From 8cf948e6d9ab19d54ec0d27357d0c2907a244474 Mon Sep 17 00:00:00 2001 From: liuhongt Date: Mon, 26 Jun 2023 09:50:25 +0800 Subject: Make option mvzeroupper independent of optimization level. pass_insert_vzeroupper is under condition TARGET_AVX && TARGET_VZEROUPPER && flag_expensive_optimizations && !optimize_size But the document of mvzeroupper doesn't mention the insertion required -O2 and above, it may confuse users when they explicitly use -Os -mvzeroupper. ------------ mvzeroupper Target Mask(VZEROUPPER) Save Generate vzeroupper instruction before a transfer of control flow out of the function. ------------ The patch moves flag_expensive_optimizations && !optimize_size to ix86_option_override_internal. It makes -mvzeroupper independent of optimization level, but still keeps the behavior of architecture tuning(emit_vzeroupper) unchanged. gcc/ChangeLog: * config/i386/i386-features.c (pass_insert_vzeroupper:gate): Move flag_expensive_optimizations && !optimize_size to .. * config/i386/i386-options.c (ix86_option_override_internal): .. this, it makes -mvzeroupper independent of optimization level, but still keeps the behavior of architecture tuning(emit_vzeroupper) unchanged. (rest_of_handle_insert_vzeroupper): Remove flag_expensive_optimizations && !optimize_size. gcc/testsuite/ChangeLog: * gcc.target/i386/avx-vzeroupper-29.c: New testcase. --- gcc/config/i386/i386-features.c | 8 ++------ gcc/config/i386/i386-options.c | 4 +++- gcc/testsuite/gcc.target/i386/avx-vzeroupper-29.c | 14 ++++++++++++++ 3 files changed, 19 insertions(+), 7 deletions(-) create mode 100644 gcc/testsuite/gcc.target/i386/avx-vzeroupper-29.c (limited to 'gcc') diff --git a/gcc/config/i386/i386-features.c b/gcc/config/i386/i386-features.c index 329f4c3..a5e0c21 100644 --- a/gcc/config/i386/i386-features.c +++ b/gcc/config/i386/i386-features.c @@ -1825,9 +1825,7 @@ ix86_add_reg_usage_to_vzerouppers (void) static unsigned int rest_of_handle_insert_vzeroupper (void) { - if (TARGET_VZEROUPPER - && flag_expensive_optimizations - && !optimize_size) + if (TARGET_VZEROUPPER) { /* vzeroupper instructions are inserted immediately after reload to account for possible spills from 256bit or 512bit registers. The pass @@ -1871,9 +1869,7 @@ public: virtual bool gate (function *) { return TARGET_AVX - && ((TARGET_VZEROUPPER - && flag_expensive_optimizations - && !optimize_size) + && (TARGET_VZEROUPPER || cfun->machine->has_explicit_vzeroupper); } diff --git a/gcc/config/i386/i386-options.c b/gcc/config/i386/i386-options.c index 7bb644b..3510ad5 100644 --- a/gcc/config/i386/i386-options.c +++ b/gcc/config/i386/i386-options.c @@ -2715,7 +2715,9 @@ ix86_option_override_internal (bool main_args_p, sorry ("%<-mcall-ms2sysv-xlogues%> isn%'t currently supported with SEH"); if (!(opts_set->x_target_flags & MASK_VZEROUPPER) - && TARGET_EMIT_VZEROUPPER) + && TARGET_EMIT_VZEROUPPER + && flag_expensive_optimizations + && !optimize_size) opts->x_target_flags |= MASK_VZEROUPPER; if (!(opts_set->x_target_flags & MASK_STV)) opts->x_target_flags |= MASK_STV; diff --git a/gcc/testsuite/gcc.target/i386/avx-vzeroupper-29.c b/gcc/testsuite/gcc.target/i386/avx-vzeroupper-29.c new file mode 100644 index 0000000..4af6377 --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/avx-vzeroupper-29.c @@ -0,0 +1,14 @@ +/* { dg-do compile } */ +/* { dg-options "-O0 -mavx -mtune=generic -mvzeroupper -dp" } */ + +#include + +extern __m256 x, y; + +void +foo () +{ + x = y; +} + +/* { dg-final { scan-assembler-times "avx_vzeroupper" 1 } } */ -- cgit v1.1