64-BitBrainstorm_2026/AMSS-NCKU
8
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add OpenMP parallelization to Fortran compute kernels

Browse Source 
Add !$omp parallel do collapse(2) directives to all triple-loop
stencil kernels (fderivs, fdderivs, fdx/fdy/fdz, kodis, lopsided,
enforce_ag/enforce_ga) across all ghost_width variants. Add !$omp
parallel workshare to RK4/ICN/Euler whole-array update routines.

Build system: add -qopenmp to compile and link flags, switch MKL
from sequential to threaded (-lmkl_intel_thread -liomp5).

Runtime: set OMP_NUM_THREADS=96, OMP_STACKSIZE=16M, OMP_PROC_BIND=close,
OMP_PLACES=cores for 96-core server target.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
CGH0S7
2026-02-10 23:40:17 +08:00
parent caf192b2e4
commit 714c6e90c6
10 changed files with 171 additions and 32 deletions
Download Patch File Download Diff File Expand all files Collapse all files

30
AMSS_NCKU_source/kodiss_sh.f90
View File

@@ -80,7 +80,8 @@ real*8,intent(in) :: eps
! dx^4
! note the sign (-1)^r-1, now r=2
do k=1,ex(3)
!$omp parallel do collapse(2) private(i,j,k)
do k=1,ex(3)
do j=1,ex(2)
do i=1,ex(1)
@@ -178,7 +179,8 @@ real*8,intent(in) :: eps
! dx^4
! note the sign (-1)^r-1, now r=2
do k=1,ex(3)
!$omp parallel do collapse(2) private(i,j,k)
do k=1,ex(3)
do j=1,ex(2)
do i=1,ex(1)
@@ -273,7 +275,8 @@ integer, parameter :: NO_SYMM=0, EQ_SYMM=1, OCTANT=2
call symmetry_stbd(2,ex,f,fh,SoA)
do k=1,ex(3)
!$omp parallel do collapse(2) private(i,j,k)
do k=1,ex(3)
do j=1,ex(2)
do i=1,ex(1)
@@ -369,7 +372,8 @@ integer, parameter :: NO_SYMM=0, EQ_SYMM=1, OCTANT=2
call symmetry_stbd(3,ex,f,fh,SoA)
do k=1,ex(3)
!$omp parallel do collapse(2) private(i,j,k)
do k=1,ex(3)
do j=1,ex(2)
do i=1,ex(1)
@@ -510,7 +514,8 @@ integer, parameter :: NO_SYMM=0, EQ_SYMM=1, OCTANT=2
call symmetry_stbd(3,ex,f,fh,SoA)
do k=1,ex(3)
!$omp parallel do collapse(2) private(i,j,k)
do k=1,ex(3)
do j=1,ex(2)
do i=1,ex(1)
@@ -598,7 +603,8 @@ integer, parameter :: NO_SYMM=0, EQ_SYMM=1, OCTANT=2
call symmetry_stbd(3,ex,f,fh,SoA)
do k=1,ex(3)
!$omp parallel do collapse(2) private(i,j,k)
do k=1,ex(3)
do j=1,ex(2)
do i=1,ex(1)
@@ -694,7 +700,8 @@ real*8,intent(in) :: eps
! dx^8
! note the sign (-1)^r-1, now r=4
do k=1,ex(3)
!$omp parallel do collapse(2) private(i,j,k)
do k=1,ex(3)
do j=1,ex(2)
do i=1,ex(1)
@@ -794,7 +801,8 @@ integer, parameter :: NO_SYMM=0, EQ_SYMM=1, OCTANT=2
call symmetry_stbd(4,ex,f,fh,SoA)
do k=1,ex(3)
!$omp parallel do collapse(2) private(i,j,k)
do k=1,ex(3)
do j=1,ex(2)
do i=1,ex(1)
@@ -903,7 +911,8 @@ real*8,intent(in) :: eps
! dx^10
! note the sign (-1)^r-1, now r=5
do k=1,ex(3)
!$omp parallel do collapse(2) private(i,j,k)
do k=1,ex(3)
do j=1,ex(2)
do i=1,ex(1)
@@ -1006,7 +1015,8 @@ integer, parameter :: NO_SYMM=0, EQ_SYMM=1, OCTANT=2
call symmetry_stbd(5,ex,f,fh,SoA)
do k=1,ex(3)
!$omp parallel do collapse(2) private(i,j,k)
do k=1,ex(3)
do j=1,ex(2)
do i=1,ex(1)