[06/16,APX,NDD] Support APX NDD for sub insns

Message ID	20231115094705.3976553-7-hongyu.wang@intel.com
State	New
Headers	show Return-Path: <gcc-patches-bounces+incoming=patchwork.ozlabs.org@gcc.gnu.org> DMARC-Filter: OpenDMARC Filter v1.4.2 sourceware.org 55A263858427 From: Hongyu Wang <hongyu.wang@intel.com> To: gcc-patches@gcc.gnu.org Cc: ubizjak@gmail.com, hongtao.liu@intel.com, Kong Lingling <lingling.kong@intel.com> Subject: [PATCH 06/16] [APX NDD] Support APX NDD for sub insns Date: Wed, 15 Nov 2023 17:46:55 +0800 Message-Id: <20231115094705.3976553-7-hongyu.wang@intel.com> In-Reply-To: <20231115094705.3976553-1-hongyu.wang@intel.com> References: <20231115094705.3976553-1-hongyu.wang@intel.com> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Precedence: list Errors-To: gcc-patches-bounces+incoming=patchwork.ozlabs.org@gcc.gnu.org
Series	Support Intel APX NDD \| expand [00/16] Support Intel APX NDD [01/16,APX,NDD] Support Intel APX NDD for legacy add insn [02/16,APX,NDD] Restrict TImode register usage when NDD enabled [03/16,APX,NDD] Support APX NDD for optimization patterns of add [04/16,APX,NDD] Disable seg_prefixed memory usage for NDD add [05/16,APX,NDD] Support APX NDD for adc insns [06/16,APX,NDD] Support APX NDD for sub insns [07/16,APX,NDD] Support APX NDD for sbb insn [08/16,APX,NDD] Support APX NDD for neg insn [09/16,APX,NDD] Support APX NDD for not insn [10/16,APX,NDD] Support APX NDD for and insn [11/16,APX,NDD] Support APX NDD for or/xor insn [12/16,APX,NDD] Support APX NDD for left shift insns [13/16,APX,NDD] Support APX NDD for right shift insns [14/16,APX,NDD] Support APX NDD for rotate insns [15/16,APX,NDD] Support APX NDD for shld/shrd insns [16/16,APX,NDD] Support APX NDD for cmove insns

diff --git a/gcc/config/i386/i386-expand.cc b/gcc/config/i386/i386-expand.cc index ea0e5881087..e5f75875e3b 100644 --- a/gcc/config/i386/i386-expand.cc +++ b/gcc/config/i386/i386-expand.cc @@ -1270,6 +1270,7 @@ bool ix86_can_use_ndd_p (enum rtx_code code) switch (code) { case PLUS: + case MINUS: return true; default: return false; @@ -1342,9 +1343,10 @@ ix86_fixup_binary_operands (enum rtx_code code, machine_mode mode, void ix86_fixup_binary_operands_no_copy (enum rtx_code code, - machine_mode mode, rtx operands[]) + machine_mode mode, rtx operands[], + bool use_ndd) { - rtx dst = ix86_fixup_binary_operands (code, mode, operands); + rtx dst = ix86_fixup_binary_operands (code, mode, operands, use_ndd); gcc_assert (dst == operands[0]); } diff --git a/gcc/config/i386/i386-protos.h b/gcc/config/i386/i386-protos.h index 5d902e2925b..ad895fac72d 100644 --- a/gcc/config/i386/i386-protos.h +++ b/gcc/config/i386/i386-protos.h @@ -111,7 +111,7 @@ extern void ix86_expand_vector_move_misalign (machine_mode, rtx[]); extern rtx ix86_fixup_binary_operands (enum rtx_code, machine_mode, rtx[], bool = false); extern void ix86_fixup_binary_operands_no_copy (enum rtx_code, - machine_mode, rtx[]); + machine_mode, rtx[], bool = false); extern void ix86_expand_binary_operator (enum rtx_code, machine_mode, rtx[], bool = false); extern void ix86_expand_vector_logical_operator (enum rtx_code, diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md index f23859d1172..1aa8469d666 100644 --- a/gcc/config/i386/i386.md +++ b/gcc/config/i386/i386.md @@ -7637,7 +7637,8 @@ (define_expand "sub<mode>3" (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, + ix86_can_use_ndd_p (MINUS)); DONE;") (define_insn_and_split "*sub<dwi>3_doubleword" [(set (match_operand:<DWI> 0 "nonimmediate_operand" "=ro,r") @@ -7663,7 +7664,10 @@ (define_insn_and_split "*sub<dwi>3_doubleword" 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], + ix86_can_use_ndd_p (MINUS)); DONE; } }) @@ -7692,25 +7696,35 @@ (define_insn_and_split "*sub<dwi>3_doubleword_zext" "split_double_mode (<DWI>mode, &operands[0], 2, &operands[0], &operands[3]);") (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>i,r,r") (minus:SWI - (match_operand:SWI 1 "nonimmediate_operand" "0,0") - (match_operand:SWI 2 "<general_operand>" "<r>,<m>"))) + (match_operand:SWI 1 "nonimmediate_operand" "0,0,rm,r") + (match_operand:SWI 2 "<general_operand>" "<r>,<m>,r,<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, + ix86_can_use_ndd_p (MINUS))" + "@ + 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") (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 "register_operand" "0,r") + (match_operand:SI 2 "x86_64_general_operand" "rBMe,rBMe")))) (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, + ix86_can_use_ndd_p (MINUS))" + "@ + sub{l}\t{%2, %k0|%k0, %2} + sub{l}\t{%2, %1, %k0|%k0, %1, %2}" + [(set_attr "isa" "*,apx_ndd") + (set_attr "type" "alu") (set_attr "mode" "SI")]) ;; Alternative 1 is needed to work around LRA limitation, see PR82524. @@ -7738,31 +7752,41 @@ (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>,<m>")) + (match_operand:SWI 1 "nonimmediate_operand" "0,0,rm,r") + (match_operand:SWI 2 "<general_operand>" "<r>,<m>,r,<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, + ix86_can_use_ndd_p (MINUS))" + "@ + 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 "register_operand" "0,r") + (match_operand:SI 2 "x86_64_general_operand" "rBMe,rBMe")) (const_int 0))) - (set (match_operand:DI 0 "register_operand" "=r") + (set (match_operand:DI 0 "register_operand" "=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, + ix86_can_use_ndd_p (MINUS))" + "@ + sub{l}\t{%2, %k0|%k0, %2} + sub{l}\t{%2, %1, %k0|%k0, %1, %2}" + [(set_attr "isa" "*,apx_ndd") + (set_attr "type" "alu") (set_attr "mode" "SI")]) (define_insn "*subqi_ext<mode>_0" @@ -7841,7 +7865,8 @@ (define_expand "subv<mode>4" (pc)))] "" { - ix86_fixup_binary_operands_no_copy (MINUS, <MODE>mode, operands); + ix86_fixup_binary_operands_no_copy (MINUS, <MODE>mode, operands, + ix86_can_use_ndd_p (MINUS)); if (CONST_SCALAR_INT_P (operands[2])) operands[4] = operands[2]; else @@ -7852,35 +7877,45 @@ (define_insn "*subv<mode>4" [(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, + ix86_can_use_ndd_p (MINUS))" + "@ + 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" ""))))) - (set (match_operand:SWI 0 "nonimmediate_operand" "=<r>m") + (match_operand:SWI 2 "x86_64_immediate_operand" ","))))) + (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, + ix86_can_use_ndd_p (MINUS)) && 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)") @@ -7976,6 +8011,8 @@ (define_insn_and_split "*subv<dwi>4_doubleword_1" 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; @@ -8057,18 +8094,25 @@ (define_expand "usubv<mode>4" (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, + ix86_can_use_ndd_p (MINUS));") (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>,<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>,<m>,r,<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, + ix86_can_use_ndd_p (MINUS))" + "@ + 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 @@ -8156,16 +8200,20 @@ (define_insn_and_split "*dec_cmov<mode>" (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 "register_operand" "0,r") + (match_operand:SI 2 "x86_64_general_operand" "rBMe,rBMe"))) + (set (match_operand:DI 0 "register_operand" "=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, + ix86_can_use_ndd_p (MINUS))" + "@ + sub{l}\t{%2, %1|%1, %2} + sub{l}\t{%2, %1, %0|%0, %1, %2}" + [(set_attr "isa" "*,apx_ndd") + (set_attr "type" "alu") (set_attr "mode" "SI")]) ;; Add with carry and subtract with borrow diff --git a/gcc/testsuite/gcc.target/i386/apx-ndd.c b/gcc/testsuite/gcc.target/i386/apx-ndd.c index 6c136174d24..9d444e0d830 100644 --- a/gcc/testsuite/gcc.target/i386/apx-ndd.c +++ b/gcc/testsuite/gcc.target/i386/apx-ndd.c @@ -42,3 +42,16 @@ FOO (long, add, +) FOO1 (long, add, +) FOO2 (long, add, +) +FOO (char, sub, -) +FOO1 (char, sub, -) +FOO (short, sub, -) +FOO1 (short, sub, -) +FOO (int, sub, -) +FOO1 (int, sub, -) +FOO (long, sub, -) +FOO1 (long, sub, -) +/* { dg-final { scan-assembler-times "add(?:l|w|q)\[^\n\r]*1, \\(%rdi\\), %(?:|r|e)ax" 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(?:l|w|q)\[^\n\r]%(?:|r|e)si, \\(%rdi\\), %(?:|r|e)ax" 4 } } */ +/* { dg-final { scan-assembler-times "sub(?:l|w|q)\[^\n\r]*1, \\(%rdi\\), %(?:|r|e)ax" 4 } } */ +/* { dg-final { scan-assembler-times "sub(?:l|w|q)\[^\n\r]%(?:|r|e)si, %(?:|r|e)di, %(?:|r|e)ax" 4 } } */

[06/16,APX,NDD] Support APX NDD for sub insns

Commit Message

Patch