;; load mode is DI result mode is clobber compare mode is CC extend is none
(define_insn_and_split "*ld_cmpdi_cr0_DI_clobber_CC_none"
[(set (match_operand:CC 2 "cc_reg_operand" "=x")
- (compare:CC (match_operand:DI 1 "ds_form_mem_operand" "m")
+ (compare:CC (match_operand:DI 1 "non_update_memory_operand" "YZ")
(match_operand:DI 3 "const_m1_to_1_operand" "n")))
(clobber (match_scratch:DI 0 "=r"))]
"(TARGET_P10_FUSION)"
;; load mode is DI result mode is clobber compare mode is CCUNS extend is none
(define_insn_and_split "*ld_cmpldi_cr0_DI_clobber_CCUNS_none"
[(set (match_operand:CCUNS 2 "cc_reg_operand" "=x")
- (compare:CCUNS (match_operand:DI 1 "ds_form_mem_operand" "m")
+ (compare:CCUNS (match_operand:DI 1 "non_update_memory_operand" "YZ")
(match_operand:DI 3 "const_0_to_1_operand" "n")))
(clobber (match_scratch:DI 0 "=r"))]
"(TARGET_P10_FUSION)"
;; load mode is DI result mode is DI compare mode is CC extend is none
(define_insn_and_split "*ld_cmpdi_cr0_DI_DI_CC_none"
[(set (match_operand:CC 2 "cc_reg_operand" "=x")
- (compare:CC (match_operand:DI 1 "ds_form_mem_operand" "m")
+ (compare:CC (match_operand:DI 1 "non_update_memory_operand" "YZ")
(match_operand:DI 3 "const_m1_to_1_operand" "n")))
(set (match_operand:DI 0 "gpc_reg_operand" "=r") (match_dup 1))]
"(TARGET_P10_FUSION)"
;; load mode is DI result mode is DI compare mode is CCUNS extend is none
(define_insn_and_split "*ld_cmpldi_cr0_DI_DI_CCUNS_none"
[(set (match_operand:CCUNS 2 "cc_reg_operand" "=x")
- (compare:CCUNS (match_operand:DI 1 "ds_form_mem_operand" "m")
+ (compare:CCUNS (match_operand:DI 1 "non_update_memory_operand" "YZ")
(match_operand:DI 3 "const_0_to_1_operand" "n")))
(set (match_operand:DI 0 "gpc_reg_operand" "=r") (match_dup 1))]
"(TARGET_P10_FUSION)"
;; load-cmpi fusion pattern generated by gen_ld_cmpi_p10
;; load mode is SI result mode is clobber compare mode is CC extend is none
-(define_insn_and_split "*lwa_cmpdi_cr0_SI_clobber_CC_none"
+(define_insn_and_split "*lwz_cmpwi_cr0_SI_clobber_CC_none"
[(set (match_operand:CC 2 "cc_reg_operand" "=x")
- (compare:CC (match_operand:SI 1 "ds_form_mem_operand" "m")
+ (compare:CC (match_operand:SI 1 "non_update_memory_operand" "m")
(match_operand:SI 3 "const_m1_to_1_operand" "n")))
(clobber (match_scratch:SI 0 "=r"))]
"(TARGET_P10_FUSION)"
- "lwa%X1 %0,%1\;cmpdi %2,%0,%3"
+ "lwz%X1 %0,%1\;cmpwi %2,%0,%3"
"&& reload_completed
&& (cc_reg_not_cr0_operand (operands[2], CCmode)
|| !address_is_non_pfx_d_or_x (XEXP (operands[1], 0),
- SImode, NON_PREFIXED_DS))"
+ SImode, NON_PREFIXED_D))"
[(set (match_dup 0) (match_dup 1))
(set (match_dup 2)
(compare:CC (match_dup 0) (match_dup 3)))]
;; load-cmpi fusion pattern generated by gen_ld_cmpi_p10
;; load mode is SI result mode is SI compare mode is CC extend is none
-(define_insn_and_split "*lwa_cmpdi_cr0_SI_SI_CC_none"
+(define_insn_and_split "*lwz_cmpwi_cr0_SI_SI_CC_none"
[(set (match_operand:CC 2 "cc_reg_operand" "=x")
- (compare:CC (match_operand:SI 1 "ds_form_mem_operand" "m")
+ (compare:CC (match_operand:SI 1 "non_update_memory_operand" "m")
(match_operand:SI 3 "const_m1_to_1_operand" "n")))
(set (match_operand:SI 0 "gpc_reg_operand" "=r") (match_dup 1))]
"(TARGET_P10_FUSION)"
- "lwa%X1 %0,%1\;cmpdi %2,%0,%3"
+ "lwz%X1 %0,%1\;cmpwi %2,%0,%3"
"&& reload_completed
&& (cc_reg_not_cr0_operand (operands[2], CCmode)
|| !address_is_non_pfx_d_or_x (XEXP (operands[1], 0),
- SImode, NON_PREFIXED_DS))"
+ SImode, NON_PREFIXED_D))"
[(set (match_dup 0) (match_dup 1))
(set (match_dup 2)
(compare:CC (match_dup 0) (match_dup 3)))]
;; load mode is SI result mode is EXTSI compare mode is CC extend is sign
(define_insn_and_split "*lwa_cmpdi_cr0_SI_EXTSI_CC_sign"
[(set (match_operand:CC 2 "cc_reg_operand" "=x")
- (compare:CC (match_operand:SI 1 "ds_form_mem_operand" "m")
+ (compare:CC (match_operand:SI 1 "non_update_memory_operand" "YZ")
(match_operand:SI 3 "const_m1_to_1_operand" "n")))
(set (match_operand:EXTSI 0 "gpc_reg_operand" "=r") (sign_extend:EXTSI (match_dup 1)))]
"(TARGET_P10_FUSION)"
""
[(set_attr "type" "fused_load_cmpi")
(set_attr "cost" "8")
+ (set_attr "sign_extend" "yes")
(set_attr "length" "8")])
;; load-cmpi fusion pattern generated by gen_ld_cmpi_p10
my $mempred = "non_update_memory_operand";
my $extend;
+ # We need to special case lwa. The prefixed_load_p function in rs6000.cc
+ # (which determines if a load instruction is prefixed) uses the fact that the
+ # register mode is different from the memory mode, and that the sign_extend
+ # attribute is set to use DS-form rules for the address instead of D-form.
+ # If the register size is the same, prefixed_load_p assumes we are doing a
+ # lwz. We change to use an lwz and word compare if we don't need to sign
+ # extend the SImode value. Otherwise if we need the value, we need to
+ # make sure the insn is marked as ds-form.
+ my $cmp_size_char = ($lmode eq "SI"
+ && $ccmode eq "CC"
+ && $result !~ /^EXT|^DI$/) ? "w" : "d";
+
if ($ccmode eq "CC") {
# ld and lwa are both DS-FORM.
- ($lmode =~ /^[SD]I$/) and $np = "NON_PREFIXED_DS";
- ($lmode =~ /^[SD]I$/) and $mempred = "ds_form_mem_operand";
+ ($lmode eq "DI") and $np = "NON_PREFIXED_DS";
+ ($lmode eq "SI" && $cmp_size_char eq "d") and $np = "NON_PREFIXED_DS";
} else {
if ($lmode eq "DI") {
# ld is DS-form, but lwz is not.
$np = "NON_PREFIXED_DS";
- $mempred = "ds_form_mem_operand";
}
}
my $cmpl = ($ccmode eq "CC") ? "" : "l";
- my $echr = ($ccmode eq "CC") ? "a" : "z";
+ my $echr = ($ccmode eq "CC" && $cmp_size_char eq "d") ? "a" : "z";
if ($lmode eq "DI") { $echr = ""; }
my $constpred = ($ccmode eq "CC") ? "const_m1_to_1_operand"
: "const_0_to_1_operand";
}
my $ldst = mode_to_ldst_char($lmode);
+
+ # DS-form addresses need YZ, and not m.
+ my $constraint = ($np eq "NON_PREFIXED_DS") ? "YZ" : "m";
print <<HERE;
;; load-cmpi fusion pattern generated by gen_ld_cmpi_p10
;; load mode is $lmode result mode is $result compare mode is $ccmode extend is $extend
-(define_insn_and_split "*l${ldst}${echr}_cmp${cmpl}di_cr0_${lmode}_${result}_${ccmode}_${extend}"
+(define_insn_and_split "*l${ldst}${echr}_cmp${cmpl}${cmp_size_char}i_cr0_${lmode}_${result}_${ccmode}_${extend}"
[(set (match_operand:${ccmode} 2 "cc_reg_operand" "=x")
- (compare:${ccmode} (match_operand:${lmode} 1 "${mempred}" "m")
+ (compare:${ccmode} (match_operand:${lmode} 1 "${mempred}" "${constraint}")
HERE
print " " if $ccmode eq "CCUNS";
print <<HERE;
print <<HERE;
"(TARGET_P10_FUSION)"
- "l${ldst}${echr}%X1 %0,%1\\;cmp${cmpl}di %2,%0,%3"
+ "l${ldst}${echr}%X1 %0,%1\\;cmp${cmpl}${cmp_size_char}i %2,%0,%3"
"&& reload_completed
&& (cc_reg_not_cr0_operand (operands[2], CCmode)
|| !address_is_non_pfx_d_or_x (XEXP (operands[1], 0),
""
[(set_attr "type" "fused_load_cmpi")
(set_attr "cost" "8")
+HERE
+
+ if ($lmode eq "SI" && $ccmode eq "CC" && $cmp_size_char eq "d") {
+ # prefixed_load_p needs the sign_extend attribute to validate lwa as a
+ # DS-form instruction instead of D-form.
+ print " (set_attr \"sign_extend\" \"yes\")\n";
+ }
+
+ print <<HERE
(set_attr "length" "8")])
HERE
return INTVAL (offset) % 4 == 0;
})
-;; Return 1 if the operand is a memory operand that has a valid address for
-;; a DS-form instruction. I.e. the address has to be either just a register,
-;; or register + const where the two low order bits of const are zero.
-(define_predicate "ds_form_mem_operand"
- (match_code "subreg,mem")
-{
- if (!any_memory_operand (op, mode))
- return false;
-
- rtx addr = XEXP (op, 0);
-
- return address_to_insn_form (addr, mode, NON_PREFIXED_DS) == INSN_FORM_DS;
-})
-
;; Return 1 if the operand, used inside a MEM, is a SYMBOL_REF.
(define_predicate "symbol_ref_operand"
(and (match_code "symbol_ref")
;; Whether this insn has a prefixed form and a non-prefixed form.
(define_attr "maybe_prefixed" "no,yes"
(if_then_else (eq_attr "type" "load,fpload,vecload,store,fpstore,vecstore,
- integer,add")
+ integer,add,fused_load_cmpi")
(const_string "yes")
(const_string "no")))
(eq_attr "maybe_prefixed" "no"))
(const_string "no")
- (eq_attr "type" "load,fpload,vecload")
+ (eq_attr "type" "load,fpload,vecload,fused_load_cmpi")
(if_then_else (match_test "prefixed_load_p (insn)")
(const_string "yes")
(const_string "no"))
--- /dev/null
+/* { dg-do assemble } */
+/* { dg-require-effective-target lp64 } */
+/* { dg-require-effective-target power10_ok } */
+/* { dg-require-effective-target powerpc_prefixed_addr } */
+/* { dg-options "-O2 -mdejagnu-cpu=power10 -fstack-protector" } */
+
+/* PR target/105324. Test that power10 fusion does not generate an LWA/CMPDI
+ with a large offset that the assembler rejects. Instead it should a
+ PLWZ/CMPWI combination.
+
+ Originally, the code was dying because the fusion load + compare -1/0/1
+ patterns did not handle the possibility that the load might be prefixed.
+ The -fstack-protector option is needed to show the bug. */
+
+struct Ath__array1D {
+ int _current;
+ int getCnt() { return _current; }
+};
+struct extMeasure {
+ int _mapTable[10000];
+ Ath__array1D _metRCTable;
+};
+void measureRC() {
+ extMeasure m;
+ for (; m._metRCTable.getCnt();)
+ for (;;)
+ ;
+}
TEST(int8_t)
/* { dg-final { scan-assembler-times "lbz_cmpldi_cr0_QI_clobber_CCUNS_zero" 4 { target lp64 } } } */
-/* { dg-final { scan-assembler-times "ld_cmpdi_cr0_DI_DI_CC_none" 4 { target lp64 } } } */
-/* { dg-final { scan-assembler-times "ld_cmpdi_cr0_DI_clobber_CC_none" 4 { target lp64 } } } */
-/* { dg-final { scan-assembler-times "ld_cmpldi_cr0_DI_DI_CCUNS_none" 1 { target lp64 } } } */
-/* { dg-final { scan-assembler-times "ld_cmpldi_cr0_DI_clobber_CCUNS_none" 1 { target lp64 } } } */
+/* { dg-final { scan-assembler-times "ld_cmpdi_cr0_DI_DI_CC_none" 24 { target lp64 } } } */
+/* { dg-final { scan-assembler-times "ld_cmpdi_cr0_DI_clobber_CC_none" 8 { target lp64 } } } */
+/* { dg-final { scan-assembler-times "ld_cmpldi_cr0_DI_DI_CCUNS_none" 2 { target lp64 } } } */
+/* { dg-final { scan-assembler-times "ld_cmpldi_cr0_DI_clobber_CCUNS_none" 2 { target lp64 } } } */
/* { dg-final { scan-assembler-times "lha_cmpdi_cr0_HI_clobber_CC_sign" 16 { target lp64 } } } */
/* { dg-final { scan-assembler-times "lhz_cmpldi_cr0_HI_clobber_CCUNS_zero" 4 { target lp64 } } } */
/* { dg-final { scan-assembler-times "lwa_cmpdi_cr0_SI_EXTSI_CC_sign" 0 { target lp64 } } } */
-/* { dg-final { scan-assembler-times "lwa_cmpdi_cr0_SI_clobber_CC_none" 4 { target lp64 } } } */
+/* { dg-final { scan-assembler-times "lwz_cmpwi_cr0_SI_clobber_CC_none" 8 { target lp64 } } } */
+/* { dg-final { scan-assembler-times "lwz_cmpwi_cr0_SI_SI_CC_none" 8 { target lp64 } } } */
/* { dg-final { scan-assembler-times "lwz_cmpldi_cr0_SI_EXTSI_CCUNS_zero" 0 { target lp64 } } } */
+/* { dg-final { scan-assembler-times "lwz_cmpldi_cr0_SI_SI_CCUNS_none" 2 { target lp64 } } } */
/* { dg-final { scan-assembler-times "lwz_cmpldi_cr0_SI_clobber_CCUNS_none" 2 { target lp64 } } } */
/* { dg-final { scan-assembler-times "lbz_cmpldi_cr0_QI_clobber_CCUNS_zero" 2 { target ilp32 } } } */
/* { dg-final { scan-assembler-times "lha_cmpdi_cr0_HI_clobber_CC_sign" 8 { target ilp32 } } } */
/* { dg-final { scan-assembler-times "lhz_cmpldi_cr0_HI_clobber_CCUNS_zero" 2 { target ilp32 } } } */
/* { dg-final { scan-assembler-times "lwa_cmpdi_cr0_SI_EXTSI_CC_sign" 0 { target ilp32 } } } */
-/* { dg-final { scan-assembler-times "lwa_cmpdi_cr0_SI_clobber_CC_none" 9 { target ilp32 } } } */
+/* { dg-final { scan-assembler-times "lwz_cmpwi_cr0_SI_SI_CC_none" 36 { target ilp32 } } } */
+/* { dg-final { scan-assembler-times "lwz_cmpwi_cr0_SI_clobber_CC_none" 16 { target ilp32 } } } */
/* { dg-final { scan-assembler-times "lwz_cmpldi_cr0_SI_EXTSI_CCUNS_zero" 0 { target ilp32 } } } */
/* { dg-final { scan-assembler-times "lwz_cmpldi_cr0_SI_clobber_CCUNS_none" 6 { target ilp32 } } } */
+/* { dg-final { scan-assembler-times "lwz_cmpldi_cr0_SI_SI_CCUNS_none" 2 { target ilp32 } } } */