From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: by sourceware.org (Postfix, from userid 2078) id 16E8A3858D39; Wed, 15 Sep 2021 08:38:35 +0000 (GMT) DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 16E8A3858D39 MIME-Version: 1.0 Content-Transfer-Encoding: 7bit Content-Type: text/plain; charset="utf-8" From: hongtao Liu To: gcc-cvs@gcc.gnu.org Subject: [gcc r12-3542] Output vextract{i, f}{32x4, 64x2} for (vec_select:(reg:Vmode) idx) when byte_offset of idx % 16 == 0. X-Act-Checkin: gcc X-Git-Author: liuhongt X-Git-Refname: refs/heads/master X-Git-Oldrev: 8b69c481fc86e04c6c83f3a49eef2760c175a8f2 X-Git-Newrev: 243e0a5b1942879bc005bf150a744e69a4fcdc87 Message-Id: <20210915083835.16E8A3858D39@sourceware.org> Date: Wed, 15 Sep 2021 08:38:35 +0000 (GMT) X-BeenThere: gcc-cvs@gcc.gnu.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Gcc-cvs mailing list List-Unsubscribe: , List-Archive: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 15 Sep 2021 08:38:35 -0000 https://gcc.gnu.org/g:243e0a5b1942879bc005bf150a744e69a4fcdc87 commit r12-3542-g243e0a5b1942879bc005bf150a744e69a4fcdc87 Author: liuhongt Date: Mon Sep 13 10:27:51 2021 +0800 Output vextract{i,f}{32x4,64x2} for (vec_select:(reg:Vmode) idx) when byte_offset of idx % 16 == 0. 2020-09-13 Hongtao Liu Peter Cordes gcc/ChangeLog: PR target/91103 * config/i386/sse.md (extract_suf): Add V8SF/V8SI/V4DF/V4DI. (*vec_extract_valign): Output vextract{i,f}{32x4,64x2} instruction when byte_offset % 16 == 0. gcc/testsuite/ChangeLog: PR target/91103 * gcc.target/i386/pr91103-1.c: Add extract tests. * gcc.target/i386/pr91103-2.c: Ditto. Diff: --- gcc/config/i386/sse.md | 21 +++++++++++++++++---- gcc/testsuite/gcc.target/i386/pr91103-1.c | 7 ++++++- gcc/testsuite/gcc.target/i386/pr91103-2.c | 4 ++++ 3 files changed, 27 insertions(+), 5 deletions(-) diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md index b67ec1507d9..15645395d83 100644 --- a/gcc/config/i386/sse.md +++ b/gcc/config/i386/sse.md @@ -9089,7 +9089,8 @@ [(V16SF "avx512f") (V16SI "avx512f") (V8DF "avx512dq") (V8DI "avx512dq")]) (define_mode_attr extract_suf - [(V16SF "32x4") (V16SI "32x4") (V8DF "64x2") (V8DI "64x2")]) + [(V16SF "32x4") (V16SI "32x4") (V8DF "64x2") (V8DI "64x2") + (V8SF "32x4") (V8SI "32x4") (V4DF "64x2") (V4DI "64x2")]) (define_mode_iterator AVX512_VEC [(V8DF "TARGET_AVX512DQ") (V8DI "TARGET_AVX512DQ") V16SF V16SI]) @@ -10661,9 +10662,21 @@ (match_operand:V48_256_512_AVX512VL 1 "register_operand" "v") (parallel [(match_operand 2 "")])))] "TARGET_AVX512F - && INTVAL(operands[2]) >= 16 / GET_MODE_SIZE (mode)" - "valign\t{%2, %1, %1, %0|%0, %1, %1, %2}"; - [(set_attr "prefix" "evex") + && INTVAL(operands[2]) * GET_MODE_SIZE (mode) >= 16" +{ + int byte_offset = INTVAL (operands[2]) * GET_MODE_SIZE (mode); + if (byte_offset % 16 == 0) + { + operands[2] = GEN_INT (byte_offset / 16); + if (byte_offset / 16 == 1) + return "vextract\t{%2, %t1, %x0|%x0, %t1, %2}"; + else + return "vextract\t{%2, %1, %x0|%x0, %1, %2}"; + } + else + return "valign\t{%2, %1, %1, %0|%0, %1, %1, %2}"; +} + [(set_attr "prefix" "maybe_evex") (set_attr "mode" "")]) (define_expand "avx512f_shufps512_mask" diff --git a/gcc/testsuite/gcc.target/i386/pr91103-1.c b/gcc/testsuite/gcc.target/i386/pr91103-1.c index 11caaa8bd1b..2d78a6da0f3 100644 --- a/gcc/testsuite/gcc.target/i386/pr91103-1.c +++ b/gcc/testsuite/gcc.target/i386/pr91103-1.c @@ -1,6 +1,7 @@ /* { dg-do compile } */ /* { dg-options "-mavx512vl -O2" } */ -/* { dg-final { scan-assembler-times "valign\[dq\]" 16 } } */ +/* { dg-final { scan-assembler-times "valign\[dq\]" 8 } } */ +/* { dg-final { scan-assembler-times "vextract" 12 } } */ typedef float v8sf __attribute__((vector_size(32))); typedef float v16sf __attribute__((vector_size(64))); @@ -23,9 +24,13 @@ EXTRACT (v8sf, float, 4); EXTRACT (v8sf, float, 7); EXTRACT (v8si, int, 4); EXTRACT (v8si, int, 7); +EXTRACT (v16sf, float, 4); EXTRACT (v16sf, float, 8); +EXTRACT (v16sf, float, 12); EXTRACT (v16sf, float, 15); +EXTRACT (v16si, int, 4); EXTRACT (v16si, int, 8); +EXTRACT (v16si, int, 12); EXTRACT (v16si, int, 15); EXTRACT (v4df, double, 2); EXTRACT (v4df, double, 3); diff --git a/gcc/testsuite/gcc.target/i386/pr91103-2.c b/gcc/testsuite/gcc.target/i386/pr91103-2.c index 010e4775723..a928d87f99a 100644 --- a/gcc/testsuite/gcc.target/i386/pr91103-2.c +++ b/gcc/testsuite/gcc.target/i386/pr91103-2.c @@ -61,9 +61,13 @@ RUNCHECK (f2, v8sf, float, 4); RUNCHECK (f2, v8sf, float, 7); RUNCHECK (di2, v8si, int, 4); RUNCHECK (di2, v8si, int, 7); +RUNCHECK (f1, v16sf, float, 4); RUNCHECK (f1, v16sf, float, 8); +RUNCHECK (f1, v16sf, float, 12); RUNCHECK (f1, v16sf, float, 15); +RUNCHECK (di1, v16si, int, 4); RUNCHECK (di1, v16si, int, 8); +RUNCHECK (di1, v16si, int, 12); RUNCHECK (di1, v16si, int, 15); RUNCHECK (d2, v4df, double, 2); RUNCHECK (d2, v4df, double, 3);