Skip to content
Snippets Groups Projects
Commit 9cf002da authored by ESCOBAR MUNOZ Juan's avatar ESCOBAR MUNOZ Juan
Browse files

30/08/2021:dotprod.f90, optimisation for GPU , add kernels + loop independent

parent d1d95ee5
Branches
No related tags found
No related merge requests found
......@@ -168,14 +168,18 @@ ENDIF
!
!JUAN16
ALLOCATE(ZDOTPROD(ILBXB:ILBXE,ILBYB:ILBYE))
!$acc kernels
ZDOTPROD = 0.
!$acc loop seq
DO JK = IKB-1,IKE+1
!$acc loop independent collapse(2)
DO JJ = ILBYB,ILBYE
DO JI = ILBXB,ILBXE
ZDOTPROD(JI,JJ) = ZDOTPROD(JI,JJ) + PA(JI,JJ,JK) * PB(JI,JJ,JK)
END DO
END DO
END DO
!$acc end kernels
PDOTPROD = SUM_DD_R2_ll(ZDOTPROD)
!JUAN16
!
......
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Please register or to comment