Hello world,
the attached patch adds an AVX-specific version of the matmul
intrinsic to the Fortran library. This works by using the target_clones
attribute.
For testing, I compiled this on powerpc64-unknown-linux-gnu,
without any ill effects.
Also, a resulting binary reached around 15 GFlops for larger matrices
on a 3.4 GHz i7-2600 CPU. I am currently building/regtesting on
that machine. This can give another 40% speed increase for large
matrices on AVX.
OK for trunk?
Regards
Thomas
2016-11-16 Thomas Koenig <[email protected]>
PR fortran/78379
* m4/matmul.m4: For x86_64, make the work function for matmul
static with target_clones for AVX and default, and create
a wrapper function to call it.
* generated/matmul_c10.c
* 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.
Index: generated/matmul_c10.c
===================================================================
--- generated/matmul_c10.c (Revision 242477)
+++ generated/matmul_c10.c (Arbeitskopie)
@@ -75,11 +75,37 @@ extern void matmul_c10 (gfc_array_c10 * const rest
int blas_limit, blas_call gemm);
export_proto(matmul_c10);
+#ifdef __x86_64__
+
+/* For x86_64, we switch to AVX if that is available. For this, we
+ let the actual work be done by the static aux_matmul - function.
+ The user-callable function will then automagically contain the
+ selection code for the right architecture. This is done to avoid
+ knowledge of architecture details in the front end. */
+
+static void aux_matmul_c10 (gfc_array_c10 * const restrict retarray,
+ gfc_array_c10 * const restrict a, gfc_array_c10 * const restrict b, int try_blas,
+ int blas_limit, blas_call gemm)
+ __attribute__ ((target_clones("avx,default")));
+
void
matmul_c10 (gfc_array_c10 * const restrict retarray,
gfc_array_c10 * const restrict a, gfc_array_c10 * const restrict b, int try_blas,
int blas_limit, blas_call gemm)
{
+ aux_matmul_c10 (retarray, a, b, try_blas, blas_limit, gemm);
+}
+
+static void
+aux_matmul_c10 (gfc_array_c10 * const restrict retarray,
+ gfc_array_c10 * const restrict a, gfc_array_c10 * const restrict b, int try_blas,
+ int blas_limit, blas_call gemm)
+#else
+matmul_c10 (gfc_array_c10 * const restrict retarray,
+ gfc_array_c10 * const restrict a, gfc_array_c10 * const restrict b, int try_blas,
+ int blas_limit, blas_call gemm)
+#endif
+{
const GFC_COMPLEX_10 * restrict abase;
const GFC_COMPLEX_10 * restrict bbase;
GFC_COMPLEX_10 * restrict dest;
Index: generated/matmul_c16.c
===================================================================
--- generated/matmul_c16.c (Revision 242477)
+++ generated/matmul_c16.c (Arbeitskopie)
@@ -75,11 +75,37 @@ extern void matmul_c16 (gfc_array_c16 * const rest
int blas_limit, blas_call gemm);
export_proto(matmul_c16);
+#ifdef __x86_64__
+
+/* For x86_64, we switch to AVX if that is available. For this, we
+ let the actual work be done by the static aux_matmul - function.
+ The user-callable function will then automagically contain the
+ selection code for the right architecture. This is done to avoid
+ knowledge of architecture details in the front end. */
+
+static void aux_matmul_c16 (gfc_array_c16 * const restrict retarray,
+ gfc_array_c16 * const restrict a, gfc_array_c16 * const restrict b, int try_blas,
+ int blas_limit, blas_call gemm)
+ __attribute__ ((target_clones("avx,default")));
+
void
matmul_c16 (gfc_array_c16 * const restrict retarray,
gfc_array_c16 * const restrict a, gfc_array_c16 * const restrict b, int try_blas,
int blas_limit, blas_call gemm)
{
+ aux_matmul_c16 (retarray, a, b, try_blas, blas_limit, gemm);
+}
+
+static void
+aux_matmul_c16 (gfc_array_c16 * const restrict retarray,
+ gfc_array_c16 * const restrict a, gfc_array_c16 * const restrict b, int try_blas,
+ int blas_limit, blas_call gemm)
+#else
+matmul_c16 (gfc_array_c16 * const restrict retarray,
+ gfc_array_c16 * const restrict a, gfc_array_c16 * const restrict b, int try_blas,
+ int blas_limit, blas_call gemm)
+#endif
+{
const GFC_COMPLEX_16 * restrict abase;
const GFC_COMPLEX_16 * restrict bbase;
GFC_COMPLEX_16 * restrict dest;
Index: generated/matmul_c4.c
===================================================================
--- generated/matmul_c4.c (Revision 242477)
+++ generated/matmul_c4.c (Arbeitskopie)
@@ -75,11 +75,37 @@ extern void matmul_c4 (gfc_array_c4 * const restri
int blas_limit, blas_call gemm);
export_proto(matmul_c4);
+#ifdef __x86_64__
+
+/* For x86_64, we switch to AVX if that is available. For this, we
+ let the actual work be done by the static aux_matmul - function.
+ The user-callable function will then automagically contain the
+ selection code for the right architecture. This is done to avoid
+ knowledge of architecture details in the front end. */
+
+static void aux_matmul_c4 (gfc_array_c4 * const restrict retarray,
+ gfc_array_c4 * const restrict a, gfc_array_c4 * const restrict b, int try_blas,
+ int blas_limit, blas_call gemm)
+ __attribute__ ((target_clones("avx,default")));
+
void
matmul_c4 (gfc_array_c4 * const restrict retarray,
gfc_array_c4 * const restrict a, gfc_array_c4 * const restrict b, int try_blas,
int blas_limit, blas_call gemm)
{
+ aux_matmul_c4 (retarray, a, b, try_blas, blas_limit, gemm);
+}
+
+static void
+aux_matmul_c4 (gfc_array_c4 * const restrict retarray,
+ gfc_array_c4 * const restrict a, gfc_array_c4 * const restrict b, int try_blas,
+ int blas_limit, blas_call gemm)
+#else
+matmul_c4 (gfc_array_c4 * const restrict retarray,
+ gfc_array_c4 * const restrict a, gfc_array_c4 * const restrict b, int try_blas,
+ int blas_limit, blas_call gemm)
+#endif
+{
const GFC_COMPLEX_4 * restrict abase;
const GFC_COMPLEX_4 * restrict bbase;
GFC_COMPLEX_4 * restrict dest;
Index: generated/matmul_c8.c
===================================================================
--- generated/matmul_c8.c (Revision 242477)
+++ generated/matmul_c8.c (Arbeitskopie)
@@ -75,11 +75,37 @@ extern void matmul_c8 (gfc_array_c8 * const restri
int blas_limit, blas_call gemm);
export_proto(matmul_c8);
+#ifdef __x86_64__
+
+/* For x86_64, we switch to AVX if that is available. For this, we
+ let the actual work be done by the static aux_matmul - function.
+ The user-callable function will then automagically contain the
+ selection code for the right architecture. This is done to avoid
+ knowledge of architecture details in the front end. */
+
+static void aux_matmul_c8 (gfc_array_c8 * const restrict retarray,
+ gfc_array_c8 * const restrict a, gfc_array_c8 * const restrict b, int try_blas,
+ int blas_limit, blas_call gemm)
+ __attribute__ ((target_clones("avx,default")));
+
void
matmul_c8 (gfc_array_c8 * const restrict retarray,
gfc_array_c8 * const restrict a, gfc_array_c8 * const restrict b, int try_blas,
int blas_limit, blas_call gemm)
{
+ aux_matmul_c8 (retarray, a, b, try_blas, blas_limit, gemm);
+}
+
+static void
+aux_matmul_c8 (gfc_array_c8 * const restrict retarray,
+ gfc_array_c8 * const restrict a, gfc_array_c8 * const restrict b, int try_blas,
+ int blas_limit, blas_call gemm)
+#else
+matmul_c8 (gfc_array_c8 * const restrict retarray,
+ gfc_array_c8 * const restrict a, gfc_array_c8 * const restrict b, int try_blas,
+ int blas_limit, blas_call gemm)
+#endif
+{
const GFC_COMPLEX_8 * restrict abase;
const GFC_COMPLEX_8 * restrict bbase;
GFC_COMPLEX_8 * restrict dest;
Index: generated/matmul_i1.c
===================================================================
--- generated/matmul_i1.c (Revision 242477)
+++ generated/matmul_i1.c (Arbeitskopie)
@@ -75,11 +75,37 @@ extern void matmul_i1 (gfc_array_i1 * const restri
int blas_limit, blas_call gemm);
export_proto(matmul_i1);
+#ifdef __x86_64__
+
+/* For x86_64, we switch to AVX if that is available. For this, we
+ let the actual work be done by the static aux_matmul - function.
+ The user-callable function will then automagically contain the
+ selection code for the right architecture. This is done to avoid
+ knowledge of architecture details in the front end. */
+
+static void aux_matmul_i1 (gfc_array_i1 * const restrict retarray,
+ gfc_array_i1 * const restrict a, gfc_array_i1 * const restrict b, int try_blas,
+ int blas_limit, blas_call gemm)
+ __attribute__ ((target_clones("avx,default")));
+
void
matmul_i1 (gfc_array_i1 * const restrict retarray,
gfc_array_i1 * const restrict a, gfc_array_i1 * const restrict b, int try_blas,
int blas_limit, blas_call gemm)
{
+ aux_matmul_i1 (retarray, a, b, try_blas, blas_limit, gemm);
+}
+
+static void
+aux_matmul_i1 (gfc_array_i1 * const restrict retarray,
+ gfc_array_i1 * const restrict a, gfc_array_i1 * const restrict b, int try_blas,
+ int blas_limit, blas_call gemm)
+#else
+matmul_i1 (gfc_array_i1 * const restrict retarray,
+ gfc_array_i1 * const restrict a, gfc_array_i1 * const restrict b, int try_blas,
+ int blas_limit, blas_call gemm)
+#endif
+{
const GFC_INTEGER_1 * restrict abase;
const GFC_INTEGER_1 * restrict bbase;
GFC_INTEGER_1 * restrict dest;
Index: generated/matmul_i16.c
===================================================================
--- generated/matmul_i16.c (Revision 242477)
+++ generated/matmul_i16.c (Arbeitskopie)
@@ -75,11 +75,37 @@ extern void matmul_i16 (gfc_array_i16 * const rest
int blas_limit, blas_call gemm);
export_proto(matmul_i16);
+#ifdef __x86_64__
+
+/* For x86_64, we switch to AVX if that is available. For this, we
+ let the actual work be done by the static aux_matmul - function.
+ The user-callable function will then automagically contain the
+ selection code for the right architecture. This is done to avoid
+ knowledge of architecture details in the front end. */
+
+static void aux_matmul_i16 (gfc_array_i16 * const restrict retarray,
+ gfc_array_i16 * const restrict a, gfc_array_i16 * const restrict b, int try_blas,
+ int blas_limit, blas_call gemm)
+ __attribute__ ((target_clones("avx,default")));
+
void
matmul_i16 (gfc_array_i16 * const restrict retarray,
gfc_array_i16 * const restrict a, gfc_array_i16 * const restrict b, int try_blas,
int blas_limit, blas_call gemm)
{
+ aux_matmul_i16 (retarray, a, b, try_blas, blas_limit, gemm);
+}
+
+static void
+aux_matmul_i16 (gfc_array_i16 * const restrict retarray,
+ gfc_array_i16 * const restrict a, gfc_array_i16 * const restrict b, int try_blas,
+ int blas_limit, blas_call gemm)
+#else
+matmul_i16 (gfc_array_i16 * const restrict retarray,
+ gfc_array_i16 * const restrict a, gfc_array_i16 * const restrict b, int try_blas,
+ int blas_limit, blas_call gemm)
+#endif
+{
const GFC_INTEGER_16 * restrict abase;
const GFC_INTEGER_16 * restrict bbase;
GFC_INTEGER_16 * restrict dest;
Index: generated/matmul_i2.c
===================================================================
--- generated/matmul_i2.c (Revision 242477)
+++ generated/matmul_i2.c (Arbeitskopie)
@@ -75,11 +75,37 @@ extern void matmul_i2 (gfc_array_i2 * const restri
int blas_limit, blas_call gemm);
export_proto(matmul_i2);
+#ifdef __x86_64__
+
+/* For x86_64, we switch to AVX if that is available. For this, we
+ let the actual work be done by the static aux_matmul - function.
+ The user-callable function will then automagically contain the
+ selection code for the right architecture. This is done to avoid
+ knowledge of architecture details in the front end. */
+
+static void aux_matmul_i2 (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_clones("avx,default")));
+
void
matmul_i2 (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)
{
+ aux_matmul_i2 (retarray, a, b, try_blas, blas_limit, gemm);
+}
+
+static void
+aux_matmul_i2 (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)
+#else
+matmul_i2 (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)
+#endif
+{
const GFC_INTEGER_2 * restrict abase;
const GFC_INTEGER_2 * restrict bbase;
GFC_INTEGER_2 * restrict dest;
Index: generated/matmul_i4.c
===================================================================
--- generated/matmul_i4.c (Revision 242477)
+++ generated/matmul_i4.c (Arbeitskopie)
@@ -75,11 +75,37 @@ extern void matmul_i4 (gfc_array_i4 * const restri
int blas_limit, blas_call gemm);
export_proto(matmul_i4);
+#ifdef __x86_64__
+
+/* For x86_64, we switch to AVX if that is available. For this, we
+ let the actual work be done by the static aux_matmul - function.
+ The user-callable function will then automagically contain the
+ selection code for the right architecture. This is done to avoid
+ knowledge of architecture details in the front end. */
+
+static void aux_matmul_i4 (gfc_array_i4 * const restrict retarray,
+ gfc_array_i4 * const restrict a, gfc_array_i4 * const restrict b, int try_blas,
+ int blas_limit, blas_call gemm)
+ __attribute__ ((target_clones("avx,default")));
+
void
matmul_i4 (gfc_array_i4 * const restrict retarray,
gfc_array_i4 * const restrict a, gfc_array_i4 * const restrict b, int try_blas,
int blas_limit, blas_call gemm)
{
+ aux_matmul_i4 (retarray, a, b, try_blas, blas_limit, gemm);
+}
+
+static void
+aux_matmul_i4 (gfc_array_i4 * const restrict retarray,
+ gfc_array_i4 * const restrict a, gfc_array_i4 * const restrict b, int try_blas,
+ int blas_limit, blas_call gemm)
+#else
+matmul_i4 (gfc_array_i4 * const restrict retarray,
+ gfc_array_i4 * const restrict a, gfc_array_i4 * const restrict b, int try_blas,
+ int blas_limit, blas_call gemm)
+#endif
+{
const GFC_INTEGER_4 * restrict abase;
const GFC_INTEGER_4 * restrict bbase;
GFC_INTEGER_4 * restrict dest;
Index: generated/matmul_i8.c
===================================================================
--- generated/matmul_i8.c (Revision 242477)
+++ generated/matmul_i8.c (Arbeitskopie)
@@ -75,11 +75,37 @@ extern void matmul_i8 (gfc_array_i8 * const restri
int blas_limit, blas_call gemm);
export_proto(matmul_i8);
+#ifdef __x86_64__
+
+/* For x86_64, we switch to AVX if that is available. For this, we
+ let the actual work be done by the static aux_matmul - function.
+ The user-callable function will then automagically contain the
+ selection code for the right architecture. This is done to avoid
+ knowledge of architecture details in the front end. */
+
+static void aux_matmul_i8 (gfc_array_i8 * const restrict retarray,
+ gfc_array_i8 * const restrict a, gfc_array_i8 * const restrict b, int try_blas,
+ int blas_limit, blas_call gemm)
+ __attribute__ ((target_clones("avx,default")));
+
void
matmul_i8 (gfc_array_i8 * const restrict retarray,
gfc_array_i8 * const restrict a, gfc_array_i8 * const restrict b, int try_blas,
int blas_limit, blas_call gemm)
{
+ aux_matmul_i8 (retarray, a, b, try_blas, blas_limit, gemm);
+}
+
+static void
+aux_matmul_i8 (gfc_array_i8 * const restrict retarray,
+ gfc_array_i8 * const restrict a, gfc_array_i8 * const restrict b, int try_blas,
+ int blas_limit, blas_call gemm)
+#else
+matmul_i8 (gfc_array_i8 * const restrict retarray,
+ gfc_array_i8 * const restrict a, gfc_array_i8 * const restrict b, int try_blas,
+ int blas_limit, blas_call gemm)
+#endif
+{
const GFC_INTEGER_8 * restrict abase;
const GFC_INTEGER_8 * restrict bbase;
GFC_INTEGER_8 * restrict dest;
Index: generated/matmul_r10.c
===================================================================
--- generated/matmul_r10.c (Revision 242477)
+++ generated/matmul_r10.c (Arbeitskopie)
@@ -75,11 +75,37 @@ extern void matmul_r10 (gfc_array_r10 * const rest
int blas_limit, blas_call gemm);
export_proto(matmul_r10);
+#ifdef __x86_64__
+
+/* For x86_64, we switch to AVX if that is available. For this, we
+ let the actual work be done by the static aux_matmul - function.
+ The user-callable function will then automagically contain the
+ selection code for the right architecture. This is done to avoid
+ knowledge of architecture details in the front end. */
+
+static void aux_matmul_r10 (gfc_array_r10 * const restrict retarray,
+ gfc_array_r10 * const restrict a, gfc_array_r10 * const restrict b, int try_blas,
+ int blas_limit, blas_call gemm)
+ __attribute__ ((target_clones("avx,default")));
+
void
matmul_r10 (gfc_array_r10 * const restrict retarray,
gfc_array_r10 * const restrict a, gfc_array_r10 * const restrict b, int try_blas,
int blas_limit, blas_call gemm)
{
+ aux_matmul_r10 (retarray, a, b, try_blas, blas_limit, gemm);
+}
+
+static void
+aux_matmul_r10 (gfc_array_r10 * const restrict retarray,
+ gfc_array_r10 * const restrict a, gfc_array_r10 * const restrict b, int try_blas,
+ int blas_limit, blas_call gemm)
+#else
+matmul_r10 (gfc_array_r10 * const restrict retarray,
+ gfc_array_r10 * const restrict a, gfc_array_r10 * const restrict b, int try_blas,
+ int blas_limit, blas_call gemm)
+#endif
+{
const GFC_REAL_10 * restrict abase;
const GFC_REAL_10 * restrict bbase;
GFC_REAL_10 * restrict dest;
Index: generated/matmul_r16.c
===================================================================
--- generated/matmul_r16.c (Revision 242477)
+++ generated/matmul_r16.c (Arbeitskopie)
@@ -75,11 +75,37 @@ extern void matmul_r16 (gfc_array_r16 * const rest
int blas_limit, blas_call gemm);
export_proto(matmul_r16);
+#ifdef __x86_64__
+
+/* For x86_64, we switch to AVX if that is available. For this, we
+ let the actual work be done by the static aux_matmul - function.
+ The user-callable function will then automagically contain the
+ selection code for the right architecture. This is done to avoid
+ knowledge of architecture details in the front end. */
+
+static void aux_matmul_r16 (gfc_array_r16 * const restrict retarray,
+ gfc_array_r16 * const restrict a, gfc_array_r16 * const restrict b, int try_blas,
+ int blas_limit, blas_call gemm)
+ __attribute__ ((target_clones("avx,default")));
+
void
matmul_r16 (gfc_array_r16 * const restrict retarray,
gfc_array_r16 * const restrict a, gfc_array_r16 * const restrict b, int try_blas,
int blas_limit, blas_call gemm)
{
+ aux_matmul_r16 (retarray, a, b, try_blas, blas_limit, gemm);
+}
+
+static void
+aux_matmul_r16 (gfc_array_r16 * const restrict retarray,
+ gfc_array_r16 * const restrict a, gfc_array_r16 * const restrict b, int try_blas,
+ int blas_limit, blas_call gemm)
+#else
+matmul_r16 (gfc_array_r16 * const restrict retarray,
+ gfc_array_r16 * const restrict a, gfc_array_r16 * const restrict b, int try_blas,
+ int blas_limit, blas_call gemm)
+#endif
+{
const GFC_REAL_16 * restrict abase;
const GFC_REAL_16 * restrict bbase;
GFC_REAL_16 * restrict dest;
Index: generated/matmul_r4.c
===================================================================
--- generated/matmul_r4.c (Revision 242477)
+++ generated/matmul_r4.c (Arbeitskopie)
@@ -75,11 +75,37 @@ extern void matmul_r4 (gfc_array_r4 * const restri
int blas_limit, blas_call gemm);
export_proto(matmul_r4);
+#ifdef __x86_64__
+
+/* For x86_64, we switch to AVX if that is available. For this, we
+ let the actual work be done by the static aux_matmul - function.
+ The user-callable function will then automagically contain the
+ selection code for the right architecture. This is done to avoid
+ knowledge of architecture details in the front end. */
+
+static void aux_matmul_r4 (gfc_array_r4 * const restrict retarray,
+ gfc_array_r4 * const restrict a, gfc_array_r4 * const restrict b, int try_blas,
+ int blas_limit, blas_call gemm)
+ __attribute__ ((target_clones("avx,default")));
+
void
matmul_r4 (gfc_array_r4 * const restrict retarray,
gfc_array_r4 * const restrict a, gfc_array_r4 * const restrict b, int try_blas,
int blas_limit, blas_call gemm)
{
+ aux_matmul_r4 (retarray, a, b, try_blas, blas_limit, gemm);
+}
+
+static void
+aux_matmul_r4 (gfc_array_r4 * const restrict retarray,
+ gfc_array_r4 * const restrict a, gfc_array_r4 * const restrict b, int try_blas,
+ int blas_limit, blas_call gemm)
+#else
+matmul_r4 (gfc_array_r4 * const restrict retarray,
+ gfc_array_r4 * const restrict a, gfc_array_r4 * const restrict b, int try_blas,
+ int blas_limit, blas_call gemm)
+#endif
+{
const GFC_REAL_4 * restrict abase;
const GFC_REAL_4 * restrict bbase;
GFC_REAL_4 * restrict dest;
Index: generated/matmul_r8.c
===================================================================
--- generated/matmul_r8.c (Revision 242477)
+++ generated/matmul_r8.c (Arbeitskopie)
@@ -75,11 +75,37 @@ extern void matmul_r8 (gfc_array_r8 * const restri
int blas_limit, blas_call gemm);
export_proto(matmul_r8);
+#ifdef __x86_64__
+
+/* For x86_64, we switch to AVX if that is available. For this, we
+ let the actual work be done by the static aux_matmul - function.
+ The user-callable function will then automagically contain the
+ selection code for the right architecture. This is done to avoid
+ knowledge of architecture details in the front end. */
+
+static void aux_matmul_r8 (gfc_array_r8 * const restrict retarray,
+ gfc_array_r8 * const restrict a, gfc_array_r8 * const restrict b, int try_blas,
+ int blas_limit, blas_call gemm)
+ __attribute__ ((target_clones("avx,default")));
+
void
matmul_r8 (gfc_array_r8 * const restrict retarray,
gfc_array_r8 * const restrict a, gfc_array_r8 * const restrict b, int try_blas,
int blas_limit, blas_call gemm)
{
+ aux_matmul_r8 (retarray, a, b, try_blas, blas_limit, gemm);
+}
+
+static void
+aux_matmul_r8 (gfc_array_r8 * const restrict retarray,
+ gfc_array_r8 * const restrict a, gfc_array_r8 * const restrict b, int try_blas,
+ int blas_limit, blas_call gemm)
+#else
+matmul_r8 (gfc_array_r8 * const restrict retarray,
+ gfc_array_r8 * const restrict a, gfc_array_r8 * const restrict b, int try_blas,
+ int blas_limit, blas_call gemm)
+#endif
+{
const GFC_REAL_8 * restrict abase;
const GFC_REAL_8 * restrict bbase;
GFC_REAL_8 * restrict dest;
Index: m4/matmul.m4
===================================================================
--- m4/matmul.m4 (Revision 242477)
+++ m4/matmul.m4 (Arbeitskopie)
@@ -76,11 +76,37 @@ extern void matmul_'rtype_code` ('rtype` * const r
int blas_limit, blas_call gemm);
export_proto(matmul_'rtype_code`);
+#ifdef __x86_64__
+
+/* For x86_64, we switch to AVX if that is available. For this, we
+ let the actual work be done by the static aux_matmul - function.
+ The user-callable function will then automagically contain the
+ selection code for the right architecture. This is done to avoid
+ knowledge of architecture details in the front end. */
+
+static void aux_matmul_'rtype_code` ('rtype` * const restrict retarray,
+ 'rtype` * const restrict a, 'rtype` * const restrict b, int try_blas,
+ int blas_limit, blas_call gemm)
+ __attribute__ ((target_clones("avx,default")));
+
void
matmul_'rtype_code` ('rtype` * const restrict retarray,
'rtype` * const restrict a, 'rtype` * const restrict b, int try_blas,
int blas_limit, blas_call gemm)
{
+ aux_matmul_'rtype_code` (retarray, a, b, try_blas, blas_limit, gemm);
+}
+
+static void
+aux_matmul_'rtype_code` ('rtype` * const restrict retarray,
+ 'rtype` * const restrict a, 'rtype` * const restrict b, int try_blas,
+ int blas_limit, blas_call gemm)
+#else
+matmul_'rtype_code` ('rtype` * const restrict retarray,
+ 'rtype` * const restrict a, 'rtype` * const restrict b, int try_blas,
+ int blas_limit, blas_call gemm)
+#endif
+{
const 'rtype_name` * restrict abase;
const 'rtype_name` * restrict bbase;
'rtype_name` * restrict dest;
