diff options
| author | tkoenig <tkoenig@138bc75d-0d04-0410-961f-82ee72b054a4> | 2017-03-02 11:04:01 +0000 |
|---|---|---|
| committer | tkoenig <tkoenig@138bc75d-0d04-0410-961f-82ee72b054a4> | 2017-03-02 11:04:01 +0000 |
| commit | 690779763a55c5ac8585cc970c1bed4dbb07f90c (patch) | |
| tree | 479218dbc398682ff55cd867e71940dd85a0c39e /libgfortran/generated/matmul_i2.c | |
| parent | b77143754db5388e0517794095bba8c7bc1b15af (diff) | |
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.
git-svn-id: svn+ssh://gcc.gnu.org/svn/gcc/trunk@245836 138bc75d-0d04-0410-961f-82ee72b054a4
Diffstat (limited to 'libgfortran/generated/matmul_i2.c')
| -rw-r--r-- | libgfortran/generated/matmul_i2.c | 8 |
1 files changed, 3 insertions, 5 deletions
diff --git a/libgfortran/generated/matmul_i2.c b/libgfortran/generated/matmul_i2.c index 2077db3ed26b..55ad5c614e66 100644 --- a/libgfortran/generated/matmul_i2.c +++ b/libgfortran/generated/matmul_i2.c @@ -74,9 +74,6 @@ extern void matmul_i2 (gfc_array_i2 * const restrict retarray, int blas_limit, blas_call gemm); export_proto(matmul_i2); - - - /* Put exhaustive list of possible architectures here here, ORed together. */ #if defined(HAVE_AVX) || defined(HAVE_AVX2) || defined(HAVE_AVX512F) @@ -628,7 +625,7 @@ matmul_i2_avx (gfc_array_i2 * const restrict retarray, static void matmul_i2_avx2 (gfc_array_i2 * const restrict retarray, gfc_array_i2 * const restrict a, gfc_array_i2 * 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 void matmul_i2_avx2 (gfc_array_i2 * const restrict retarray, gfc_array_i2 * const restrict a, gfc_array_i2 * const restrict b, int try_blas, @@ -2277,7 +2274,8 @@ void matmul_i2 (gfc_array_i2 * 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_i2_avx2; goto tailcall; |