Skip to content

Add line numbering to gpu loops #1029

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 15 commits into
base: master
Choose a base branch
from
Open

Add line numbering to gpu loops #1029

Show file tree
Hide file tree
Changes from 8 commits
Commits
Show all changes
15 commits
Select commit Hold shift + click to select a range
ed2bc5e
Correct line markers have been recovered
danieljvickers Nov 6, 2025
35c57eb
Made it through common
danieljvickers Nov 6, 2025
477a13b
Modified a few hundred macros
danieljvickers Nov 6, 2025
3c010f8
Finished with parallel loops
danieljvickers Nov 6, 2025
f8dd4cd
Removed duplicate parallel statements
danieljvickers Nov 6, 2025
fd482ed
This builds
danieljvickers Nov 6, 2025
ceec116
Removed all warnings
danieljvickers Nov 6, 2025
0ce8883
Spelling and Format
danieljvickers Nov 6, 2025
824585f
Updated macro API documentation
danieljvickers Nov 6, 2025
28a20bb
Spelling
danieljvickers Nov 6, 2025
5f768ec
Found an error in how FYPP processes that resulted in only openMP dir…
danieljvickers Nov 7, 2025
5ea3506
Resolved chemistry issues
danieljvickers Nov 7, 2025
1980851
Ben found my IO error
danieljvickers Nov 7, 2025
1d5e33c
Fixed issue with s_get_char_vol being elemental, which means that it …
danieljvickers Nov 7, 2025
723822d
All tests pass on wingtip
danieljvickers Nov 7, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 2 additions & 5 deletions src/common/include/acc_macros.fpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -129,7 +129,7 @@
$:end_acc_directive
#:enddef

#:def ACC_PARALLEL_LOOP(code, collapse=None, private=None, parallelism='[gang, vector]', &
#:def ACC_PARALLEL_LOOP(collapse=None, private=None, parallelism='[gang, vector]', &
& default='present', firstprivate=None, reduction=None, reductionOp=None, &
& copy=None, copyin=None, copyinReadOnly=None, copyout=None, create=None, &
& no_create=None, present=None, deviceptr=None, attach=None, extraAccArgs=None)
Expand All @@ -155,10 +155,7 @@
& deviceptr_val.strip('\n') + attach_val.strip('\n')
#:set acc_directive = '!$acc parallel loop ' + &
& clause_val + extraAccArgs_val.strip('\n')
#:set acc_end_directive = '!$acc end parallel loop'
$:acc_directive
$:code
$:acc_end_directive
#:enddef

#:def ACC_ROUTINE(function_name=None, parallelism=None, nohost=False, extraAccArgs=None)
Expand Down Expand Up @@ -308,4 +305,4 @@
#:set acc_directive = '!$acc wait ' + clause_val + extraAccArgs_val.strip('\n')
$:acc_directive
#:enddef
! New line at end of file is required for FYPP
! New line at end of file is required for FYPP
21 changes: 15 additions & 6 deletions src/common/include/omp_macros.fpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -149,7 +149,7 @@
$:omp_end_directive
#:enddef

#:def OMP_PARALLEL_LOOP(code, collapse=None, private=None, parallelism='[gang, vector]', &
#:def OMP_PARALLEL_LOOP(collapse=None, private=None, parallelism='[gang, vector]', &
& default='present', firstprivate=None, reduction=None, reductionOp=None, &
& copy=None, copyin=None, copyinReadOnly=None, copyout=None, create=None, &
& no_create=None, present=None, deviceptr=None, attach=None, extraOmpArgs=None)
Expand Down Expand Up @@ -178,21 +178,30 @@

#:if MFC_COMPILER == NVIDIA_COMPILER_ID or MFC_COMPILER == PGI_COMPILER_ID
#:set omp_start_directive = '!$omp target teams loop defaultmap(firstprivate:scalar) bind(teams,parallel) '
#:set omp_end_directive = '!$omp end target teams loop'
#:elif MFC_COMPILER == CCE_COMPILER_ID
#:set omp_start_directive = '!$omp target teams distribute parallel do simd defaultmap(firstprivate:scalar) '
#:set omp_end_directive = '!$omp end target teams distribute parallel do simd'
#:elif MFC_COMPILER == AMD_COMPILER_ID
#:set omp_start_directive = '!$omp target teams distribute parallel do '
#:set omp_end_directive = '!$omp end target teams distribute parallel do'
#:else
#:set omp_start_directive = '!$omp target teams loop defaultmap(firstprivate:scalar) bind(teams,parallel) '
#:set omp_end_directive = '!$omp end target teams loop'
#:endif

#:set omp_directive = omp_start_directive + clause_val + extraOmpArgs_val.strip('\n')
$:omp_directive
$:code
#:enddef

#:def END_OMP_PARALLEL_LOOP()

#:if MFC_COMPILER == NVIDIA_COMPILER_ID or MFC_COMPILER == PGI_COMPILER_ID
#:set omp_end_directive = '!$omp end target teams loop'
#:elif MFC_COMPILER == CCE_COMPILER_ID
#:set omp_end_directive = '!$omp end target teams distribute parallel do simd'
#:elif MFC_COMPILER == AMD_COMPILER_ID
#:set omp_end_directive = '!$omp end target teams distribute parallel do'
#:else
#:set omp_end_directive = '!$omp end target teams loop'
#:endif

$:omp_end_directive
#:enddef

Expand Down
24 changes: 17 additions & 7 deletions src/common/include/parallel_macros.fpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,21 +19,31 @@

#:enddef

#:def GPU_PARALLEL_LOOP(code, collapse=None, private=None, parallelism='[gang, vector]', &
#:def GPU_PARALLEL_LOOP(collapse=None, private=None, parallelism='[gang, vector]', &
& default='present', firstprivate=None, reduction=None, reductionOp=None, &
& copy=None, copyin=None, copyinReadOnly=None, copyout=None, create=None, &
& no_create=None, present=None, deviceptr=None, attach=None, extraAccArgs=None, extraOmpArgs=None)

#:set acc_code = ACC_PARALLEL_LOOP(code, collapse, private, parallelism, default, firstprivate, reduction, reductionOp, copy, copyin, copyinReadOnly, copyout, create, no_create, present, deviceptr, attach, extraAccArgs)
#:set omp_code = OMP_PARALLEL_LOOP(code, collapse, private, parallelism, default, firstprivate, reduction, reductionOp, copy, copyin, copyinReadOnly, copyout, create, no_create, present, deviceptr, attach, extraOmpArgs)
#if defined(MFC_OpenACC)
#:set directive = ACC_PARALLEL_LOOP(collapse, private, parallelism, default, firstprivate, reduction, reductionOp, copy, copyin, copyinReadOnly, copyout, create, no_create, present, deviceptr, attach, extraAccArgs)
#elif defined(MFC_OpenMP)
#:set directive = OMP_PARALLEL_LOOP(collapse, private, parallelism, default, firstprivate, reduction, reductionOp, copy, copyin, copyinReadOnly, copyout, create, no_create, present, deviceptr, attach, extraOmpArgs)
#endif

$:directive

#:enddef

#:def END_GPU_PARALLEL_LOOP()

#if defined(MFC_OpenACC)
$:acc_code
#:set end_directive = '!$acc end parallel loop'
#elif defined(MFC_OpenMP)
$:omp_code
#else
$:code
#:set end_directive = END_OMP_PARALLEL_LOOP()
#endif

$:end_directive

#:enddef

#:def GPU_ROUTINE(function_name=None, parallelism=None, nohost=False, cray_inline=False, extraAccArgs=None, extraOmpArgs=None)
Expand Down
2 changes: 1 addition & 1 deletion src/common/include/shared_parallel_macros.fpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -107,4 +107,4 @@
#:endif
$:extraArgs_val
#:enddef
! New line at end of file is required for FYPP
! New line at end of file is required for FYPP
Loading
Loading