aboutsummaryrefslogtreecommitdiff
path: root/gotools
diff options
context:
space:
mode:
authorH.J. Lu <hongjiu.lu@intel.com>2018-10-21 20:28:56 +0000
committerH.J. Lu <hjl@gcc.gnu.org>2018-10-21 13:28:56 -0700
commit38ef6fb19d81a9da321e95f35940121e3cf858ff (patch)
tree6905a839cf987be79e39384dba02f4862f012dd6 /gotools
parent5ca9497788cb44abe81529844ebc0077c0fc2b91 (diff)
downloadgcc-38ef6fb19d81a9da321e95f35940121e3cf858ff.zip
gcc-38ef6fb19d81a9da321e95f35940121e3cf858ff.tar.gz
gcc-38ef6fb19d81a9da321e95f35940121e3cf858ff.tar.bz2
i386: Enable AVX512 memory broadcast for FNMSUB
Many AVX512 vector operations can broadcast from a scalar memory source. This patch enables memory broadcast for FNMSUB operations. In order to support AVX512 memory broadcast for FNMSUB, FNMSUB builtin functions are also added, instead of passing the negated value to FMA builtin functions. gcc/ PR target/72782 * config/i386/avx512fintrin.h (_mm512_fnmsub_round_pd): Use __builtin_ia32_vfnmsubpd512_mask. (_mm512_mask_fnmsub_round_pd): Likewise. (_mm512_fnmsub_pd): Likewise. (_mm512_mask_fnmsub_pd): Likewise. (_mm512_maskz_fnmsub_round_pd): Use __builtin_ia32_vfnmsubpd512_maskz. (_mm512_maskz_fnmsub_pd): Likewise. (_mm512_fnmsub_round_ps): Use __builtin_ia32_vfnmsubps512_mask. (_mm512_mask_fnmsub_round_ps): Likewise. (_mm512_fnmsub_ps): Likewise. (_mm512_mask_fnmsub_ps): Likewise. (_mm512_maskz_fnmsub_round_ps): Use __builtin_ia32_vfnmsubps512_maskz. (_mm512_maskz_fnmsub_ps): Likewise. * config/i386/avx512vlintrin.h (_mm256_mask_fnmsub_pd): Use __builtin_ia32_vfnmsubpd256_mask. (_mm256_maskz_fnmsub_pd): Use __builtin_ia32_vfnmsubpd256_maskz. (_mm_mask_fnmsub_pd): Use __builtin_ia32_vfmaddpd128_mask (_mm_maskz_fnmsub_pd): Use __builtin_ia32_vfnmsubpd128_maskz. (_mm256_mask_fnmsub_ps): Use __builtin_ia32_vfnmsubps256_mask. (_mm256_mask_fnmsub_ps): Use __builtin_ia32_vfnmsubps256_mask. (_mm256_maskz_fnmsub_ps): Use __builtin_ia32_vfnmsubps256_maskz. (_mm_mask_fnmsub_ps): Use __builtin_ia32_vfnmsubps128_mask. (_mm_maskz_fnmsub_ps): Use __builtin_ia32_vfnmsubps128_maskz. * config/i386/fmaintrin.h (_mm_fnmsub_pd): Use __builtin_ia32_vfnmsubpd. (_mm256_fnmsub_pd): Use __builtin_ia32_vfnmsubpd256. (_mm_fnmsub_ps): Use __builtin_ia32_vfnmsubps. (_mm256_fnmsub_ps): Use __builtin_ia32_vfnmsubps256. (_mm_fnmsub_sd): Use __builtin_ia32_vfnmsubsd3. (_mm_fnmsub_ss): Use __builtin_ia32_vfnmsubss3. * config/i386/i386-builtin.def: Add __builtin_ia32_vfnmsubpd256_mask, __builtin_ia32_vfnmsubpd256_maskz, __builtin_ia32_vfnmsubpd128_mask, __builtin_ia32_vfnmsubpd128_maskz, __builtin_ia32_vfnmsubps256_mask, __builtin_ia32_vfnmsubps256_maskz, __builtin_ia32_vfnmsubps128_mask, __builtin_ia32_vfnmsubps128_maskz, __builtin_ia32_vfnmsubpd512_mask, __builtin_ia32_vfnmsubpd512_maskz, __builtin_ia32_vfnmsubps512_mask, __builtin_ia32_vfnmsubps512_maskz, __builtin_ia32_vfnmsubss3, __builtin_ia32_vfnmsubsd3, __builtin_ia32_vfnmsubps, __builtin_ia32_vfnmsubpd, __builtin_ia32_vfnmsubps256 and. __builtin_ia32_vfnmsubpd256. * config/i386/sse.md (fma4i_fnmsub_<mode>): New. (<avx512>_fnmsub_<mode>_maskz<round_expand_name>): Likewise. (*<sd_mask_codefor>fma_fnmsub_<mode><sd_maskz_name>_bcst_1): Likewise. (*<sd_mask_codefor>fma_fnmsub_<mode><sd_maskz_name>_bcst_2): Likewise. (*<sd_mask_codefor>fma_fnmsub_<mode><sd_maskz_name>_bcst_3): Likewise. (fmai_vmfnmsub_<mode><round_name>): Likewise. gcc/testsuite/ PR target/72782 * gcc.target/i386/avx512f-fnmsub-df-zmm-1.c: New test. * gcc.target/i386/avx512f-fnmsub-sf-zmm-1.c: Likewise. * gcc.target/i386/avx512f-fnmsub-sf-zmm-2.c: Likewise. * gcc.target/i386/avx512f-fnmsub-sf-zmm-3.c: Likewise. * gcc.target/i386/avx512f-fnmsub-sf-zmm-4.c: Likewise. * gcc.target/i386/avx512f-fnmsub-sf-zmm-5.c: Likewise. * gcc.target/i386/avx512f-fnmsub-sf-zmm-6.c: Likewise. * gcc.target/i386/avx512f-fnmsub-sf-zmm-7.c: Likewise. * gcc.target/i386/avx512f-fnmsub-sf-zmm-8.c: Likewise. * gcc.target/i386/avx512vl-fnmsub-sf-xmm-1.c: Likewise. * gcc.target/i386/avx512vl-fnmsub-sf-ymm-1.c: Likewise. From-SVN: r265358
Diffstat (limited to 'gotools')
0 files changed, 0 insertions, 0 deletions