diff options
| author | Thomas Koenig <tkoenig@gcc.gnu.org> | 2017-03-02 11:04:01 +0000 |
|---|---|---|
| committer | Thomas Koenig <tkoenig@gcc.gnu.org> | 2017-03-02 11:04:01 +0000 |
| commit | 6d03bdcc8196414a7d14d21629257ea746e82385 (patch) | |
| tree | 479218dbc398682ff55cd867e71940dd85a0c39e /libgfortran/m4 | |
| parent | db9f7f657e035786836f8371b56d876a9bec46bc (diff) | |
re PR libfortran/78379 (Processor-specific versions for matmul)
2017-03-02 Thomas Koenig <tkoenig@gcc.gnu.org>
PR fortran/78379
* m4/matmul.m4: (matmul_'rtype_code`_avx2): Also generate for
reals. Add fma to target options.
(matmul_'rtype_code`): Call AVX2 only if FMA is available.
* generated/matmul_c10.c: Regenerated.
* generated/matmul_c16.c: Regenerated.
* generated/matmul_c4.c: Regenerated.
* generated/matmul_c8.c: Regenerated.
* generated/matmul_i1.c: Regenerated.
* generated/matmul_i16.c: Regenerated.
* generated/matmul_i2.c: Regenerated.
* generated/matmul_i4.c: Regenerated.
* generated/matmul_i8.c: Regenerated.
* generated/matmul_r10.c: Regenerated.
* generated/matmul_r16.c: Regenerated.
* generated/matmul_r4.c: Regenerated.
* generated/matmul_r8.c: Regenerated.
From-SVN: r245836
Diffstat (limited to 'libgfortran/m4')
| -rw-r--r-- | libgfortran/m4/matmul.m4 | 13 |
1 files changed, 3 insertions, 10 deletions
diff --git a/libgfortran/m4/matmul.m4 b/libgfortran/m4/matmul.m4 index 27381293dba..812a7e7e571 100644 --- a/libgfortran/m4/matmul.m4 +++ b/libgfortran/m4/matmul.m4 @@ -75,14 +75,6 @@ extern void matmul_'rtype_code` ('rtype` * const restrict retarray, int blas_limit, blas_call gemm); export_proto(matmul_'rtype_code`); -'ifelse(rtype_letter,`r',dnl -`#if defined(HAVE_AVX) && defined(HAVE_AVX2) -/* REAL types generate identical code for AVX and AVX2. Only generate - an AVX2 function if we are dealing with integer. */ -#undef HAVE_AVX2 -#endif') -` - /* Put exhaustive list of possible architectures here here, ORed together. */ #if defined(HAVE_AVX) || defined(HAVE_AVX2) || defined(HAVE_AVX512F) @@ -101,7 +93,7 @@ static' include(matmul_internal.m4)dnl `static void 'matmul_name` ('rtype` * const restrict retarray, 'rtype` * const restrict a, 'rtype` * const restrict b, int try_blas, - int blas_limit, blas_call gemm) __attribute__((__target__("avx2"))); + int blas_limit, blas_call gemm) __attribute__((__target__("avx2,fma"))); static' include(matmul_internal.m4)dnl `#endif /* HAVE_AVX2 */ @@ -147,7 +139,8 @@ void matmul_'rtype_code` ('rtype` * const restrict retarray, #endif /* HAVE_AVX512F */ #ifdef HAVE_AVX2 - if (__cpu_model.__cpu_features[0] & (1 << FEATURE_AVX2)) + if ((__cpu_model.__cpu_features[0] & (1 << FEATURE_AVX2)) + && (__cpu_model.__cpu_features[0] & (1 << FEATURE_FMA))) { matmul_p = matmul_'rtype_code`_avx2; goto tailcall; |