https://gcc.gnu.org/bugzilla/show_bug.cgi?id=106565
Bug ID: 106565
Summary: Using a transposed matrix in matmul (GCC-10.3.0) is
very slow
Product: gcc
Version: unknown
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: fortran
Assignee: unassigned at gcc dot gnu.org
Reporter: quanhua.liu at noaa dot gov
Target Milestone: ---
gcc version 10.3.0 (GCC)
linux
Using (2) BB = transpose(B)
C = matmul(A, BB)
is 5 times faster than
using (1) C = matmul(A, transpose(B))
ifort 19 doesn't have the problem.
PROGRAM test_matrixCal
! ------------------------------------------------------
! This code test
! (1) C = matmul(A, transpose(B))
! against
! (2) BB = transpose(B)
! C = matmul(A, BB)
! (2) is 5 times faster than (1)
! gfortran -O3 test_matrixCal
! time a.ot
! ------------------------------------------------------
INTEGER, PARAMETER :: m = 200, n = 300, nn = 150
REAL :: A(m,n), B(nn,n), C(m,nn), BB(n,nn)
INTEGER :: i, j, k, L
A(:,:) = 3.0
B(:,:) = 1.7
iterative_loop: DO L = 1, 1000
A(:,10) = A(:,10) + 0.0001*L
! C = matmul(A, transpose(B))
BB = transpose(B)
C = matmul(A, BB)
IF(mod(L,50) == 0) print *,L, C(10,20)
END DO iterative_loop
STOP
END PROGRAM test_matrixCal
