derek.holloway
7502bf64a4
CodeQL / Analyze (actions) (push) Canceled after 0s
CodeQL / Analyze (python) (push) Canceled after 0s
pre-commit / pre-commit (push) Canceled after 0s
Multi-Arch CI / setup (push) Canceled after 0s
Publish build_manylinux_x86_64 images / publish_build_manylinux_x86_64 (push) Canceled after 0s
Setup (Multi-Arch) / setup (push) Canceled after 0s
Multi-Arch CI / Linux::${{ fromJSON(needs.setup.outputs.linux_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubi10 image / publish_no_rocm_image_ubi10 (push) Canceled after 0s
Multi-Arch CI / Windows::${{ fromJSON(needs.setup.outputs.windows_build_config || '{}').build_variant_label || 'skip' }} (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Multi-Arch CI / Manifest Diff (push) Canceled after 0s
TheRock Manifest Diff Report / Generate Manifest Diff Report (push) Canceled after 0s
Multi-Arch CI / CI Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_ocl_rt images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04_rocgdb images / publish_no_rocm_image_ubuntu24_04_rocgdb (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_ocl_rt (push) Canceled after 0s
Publish TheRock Docker image / build-and-push-image (push) Canceled after 0s
Unit Tests / Unit Tests :: ubuntu-24.04 (push) Canceled after 0s
Unit Tests / Unit Tests :: windows-2022 (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_media (push) Canceled after 0s
Unit Tests / Unit Tests Summary (push) Canceled after 0s
Publish no_rocm_image_ubuntu24_04 images / publish_no_rocm_image_ubuntu24_04_openmpi (push) Canceled after 0s
352 lines
8.2 KiB
Fortran
352 lines
8.2 KiB
Fortran
! The "thread_limit" clause was added to the "target" construct in OpenMP 5.1.
|
|
! RUN: %flang_fc1 -emit-hlfir -fopenmp -fopenmp-version=51 %s -o - | FileCheck %s --check-prefixes=BOTH,HOST
|
|
! RUN: %flang_fc1 -emit-hlfir -fopenmp -fopenmp-version=51 -fopenmp-is-target-device %s -o - | FileCheck %s --check-prefixes=BOTH,DEVICE
|
|
|
|
! BOTH-LABEL: func.func @_QPteams
|
|
subroutine teams()
|
|
! BOTH: omp.target
|
|
|
|
! HOST-SAME: host_eval(%{{.*}} -> %[[NUM_TEAMS:.*]], %{{.*}} -> %[[THREAD_LIMIT:.*]] : i32, i32)
|
|
|
|
! DEVICE-NOT: host_eval({{.*}})
|
|
! DEVICE-SAME: {
|
|
!$omp target
|
|
|
|
! BOTH: omp.teams
|
|
|
|
! HOST-SAME: num_teams( to %[[NUM_TEAMS]] : i32) thread_limit(%[[THREAD_LIMIT]] : i32)
|
|
! DEVICE-SAME: num_teams({{.*}}) thread_limit({{.*}})
|
|
!$omp teams num_teams(1) thread_limit(2)
|
|
call foo()
|
|
!$omp end teams
|
|
|
|
!$omp end target
|
|
|
|
! HOST: omp.teams
|
|
! HOST-SAME: num_teams({{.*}}) thread_limit({{.*}}) {
|
|
|
|
! DEVICE-NOT: omp.teams
|
|
!$omp teams num_teams(1) thread_limit(2)
|
|
call foo()
|
|
!$omp end teams
|
|
end subroutine teams
|
|
|
|
! BOTH-LABEL: func.func @_QPdistribute_parallel_do
|
|
subroutine distribute_parallel_do()
|
|
! BOTH: omp.target
|
|
|
|
! HOST-SAME: host_eval(%{{.*}} -> %[[LB:.*]], %{{.*}} -> %[[UB:.*]], %{{.*}} -> %[[STEP:.*]], %{{.*}} -> %[[NUM_THREADS:.*]] : i32, i32, i32, i32)
|
|
|
|
! DEVICE-NOT: host_eval({{.*}})
|
|
! DEVICE-SAME: {
|
|
|
|
! BOTH: omp.teams
|
|
!$omp target teams
|
|
|
|
! BOTH: omp.parallel
|
|
|
|
! HOST-SAME: num_threads(%[[NUM_THREADS]] : i32)
|
|
! DEVICE-SAME: num_threads({{.*}})
|
|
|
|
! BOTH: omp.distribute
|
|
! BOTH-NEXT: omp.wsloop
|
|
! BOTH-NEXT: omp.loop_nest
|
|
|
|
! HOST-SAME: (%{{.*}}) : i32 = (%[[LB]]) to (%[[UB]]) inclusive step (%[[STEP]])
|
|
!$omp distribute parallel do num_threads(1)
|
|
do i=1,10
|
|
call foo()
|
|
end do
|
|
!$omp end distribute parallel do
|
|
!$omp end target teams
|
|
|
|
! BOTH: omp.target
|
|
! BOTH-NOT: host_eval({{.*}})
|
|
! BOTH-SAME: {
|
|
! BOTH: omp.teams
|
|
!$omp target teams
|
|
call foo() !< Prevents this from being SPMD.
|
|
|
|
! BOTH: omp.parallel
|
|
! BOTH-SAME: num_threads({{.*}})
|
|
! BOTH: omp.distribute
|
|
! BOTH-NEXT: omp.wsloop
|
|
!$omp distribute parallel do num_threads(1)
|
|
do i=1,10
|
|
call foo()
|
|
end do
|
|
!$omp end distribute parallel do
|
|
!$omp end target teams
|
|
|
|
! HOST: omp.teams
|
|
! DEVICE-NOT: omp.teams
|
|
!$omp teams
|
|
|
|
! HOST: omp.parallel
|
|
! HOST-SAME: num_threads({{.*}})
|
|
! HOST: omp.distribute
|
|
! HOST-NEXT: omp.wsloop
|
|
|
|
! DEVICE-NOT: omp.parallel
|
|
! DEVICE-NOT: omp.distribute
|
|
! DEVICE-NOT: omp.wsloop
|
|
!$omp distribute parallel do num_threads(1)
|
|
do i=1,10
|
|
call foo()
|
|
end do
|
|
!$omp end distribute parallel do
|
|
!$omp end teams
|
|
end subroutine distribute_parallel_do
|
|
|
|
! BOTH-LABEL: func.func @_QPdistribute_parallel_do_simd
|
|
subroutine distribute_parallel_do_simd()
|
|
! BOTH: omp.target
|
|
|
|
! HOST-SAME: host_eval(%{{.*}} -> %[[LB:.*]], %{{.*}} -> %[[UB:.*]], %{{.*}} -> %[[STEP:.*]], %{{.*}} -> %[[NUM_THREADS:.*]] : i32, i32, i32, i32)
|
|
|
|
! DEVICE-NOT: host_eval({{.*}})
|
|
! DEVICE-SAME: {
|
|
|
|
! BOTH: omp.teams
|
|
!$omp target teams
|
|
|
|
! BOTH: omp.parallel
|
|
|
|
! HOST-SAME: num_threads(%[[NUM_THREADS]] : i32)
|
|
! DEVICE-SAME: num_threads({{.*}})
|
|
|
|
! BOTH: omp.distribute
|
|
! BOTH-NEXT: omp.wsloop
|
|
! BOTH-NEXT: omp.simd
|
|
! BOTH-NEXT: omp.loop_nest
|
|
|
|
! HOST-SAME: (%{{.*}}) : i32 = (%[[LB]]) to (%[[UB]]) inclusive step (%[[STEP]])
|
|
!$omp distribute parallel do simd num_threads(1)
|
|
do i=1,10
|
|
call foo()
|
|
end do
|
|
!$omp end distribute parallel do simd
|
|
!$omp end target teams
|
|
|
|
! BOTH: omp.target
|
|
! BOTH-NOT: host_eval({{.*}})
|
|
! BOTH-SAME: {
|
|
! BOTH: omp.teams
|
|
!$omp target teams
|
|
call foo() !< Prevents this from being SPMD.
|
|
|
|
! BOTH: omp.parallel
|
|
! BOTH-SAME: num_threads({{.*}})
|
|
! BOTH: omp.distribute
|
|
! BOTH-NEXT: omp.wsloop
|
|
! BOTH-NEXT: omp.simd
|
|
!$omp distribute parallel do simd num_threads(1)
|
|
do i=1,10
|
|
call foo()
|
|
end do
|
|
!$omp end distribute parallel do simd
|
|
!$omp end target teams
|
|
|
|
! HOST: omp.teams
|
|
! DEVICE-NOT: omp.teams
|
|
!$omp teams
|
|
|
|
! HOST: omp.parallel
|
|
! HOST-SAME: num_threads({{.*}})
|
|
! HOST: omp.distribute
|
|
! HOST-NEXT: omp.wsloop
|
|
! HOST-NEXT: omp.simd
|
|
|
|
! DEVICE-NOT: omp.parallel
|
|
! DEVICE-NOT: omp.distribute
|
|
! DEVICE-NOT: omp.wsloop
|
|
! DEVICE-NOT: omp.simd
|
|
!$omp distribute parallel do simd num_threads(1)
|
|
do i=1,10
|
|
call foo()
|
|
end do
|
|
!$omp end distribute parallel do simd
|
|
!$omp end teams
|
|
end subroutine distribute_parallel_do_simd
|
|
|
|
! BOTH-LABEL: func.func @_QPdistribute
|
|
subroutine distribute()
|
|
! BOTH: omp.target
|
|
|
|
! HOST-SAME: host_eval(%{{.*}} -> %[[LB:.*]], %{{.*}} -> %[[UB:.*]], %{{.*}} -> %[[STEP:.*]] : i32, i32, i32)
|
|
|
|
! DEVICE-NOT: host_eval({{.*}})
|
|
! DEVICE-SAME: {
|
|
|
|
! BOTH: omp.teams
|
|
!$omp target teams
|
|
|
|
! BOTH: omp.distribute
|
|
! BOTH-NEXT: omp.loop_nest
|
|
|
|
! HOST-SAME: (%{{.*}}) : i32 = (%[[LB]]) to (%[[UB]]) inclusive step (%[[STEP]])
|
|
!$omp distribute
|
|
do i=1,10
|
|
call foo()
|
|
end do
|
|
!$omp end distribute
|
|
!$omp end target teams
|
|
|
|
! BOTH: omp.target
|
|
! BOTH-NOT: host_eval({{.*}})
|
|
! BOTH-SAME: {
|
|
! BOTH: omp.teams
|
|
!$omp target teams
|
|
call foo() !< Prevents this from being Generic-SPMD.
|
|
|
|
! BOTH: omp.distribute
|
|
!$omp distribute
|
|
do i=1,10
|
|
call foo()
|
|
end do
|
|
!$omp end distribute
|
|
!$omp end target teams
|
|
|
|
! HOST: omp.teams
|
|
! DEVICE-NOT: omp.teams
|
|
!$omp teams
|
|
|
|
! HOST: omp.distribute
|
|
! DEVICE-NOT: omp.distribute
|
|
!$omp distribute
|
|
do i=1,10
|
|
call foo()
|
|
end do
|
|
!$omp end distribute
|
|
!$omp end teams
|
|
end subroutine distribute
|
|
|
|
! BOTH-LABEL: func.func @_QPdistribute_simd
|
|
subroutine distribute_simd()
|
|
! BOTH: omp.target
|
|
|
|
! HOST-SAME: host_eval(%{{.*}} -> %[[LB:.*]], %{{.*}} -> %[[UB:.*]], %{{.*}} -> %[[STEP:.*]] : i32, i32, i32)
|
|
|
|
! DEVICE-NOT: host_eval({{.*}})
|
|
! DEVICE-SAME: {
|
|
|
|
! BOTH: omp.teams
|
|
!$omp target teams
|
|
|
|
! BOTH: omp.distribute
|
|
! BOTH-NEXT: omp.simd
|
|
! BOTH-NEXT: omp.loop_nest
|
|
|
|
! HOST-SAME: (%{{.*}}) : i32 = (%[[LB]]) to (%[[UB]]) inclusive step (%[[STEP]])
|
|
!$omp distribute simd
|
|
do i=1,10
|
|
call foo()
|
|
end do
|
|
!$omp end distribute simd
|
|
!$omp end target teams
|
|
|
|
! BOTH: omp.target
|
|
! BOTH-NOT: host_eval({{.*}})
|
|
! BOTH-SAME: {
|
|
! BOTH: omp.teams
|
|
!$omp target teams
|
|
call foo() !< Prevents this from being Generic-SPMD.
|
|
|
|
! BOTH: omp.distribute
|
|
! BOTH-NEXT: omp.simd
|
|
!$omp distribute simd
|
|
do i=1,10
|
|
call foo()
|
|
end do
|
|
!$omp end distribute simd
|
|
!$omp end target teams
|
|
|
|
! HOST: omp.teams
|
|
! DEVICE-NOT: omp.teams
|
|
!$omp teams
|
|
|
|
! HOST: omp.distribute
|
|
! HOST-NEXT: omp.simd
|
|
|
|
! DEVICE-NOT: omp.distribute
|
|
! DEVICE-NOT: omp.simd
|
|
!$omp distribute simd
|
|
do i=1,10
|
|
call foo()
|
|
end do
|
|
!$omp end distribute simd
|
|
!$omp end teams
|
|
end subroutine distribute_simd
|
|
|
|
! BOTH-LABEL: func.func @_QPloop
|
|
subroutine loop()
|
|
! BOTH: omp.target
|
|
|
|
! HOST-SAME: host_eval(%{{.*}} -> %[[LB:.*]], %{{.*}} -> %[[UB:.*]], %{{.*}} -> %[[STEP:.*]] : i32, i32, i32)
|
|
|
|
! DEVICE-NOT: host_eval({{.*}})
|
|
! DEVICE-SAME: {
|
|
|
|
! BOTH: omp.teams
|
|
!$omp target teams
|
|
|
|
! BOTH: omp.parallel
|
|
|
|
! BOTH: omp.distribute
|
|
! BOTH-NEXT: omp.wsloop
|
|
! BOTH-NEXT: omp.loop_nest
|
|
|
|
! HOST-SAME: (%{{.*}}) : i32 = (%[[LB]]) to (%[[UB]]) inclusive step (%[[STEP]])
|
|
!$omp loop
|
|
do i=1,10
|
|
end do
|
|
!$omp end target teams
|
|
end subroutine loop
|
|
|
|
! BOTH-LABEL: func.func @_QPdistribute_parallel_do_with_modified_trip
|
|
subroutine distribute_parallel_do_with_modified_trip()
|
|
integer :: i, x
|
|
integer :: m(1)
|
|
integer :: res(10)
|
|
m(1) = 10
|
|
x = 1000000
|
|
|
|
! BOTH: omp.target
|
|
! BOTH-NOT: host_eval({{.*}})
|
|
! BOTH-SAME: {
|
|
! BOTH: omp.teams
|
|
!$omp target teams map(res)
|
|
x = 1
|
|
! BOTH: omp.parallel
|
|
! BOTH: omp.distribute
|
|
! BOTH-NEXT: omp.wsloop
|
|
!$omp distribute parallel do
|
|
do i = 1, m(x)
|
|
res(i) = 5 + i
|
|
end do
|
|
!$omp end distribute parallel do
|
|
!$omp end target teams
|
|
end subroutine distribute_parallel_do_with_modified_trip
|
|
|
|
! BOTH-LABEL: func.func @_QPdistribute_parallel_do_with_assignment
|
|
subroutine distribute_parallel_do_with_assignment()
|
|
integer :: i, m
|
|
integer :: res(10)
|
|
|
|
! BOTH: omp.target
|
|
! BOTH-NOT: host_eval({{.*}})
|
|
! BOTH-SAME: {
|
|
! BOTH: omp.teams
|
|
!$omp target teams map(from:m,res) private(m)
|
|
m = 5
|
|
! BOTH: omp.parallel
|
|
! BOTH: omp.distribute
|
|
! BOTH-NEXT: omp.wsloop
|
|
!$omp distribute parallel do
|
|
do i = 1, 10
|
|
res(i) = 5 + i
|
|
end do
|
|
!$omp end distribute parallel do
|
|
!$omp end target teams
|
|
end subroutine distribute_parallel_do_with_assignment
|