On Tue, Oct 29, 2024 at 5:04 PM Haochen Jiang <haochen.ji...@intel.com> wrote:
>
> Hi all,
>
> Since Binutils haven't fully merged all AVX10.2 insts, only testing
> one inst/intrin in AVX10.2 is never sufficient for check_effective_target.
> Like APX_F, use inline asm to do the target check.
>
> Testes w/ and w/o Binutils with full AVX10.2 support. Ok for trunk?
Ok.
>
> Thx,
> Haochen
>
> gcc/testsuite/ChangeLog:
>
> PR target/117301
> * lib/target-supports.exp (check_effective_target_avx10_2):
> Use inline asm instead of intrin for check_effective_target.
> (check_effective_target_avx10_2_512): Ditto.
> ---
> gcc/testsuite/lib/target-supports.exp | 34 +++++++++++----------------
> 1 file changed, 14 insertions(+), 20 deletions(-)
>
> diff --git a/gcc/testsuite/lib/target-supports.exp
> b/gcc/testsuite/lib/target-supports.exp
> index 70f74d1e288..9c65fd0fd7b 100644
> --- a/gcc/testsuite/lib/target-supports.exp
> +++ b/gcc/testsuite/lib/target-supports.exp
> @@ -10748,17 +10748,14 @@ proc check_effective_target_apxf { } {
> # Return 1 if avx10.2 instructions can be compiled.
> proc check_effective_target_avx10_2 { } {
> return [check_no_compiler_messages avx10.2 object {
> - typedef int __v8si __attribute__ ((__vector_size__ (32)));
> - typedef char __mmask8;
> -
> - __v8si
> - _mm256_mask_vpdpbssd_epi32 (__v8si __A, __mmask8 __U,
> - __v8si __B, __v8si __C)
> + void
> + foo ()
> {
> - return (__v8si) __builtin_ia32_vpdpbssd_v8si_mask ((__v8si)__A,
> - (__v8si)__B,
> - (__v8si)__C,
> - (__mmask8)__U);
> + __asm__ volatile ("vdpphps\t%ymm4, %ymm5, %ymm6");
> + __asm__ volatile ("vcvthf82ph\t%xmm5, %ymm6");
> + __asm__ volatile ("vaddnepbf16\t%ymm4, %ymm5, %ymm6");
> + __asm__ volatile ("vcvtph2ibs\t%ymm5, %ymm6");
> + __asm__ volatile ("vminmaxpd\t$123, %ymm4, %ymm5, %ymm6");
> }
> } "-mavx10.2" ]
> }
> @@ -10766,17 +10763,14 @@ proc check_effective_target_avx10_2 { } {
> # Return 1 if avx10.2-512 instructions can be compiled.
> proc check_effective_target_avx10_2_512 { } {
> return [check_no_compiler_messages avx10.2-512 object {
> - typedef int __v16si __attribute__ ((__vector_size__ (64)));
> - typedef short __mmask16;
> -
> - __v16si
> - _mm512_vpdpbssd_epi32 (__v16si __A, __mmask16 __U,
> - __v16si __B, __v16si __C)
> + void
> + foo ()
> {
> - return (__v16si) __builtin_ia32_vpdpbssd_v16si_mask ((__v16si)__A,
> - (__v16si)__B,
> - (__v16si)__C,
> -
> (__mmask16)__U);
> + __asm__ volatile ("vdpphps\t%zmm4, %zmm5, %zmm6");
> + __asm__ volatile ("vcvthf82ph\t%ymm5, %zmm6");
> + __asm__ volatile ("vaddnepbf16\t%zmm4, %zmm5, %zmm6");
> + __asm__ volatile ("vcvtph2ibs\t%zmm5, %zmm6");
> + __asm__ volatile ("vminmaxpd\t$123, %zmm4, %zmm5, %zmm6");
> }
> } "-mavx10.2-512" ]
> }
> --
> 2.31.1
>
--
BR,
Hongtao
