PR libfortran/99218 - matmul on temporary array accesses invalid memory

Do not invoke tuned rank-2 times rank-2 matmul if rank(b) == 1.

libgfortran/ChangeLog:

	PR libfortran/99218
	* m4/matmul_internal.m4: Invoke tuned matmul only for rank(b)>1.
	* generated/matmul_c10.c: Regenerated.
	* generated/matmul_c16.c: Likewise.
	* generated/matmul_c4.c: Likewise.
	* generated/matmul_c8.c: Likewise.
	* generated/matmul_i1.c: Likewise.
	* generated/matmul_i16.c: Likewise.
	* generated/matmul_i2.c: Likewise.
	* generated/matmul_i4.c: Likewise.
	* generated/matmul_i8.c: Likewise.
	* generated/matmul_r10.c: Likewise.
	* generated/matmul_r16.c: Likewise.
	* generated/matmul_r4.c: Likewise.
	* generated/matmul_r8.c: Likewise.
	* generated/matmulavx128_c10.c: Likewise.
	* generated/matmulavx128_c16.c: Likewise.
	* generated/matmulavx128_c4.c: Likewise.
	* generated/matmulavx128_c8.c: Likewise.
	* generated/matmulavx128_i1.c: Likewise.
	* generated/matmulavx128_i16.c: Likewise.
	* generated/matmulavx128_i2.c: Likewise.
	* generated/matmulavx128_i4.c: Likewise.
	* generated/matmulavx128_i8.c: Likewise.
	* generated/matmulavx128_r10.c: Likewise.
	* generated/matmulavx128_r16.c: Likewise.
	* generated/matmulavx128_r4.c: Likewise.
	* generated/matmulavx128_r8.c: Likewise.

gcc/testsuite/ChangeLog:

	PR libfortran/99218
	* gfortran.dg/matmul_21.f90: New test.
This commit is contained in:
Harald Anlauf 2021-03-05 20:57:54 +01:00
parent 1e5cdb9f89
commit b1bee29167
28 changed files with 199 additions and 92 deletions

View File

@ -0,0 +1,15 @@
! { dg-do run }
! PR libfortran/99218 - matmul on temporary array accesses invalid memory
program p
implicit none
integer, parameter :: nState = 300000
integer, parameter :: nCon = 1
real, parameter :: ZERO = 0.0
real :: G(nCon,nState) = ZERO
real :: H(nState,nCon) = ZERO
real :: lambda(nCon) = ZERO
real :: f(nState) = ZERO
f = matmul (transpose (G), lambda)
if (f(1) /= ZERO) stop 1
end program

View File

@ -276,7 +276,8 @@ matmul_c10_avx (gfc_array_c10 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1
@ -844,7 +845,8 @@ matmul_c10_avx2 (gfc_array_c10 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1
@ -1412,7 +1414,8 @@ matmul_c10_avx512f (gfc_array_c10 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1
@ -1994,7 +1997,8 @@ matmul_c10_vanilla (gfc_array_c10 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1
@ -2635,7 +2639,8 @@ matmul_c10 (gfc_array_c10 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1

View File

@ -276,7 +276,8 @@ matmul_c16_avx (gfc_array_c16 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1
@ -844,7 +845,8 @@ matmul_c16_avx2 (gfc_array_c16 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1
@ -1412,7 +1414,8 @@ matmul_c16_avx512f (gfc_array_c16 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1
@ -1994,7 +1997,8 @@ matmul_c16_vanilla (gfc_array_c16 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1
@ -2635,7 +2639,8 @@ matmul_c16 (gfc_array_c16 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1

View File

@ -276,7 +276,8 @@ matmul_c4_avx (gfc_array_c4 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1
@ -844,7 +845,8 @@ matmul_c4_avx2 (gfc_array_c4 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1
@ -1412,7 +1414,8 @@ matmul_c4_avx512f (gfc_array_c4 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1
@ -1994,7 +1997,8 @@ matmul_c4_vanilla (gfc_array_c4 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1
@ -2635,7 +2639,8 @@ matmul_c4 (gfc_array_c4 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1

View File

@ -276,7 +276,8 @@ matmul_c8_avx (gfc_array_c8 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1
@ -844,7 +845,8 @@ matmul_c8_avx2 (gfc_array_c8 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1
@ -1412,7 +1414,8 @@ matmul_c8_avx512f (gfc_array_c8 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1
@ -1994,7 +1997,8 @@ matmul_c8_vanilla (gfc_array_c8 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1
@ -2635,7 +2639,8 @@ matmul_c8 (gfc_array_c8 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1

View File

@ -276,7 +276,8 @@ matmul_i1_avx (gfc_array_i1 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1
@ -844,7 +845,8 @@ matmul_i1_avx2 (gfc_array_i1 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1
@ -1412,7 +1414,8 @@ matmul_i1_avx512f (gfc_array_i1 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1
@ -1994,7 +1997,8 @@ matmul_i1_vanilla (gfc_array_i1 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1
@ -2635,7 +2639,8 @@ matmul_i1 (gfc_array_i1 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1

View File

@ -276,7 +276,8 @@ matmul_i16_avx (gfc_array_i16 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1
@ -844,7 +845,8 @@ matmul_i16_avx2 (gfc_array_i16 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1
@ -1412,7 +1414,8 @@ matmul_i16_avx512f (gfc_array_i16 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1
@ -1994,7 +1997,8 @@ matmul_i16_vanilla (gfc_array_i16 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1
@ -2635,7 +2639,8 @@ matmul_i16 (gfc_array_i16 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1

View File

@ -276,7 +276,8 @@ matmul_i2_avx (gfc_array_i2 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1
@ -844,7 +845,8 @@ matmul_i2_avx2 (gfc_array_i2 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1
@ -1412,7 +1414,8 @@ matmul_i2_avx512f (gfc_array_i2 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1
@ -1994,7 +1997,8 @@ matmul_i2_vanilla (gfc_array_i2 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1
@ -2635,7 +2639,8 @@ matmul_i2 (gfc_array_i2 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1

View File

@ -276,7 +276,8 @@ matmul_i4_avx (gfc_array_i4 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1
@ -844,7 +845,8 @@ matmul_i4_avx2 (gfc_array_i4 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1
@ -1412,7 +1414,8 @@ matmul_i4_avx512f (gfc_array_i4 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1
@ -1994,7 +1997,8 @@ matmul_i4_vanilla (gfc_array_i4 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1
@ -2635,7 +2639,8 @@ matmul_i4 (gfc_array_i4 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1

View File

@ -276,7 +276,8 @@ matmul_i8_avx (gfc_array_i8 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1
@ -844,7 +845,8 @@ matmul_i8_avx2 (gfc_array_i8 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1
@ -1412,7 +1414,8 @@ matmul_i8_avx512f (gfc_array_i8 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1
@ -1994,7 +1997,8 @@ matmul_i8_vanilla (gfc_array_i8 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1
@ -2635,7 +2639,8 @@ matmul_i8 (gfc_array_i8 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1

View File

@ -276,7 +276,8 @@ matmul_r10_avx (gfc_array_r10 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1
@ -844,7 +845,8 @@ matmul_r10_avx2 (gfc_array_r10 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1
@ -1412,7 +1414,8 @@ matmul_r10_avx512f (gfc_array_r10 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1
@ -1994,7 +1997,8 @@ matmul_r10_vanilla (gfc_array_r10 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1
@ -2635,7 +2639,8 @@ matmul_r10 (gfc_array_r10 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1

View File

@ -276,7 +276,8 @@ matmul_r16_avx (gfc_array_r16 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1
@ -844,7 +845,8 @@ matmul_r16_avx2 (gfc_array_r16 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1
@ -1412,7 +1414,8 @@ matmul_r16_avx512f (gfc_array_r16 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1
@ -1994,7 +1997,8 @@ matmul_r16_vanilla (gfc_array_r16 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1
@ -2635,7 +2639,8 @@ matmul_r16 (gfc_array_r16 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1

View File

@ -276,7 +276,8 @@ matmul_r4_avx (gfc_array_r4 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1
@ -844,7 +845,8 @@ matmul_r4_avx2 (gfc_array_r4 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1
@ -1412,7 +1414,8 @@ matmul_r4_avx512f (gfc_array_r4 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1
@ -1994,7 +1997,8 @@ matmul_r4_vanilla (gfc_array_r4 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1
@ -2635,7 +2639,8 @@ matmul_r4 (gfc_array_r4 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1

View File

@ -276,7 +276,8 @@ matmul_r8_avx (gfc_array_r8 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1
@ -844,7 +845,8 @@ matmul_r8_avx2 (gfc_array_r8 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1
@ -1412,7 +1414,8 @@ matmul_r8_avx512f (gfc_array_r8 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1
@ -1994,7 +1997,8 @@ matmul_r8_vanilla (gfc_array_r8 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1
@ -2635,7 +2639,8 @@ matmul_r8 (gfc_array_r8 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1

View File

@ -241,7 +241,8 @@ matmul_c10_avx128_fma3 (gfc_array_c10 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1
@ -810,7 +811,8 @@ matmul_c10_avx128_fma4 (gfc_array_c10 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1

View File

@ -241,7 +241,8 @@ matmul_c16_avx128_fma3 (gfc_array_c16 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1
@ -810,7 +811,8 @@ matmul_c16_avx128_fma4 (gfc_array_c16 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1

View File

@ -241,7 +241,8 @@ matmul_c4_avx128_fma3 (gfc_array_c4 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1
@ -810,7 +811,8 @@ matmul_c4_avx128_fma4 (gfc_array_c4 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1

View File

@ -241,7 +241,8 @@ matmul_c8_avx128_fma3 (gfc_array_c8 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1
@ -810,7 +811,8 @@ matmul_c8_avx128_fma4 (gfc_array_c8 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1

View File

@ -241,7 +241,8 @@ matmul_i1_avx128_fma3 (gfc_array_i1 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1
@ -810,7 +811,8 @@ matmul_i1_avx128_fma4 (gfc_array_i1 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1

View File

@ -241,7 +241,8 @@ matmul_i16_avx128_fma3 (gfc_array_i16 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1
@ -810,7 +811,8 @@ matmul_i16_avx128_fma4 (gfc_array_i16 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1

View File

@ -241,7 +241,8 @@ matmul_i2_avx128_fma3 (gfc_array_i2 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1
@ -810,7 +811,8 @@ matmul_i2_avx128_fma4 (gfc_array_i2 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1

View File

@ -241,7 +241,8 @@ matmul_i4_avx128_fma3 (gfc_array_i4 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1
@ -810,7 +811,8 @@ matmul_i4_avx128_fma4 (gfc_array_i4 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1

View File

@ -241,7 +241,8 @@ matmul_i8_avx128_fma3 (gfc_array_i8 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1
@ -810,7 +811,8 @@ matmul_i8_avx128_fma4 (gfc_array_i8 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1

View File

@ -241,7 +241,8 @@ matmul_r10_avx128_fma3 (gfc_array_r10 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1
@ -810,7 +811,8 @@ matmul_r10_avx128_fma4 (gfc_array_r10 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1

View File

@ -241,7 +241,8 @@ matmul_r16_avx128_fma3 (gfc_array_r16 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1
@ -810,7 +811,8 @@ matmul_r16_avx128_fma4 (gfc_array_r16 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1

View File

@ -241,7 +241,8 @@ matmul_r4_avx128_fma3 (gfc_array_r4 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1
@ -810,7 +811,8 @@ matmul_r4_avx128_fma4 (gfc_array_r4 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1

View File

@ -241,7 +241,8 @@ matmul_r8_avx128_fma3 (gfc_array_r8 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1
@ -810,7 +811,8 @@ matmul_r8_avx128_fma4 (gfc_array_r8 * const restrict retarray,
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1

View File

@ -192,7 +192,8 @@ sinclude(`matmul_asm_'rtype_code`.m4')dnl
}
}
if (rxstride == 1 && axstride == 1 && bxstride == 1)
if (rxstride == 1 && axstride == 1 && bxstride == 1
&& GFC_DESCRIPTOR_RANK (b) != 1)
{
/* This block of code implements a tuned matmul, derived from
Superscalar GEMM-based level 3 BLAS, Beta version 0.1