From: Kong Lingling Date: Fri, 19 May 2023 02:50:29 +0000 (+0800) Subject: [APX NDD] Support APX NDD for or/xor insn X-Git-Tag: basepoints/gcc-15~3890 X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=c95f67b8966dff4f7b22e794e410c5aa7490877a;p=thirdparty%2Fgcc.git [APX NDD] Support APX NDD for or/xor insn Similar to AND insn, two splitters need to be adjusted to prevent misoptimizaiton for NDD OR/XOR. Also adjust *one_cmplsi2_2_zext and its corresponding splitter that will generate xor insn. gcc/ChangeLog: * config/i386/i386.md (3): Add new alternative for NDD and adjust output templates. (*_1): Likewise. (*qi_1): Likewise. (*notxor_1): Likewise. (*si_1_zext): Likewise. (*notxorqi_1): Likewise. (*_2): Likewise. (*si_2_zext): Likewise. (*si_2_zext_imm): Likewise. (*si_1_zext_imm): Likewise, and use nonimmediate_operand for operands[1] to accept memory input for NDD alternative. (*one_cmplsi2_2_zext): Likewise. (define_split for *one_cmplsi2_2_zext): Use nonimmediate_operand for operands[3]. (*3_doubleword): Add NDD constraints, adopt '&' to NDD dest and emit move for optimized case if operands[0] != operands[1] or operands[4] != operands[5]. (define_split for QI highpart OR/XOR): Prohibit splitter to split NDD form OR/XOR insn to qi_ext_3. (define_split for QI strict_lowpart optimization): Prohibit splitter to split NDD form AND insn to *3_1_slp. gcc/testsuite/ChangeLog: * gcc.target/i386/apx-ndd.c: Add or and xor test. --- diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md index d2528e0dcf6c..ad4c958a1e84 100644 --- a/gcc/config/i386/i386.md +++ b/gcc/config/i386/i386.md @@ -12703,17 +12703,19 @@ && !x86_64_hilo_general_operand (operands[2], mode)) operands[2] = force_reg (mode, operands[2]); - ix86_expand_binary_operator (, mode, operands); + ix86_expand_binary_operator (, mode, operands, + TARGET_APX_NDD); DONE; }) (define_insn_and_split "*3_doubleword" - [(set (match_operand: 0 "nonimmediate_operand" "=ro,r") + [(set (match_operand: 0 "nonimmediate_operand" "=ro,r,&r,&r") (any_or: - (match_operand: 1 "nonimmediate_operand" "%0,0") - (match_operand: 2 "x86_64_hilo_general_operand" "r,o"))) + (match_operand: 1 "nonimmediate_operand" "%0,0,ro,r") + (match_operand: 2 "x86_64_hilo_general_operand" "r,o,r,o"))) (clobber (reg:CC FLAGS_REG))] - "ix86_binary_operator_ok (, mode, operands)" + "ix86_binary_operator_ok (, mode, operands, + TARGET_APX_NDD)" "#" "&& reload_completed" [(const_int:DWIH 0)] @@ -12725,20 +12727,29 @@ split_double_mode (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 ( == IOR) emit_move_insn (operands[0], constm1_rtx); else - ix86_expand_unary_operator (NOT, mode, &operands[0]); + ix86_expand_unary_operator (NOT, mode, &operands[0], + TARGET_APX_NDD); } else - ix86_expand_binary_operator (, mode, &operands[0]); + ix86_expand_binary_operator (, 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) @@ -12746,37 +12757,43 @@ if ( == IOR) emit_move_insn (operands[3], constm1_rtx); else - ix86_expand_unary_operator (NOT, mode, &operands[3]); + ix86_expand_unary_operator (NOT, mode, &operands[3], + TARGET_APX_NDD); } else - ix86_expand_binary_operator (, mode, &operands[3]); + ix86_expand_binary_operator (, mode, &operands[3], + TARGET_APX_NDD); DONE; -}) +} +[(set_attr "isa" "*,*,apx_ndd,apx_ndd")]) (define_insn "*_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 "" "r,,k"))) + (match_operand:SWI248 1 "nonimmediate_operand" "%0,0,rm,r,k") + (match_operand:SWI248 2 "" "r,,r,,k"))) (clobber (reg:CC FLAGS_REG))] - "ix86_binary_operator_ok (, mode, operands)" + "ix86_binary_operator_ok (, mode, operands, + TARGET_APX_NDD)" "@ {}\t{%2, %0|%0, %2} {}\t{%2, %0|%0, %2} + {}\t{%2, %1, %0|%0, %1, %2} + {}\t{%2, %1, %0|%0, %1, %2} #" - [(set_attr "isa" "*,*,") - (set_attr "type" "alu, alu, msklog") + [(set_attr "isa" "*,*,apx_ndd,apx_ndd,") + (set_attr "type" "alu, alu, alu, alu, msklog") (set_attr "mode" "")]) (define_insn_and_split "*notxor_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 "" "r,,k")))) + (match_operand:SWI248 1 "nonimmediate_operand" "%0,0,rm,r,k") + (match_operand:SWI248 2 "" "r,,r,,k")))) (clobber (reg:CC FLAGS_REG))] - "ix86_binary_operator_ok (XOR, mode, operands)" + "ix86_binary_operator_ok (XOR, mode, operands, TARGET_APX_NDD)" "#" "&& reload_completed" [(parallel @@ -12792,8 +12809,8 @@ DONE; } } - [(set_attr "isa" "*,*,") - (set_attr "type" "alu, alu, msklog") + [(set_attr "isa" "*,*,apx_ndd,apx_ndd,") + (set_attr "type" "alu, alu, alu, alu, msklog") (set_attr "mode" "")]) (define_insn_and_split "*iordi_1_bts" @@ -12881,44 +12898,55 @@ ;; See comment for addsi_1_zext why we do use nonimmediate_operand (define_insn "*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 (, SImode, operands)" - "{l}\t{%2, %k0|%k0, %2}" + "TARGET_64BIT && ix86_binary_operator_ok (, SImode, operands, + TARGET_APX_NDD)" + "@ + {l}\t{%2, %k0|%k0, %2} + {l}\t{%2, %1, %k0|%k0, %1, %2} + {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 "*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 (, SImode, operands)" - "{l}\t{%2, %k0|%k0, %2}" + "TARGET_64BIT && ix86_binary_operator_ok (, SImode, operands, + TARGET_APX_NDD)" + "@ + {l}\t{%2, %k0|%k0, %2} + {l}\t{%2, %1, %k0|%k0, %1, %2}" [(set_attr "type" "alu") + (set_attr "isa" "*,apx_ndd") (set_attr "mode" "SI")]) (define_insn "*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 (, QImode, operands)" + "ix86_binary_operator_ok (, QImode, operands, TARGET_APX_NDD)" "@ {b}\t{%2, %0|%0, %2} {b}\t{%2, %0|%0, %2} {l}\t{%k2, %k0|%k0, %k2} + {b}\t{%2, %1, %0|%0, %1, %2} + {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") ] @@ -12930,12 +12958,12 @@ (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 @@ -12951,12 +12979,12 @@ 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") ] @@ -13004,44 +13032,59 @@ (define_insn "*_2" [(set (reg FLAGS_REG) (compare (any_or:SWI - (match_operand:SWI 1 "nonimmediate_operand" "%0,0") - (match_operand:SWI 2 "" ",")) + (match_operand:SWI 1 "nonimmediate_operand" "%0,0,rm,r") + (match_operand:SWI 2 "" ",,r,")) (const_int 0))) - (set (match_operand:SWI 0 "nonimmediate_operand" "=m,") + (set (match_operand:SWI 0 "nonimmediate_operand" "=m,,r,r") (any_or:SWI (match_dup 1) (match_dup 2)))] "ix86_match_ccmode (insn, CCNOmode) - && ix86_binary_operator_ok (, mode, operands)" - "{}\t{%2, %0|%0, %2}" + && ix86_binary_operator_ok (, mode, operands, + TARGET_APX_NDD)" + "@ + {}\t{%2, %0|%0, %2} + {}\t{%2, %0|%0, %2} + {}\t{%2, %1, %0|%0, %1, %2} + {}\t{%2, %1, %0|%0, %1, %2}" [(set_attr "type" "alu") + (set_attr "isa" "*,*,apx_ndd,apx_ndd") (set_attr "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 "*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 (, SImode, operands)" - "{l}\t{%2, %k0|%k0, %2}" + && ix86_binary_operator_ok (, SImode, operands, + TARGET_APX_NDD)" + "@ + {l}\t{%2, %k0|%k0, %2} + {l}\t{%2, %1, %k0|%k0, %1, %2} + {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 "*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 (, SImode, operands)" - "{l}\t{%2, %k0|%k0, %2}" + && ix86_binary_operator_ok (, SImode, operands, + TARGET_APX_NDD)" + "@ + {l}\t{%2, %k0|%k0, %2} + {l}\t{%2, %1, %k0|%k0, %1, %2}" [(set_attr "type" "alu") + (set_attr "isa" "*,apx_ndd") (set_attr "mode" "SI")]) (define_insn "*_3" @@ -13062,6 +13105,7 @@ ;; 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") @@ -13069,7 +13113,8 @@ (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) @@ -13107,7 +13152,9 @@ "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))) @@ -14173,20 +14220,21 @@ (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))))] diff --git a/gcc/testsuite/gcc.target/i386/apx-ndd.c b/gcc/testsuite/gcc.target/i386/apx-ndd.c index be436d57bdfb..d97648c876d4 100644 --- a/gcc/testsuite/gcc.target/i386/apx-ndd.c +++ b/gcc/testsuite/gcc.target/i386/apx-ndd.c @@ -94,6 +94,24 @@ FOO (int, and, &) FOO1 (int, and, &) FOO (long, and, &) FOO1 (long, and, &) + +FOO (char, or, |) +FOO1 (char, or, |) +FOO (short, or, |) +FOO1 (short, or, |) +FOO (int, or, |) +FOO1 (int, or, |) +FOO (long, or, |) +FOO1 (long, or, |) + +FOO (char, xor, ^) +FOO1 (char, xor, ^) +FOO (short, xor, ^) +FOO1 (short, xor, ^) +FOO (int, xor, ^) +FOO1 (int, xor, ^) +FOO (long, xor, ^) +FOO1 (long, xor, ^) /* { dg-final { scan-assembler-times "add(?:b|l|w|q)\[^\n\r]*1, \\(%rdi\\), %(?:|r|e)a(?:x|l)" 4 } } */ /* { dg-final { scan-assembler-times "lea(?:l|q)\[^\n\r]\\(%r(?:d|s)i,%r(?:d|s)i\\), %(?:|r|e)ax" 4 } } */ /* { dg-final { scan-assembler-times "add(?:b|l|w|q)\[^\n\r]%(?:|r|e)si(?:|l), \\(%rdi\\), %(?:|r|e)a(?:x|l)" 4 } } */ @@ -108,3 +126,11 @@ FOO1 (long, and, &) /* { dg-final { scan-assembler-times "and(?:l|w|q)\[^\n\r]*1, \\(%rdi\\), %(?:|r|e)ax" 3 } } */ /* { dg-final { scan-assembler-times "and(?:l|w|q)\[^\n\r]%(?:|r|e)di, %(?:|r|e)si, %(?:|r|e)ax" 2 } } */ /* { dg-final { scan-assembler-times "and(?:l|w|q)\[^\n\r]%(?:|r|e)si, %(?:|r|e)di, %(?:|r|e)ax" 2 } } */ +/* { dg-final { scan-assembler-times "orb\[^\n\r]*1, \\(%rdi\\), %al" 2} } */ +/* { dg-final { scan-assembler-times "or(?:l|w|q)\[^\n\r]*1, \\(%rdi\\), %(?:|r|e)ax" 6 } } */ +/* { dg-final { scan-assembler-times "or(?:l|w|q)\[^\n\r]%(?:|r|e)di, %(?:|r|e)si, %(?:|r|e)ax" 4 } } */ +/* { dg-final { scan-assembler-times "or(?:l|w|q)\[^\n\r]%(?:|r|e)si, %(?:|r|e)di, %(?:|r|e)ax" 4 } } */ +/* { dg-final { scan-assembler-times "xorb\[^\n\r]*1, \\(%rdi\\), %al" 1 } } */ +/* { dg-final { scan-assembler-times "xor(?:l|w|q)\[^\n\r]*1, \\(%rdi\\), %(?:|r|e)ax" 3 } } */ +/* { dg-final { scan-assembler-times "xor(?:l|w|q)\[^\n\r]%(?:|r|e)di, %(?:|r|e)si, %(?:|r|e)ax" 2 } } */ +/* { dg-final { scan-assembler-times "xor(?:l|w|q)\[^\n\r]%(?:|r|e)si, %(?:|r|e)di, %(?:|r|e)ax" 2 } } */