From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: by sourceware.org (Postfix, from userid 7888) id 0F60F3858004; Fri, 21 Oct 2022 02:50:01 +0000 (GMT) DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 0F60F3858004 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gcc.gnu.org; s=default; t=1666320601; bh=xjEhohg56AdlIF0mvz9r74sFgrarS6FDYDm74FTPmAU=; h=From:To:Subject:Date:From; b=iCgyEH1tjNM1W5irZ2pLTCcF4iapF1lSj0BGWaODSZTYhwwDxttvQEr/2WPU5VumS nqtM+9YcS/MsAw1v1RatHVkc75VqXpWcYpSCR/RcsveVEZhiGfJWs7r+2gAV/aIUi6 p22LQXikkdef70GLlQY18XcQb4a5iNi2/d/B3K3c= MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Content-Type: text/plain; charset="utf-8" From: Haochen Jiang To: gcc-cvs@gcc.gnu.org Subject: [gcc r13-3425] i386: Auto vectorize sdot_prod, udot_prod with VNNIINT8 instruction. X-Act-Checkin: gcc X-Git-Author: Haochen Jiang X-Git-Refname: refs/heads/master X-Git-Oldrev: 406675947d26ccbc2108e9689a2918bb36f61a63 X-Git-Newrev: 4e7ec7dbbbef3b4a83da5967b5f25e3be90c2dc6 Message-Id: <20221021025001.0F60F3858004@sourceware.org> Date: Fri, 21 Oct 2022 02:50:01 +0000 (GMT) List-Id: https://gcc.gnu.org/g:4e7ec7dbbbef3b4a83da5967b5f25e3be90c2dc6 commit r13-3425-g4e7ec7dbbbef3b4a83da5967b5f25e3be90c2dc6 Author: Haochen Jiang Date: Thu May 26 15:46:40 2022 +0800 i386: Auto vectorize sdot_prod, udot_prod with VNNIINT8 instruction. gcc/ChangeLog: * config/i386/sse.md (ssedvecmode): Rename from VI1SI. (ssedvecmodelower): Rename from vi1si. (sdot_prod): New define_expand. (udot_prod): Ditto. gcc/testsuite/ChangeLog: * gcc.target/i386/vnniint8-auto-vectorize-1.c: New test. * gcc.target/i386/vnniint8-auto-vectorize-2.c: Ditto. Diff: --- gcc/config/i386/sse.md | 61 ++++++++++++++---- .../gcc.target/i386/vnniint8-auto-vectorize-1.c | 28 ++++++++ .../gcc.target/i386/vnniint8-auto-vectorize-2.c | 75 ++++++++++++++++++++++ 3 files changed, 153 insertions(+), 11 deletions(-) diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md index 014b0b220bd..f4b5506703f 100644 --- a/gcc/config/i386/sse.md +++ b/gcc/config/i386/sse.md @@ -1035,6 +1035,13 @@ (V16HI "v16hi") (V8HI "v8hi") (V32QI "v32qi") (V16QI "v16qi")]) +;; Mapping of vector modes to an V*SImode of the same size +(define_mode_attr ssedvecmode + [(V64QI "V16SI") (V32QI "V8SI") (V16QI "V4SI")]) + +(define_mode_attr ssedvecmodelower + [(V64QI "v16si") (V32QI "v8si") (V16QI "v4si")]) + ;; Mapping of vector modes to a vector mode of double size (define_mode_attr ssedoublevecmode [(V64QI "V128QI") (V32HI "V64HI") (V16SI "V32SI") (V8DI "V16DI") @@ -28509,29 +28516,23 @@ [(set_attr ("prefix") ("evex")) (set_attr "mode" "")]) -(define_mode_attr VI1SI - [(V64QI "V16SI") (V32QI "V8SI") (V16QI "V4SI")]) - -(define_mode_attr vi1si - [(V64QI "v16si") (V32QI "v8si") (V16QI "v4si")]) - (define_expand "usdot_prod" - [(match_operand: 0 "register_operand") + [(match_operand: 0 "register_operand") (match_operand:VI1_AVX512VNNI 1 "register_operand") (match_operand:VI1_AVX512VNNI 2 "register_operand") - (match_operand: 3 "register_operand")] + (match_operand: 3 "register_operand")] "( == 64 ||((TARGET_AVX512VNNI && TARGET_AVX512VL) || TARGET_AVXVNNI))" { - operands[1] = lowpart_subreg (mode, + operands[1] = lowpart_subreg (mode, force_reg (mode, operands[1]), mode); - operands[2] = lowpart_subreg (mode, + operands[2] = lowpart_subreg (mode, force_reg (mode, operands[2]), mode); emit_insn (gen_rtx_SET (operands[0], operands[3])); - emit_insn (gen_vpdpbusd_ (operands[0], operands[3], + emit_insn (gen_vpdpbusd_ (operands[0], operands[3], operands[1], operands[2])); DONE; }) @@ -29256,6 +29257,44 @@ (UNSPEC_VPDPBSUD "bsud") (UNSPEC_VPDPBSUDS "bsuds") (UNSPEC_VPDPBUUD "buud") (UNSPEC_VPDPBUUDS "buuds")]) +(define_expand "sdot_prod" + [(match_operand: 0 "register_operand") + (match_operand:VI1 1 "register_operand") + (match_operand:VI1 2 "register_operand") + (match_operand: 3 "register_operand")] + "TARGET_AVXVNNIINT8" +{ + operands[1] = lowpart_subreg (mode, + force_reg (mode, operands[1]), + mode); + operands[2] = lowpart_subreg (mode, + force_reg (mode, operands[2]), + mode); + emit_insn (gen_rtx_SET (operands[0], operands[3])); + emit_insn (gen_vpdpbssd_ (operands[0], operands[3], + operands[1], operands[2])); + DONE; +}) + +(define_expand "udot_prod" + [(match_operand: 0 "register_operand") + (match_operand:VI1 1 "register_operand") + (match_operand:VI1 2 "register_operand") + (match_operand: 3 "register_operand")] + "TARGET_AVXVNNIINT8" +{ + operands[1] = lowpart_subreg (mode, + force_reg (mode, operands[1]), + mode); + operands[2] = lowpart_subreg (mode, + force_reg (mode, operands[2]), + mode); + emit_insn (gen_rtx_SET (operands[0], operands[3])); + emit_insn (gen_vpdpbuud_ (operands[0], operands[3], + operands[1], operands[2])); + DONE; +}) + (define_insn "vpdp_" [(set (match_operand:VI4_AVX 0 "register_operand" "=x") (unspec:VI4_AVX diff --git a/gcc/testsuite/gcc.target/i386/vnniint8-auto-vectorize-1.c b/gcc/testsuite/gcc.target/i386/vnniint8-auto-vectorize-1.c new file mode 100644 index 00000000000..9cadab6a845 --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/vnniint8-auto-vectorize-1.c @@ -0,0 +1,28 @@ +/* { dg-do compile } */ +/* { dg-options "-mavxvnniint8 -O2" } */ +/* { dg-final { scan-assembler "vpdpbssd\t" } } */ +/* { dg-final { scan-assembler "vpdpbuud\t" } } */ + +int __attribute__((noinline, noclone, optimize("tree-vectorize"))) +sdot_prod_qi (char * restrict a, char * restrict b, + int c, int n) +{ + int i; + for (i = 0; i < n; i++) + { + c += ((int) a[i] * (int) b[i]); + } + return c; +} + +int __attribute__((noinline, noclone, optimize("tree-vectorize"))) +udot_prod_qi (unsigned char * restrict a, unsigned char *restrict b, + int c, int n) +{ + int i; + for (i = 0; i < n; i++) + { + c += ((int) a[i] * (int) b[i]); + } + return c; +} diff --git a/gcc/testsuite/gcc.target/i386/vnniint8-auto-vectorize-2.c b/gcc/testsuite/gcc.target/i386/vnniint8-auto-vectorize-2.c new file mode 100644 index 00000000000..99853e6c3b7 --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/vnniint8-auto-vectorize-2.c @@ -0,0 +1,75 @@ +/* { dg-do run } */ +/* { dg-options "-O2 -mavxvnniint8" } */ +/* { dg-require-effective-target avxvnniint8 } */ + +#define AVXVNNIINT8 +#ifndef CHECK +#define CHECK "avx-check.h" +#endif + +#ifndef TEST +#define TEST avx_test +#endif + +#include CHECK +#include "vnniint8-auto-vectorize-1.c" + +#define N 256 +char a_i8[N], b_i8[N]; +unsigned char c_u8[N], d_u8[N]; +int i8_exp, i8_ref; + +int __attribute__((noipa, optimize("no-tree-vectorize"))) +sdot_prod_qi_scalar (char * restrict a, char * restrict b, + int c, int n) +{ + int i; + for (i = 0; i < n; i++) + { + c += ((int) a[i] * (int) b[i]); + } + return c; +} + +int __attribute__((noipa, optimize("no-tree-vectorize"))) +udot_prod_qi_scalar (unsigned char * restrict a, unsigned char *restrict b, + int c, int n) +{ + int i; + for (i = 0; i < n; i++) + { + c += ((int) a[i] * (int) b[i]); + } + return c; +} + +void init () +{ + int i; + + i8_exp = i8_ref = 127; + + for (i = 0; i < N; i++) + { + a_i8[i] = (-i + 4) % 128; + b_i8[i] = (i + 1) % 128; + c_u8[i] = (i + 3) % 256; + d_u8[i] = (i + 5) % 256; + } +} + +void +TEST (void) +{ + init (); + i8_exp = sdot_prod_qi (a_i8, b_i8, i8_exp, N); + i8_ref = sdot_prod_qi_scalar (a_i8, b_i8, i8_ref, N); + if (i8_exp != i8_ref) + abort (); + + init (); + i8_exp = udot_prod_qi (c_u8, d_u8, i8_exp, N); + i8_ref = udot_prod_qi_scalar (c_u8, d_u8, i8_ref, N); + if (i8_exp != i8_ref) + abort (); +}