5ca9497788
Many AVX512 vector operations can broadcast from a scalar memory source. This patch enables memory broadcast for FNMADD operations. In order to support AVX512 memory broadcast for FNMADD, FNMADD builtin functions are also added, instead of passing the negated value to FMA builtin functions. gcc/ PR target/72782 * config/i386/avx512fintrin.h (_mm512_fnmadd_round_pd): Use __builtin_ia32_vfnmaddpd512_mask. (_mm512_mask_fnmadd_round_pd): Likewise. (_mm512_fnmadd_pd): Likewise. (_mm512_mask_fnmadd_pd): Likewise. (_mm512_maskz_fnmadd_round_pd): Use __builtin_ia32_vfnmaddpd512_maskz. (_mm512_maskz_fnmadd_pd): Likewise. (_mm512_fnmadd_round_ps): Use __builtin_ia32_vfnmaddps512_mask. (_mm512_mask_fnmadd_round_ps): Likewise. (_mm512_fnmadd_ps): Likewise. (_mm512_mask_fnmadd_ps): Likewise. (_mm512_maskz_fnmadd_round_ps): Use __builtin_ia32_vfnmaddps512_maskz. (_mm512_maskz_fnmadd_ps): Likewise. * config/i386/avx512vlintrin.h (_mm256_mask_fnmadd_pd): Use __builtin_ia32_vfnmaddpd256_mask. (_mm256_maskz_fnmadd_pd): Use __builtin_ia32_vfnmaddpd256_maskz. (_mm_mask_fnmadd_pd): Use __builtin_ia32_vfmaddpd128_mask (_mm_maskz_fnmadd_pd): Use __builtin_ia32_vfnmaddpd128_maskz. (_mm256_mask_fnmadd_ps): Use __builtin_ia32_vfnmaddps256_mask. (_mm256_mask_fnmadd_ps): Use __builtin_ia32_vfnmaddps256_mask. (_mm256_maskz_fnmadd_ps): Use __builtin_ia32_vfnmaddps256_maskz. (_mm_mask_fnmadd_ps): Use __builtin_ia32_vfnmaddps128_mask. (_mm_maskz_fnmadd_ps): Use __builtin_ia32_vfnmaddps128_maskz. * config/i386/fmaintrin.h (_mm_fnmadd_pd): Use __builtin_ia32_vfnmaddpd. (_mm256_fnmadd_pd): Use __builtin_ia32_vfnmaddpd256. (_mm_fnmadd_ps): Use __builtin_ia32_vfnmaddps. (_mm256_fnmadd_ps): Use __builtin_ia32_vfnmaddps256. (_mm_fnmadd_sd): Use __builtin_ia32_vfnmaddsd3. (_mm_fnmadd_ss): Use __builtin_ia32_vfnmaddss3. * config/i386/i386-builtin.def: Add __builtin_ia32_vfnmaddpd256_mask, __builtin_ia32_vfnmaddpd256_maskz, __builtin_ia32_vfnmaddpd128_mask, __builtin_ia32_vfnmaddpd128_maskz, __builtin_ia32_vfnmaddps256_mask, __builtin_ia32_vfnmaddps256_maskz, __builtin_ia32_vfnmaddps128_mask, __builtin_ia32_vfnmaddps128_maskz, __builtin_ia32_vfnmaddpd512_mask, __builtin_ia32_vfnmaddpd512_maskz, __builtin_ia32_vfnmaddps512_mask, __builtin_ia32_vfnmaddps512_maskz, __builtin_ia32_vfnmaddss3, __builtin_ia32_vfnmaddsd3, __builtin_ia32_vfnmaddps, __builtin_ia32_vfnmaddpd, __builtin_ia32_vfnmaddps256 and. __builtin_ia32_vfnmaddpd256. * config/i386/sse.md (fma4i_fnmadd_<mode>): New. (<avx512>_fnmadd_<mode>_maskz<round_expand_name>): Likewise. (*<sd_mask_codefor>fma_fnmadd_<mode><sd_maskz_name>_bcst_1): Likewise. (*<sd_mask_codefor>fma_fnmadd_<mode><sd_maskz_name>_bcst_2): Likewise. (*<sd_mask_codefor>fma_fnmadd_<mode><sd_maskz_name>_bcst_3): Likewise. (fmai_vmfnmadd_<mode><round_name>): Likewise. gcc/testsuite/ PR target/72782 * gcc.target/i386/avx512f-fnmadd-df-zmm-1.c: New test. * gcc.target/i386/avx512f-fnmadd-sf-zmm-1.c: Likewise. * gcc.target/i386/avx512f-fnmadd-sf-zmm-2.c: Likewise. * gcc.target/i386/avx512f-fnmadd-sf-zmm-3.c: Likewise. * gcc.target/i386/avx512f-fnmadd-sf-zmm-4.c: Likewise. * gcc.target/i386/avx512f-fnmadd-sf-zmm-5.c: Likewise. * gcc.target/i386/avx512f-fnmadd-sf-zmm-6.c: Likewise. * gcc.target/i386/avx512f-fnmadd-sf-zmm-7.c: Likewise. * gcc.target/i386/avx512f-fnmadd-sf-zmm-8.c: Likewise. * gcc.target/i386/avx512vl-fnmadd-sf-xmm-1.c: Likewise. * gcc.target/i386/avx512vl-fnmadd-sf-ymm-1.c: Likewise. From-SVN: r265357 |
||
|---|---|---|
| config | ||
| contrib | ||
| fixincludes | ||
| gcc | ||
| gnattools | ||
| gotools | ||
| include | ||
| INSTALL | ||
| intl | ||
| libada | ||
| libatomic | ||
| libbacktrace | ||
| libcc1 | ||
| libcpp | ||
| libdecnumber | ||
| libffi | ||
| libgcc | ||
| libgfortran | ||
| libgo | ||
| libgomp | ||
| libhsail-rt | ||
| libiberty | ||
| libitm | ||
| libobjc | ||
| liboffloadmic | ||
| libquadmath | ||
| libsanitizer | ||
| libssp | ||
| libstdc++-v3 | ||
| libvtv | ||
| lto-plugin | ||
| maintainer-scripts | ||
| zlib | ||
| .dir-locals.el | ||
| .gitattributes | ||
| .gitignore | ||
| ABOUT-NLS | ||
| ChangeLog | ||
| ChangeLog.jit | ||
| ChangeLog.tree-ssa | ||
| compile | ||
| config-ml.in | ||
| config.guess | ||
| config.rpath | ||
| config.sub | ||
| configure | ||
| configure.ac | ||
| COPYING | ||
| COPYING3 | ||
| COPYING3.LIB | ||
| COPYING.LIB | ||
| COPYING.RUNTIME | ||
| depcomp | ||
| install-sh | ||
| libtool-ldflags | ||
| libtool.m4 | ||
| lt~obsolete.m4 | ||
| ltgcc.m4 | ||
| ltmain.sh | ||
| ltoptions.m4 | ||
| ltsugar.m4 | ||
| ltversion.m4 | ||
| MAINTAINERS | ||
| Makefile.def | ||
| Makefile.in | ||
| Makefile.tpl | ||
| missing | ||
| mkdep | ||
| mkinstalldirs | ||
| move-if-change | ||
| README | ||
| symlink-tree | ||
| ylwrap | ||
This directory contains the GNU Compiler Collection (GCC). The GNU Compiler Collection is free software. See the files whose names start with COPYING for copying permission. The manuals, and some of the runtime libraries, are under different terms; see the individual source files for details. The directory INSTALL contains copies of the installation information as HTML and plain text. The source of this information is gcc/doc/install.texi. The installation information includes details of what is included in the GCC sources and what files GCC installs. See the file gcc/doc/gcc.texi (together with other files that it includes) for usage and porting information. An online readable version of the manual is in the files gcc/doc/gcc.info*. See http://gcc.gnu.org/bugs/ for how to report bugs usefully. Copyright years on GCC source files may be listed using range notation, e.g., 1987-2012, indicating that every year in the range, inclusive, is a copyrightable year that could otherwise be listed individually.