aboutsummaryrefslogtreecommitdiff
path: root/gcc/tree-inline.c
diff options
context:
space:
mode:
authorH.J. Lu <hongjiu.lu@intel.com>2018-10-21 20:24:50 +0000
committerH.J. Lu <hjl@gcc.gnu.org>2018-10-21 13:24:50 -0700
commitfe7f972d6ecc1f1df34f15615b7e3dea6f39e564 (patch)
treee1eb0e9ceeeaffb0ac1c74cebe434dcc0f271985 /gcc/tree-inline.c
parent88c08ac43c47bb5d21734be744df913dd568d108 (diff)
downloadgcc-fe7f972d6ecc1f1df34f15615b7e3dea6f39e564.zip
gcc-fe7f972d6ecc1f1df34f15615b7e3dea6f39e564.tar.gz
gcc-fe7f972d6ecc1f1df34f15615b7e3dea6f39e564.tar.bz2
Enable AVX512 memory broadcast for FMSUB
Many AVX512 vector operations can broadcast from a scalar memory source. This patch enables memory broadcast for FMSUB operations. In order to support AVX512 memory broadcast for FMSUB, FMSUB builtin functions are also added, instead of passing the negated value to FMA builtin functions. gcc/ PR target/72782 * config/i386/avx512fintrin.h (_mm512_fmsub_round_pd): Use __builtin_ia32_vfmsubpd512_mask. (_mm512_mask_fmsub_round_pd): Likewise. (_mm512_fmsub_pd): Likewise. (_mm512_mask_fmsub_pd): Likewise. (_mm512_maskz_fmsub_round_pd): Use __builtin_ia32_vfmsubpd512_maskz. (_mm512_maskz_fmsub_pd): Likewise. (_mm512_fmsub_round_ps): Use __builtin_ia32_vfmsubps512_mask. (_mm512_mask_fmsub_round_ps): Likewise. (_mm512_fmsub_ps): Likewise. (_mm512_mask_fmsub_ps): Likewise. (_mm512_maskz_fmsub_round_ps): Use __builtin_ia32_vfmsubps512_maskz. (_mm512_maskz_fmsub_ps): Likewise. * config/i386/avx512vlintrin.h (_mm256_mask_fmsub_pd): Use __builtin_ia32_vfmsubpd256_mask. (_mm256_maskz_fmsub_pd): Use __builtin_ia32_vfmsubpd256_maskz. (_mm_mask_fmsub_pd): Use __builtin_ia32_vfmaddpd128_mask (_mm_maskz_fmsub_pd): Use __builtin_ia32_vfmsubpd128_maskz. (_mm256_mask_fmsub_ps): Use __builtin_ia32_vfmsubps256_mask. (_mm256_mask_fmsub_ps): Use __builtin_ia32_vfmsubps256_mask. (_mm256_maskz_fmsub_ps): Use __builtin_ia32_vfmsubps256_maskz. (_mm_mask_fmsub_ps): Use __builtin_ia32_vfmsubps128_mask. (_mm_maskz_fmsub_ps): Use __builtin_ia32_vfmsubps128_maskz. * config/i386/fmaintrin.h (_mm_fmsub_pd): Use __builtin_ia32_vfmsubpd. (_mm256_fmsub_pd): Use __builtin_ia32_vfmsubpd256. (_mm_fmsub_ps): Use __builtin_ia32_vfmsubps. (_mm256_fmsub_ps): Use __builtin_ia32_vfmsubps256. (_mm_fmsub_sd): Use __builtin_ia32_vfmsubsd3. (_mm_fmsub_ss): Use __builtin_ia32_vfmsubss3. * config/i386/i386-builtin.def: Add __builtin_ia32_vfmsubpd256_mask, __builtin_ia32_vfmsubpd256_maskz, __builtin_ia32_vfmsubpd128_mask, __builtin_ia32_vfmsubpd128_maskz, __builtin_ia32_vfmsubps256_mask, __builtin_ia32_vfmsubps256_maskz, __builtin_ia32_vfmsubps128_mask, __builtin_ia32_vfmsubps128_maskz, __builtin_ia32_vfmsubpd512_mask, __builtin_ia32_vfmsubpd512_maskz, __builtin_ia32_vfmsubps512_mask, __builtin_ia32_vfmsubps512_maskz, __builtin_ia32_vfmsubss3, __builtin_ia32_vfmsubsd3, __builtin_ia32_vfmsubps, __builtin_ia32_vfmsubpd, __builtin_ia32_vfmsubps256 and. __builtin_ia32_vfmsubpd256. * config/i386/sse.md (fma4i_fmsub_<mode>): New. (<avx512>_fmsub_<mode>_maskz<round_expand_name>): Likewise. (*<sd_mask_codefor>fma_fmsub_<mode><sd_maskz_name>_bcst_1): Likewise. (*<sd_mask_codefor>fma_fmsub_<mode><sd_maskz_name>_bcst_2): Likewise. (*<sd_mask_codefor>fma_fmsub_<mode><sd_maskz_name>_bcst_3): Likewise. (fmai_vmfmsub_<mode><round_name>): Likewise. gcc/testsuite/ PR target/72782 * gcc.target/i386/avx512f-fmsub-df-zmm-1.c: New test. * gcc.target/i386/avx512f-fmsub-sf-zmm-1.c: Likewise. * gcc.target/i386/avx512f-fmsub-sf-zmm-2.c: Likewise. * gcc.target/i386/avx512f-fmsub-sf-zmm-3.c: Likewise. * gcc.target/i386/avx512f-fmsub-sf-zmm-4.c: Likewise. * gcc.target/i386/avx512f-fmsub-sf-zmm-5.c: Likewise. * gcc.target/i386/avx512f-fmsub-sf-zmm-6.c: Likewise. * gcc.target/i386/avx512f-fmsub-sf-zmm-7.c: Likewise. * gcc.target/i386/avx512f-fmsub-sf-zmm-8.c: Likewise. * gcc.target/i386/avx512vl-fmsub-sf-xmm-1.c: Likewise. * gcc.target/i386/avx512vl-fmsub-sf-ymm-1.c: Likewise. From-SVN: r265356
Diffstat (limited to 'gcc/tree-inline.c')
0 files changed, 0 insertions, 0 deletions