subreg (SImode, operands[2], QImode);
+ operands[2] = gen_lowpart (QImode, operands[2]);
operands[3] = gen_reg_rtx (QImode);
})
\f
FAIL;
})
+;; Eliminate redundant compare between set{z,nz} and j{z,nz}:
+;; setz %al; test %al,%al; jz <...> -> setz %al; jnz <...> and
+;; setnz %al, test %al,%al; jz <...> -> setnz %al; jz <...>.
+(define_peephole2
+ [(set (match_operand:QI 0 "nonimmediate_operand")
+ (match_operator:QI 1 "bt_comparison_operator"
+ [(reg:CCZ FLAGS_REG) (const_int 0)]))
+ (set (reg:CCZ FLAGS_REG)
+ (compare:CCZ (match_dup 0) (const_int 0)))
+ (set (pc)
+ (if_then_else (match_operator 2 "bt_comparison_operator"
+ [(reg:CCZ FLAGS_REG) (const_int 0)])
+ (match_operand 3)
+ (pc)))]
+ "peep2_regno_dead_p (3, FLAGS_REG)"
+ [(set (match_dup 0)
+ (match_op_dup 1 [(reg:CCZ FLAGS_REG) (const_int 0)]))
+ (set (pc)
+ (if_then_else (match_dup 2)
+ (match_dup 3)
+ (pc)))]
+{
+ if (GET_CODE (operands[1]) == EQ)
+ {
+ operands[2] = shallow_copy_rtx (operands[2]);
+ PUT_CODE (operands[2], reverse_condition (GET_CODE (operands[2])));
+ }
+})
+
;; The SSE store flag instructions saves 0 or 0xffffffff to the result.
;; subsequent logical operations are used to imitate conditional moves.
;; 0xffffffff is NaN, but not in normalized form, so we can't represent
[(set (match_operand:MODEF 0 "register_operand" "=x,x")
(match_operator:MODEF 3 "sse_comparison_operator"
[(match_operand:MODEF 1 "register_operand" "0,x")
- (match_operand:MODEF 2 "nonimmediate_operand" "xm,xm")]))]
+ (match_operand:MODEF 2 "nonimmediate_operand" "xm,xjm")]))]
"SSE_FLOAT_MODE_P (<MODE>mode)"
"@
cmp%D3<ssemodesuffix>\t{%2, %0|%0, %2}
vcmp%D3<ssemodesuffix>\t{%2, %1, %0|%0, %1, %2}"
[(set_attr "isa" "noavx,avx")
+ (set_attr "addr" "*,gpr16")
(set_attr "type" "ssecmp")
(set_attr "length_immediate" "1")
(set_attr "prefix" "orig,vex")
[(parallel
[(set (match_operand:SWI48 0 "register_operand")
(if_then_else:SWI48
- (ne:QI (and:SWI48 (match_operand:SWI48 2 "register_operand")
- (const_int 255))
+ (ne:QI (match_operand:QI 2 "register_operand")
(const_int 0))
(zero_extract:SWI48
(match_operand:SWI48 1 "nonimmediate_operand")
- (umin:SWI48 (and:SWI48 (match_dup 2) (const_int 255))
- (match_dup 3))
+ (umin:QI (match_dup 2) (match_dup 3))
(const_int 0))
(const_int 0)))
(clobber (reg:CC FLAGS_REG))])]
"TARGET_BMI2"
- "operands[3] = GEN_INT (<MODE_SIZE> * BITS_PER_UNIT);")
+{
+ operands[2] = gen_lowpart (QImode, operands[2]);
+ operands[3] = GEN_INT (<MODE_SIZE> * BITS_PER_UNIT);
+})
(define_insn "*bmi2_bzhi_<mode>3"
[(set (match_operand:SWI48 0 "register_operand" "=r")
(if_then_else:SWI48
- (ne:QI (and:SWI48 (match_operand:SWI48 2 "register_operand" "r")
- (const_int 255))
+ (ne:QI (match_operand:QI 2 "register_operand" "q")
(const_int 0))
(zero_extract:SWI48
(match_operand:SWI48 1 "nonimmediate_operand" "rm")
- (umin:SWI48 (and:SWI48 (match_dup 2) (const_int 255))
- (match_operand:SWI48 3 "const_int_operand"))
- (const_int 0))
- (const_int 0)))
- (clobber (reg:CC FLAGS_REG))]
- "TARGET_BMI2 && INTVAL (operands[3]) == <MODE_SIZE> * BITS_PER_UNIT"
- "bzhi\t{%2, %1, %0|%0, %1, %2}"
- [(set_attr "type" "bitmanip")
- (set_attr "prefix" "vex")
- (set_attr "mode" "<MODE>")])
-
-(define_insn "*bmi2_bzhi_<mode>3_1"
- [(set (match_operand:SWI48 0 "register_operand" "=r")
- (if_then_else:SWI48
- (ne:QI (match_operand:QI 2 "register_operand" "r") (const_int 0))
- (zero_extract:SWI48
- (match_operand:SWI48 1 "nonimmediate_operand" "rm")
- (umin:SWI48 (zero_extend:SWI48 (match_dup 2))
- (match_operand:SWI48 3 "const_int_operand"))
+ (umin:QI (match_dup 2)
+ (match_operand:QI 3 "const_int_operand"))
(const_int 0))
(const_int 0)))
(clobber (reg:CC FLAGS_REG))]
(ne:QI (match_operand:QI 2 "register_operand" "r") (const_int 0))
(zero_extract:SWI48
(match_operand:SWI48 1 "nonimmediate_operand" "rm")
- (umin:SWI48 (zero_extend:SWI48 (match_dup 2))
- (match_operand:SWI48 3 "const_int_operand"))
+ (umin:QI (match_dup 2)
+ (match_operand:QI 3 "const_int_operand"))
(const_int 0))
(const_int 0))
(const_int 0)))
[(set (match_operand:SWI48 0 "register_operand" "=r")
(zero_extract:SWI48
(match_operand:SWI48 1 "nonimmediate_operand" "rm")
- (match_operand 2 "const_0_to_255_operand")
- (match_operand 3 "const_0_to_255_operand")))
+ (match_operand:QI 2 "const_0_to_255_operand")
+ (match_operand:QI 3 "const_0_to_255_operand")))
(clobber (reg:CC FLAGS_REG))]
"TARGET_TBM"
{
"! TARGET_POPCNT"
{
rtx scratch = gen_reg_rtx (QImode);
+ rtx tmp = gen_reg_rtx (HImode);
- emit_insn (gen_parityhi2_cmp (operands[1]));
+ emit_move_insn (tmp, operands[1]);
+ emit_insn (gen_parityhi2_cmp (tmp));
ix86_expand_setcc (scratch, ORDERED,
gen_rtx_REG (CCmode, FLAGS_REG), const0_rtx);
(set_attr "mode" "HF")])
(define_insn "*rcpsf2_sse"
- [(set (match_operand:SF 0 "register_operand" "=x,x,x")
- (unspec:SF [(match_operand:SF 1 "nonimmediate_operand" "0,x,m")]
+ [(set (match_operand:SF 0 "register_operand" "=x,x,x,x")
+ (unspec:SF [(match_operand:SF 1 "nonimmediate_operand" "0,x,m,ja")]
UNSPEC_RCP))]
"TARGET_SSE && TARGET_SSE_MATH"
"@
%vrcpss\t{%d1, %0|%0, %d1}
%vrcpss\t{%d1, %0|%0, %d1}
- %vrcpss\t{%1, %d0|%d0, %1}"
- [(set_attr "type" "sse")
+ rcpss\t{%1, %d0|%d0, %1}
+ vrcpss\t{%1, %d0|%d0, %1}"
+ [(set_attr "isa" "*,*,noavx,avx")
+ (set_attr "addr" "*,*,*,gpr16")
+ (set_attr "type" "sse")
(set_attr "atom_sse_attr" "rcp")
(set_attr "btver2_sse_attr" "rcp")
(set_attr "prefix" "maybe_vex")
(set_attr "mode" "SF")
- (set_attr "avx_partial_xmm_update" "false,false,true")
+ (set_attr "avx_partial_xmm_update" "false,false,true,true")
(set (attr "preferred_for_speed")
(cond [(match_test "TARGET_AVX")
(symbol_ref "true")
- (eq_attr "alternative" "1,2")
+ (eq_attr "alternative" "1,2,3")
(symbol_ref "!TARGET_SSE_PARTIAL_REG_DEPENDENCY")
]
(symbol_ref "true")))])
(set_attr "bdver1_decode" "direct")])
(define_insn "*rsqrtsf2_sse"
- [(set (match_operand:SF 0 "register_operand" "=x,x,x")
- (unspec:SF [(match_operand:SF 1 "nonimmediate_operand" "0,x,m")]
+ [(set (match_operand:SF 0 "register_operand" "=x,x,x,x")
+ (unspec:SF [(match_operand:SF 1 "nonimmediate_operand" "0,x,m,ja")]
UNSPEC_RSQRT))]
"TARGET_SSE && TARGET_SSE_MATH"
"@
%vrsqrtss\t{%d1, %0|%0, %d1}
%vrsqrtss\t{%d1, %0|%0, %d1}
- %vrsqrtss\t{%1, %d0|%d0, %1}"
- [(set_attr "type" "sse")
+ rsqrtss\t{%1, %d0|%d0, %1}
+ vrsqrtss\t{%1, %d0|%d0, %1}"
+ [(set_attr "isa" "*,*,noavx,avx")
+ (set_attr "addr" "*,*,*,gpr16")
+ (set_attr "type" "sse")
(set_attr "atom_sse_attr" "rcp")
(set_attr "btver2_sse_attr" "rcp")
(set_attr "prefix" "maybe_vex")
(set_attr "mode" "SF")
- (set_attr "avx_partial_xmm_update" "false,false,true")
+ (set_attr "avx_partial_xmm_update" "false,false,true,true")
(set (attr "preferred_for_speed")
(cond [(match_test "TARGET_AVX")
(symbol_ref "true")
- (eq_attr "alternative" "1,2")
+ (eq_attr "alternative" "1,2,3")
(symbol_ref "!TARGET_SSE_PARTIAL_REG_DEPENDENCY")
]
(symbol_ref "true")))])
(define_insn "sse4_1_round<mode>2"
[(set (match_operand:MODEFH 0 "register_operand" "=x,x,x,v,v")
(unspec:MODEFH
- [(match_operand:MODEFH 1 "nonimmediate_operand" "0,x,m,v,m")
+ [(match_operand:MODEFH 1 "nonimmediate_operand" "0,x,jm,v,m")
(match_operand:SI 2 "const_0_to_15_operand")]
UNSPEC_ROUND))]
"TARGET_SSE4_1"
vrndscale<ssemodesuffix>\t{%2, %1, %d0|%d0, %1, %2}"
[(set_attr "type" "ssecvt")
(set_attr "prefix_extra" "1,1,1,*,*")
- (set_attr "length_immediate" "*,*,*,1,1")
+ (set_attr "length_immediate" "1")
+ (set_attr "addr" "*,*,gpr16,*,*")
(set_attr "prefix" "maybe_vex,maybe_vex,maybe_vex,evex,evex")
(set_attr "isa" "noavx512f,noavx512f,noavx512f,avx512f,avx512f")
(set_attr "avx_partial_xmm_update" "false,false,true,false,true")
DONE;
})
+(define_expand "roundhf2"
+ [(match_operand:HF 0 "register_operand")
+ (match_operand:HF 1 "register_operand")]
+ "TARGET_AVX512FP16 && !flag_trapping_math && !flag_rounding_math"
+{
+ ix86_expand_round_sse4 (operands[0], operands[1]);
+ DONE;
+})
+
(define_expand "round<mode>2"
[(match_operand:X87MODEF 0 "register_operand")
(match_operand:X87MODEF 1 "nonimmediate_operand")]
[(set_attr "type" "fpspc")
(set_attr "mode" "<MODE>")])
+(define_expand "lroundhf<mode>2"
+ [(set (match_operand:SWI248 0 "register_operand")
+ (unspec:SWI248 [(match_operand:HF 1 "nonimmediate_operand")]
+ UNSPEC_FIX_NOTRUNC))]
+ "TARGET_AVX512FP16 && !flag_trapping_math && !flag_rounding_math"
+{
+ ix86_expand_lround (operands[0], operands[1]);
+ DONE;
+})
+
+(define_expand "lrinthf<mode>2"
+ [(set (match_operand:SWI48 0 "register_operand")
+ (unspec:SWI48 [(match_operand:HF 1 "nonimmediate_operand")]
+ UNSPEC_FIX_NOTRUNC))]
+ "TARGET_AVX512FP16")
+
(define_expand "lrint<MODEF:mode><SWI48:mode>2"
[(set (match_operand:SWI48 0 "register_operand")
(unspec:SWI48 [(match_operand:MODEF 1 "nonimmediate_operand")]
&& (!TARGET_SSE_MATH || TARGET_MIX_SSE_I387)
&& flag_unsafe_math_optimizations")
+(define_expand "l<rounding_insn>hf<mode>2"
+ [(set (match_operand:SWI48 0 "nonimmediate_operand")
+ (unspec:SWI48 [(match_operand:HF 1 "register_operand")]
+ FIST_ROUNDING))]
+ "TARGET_AVX512FP16"
+{
+ rtx tmp = gen_reg_rtx (HFmode);
+ emit_insn (gen_sse4_1_roundhf2 (tmp, operands[1],
+ GEN_INT (ROUND_<ROUNDING> | ROUND_NO_EXC)));
+ emit_insn (gen_fix_trunchf<mode>2 (operands[0], tmp));
+ DONE;
+})
+
(define_expand "l<rounding_insn><MODEF:mode><SWI48:mode>2"
[(parallel [(set (match_operand:SWI48 0 "nonimmediate_operand")
(unspec:SWI48 [(match_operand:MODEF 1 "register_operand")]
})
(define_insn "movmsk_df"
- [(set (match_operand:SI 0 "register_operand" "=r")
+ [(set (match_operand:SI 0 "register_operand" "=r,jr")
(unspec:SI
- [(match_operand:DF 1 "register_operand" "x")]
+ [(match_operand:DF 1 "register_operand" "x,x")]
UNSPEC_MOVMSK))]
"SSE_FLOAT_MODE_P (DFmode) && TARGET_SSE_MATH"
"%vmovmskpd\t{%1, %0|%0, %1}"
- [(set_attr "type" "ssemov")
- (set_attr "prefix" "maybe_vex")
+ [(set_attr "isa" "noavx,avx")
+ (set_attr "type" "ssemov")
+ (set_attr "prefix" "maybe_evex")
(set_attr "mode" "DF")])
;; Use movmskpd in SSE mode to avoid store forwarding stall
(const_int 0))
(compare:CC (match_operand 4 "memory_operand")
(match_operand 5 "memory_operand"))
- (const_int 0)))
+ (reg:CC FLAGS_REG)))
(use (match_operand:SI 3 "immediate_operand"))
- (use (reg:CC FLAGS_REG))
(clobber (match_operand 0 "register_operand"))
(clobber (match_operand 1 "register_operand"))
(clobber (match_dup 2))])]
(const_int 0))
(compare:CC (mem:BLK (match_operand:P 4 "register_operand" "0"))
(mem:BLK (match_operand:P 5 "register_operand" "1")))
- (const_int 0)))
+ (reg:CC FLAGS_REG)))
(use (match_operand:SI 3 "immediate_operand" "i"))
- (use (reg:CC FLAGS_REG))
(clobber (match_operand:P 0 "register_operand" "=S"))
(clobber (match_operand:P 1 "register_operand" "=D"))
(clobber (match_operand:P 2 "register_operand" "=c"))]
(const_int 0))
(compare:CC (mem:BLK (match_operand 4 "register_operand"))
(mem:BLK (match_operand 5 "register_operand")))
- (const_int 0)))
+ (reg:CC FLAGS_REG)))
(use (match_operand:SI 3 "immediate_operand"))
- (use (reg:CC FLAGS_REG))
(clobber (match_operand 0 "register_operand"))
(clobber (match_operand 1 "register_operand"))
(clobber (match_operand 2 "register_operand"))])
(const_int 0))
(compare:CC (mem:BLK (match_dup 4))
(mem:BLK (match_dup 5)))
- (const_int 0)))
+ (reg:CC FLAGS_REG)))
(use (match_dup 3))
- (use (reg:CC FLAGS_REG))
(clobber (match_dup 0))
(clobber (match_dup 1))
(clobber (match_dup 2))])])
(neg:SWI (ltu:SWI (reg:CCC FLAGS_REG) (const_int 0))))])
(define_insn "*mov<mode>cc_noc"
- [(set (match_operand:SWI248 0 "register_operand" "=r,r")
+ [(set (match_operand:SWI248 0 "register_operand" "=r,r,r,r")
(if_then_else:SWI248 (match_operator 1 "ix86_comparison_operator"
[(reg FLAGS_REG) (const_int 0)])
- (match_operand:SWI248 2 "nonimmediate_operand" "rm,0")
- (match_operand:SWI248 3 "nonimmediate_operand" "0,rm")))]
+ (match_operand:SWI248 2 "nonimmediate_operand" "rm,0,rm,r")
+ (match_operand:SWI248 3 "nonimmediate_operand" "0,rm,r,rm")))]
"TARGET_CMOVE && !(MEM_P (operands[2]) && MEM_P (operands[3]))"
"@
cmov%O2%C1\t{%2, %0|%0, %2}
- cmov%O2%c1\t{%3, %0|%0, %3}"
- [(set_attr "type" "icmov")
+ cmov%O2%c1\t{%3, %0|%0, %3}
+ cmov%O2%C1\t{%2, %3, %0|%0, %3, %2}
+ cmov%O2%c1\t{%3, %2, %0|%0, %2, %3}"
+ [(set_attr "isa" "*,*,apx_ndd,apx_ndd")
+ (set_attr "type" "icmov")
(set_attr "mode" "<MODE>")])
(define_insn "*movsicc_noc_zext"
- [(set (match_operand:DI 0 "register_operand" "=r,r")
+ [(set (match_operand:DI 0 "register_operand" "=r,r,r,r")
(if_then_else:DI (match_operator 1 "ix86_comparison_operator"
[(reg FLAGS_REG) (const_int 0)])
(zero_extend:DI
- (match_operand:SI 2 "nonimmediate_operand" "rm,0"))
+ (match_operand:SI 2 "nonimmediate_operand" "rm,0,rm,r"))
(zero_extend:DI
- (match_operand:SI 3 "nonimmediate_operand" "0,rm"))))]
+ (match_operand:SI 3 "nonimmediate_operand" "0,rm,r,rm"))))]
"TARGET_64BIT
&& TARGET_CMOVE && !(MEM_P (operands[2]) && MEM_P (operands[3]))"
"@
cmov%O2%C1\t{%2, %k0|%k0, %2}
- cmov%O2%c1\t{%3, %k0|%k0, %3}"
- [(set_attr "type" "icmov")
+ cmov%O2%c1\t{%3, %k0|%k0, %3}
+ cmov%O2%C1\t{%2, %3, %k0|%k0, %3, %2}
+ cmov%O2%c1\t{%3, %2, %k0|%k0, %2, %3}"
+ [(set_attr "isa" "*,*,apx_ndd,apx_ndd")
+ (set_attr "type" "icmov")
(set_attr "mode" "SI")])
(define_insn "*movsicc_noc_zext_1"
- [(set (match_operand:DI 0 "nonimmediate_operand" "=r,r")
+ [(set (match_operand:DI 0 "nonimmediate_operand" "=r,r,r,r")
(zero_extend:DI
(if_then_else:SI (match_operator 1 "ix86_comparison_operator"
[(reg FLAGS_REG) (const_int 0)])
- (match_operand:SI 2 "nonimmediate_operand" "rm,0")
- (match_operand:SI 3 "nonimmediate_operand" "0,rm"))))]
+ (match_operand:SI 2 "nonimmediate_operand" "rm,0,rm,r")
+ (match_operand:SI 3 "nonimmediate_operand" "0,rm,r,rm"))))]
"TARGET_64BIT
&& TARGET_CMOVE && !(MEM_P (operands[2]) && MEM_P (operands[3]))"
"@
cmov%O2%C1\t{%2, %k0|%k0, %2}
- cmov%O2%c1\t{%3, %k0|%k0, %3}"
- [(set_attr "type" "icmov")
+ cmov%O2%c1\t{%3, %k0|%k0, %3}
+ cmov%O2%C1\t{%2, %3, %k0|%k0, %3, %2}
+ cmov%O2%c1\t{%3, %2, %k0|%k0, %2, %3}"
+ [(set_attr "isa" "*,*,apx_ndd,apx_ndd")
+ (set_attr "type" "icmov")
(set_attr "mode" "SI")])
})
(define_insn "*movqicc_noc"
- [(set (match_operand:QI 0 "register_operand" "=r,r")
+ [(set (match_operand:QI 0 "register_operand" "=r,r,r")
(if_then_else:QI (match_operator 1 "ix86_comparison_operator"
[(reg FLAGS_REG) (const_int 0)])
- (match_operand:QI 2 "register_operand" "r,0")
- (match_operand:QI 3 "register_operand" "0,r")))]
+ (match_operand:QI 2 "register_operand" "r,0,r")
+ (match_operand:QI 3 "register_operand" "0,r,r")))]
"TARGET_CMOVE && !TARGET_PARTIAL_REG_STALL"
"#"
- [(set_attr "type" "icmov")
+ [(set_attr "isa" "*,*,apx_ndd")
+ (set_attr "type" "icmov")
(set_attr "mode" "QI")])
(define_split
(match_operand:MODEF 3 "register_operand" "x")))]
"TARGET_XOP"
"vpcmov\t{%1, %3, %2, %0|%0, %2, %3, %1}"
- [(set_attr "type" "sse4arg")])
+ [(set_attr "type" "sse4arg")
+ (set_attr "mode" "TI")])
;; These versions of the min/max patterns are intentionally ignorant of
;; their behavior wrt -0.0 and NaN (via the commutative operand mark).
{
rtx stack_slot;
- if (flag_cf_protection & CF_RETURN)
- {
- /* Copy shadow stack pointer to the first slot
- and stack pointer to the second slot. */
- rtx ssp_slot = adjust_address (operands[0], word_mode, 0);
- stack_slot = adjust_address (operands[0], Pmode, UNITS_PER_WORD);
+ if (flag_cf_protection & CF_RETURN)
+ {
+ /* Copy shadow stack pointer to the first slot
+ and stack pointer to the second slot. */
+ rtx ssp_slot = adjust_address (operands[0], word_mode, 0);
+ stack_slot = adjust_address (operands[0], Pmode, UNITS_PER_WORD);
+
+ rtx reg_ssp = force_reg (word_mode, const0_rtx);
+ emit_insn (gen_rdssp (word_mode, reg_ssp, reg_ssp));
+ emit_move_insn (ssp_slot, reg_ssp);
+ }
+ else
+ stack_slot = adjust_address (operands[0], Pmode, 0);
+ emit_move_insn (stack_slot, operands[1]);
+ DONE;
+})
+
+(define_expand "restore_stack_nonlocal"
+ [(set (match_operand 0 "register_operand" "")
+ (match_operand 1 "memory_operand" ""))]
+ ""
+{
+ rtx stack_slot;
+
+ if (flag_cf_protection & CF_RETURN)
+ {
+ /* Restore shadow stack pointer from the first slot
+ and stack pointer from the second slot. */
+ rtx ssp_slot = adjust_address (operands[1], word_mode, 0);
+ stack_slot = adjust_address (operands[1], Pmode, UNITS_PER_WORD);
+
+ /* Get the current shadow stack pointer. The code below will check if
+ SHSTK feature is enabled. If it is not enabled the RDSSP instruction
+ is a NOP. */
+ rtx reg_ssp = force_reg (word_mode, const0_rtx);
+ emit_insn (gen_rdssp (word_mode, reg_ssp, reg_ssp));
+
+ /* Compare through subtraction the saved and the current ssp
+ to decide if ssp has to be adjusted. */
+ reg_ssp = expand_simple_binop (word_mode, MINUS,
+ reg_ssp, ssp_slot,
+ reg_ssp, 1, OPTAB_DIRECT);
+
+ /* Compare and jump over adjustment code. */
+ rtx noadj_label = gen_label_rtx ();
+ emit_cmp_and_jump_insns (reg_ssp, const0_rtx, EQ, NULL_RTX,
+ word_mode, 1, noadj_label);
+
+ /* Compute the number of frames to adjust. */
+ rtx reg_adj = gen_lowpart (ptr_mode, reg_ssp);
+ rtx reg_adj_neg = expand_simple_unop (ptr_mode, NEG, reg_adj,
+ NULL_RTX, 1);
+
+ reg_adj = expand_simple_binop (ptr_mode, LSHIFTRT, reg_adj_neg,
+ GEN_INT (exact_log2 (UNITS_PER_WORD)),
+ reg_adj, 1, OPTAB_DIRECT);
+
+ /* Check if number of frames <= 255 so no loop is needed. */
+ rtx inc_label = gen_label_rtx ();
+ emit_cmp_and_jump_insns (reg_adj, GEN_INT (255), LEU, NULL_RTX,
+ ptr_mode, 1, inc_label);
+
+ /* Adjust the ssp in a loop. */
+ rtx loop_label = gen_label_rtx ();
+ emit_label (loop_label);
+ LABEL_NUSES (loop_label) = 1;
+
+ rtx reg_255 = force_reg (word_mode, GEN_INT (255));
+ emit_insn (gen_incssp (word_mode, reg_255));
+
+ reg_adj = expand_simple_binop (ptr_mode, MINUS,
+ reg_adj, GEN_INT (255),
+ reg_adj, 1, OPTAB_DIRECT);
+
+ /* Compare and jump to the loop label. */
+ emit_cmp_and_jump_insns (reg_adj, GEN_INT (255), GTU, NULL_RTX,
+ ptr_mode, 1, loop_label);
+
+ emit_label (inc_label);
+ LABEL_NUSES (inc_label) = 1;
+
+ emit_insn (gen_incssp (word_mode, reg_ssp));
+
+ emit_label (noadj_label);
+ LABEL_NUSES (noadj_label) = 1;
+ }
+ else
+ stack_slot = adjust_address (operands[1], Pmode, 0);
+ emit_move_insn (operands[0], stack_slot);
+ DONE;
+})
+
+(define_expand "stack_protect_set"
+ [(match_operand 0 "memory_operand")
+ (match_operand 1 "memory_operand")]
+ ""
+{
+ rtx scratch = gen_reg_rtx (word_mode);
+
+ emit_insn (gen_stack_protect_set_1
+ (ptr_mode, word_mode, operands[0], operands[1], scratch));
+ DONE;
+})
+
+(define_insn "@stack_protect_set_1_<PTR:mode>_<W:mode>"
+ [(set (match_operand:PTR 0 "memory_operand" "=m")
+ (unspec:PTR [(match_operand:PTR 1 "memory_operand" "m")]
+ UNSPEC_SP_SET))
+ (set (match_operand:W 2 "register_operand" "=&r") (const_int 0))
+ (clobber (reg:CC FLAGS_REG))]
+ ""
+{
+ output_asm_insn ("mov{<PTR:imodesuffix>}\t{%1, %<PTR:k>2|%<PTR:k>2, %1}",
+ operands);
+ output_asm_insn ("mov{<PTR:imodesuffix>}\t{%<PTR:k>2, %0|%0, %<PTR:k>2}",
+ operands);
+ if (!TARGET_USE_MOV0 || optimize_insn_for_size_p ())
+ return "xor{l}\t%k2, %k2";
+ else
+ return "mov{l}\t{$0, %k2|%k2, 0}";
+}
+ [(set_attr "type" "multi")])
+
+;; Patterns and peephole2s to optimize stack_protect_set_1_<mode>
+;; immediately followed by *mov{s,d}i_internal, where we can avoid
+;; the xor{l} above. We don't split this, so that scheduling or
+;; anything else doesn't separate the *stack_protect_set* pattern from
+;; the set of the register that overwrites the register with a new value.
+
+(define_peephole2
+ [(parallel [(set (match_operand:PTR 0 "memory_operand")
+ (unspec:PTR [(match_operand:PTR 1 "memory_operand")]
+ UNSPEC_SP_SET))
+ (set (match_operand 2 "general_reg_operand") (const_int 0))
+ (clobber (reg:CC FLAGS_REG))])
+ (set (match_operand 3 "general_reg_operand")
+ (match_operand 4 "const0_operand"))]
+ "GET_MODE (operands[2]) == word_mode
+ && GET_MODE_SIZE (GET_MODE (operands[3])) <= UNITS_PER_WORD
+ && peep2_reg_dead_p (0, operands[3])
+ && peep2_reg_dead_p (1, operands[2])"
+ [(parallel [(set (match_dup 0)
+ (unspec:PTR [(match_dup 1)] UNSPEC_SP_SET))
+ (set (match_dup 3) (const_int 0))
+ (clobber (reg:CC FLAGS_REG))])]
+ "operands[3] = gen_lowpart (word_mode, operands[3]);")
+
+(define_insn "*stack_protect_set_2_<mode>_si"
+ [(set (match_operand:PTR 0 "memory_operand" "=m")
+ (unspec:PTR [(match_operand:PTR 3 "memory_operand" "m")]
+ UNSPEC_SP_SET))
+ (set (match_operand:SI 1 "register_operand" "=&r")
+ (match_operand:SI 2 "general_operand" "g"))]
+ "reload_completed"
+{
+ output_asm_insn ("mov{<imodesuffix>}\t{%3, %<k>1|%<k>1, %3}", operands);
+ output_asm_insn ("mov{<imodesuffix>}\t{%<k>1, %0|%0, %<k>1}", operands);
+ if (pic_32bit_operand (operands[2], SImode)
+ || ix86_use_lea_for_mov (insn, operands + 1))
+ return "lea{l}\t{%E2, %1|%1, %E2}";
+ else
+ return "mov{l}\t{%2, %1|%1, %2}";
+}
+ [(set_attr "type" "multi")
+ (set_attr "length" "24")])
+
+(define_insn "*stack_protect_set_2_<mode>_di"
+ [(set (match_operand:PTR 0 "memory_operand" "=m,m,m")
+ (unspec:PTR [(match_operand:PTR 3 "memory_operand" "m,m,m")]
+ UNSPEC_SP_SET))
+ (set (match_operand:DI 1 "register_operand" "=&r,&r,&r")
+ (match_operand:DI 2 "general_operand" "Z,rem,i"))]
+ "TARGET_64BIT && reload_completed"
+{
+ output_asm_insn ("mov{<imodesuffix>}\t{%3, %<k>1|%<k>1, %3}", operands);
+ output_asm_insn ("mov{<imodesuffix>}\t{%<k>1, %0|%0, %<k>1}", operands);
+ if (pic_32bit_operand (operands[2], DImode))
+ return "lea{q}\t{%E2, %1|%1, %E2}";
+ else if (which_alternative == 0)
+ return "mov{l}\t{%k2, %k1|%k1, %k2}";
+ else if (which_alternative == 2)
+ return "movabs{q}\t{%2, %1|%1, %2}";
+ else if (ix86_use_lea_for_mov (insn, operands + 1))
+ return "lea{q}\t{%E2, %1|%1, %E2}";
+ else
+ return "mov{q}\t{%2, %1|%1, %2}";
+}
+ [(set_attr "type" "multi")
+ (set_attr "length" "24")])
+
+(define_peephole2
+ [(parallel [(set (match_operand:PTR 0 "memory_operand")
+ (unspec:PTR [(match_operand:PTR 1 "memory_operand")]
+ UNSPEC_SP_SET))
+ (set (match_operand 2 "general_reg_operand") (const_int 0))
+ (clobber (reg:CC FLAGS_REG))])
+ (set (match_operand:SWI48 3 "general_reg_operand")
+ (match_operand:SWI48 4 "general_gr_operand"))]
+ "GET_MODE (operands[2]) == word_mode
+ && peep2_reg_dead_p (0, operands[3])
+ && peep2_reg_dead_p (1, operands[2])"
+ [(parallel [(set (match_dup 0)
+ (unspec:PTR [(match_dup 1)] UNSPEC_SP_SET))
+ (set (match_dup 3) (match_dup 4))])])
- rtx reg_ssp = force_reg (word_mode, const0_rtx);
- emit_insn (gen_rdssp (word_mode, reg_ssp, reg_ssp));
- emit_move_insn (ssp_slot, reg_ssp);
- }
- else
- stack_slot = adjust_address (operands[0], Pmode, 0);
- emit_move_insn (stack_slot, operands[1]);
- DONE;
-})
+(define_peephole2
+ [(set (match_operand:SWI48 3 "general_reg_operand")
+ (match_operand:SWI48 4 "general_gr_operand"))
+ (parallel [(set (match_operand:PTR 0 "memory_operand")
+ (unspec:PTR [(match_operand:PTR 1 "memory_operand")]
+ UNSPEC_SP_SET))
+ (set (match_operand 2 "general_reg_operand") (const_int 0))
+ (clobber (reg:CC FLAGS_REG))])]
+ "GET_MODE (operands[2]) == word_mode
+ && peep2_reg_dead_p (0, operands[3])
+ && peep2_reg_dead_p (2, operands[2])
+ && !reg_mentioned_p (operands[3], operands[0])
+ && !reg_mentioned_p (operands[3], operands[1])"
+ [(parallel [(set (match_dup 0)
+ (unspec:PTR [(match_dup 1)] UNSPEC_SP_SET))
+ (set (match_dup 3) (match_dup 4))])])
-(define_expand "restore_stack_nonlocal"
- [(set (match_operand 0 "register_operand" "")
- (match_operand 1 "memory_operand" ""))]
+(define_insn "*stack_protect_set_3_<PTR:mode>_<SWI48:mode>"
+ [(set (match_operand:PTR 0 "memory_operand" "=m")
+ (unspec:PTR [(match_operand:PTR 3 "memory_operand" "m")]
+ UNSPEC_SP_SET))
+ (set (match_operand:SWI48 1 "register_operand" "=&r")
+ (match_operand:SWI48 2 "address_no_seg_operand" "Ts"))]
""
{
- rtx stack_slot;
-
- if (flag_cf_protection & CF_RETURN)
+ output_asm_insn ("mov{<PTR:imodesuffix>}\t{%3, %<PTR:k>1|%<PTR:k>1, %3}",
+ operands);
+ output_asm_insn ("mov{<PTR:imodesuffix>}\t{%<PTR:k>1, %0|%0, %<PTR:k>1}",
+ operands);
+ if (SImode_address_operand (operands[2], VOIDmode))
{
- /* Restore shadow stack pointer from the first slot
- and stack pointer from the second slot. */
- rtx ssp_slot = adjust_address (operands[1], word_mode, 0);
- stack_slot = adjust_address (operands[1], Pmode, UNITS_PER_WORD);
-
- /* Get the current shadow stack pointer. The code below will check if
- SHSTK feature is enabled. If it is not enabled the RDSSP instruction
- is a NOP. */
- rtx reg_ssp = force_reg (word_mode, const0_rtx);
- emit_insn (gen_rdssp (word_mode, reg_ssp, reg_ssp));
-
- /* Compare through subtraction the saved and the current ssp
- to decide if ssp has to be adjusted. */
- reg_ssp = expand_simple_binop (word_mode, MINUS,
- reg_ssp, ssp_slot,
- reg_ssp, 1, OPTAB_DIRECT);
-
- /* Compare and jump over adjustment code. */
- rtx noadj_label = gen_label_rtx ();
- emit_cmp_and_jump_insns (reg_ssp, const0_rtx, EQ, NULL_RTX,
- word_mode, 1, noadj_label);
-
- /* Compute the number of frames to adjust. */
- rtx reg_adj = gen_lowpart (ptr_mode, reg_ssp);
- rtx reg_adj_neg = expand_simple_unop (ptr_mode, NEG, reg_adj,
- NULL_RTX, 1);
-
- reg_adj = expand_simple_binop (ptr_mode, LSHIFTRT, reg_adj_neg,
- GEN_INT (exact_log2 (UNITS_PER_WORD)),
- reg_adj, 1, OPTAB_DIRECT);
-
- /* Check if number of frames <= 255 so no loop is needed. */
- rtx inc_label = gen_label_rtx ();
- emit_cmp_and_jump_insns (reg_adj, GEN_INT (255), LEU, NULL_RTX,
- ptr_mode, 1, inc_label);
+ gcc_assert (TARGET_64BIT);
+ return "lea{l}\t{%E2, %k1|%k1, %E2}";
+ }
+ else
+ return "lea{<SWI48:imodesuffix>}\t{%E2, %1|%1, %E2}";
+}
+ [(set_attr "type" "multi")
+ (set_attr "length" "24")])
- /* Adjust the ssp in a loop. */
- rtx loop_label = gen_label_rtx ();
- emit_label (loop_label);
- LABEL_NUSES (loop_label) = 1;
+(define_peephole2
+ [(parallel [(set (match_operand:PTR 0 "memory_operand")
+ (unspec:PTR [(match_operand:PTR 1 "memory_operand")]
+ UNSPEC_SP_SET))
+ (set (match_operand 2 "general_reg_operand") (const_int 0))
+ (clobber (reg:CC FLAGS_REG))])
+ (set (match_operand:SWI48 3 "general_reg_operand")
+ (match_operand:SWI48 4 "address_no_seg_operand"))]
+ "GET_MODE (operands[2]) == word_mode
+ && peep2_reg_dead_p (0, operands[3])
+ && peep2_reg_dead_p (1, operands[2])"
+ [(parallel [(set (match_dup 0)
+ (unspec:PTR [(match_dup 1)] UNSPEC_SP_SET))
+ (set (match_dup 3) (match_dup 4))])])
- rtx reg_255 = force_reg (word_mode, GEN_INT (255));
- emit_insn (gen_incssp (word_mode, reg_255));
+(define_insn "*stack_protect_set_4z_<mode>_di"
+ [(set (match_operand:PTR 0 "memory_operand" "=m")
+ (unspec:PTR [(match_operand:PTR 3 "memory_operand" "m")]
+ UNSPEC_SP_SET))
+ (set (match_operand:DI 1 "register_operand" "=&r")
+ (zero_extend:DI (match_operand:SI 2 "nonimmediate_operand" "rm")))]
+ "TARGET_64BIT && reload_completed"
+{
+ output_asm_insn ("mov{<imodesuffix>}\t{%3, %<k>1|%<k>1, %3}", operands);
+ output_asm_insn ("mov{<imodesuffix>}\t{%<k>1, %0|%0, %<k>1}", operands);
+ if (ix86_use_lea_for_mov (insn, operands + 1))
+ return "lea{l}\t{%E2, %k1|%k1, %E2}";
+ else
+ return "mov{l}\t{%2, %k1|%k1, %2}";
+}
+ [(set_attr "type" "multi")
+ (set_attr "length" "24")])
- reg_adj = expand_simple_binop (ptr_mode, MINUS,
- reg_adj, GEN_INT (255),
- reg_adj, 1, OPTAB_DIRECT);
+(define_insn "*stack_protect_set_4s_<mode>_di"
+ [(set (match_operand:PTR 0 "memory_operand" "=m")
+ (unspec:PTR [(match_operand:PTR 3 "memory_operand" "m")]
+ UNSPEC_SP_SET))
+ (set (match_operand:DI 1 "register_operand" "=&r")
+ (sign_extend:DI (match_operand:SI 2 "nonimmediate_operand" "rm")))]
+ "TARGET_64BIT && reload_completed"
+{
+ output_asm_insn ("mov{<imodesuffix>}\t{%3, %<k>1|%<k>1, %3}", operands);
+ output_asm_insn ("mov{<imodesuffix>}\t{%<k>1, %0|%0, %<k>1}", operands);
+ return "movs{lq|x}\t{%2, %1|%1, %2}";
+}
+ [(set_attr "type" "multi")
+ (set_attr "length" "24")])
- /* Compare and jump to the loop label. */
- emit_cmp_and_jump_insns (reg_adj, GEN_INT (255), GTU, NULL_RTX,
- ptr_mode, 1, loop_label);
+(define_peephole2
+ [(parallel [(set (match_operand:PTR 0 "memory_operand")
+ (unspec:PTR [(match_operand:PTR 1 "memory_operand")]
+ UNSPEC_SP_SET))
+ (set (match_operand 2 "general_reg_operand") (const_int 0))
+ (clobber (reg:CC FLAGS_REG))])
+ (set (match_operand:DI 3 "general_reg_operand")
+ (any_extend:DI
+ (match_operand:SI 4 "nonimmediate_gr_operand")))]
+ "TARGET_64BIT
+ && GET_MODE (operands[2]) == word_mode
+ && peep2_reg_dead_p (0, operands[3])
+ && peep2_reg_dead_p (1, operands[2])"
+ [(parallel [(set (match_dup 0)
+ (unspec:PTR [(match_dup 1)] UNSPEC_SP_SET))
+ (set (match_dup 3)
+ (any_extend:DI (match_dup 4)))])])
- emit_label (inc_label);
- LABEL_NUSES (inc_label) = 1;
+(define_expand "stack_protect_test"
+ [(match_operand 0 "memory_operand")
+ (match_operand 1 "memory_operand")
+ (match_operand 2)]
+ ""
+{
+ rtx flags = gen_rtx_REG (CCZmode, FLAGS_REG);
- emit_insn (gen_incssp (word_mode, reg_ssp));
+ emit_insn (gen_stack_protect_test_1
+ (ptr_mode, flags, operands[0], operands[1]));
- emit_label (noadj_label);
- LABEL_NUSES (noadj_label) = 1;
- }
- else
- stack_slot = adjust_address (operands[1], Pmode, 0);
- emit_move_insn (operands[0], stack_slot);
+ emit_jump_insn (gen_cbranchcc4 (gen_rtx_EQ (VOIDmode, flags, const0_rtx),
+ flags, const0_rtx, operands[2]));
DONE;
})
+(define_insn "@stack_protect_test_1_<mode>"
+ [(set (match_operand:CCZ 0 "flags_reg_operand")
+ (unspec:CCZ [(match_operand:PTR 1 "memory_operand" "m")
+ (match_operand:PTR 2 "memory_operand" "m")]
+ UNSPEC_SP_TEST))
+ (clobber (match_scratch:PTR 3 "=&r"))]
+ ""
+{
+ output_asm_insn ("mov{<imodesuffix>}\t{%1, %3|%3, %1}", operands);
+ return "sub{<imodesuffix>}\t{%2, %3|%3, %2}";
+}
+ [(set_attr "type" "multi")])
;; Avoid redundant prefixes by splitting HImode arithmetic to SImode.
;; Do not split instructions with mask registers.
(symbol_ref "memory_address_length (operands[0], false)"))
(set_attr "memory" "none")])
-(define_expand "stack_protect_set"
- [(match_operand 0 "memory_operand")
- (match_operand 1 "memory_operand")]
- ""
-{
- emit_insn (gen_stack_protect_set_1
- (ptr_mode, operands[0], operands[1]));
- DONE;
-})
-
-(define_insn "@stack_protect_set_1_<mode>"
- [(set (match_operand:PTR 0 "memory_operand" "=m")
- (unspec:PTR [(match_operand:PTR 1 "memory_operand" "m")]
- UNSPEC_SP_SET))
- (set (match_scratch:PTR 2 "=&r") (const_int 0))
- (clobber (reg:CC FLAGS_REG))]
- ""
-{
- output_asm_insn ("mov{<imodesuffix>}\t{%1, %2|%2, %1}", operands);
- output_asm_insn ("mov{<imodesuffix>}\t{%2, %0|%0, %2}", operands);
- return "xor{l}\t%k2, %k2";
-}
- [(set_attr "type" "multi")])
-
-;; Patterns and peephole2s to optimize stack_protect_set_1_<mode>
-;; immediately followed by *mov{s,d}i_internal to the same register,
-;; where we can avoid the xor{l} above. We don't split this, so that
-;; scheduling or anything else doesn't separate the *stack_protect_set*
-;; pattern from the set of the register that overwrites the register
-;; with a new value.
-(define_insn "*stack_protect_set_2_<mode>"
- [(set (match_operand:PTR 0 "memory_operand" "=m")
- (unspec:PTR [(match_operand:PTR 3 "memory_operand" "m")]
- UNSPEC_SP_SET))
- (set (match_operand:SI 1 "register_operand" "=&r")
- (match_operand:SI 2 "general_operand" "g"))
- (clobber (reg:CC FLAGS_REG))]
- "reload_completed
- && !reg_overlap_mentioned_p (operands[1], operands[2])"
-{
- output_asm_insn ("mov{<imodesuffix>}\t{%3, %<k>1|%<k>1, %3}", operands);
- output_asm_insn ("mov{<imodesuffix>}\t{%<k>1, %0|%0, %<k>1}", operands);
- if (pic_32bit_operand (operands[2], SImode)
- || ix86_use_lea_for_mov (insn, operands + 1))
- return "lea{l}\t{%E2, %1|%1, %E2}";
- else
- return "mov{l}\t{%2, %1|%1, %2}";
-}
- [(set_attr "type" "multi")
- (set_attr "length" "24")])
-
-(define_peephole2
- [(parallel [(set (match_operand:PTR 0 "memory_operand")
- (unspec:PTR [(match_operand:PTR 1 "memory_operand")]
- UNSPEC_SP_SET))
- (set (match_operand:PTR 2 "general_reg_operand") (const_int 0))
- (clobber (reg:CC FLAGS_REG))])
- (set (match_operand:SI 3 "general_reg_operand")
- (match_operand:SI 4))]
- "REGNO (operands[2]) == REGNO (operands[3])
- && general_operand (operands[4], SImode)
- && (general_reg_operand (operands[4], SImode)
- || memory_operand (operands[4], SImode)
- || immediate_operand (operands[4], SImode))
- && !reg_overlap_mentioned_p (operands[3], operands[4])"
- [(parallel [(set (match_dup 0)
- (unspec:PTR [(match_dup 1)] UNSPEC_SP_SET))
- (set (match_dup 3) (match_dup 4))
- (clobber (reg:CC FLAGS_REG))])])
-
-(define_insn "*stack_protect_set_3"
- [(set (match_operand:DI 0 "memory_operand" "=m,m,m")
- (unspec:DI [(match_operand:DI 3 "memory_operand" "m,m,m")]
- UNSPEC_SP_SET))
- (set (match_operand:DI 1 "register_operand" "=&r,r,r")
- (match_operand:DI 2 "general_operand" "Z,rem,i"))
- (clobber (reg:CC FLAGS_REG))]
- "TARGET_64BIT
- && reload_completed
- && !reg_overlap_mentioned_p (operands[1], operands[2])"
-{
- output_asm_insn ("mov{q}\t{%3, %1|%1, %3}", operands);
- output_asm_insn ("mov{q}\t{%1, %0|%0, %1}", operands);
- if (pic_32bit_operand (operands[2], DImode))
- return "lea{q}\t{%E2, %1|%1, %E2}";
- else if (which_alternative == 0)
- return "mov{l}\t{%k2, %k1|%k1, %k2}";
- else if (which_alternative == 2)
- return "movabs{q}\t{%2, %1|%1, %2}";
- else if (ix86_use_lea_for_mov (insn, operands + 1))
- return "lea{q}\t{%E2, %1|%1, %E2}";
- else
- return "mov{q}\t{%2, %1|%1, %2}";
-}
- [(set_attr "type" "multi")
- (set_attr "length" "24")])
-
-(define_peephole2
- [(parallel [(set (match_operand:DI 0 "memory_operand")
- (unspec:DI [(match_operand:DI 1 "memory_operand")]
- UNSPEC_SP_SET))
- (set (match_operand:DI 2 "general_reg_operand") (const_int 0))
- (clobber (reg:CC FLAGS_REG))])
- (set (match_dup 2) (match_operand:DI 3))]
- "TARGET_64BIT
- && general_operand (operands[3], DImode)
- && (general_reg_operand (operands[3], DImode)
- || memory_operand (operands[3], DImode)
- || x86_64_zext_immediate_operand (operands[3], DImode)
- || x86_64_immediate_operand (operands[3], DImode)
- || (CONSTANT_P (operands[3])
- && (!flag_pic || LEGITIMATE_PIC_OPERAND_P (operands[3]))))
- && !reg_overlap_mentioned_p (operands[2], operands[3])"
- [(parallel [(set (match_dup 0)
- (unspec:PTR [(match_dup 1)] UNSPEC_SP_SET))
- (set (match_dup 2) (match_dup 3))
- (clobber (reg:CC FLAGS_REG))])])
-
-(define_expand "stack_protect_test"
- [(match_operand 0 "memory_operand")
- (match_operand 1 "memory_operand")
- (match_operand 2)]
- ""
-{
- rtx flags = gen_rtx_REG (CCZmode, FLAGS_REG);
-
- emit_insn (gen_stack_protect_test_1
- (ptr_mode, flags, operands[0], operands[1]));
-
- emit_jump_insn (gen_cbranchcc4 (gen_rtx_EQ (VOIDmode, flags, const0_rtx),
- flags, const0_rtx, operands[2]));
- DONE;
-})
-
-(define_insn "@stack_protect_test_1_<mode>"
- [(set (match_operand:CCZ 0 "flags_reg_operand")
- (unspec:CCZ [(match_operand:PTR 1 "memory_operand" "m")
- (match_operand:PTR 2 "memory_operand" "m")]
- UNSPEC_SP_TEST))
- (clobber (match_scratch:PTR 3 "=&r"))]
- ""
-{
- output_asm_insn ("mov{<imodesuffix>}\t{%1, %3|%3, %1}", operands);
- return "sub{<imodesuffix>}\t{%2, %3|%3, %2}";
-}
- [(set_attr "type" "multi")])
-
(define_insn "sse4_2_crc32<mode>"
[(set (match_operand:SI 0 "register_operand" "=r")
(unspec:SI
(symbol_ref "ix86_attr_length_address_default (insn) + 3"))])
(define_insn "fxsave64"
- [(set (match_operand:BLK 0 "memory_operand" "=m")
+ [(set (match_operand:BLK 0 "memory_operand" "=jm")
(unspec_volatile:BLK [(const_int 0)] UNSPECV_FXSAVE64))]
"TARGET_64BIT && TARGET_FXSR"
"fxsave64\t%0"
[(set_attr "type" "other")
+ (set_attr "addr" "gpr16")
(set_attr "memory" "store")
(set (attr "length")
(symbol_ref "ix86_attr_length_address_default (insn) + 4"))])
(symbol_ref "ix86_attr_length_address_default (insn) + 3"))])
(define_insn "fxrstor64"
- [(unspec_volatile [(match_operand:BLK 0 "memory_operand" "m")]
+ [(unspec_volatile [(match_operand:BLK 0 "memory_operand" "jm")]
UNSPECV_FXRSTOR64)]
"TARGET_64BIT && TARGET_FXSR"
"fxrstor64\t%0"
[(set_attr "type" "other")
+ (set_attr "addr" "gpr16")
(set_attr "memory" "load")
(set (attr "length")
(symbol_ref "ix86_attr_length_address_default (insn) + 4"))])
(symbol_ref "ix86_attr_length_address_default (insn) + 3"))])
(define_insn "<xsave>_rex64"
- [(set (match_operand:BLK 0 "memory_operand" "=m")
+ [(set (match_operand:BLK 0 "memory_operand" "=jm")
(unspec_volatile:BLK
[(match_operand:SI 1 "register_operand" "a")
(match_operand:SI 2 "register_operand" "d")]
"<xsave>\t%0"
[(set_attr "type" "other")
(set_attr "memory" "store")
+ (set_attr "addr" "gpr16")
(set (attr "length")
(symbol_ref "ix86_attr_length_address_default (insn) + 3"))])
(define_insn "<xsave>"
- [(set (match_operand:BLK 0 "memory_operand" "=m")
+ [(set (match_operand:BLK 0 "memory_operand" "=jm")
(unspec_volatile:BLK
[(match_operand:SI 1 "register_operand" "a")
(match_operand:SI 2 "register_operand" "d")]
"<xsave>\t%0"
[(set_attr "type" "other")
(set_attr "memory" "store")
+ (set_attr "addr" "gpr16")
(set (attr "length")
(symbol_ref "ix86_attr_length_address_default (insn) + 4"))])
(define_insn "<xrstor>_rex64"
[(unspec_volatile:BLK
- [(match_operand:BLK 0 "memory_operand" "m")
+ [(match_operand:BLK 0 "memory_operand" "jm")
(match_operand:SI 1 "register_operand" "a")
(match_operand:SI 2 "register_operand" "d")]
ANY_XRSTOR)]
"<xrstor>\t%0"
[(set_attr "type" "other")
(set_attr "memory" "load")
+ (set_attr "addr" "gpr16")
(set (attr "length")
(symbol_ref "ix86_attr_length_address_default (insn) + 3"))])
(define_insn "<xrstor>64"
[(unspec_volatile:BLK
- [(match_operand:BLK 0 "memory_operand" "m")
+ [(match_operand:BLK 0 "memory_operand" "jm")
(match_operand:SI 1 "register_operand" "a")
(match_operand:SI 2 "register_operand" "d")]
ANY_XRSTOR64)]
"<xrstor>64\t%0"
[(set_attr "type" "other")
(set_attr "memory" "load")
+ (set_attr "addr" "gpr16")
(set (attr "length")
(symbol_ref "ix86_attr_length_address_default (insn) + 4"))])
"TARGET_64BIT && TARGET_FSGSBASE"
"rd<fsgs>base\t%0"
[(set_attr "type" "other")
- (set_attr "prefix_extra" "2")])
+ (set_attr "prefix_0f" "1")
+ (set_attr "prefix_rep" "1")])
(define_insn "wr<fsgs>base<mode>"
[(unspec_volatile [(match_operand:SWI48 0 "register_operand" "r")]
"TARGET_64BIT && TARGET_FSGSBASE"
"wr<fsgs>base\t%0"
[(set_attr "type" "other")
- (set_attr "prefix_extra" "2")])
+ (set_attr "prefix_0f" "1")
+ (set_attr "prefix_rep" "1")])
(define_insn "ptwrite<mode>"
[(unspec_volatile [(match_operand:SWI48 0 "nonimmediate_operand" "rm")]
"TARGET_PTWRITE"
"ptwrite\t%0"
[(set_attr "type" "other")
- (set_attr "prefix_extra" "2")])
+ (set_attr "prefix_0f" "1")
+ (set_attr "prefix_rep" "1")])
(define_insn "@rdrand<mode>"
[(set (match_operand:SWI248 0 "register_operand" "=r")
"TARGET_RDRND"
"rdrand\t%0"
[(set_attr "type" "other")
- (set_attr "prefix_extra" "1")])
+ (set_attr "prefix_0f" "1")])
(define_insn "@rdseed<mode>"
[(set (match_operand:SWI248 0 "register_operand" "=r")
"TARGET_RDSEED"
"rdseed\t%0"
[(set_attr "type" "other")
- (set_attr "prefix_extra" "1")])
+ (set_attr "prefix_0f" "1")])
(define_expand "pause"
[(set (match_dup 0)
DONE;
})
+(define_insn "urdmsr"
+ [(set (match_operand:DI 0 "register_operand" "=r")
+ (unspec_volatile:DI
+ [(match_operand:DI 1 "x86_64_szext_nonmemory_operand" "reZ")]
+ UNSPECV_URDMSR))]
+ "TARGET_USER_MSR && TARGET_64BIT"
+ "urdmsr\t{%1, %0|%0, %1}"
+ [(set_attr "prefix" "vex")
+ (set_attr "type" "other")])
+
+(define_insn "uwrmsr"
+ [(unspec_volatile
+ [(match_operand:DI 0 "x86_64_szext_nonmemory_operand" "reZ")
+ (match_operand:DI 1 "register_operand" "r")]
+ UNSPECV_UWRMSR)]
+ "TARGET_USER_MSR && TARGET_64BIT"
+ "uwrmsr\t{%1, %0|%0, %1}"
+ [(set_attr "prefix" "vex")
+ (set_attr "type" "other")])
+
(include "mmx.md")
(include "sse.md")
(include "sync.md")
projects / thirdparty / gcc.git / blobdiff