-mzeroupper is specified to generate vzeroupper instruction. If it isn't used, the default should depend on !TARGET_AVX512ER. Users can always use -mzeroupper or -mno-zeroupper to override it.
Sebastian, can you run the full test with it? OK for trunk if there is no regression? Thanks. H.J. --- gcc/ PR target/82990 * config/i386/i386.c (pass_insert_vzeroupper::gate): Remove TARGET_AVX512ER check. (ix86_option_override_internal): Set MASK_VZEROUPPER if neither -mzeroupper nor -mno-zeroupper is used and AVX512ER is disabled. gcc/testsuite/ PR target/82990 * gcc.target/i386/pr82990-1.c: New test. * gcc.target/i386/pr82990-2.c: Likewise. * gcc.target/i386/pr82990-3.c: Likewise. * gcc.target/i386/pr82990-4.c: Likewise. --- gcc/config/i386/i386.c | 5 +++-- gcc/testsuite/gcc.target/i386/pr82990-1.c | 14 ++++++++++++++ gcc/testsuite/gcc.target/i386/pr82990-2.c | 6 ++++++ gcc/testsuite/gcc.target/i386/pr82990-3.c | 6 ++++++ gcc/testsuite/gcc.target/i386/pr82990-4.c | 6 ++++++ 5 files changed, 35 insertions(+), 2 deletions(-) create mode 100644 gcc/testsuite/gcc.target/i386/pr82990-1.c create mode 100644 gcc/testsuite/gcc.target/i386/pr82990-2.c create mode 100644 gcc/testsuite/gcc.target/i386/pr82990-3.c create mode 100644 gcc/testsuite/gcc.target/i386/pr82990-4.c diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c index c5e84a09954..2c729236a29 100644 --- a/gcc/config/i386/i386.c +++ b/gcc/config/i386/i386.c @@ -2497,7 +2497,7 @@ public: /* opt_pass methods: */ virtual bool gate (function *) { - return TARGET_AVX && !TARGET_AVX512ER + return TARGET_AVX && TARGET_VZEROUPPER && flag_expensive_optimizations && !optimize_size; } @@ -4666,7 +4666,8 @@ ix86_option_override_internal (bool main_args_p, if (TARGET_SEH && TARGET_CALL_MS2SYSV_XLOGUES) sorry ("-mcall-ms2sysv-xlogues isn%'t currently supported with SEH"); - if (!(opts_set->x_target_flags & MASK_VZEROUPPER)) + if (!(opts_set->x_target_flags & MASK_VZEROUPPER) + && !TARGET_AVX512ER_P (opts->x_ix86_isa_flags)) 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/pr82990-1.c b/gcc/testsuite/gcc.target/i386/pr82990-1.c new file mode 100644 index 00000000000..ff1d6d40eb2 --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/pr82990-1.c @@ -0,0 +1,14 @@ +/* { dg-do compile } */ +/* { dg-options "-O2 -march=knl -mvzeroupper" } */ + +#include <immintrin.h> + +extern __m512d y, z; + +void +pr82941 () +{ + z = y; +} + +/* { dg-final { scan-assembler-times "vzeroupper" 1 } } */ diff --git a/gcc/testsuite/gcc.target/i386/pr82990-2.c b/gcc/testsuite/gcc.target/i386/pr82990-2.c new file mode 100644 index 00000000000..0d3cb2333dd --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/pr82990-2.c @@ -0,0 +1,6 @@ +/* { dg-do compile } */ +/* { dg-options "-O2 -march=skylake-avx512 -mno-vzeroupper" } */ + +#include "pr82941-1.c" + +/* { dg-final { scan-assembler-not "vzeroupper" } } */ diff --git a/gcc/testsuite/gcc.target/i386/pr82990-3.c b/gcc/testsuite/gcc.target/i386/pr82990-3.c new file mode 100644 index 00000000000..201fa98d8d4 --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/pr82990-3.c @@ -0,0 +1,6 @@ +/* { dg-do compile } */ +/* { dg-options "-mavx512f -mavx512er -mvzeroupper -O2" } */ + +#include "pr82941-1.c" + +/* { dg-final { scan-assembler-times "vzeroupper" 1 } } */ diff --git a/gcc/testsuite/gcc.target/i386/pr82990-4.c b/gcc/testsuite/gcc.target/i386/pr82990-4.c new file mode 100644 index 00000000000..09f161c7291 --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/pr82990-4.c @@ -0,0 +1,6 @@ +/* { dg-do compile } */ +/* { dg-options "-mavx512f -mno-avx512er -mno-vzeroupper -O2" } */ + +#include "pr82941-1.c" + +/* { dg-final { scan-assembler-not "vzeroupper" } } */ -- 2.13.6