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
135 lines
6.2 KiB
Plaintext
135 lines
6.2 KiB
Plaintext
// RUN: fir-opt %s --pass-pipeline="builtin.module(acc-initialize-fir-analyses,acc-implicit-data{enable-implicit-reduction-copy=true})" -split-input-file | FileCheck %s --check-prefix=COPY
|
|
// RUN: fir-opt %s --pass-pipeline="builtin.module(acc-initialize-fir-analyses,acc-implicit-data{enable-implicit-reduction-copy=false})" -split-input-file | FileCheck %s --check-prefix=FIRSTPRIVATE
|
|
|
|
// Test case: integer reduction in parallel loop
|
|
// This corresponds to Fortran code:
|
|
// integer :: r, i
|
|
// r = 0
|
|
// !$acc parallel
|
|
// !$acc loop gang reduction(+:r)
|
|
// do i = 1, N
|
|
// r = r + 1
|
|
// enddo
|
|
// !$acc end parallel
|
|
|
|
acc.reduction.recipe @reduction_add_ref_i32 : !fir.ref<i32> reduction_operator <add> init {
|
|
^bb0(%arg0: !fir.ref<i32>):
|
|
%c0_i32 = arith.constant 0 : i32
|
|
%0 = fir.alloca i32
|
|
%1 = fir.declare %0 {uniq_name = "acc.reduction.init"} : (!fir.ref<i32>) -> !fir.ref<i32>
|
|
fir.store %c0_i32 to %1 : !fir.ref<i32>
|
|
acc.yield %1 : !fir.ref<i32>
|
|
} combiner {
|
|
^bb0(%arg0: !fir.ref<i32>, %arg1: !fir.ref<i32>):
|
|
%0 = fir.load %arg0 : !fir.ref<i32>
|
|
%1 = fir.load %arg1 : !fir.ref<i32>
|
|
%2 = arith.addi %0, %1 : i32
|
|
fir.store %2 to %arg0 : !fir.ref<i32>
|
|
acc.yield %arg0 : !fir.ref<i32>
|
|
}
|
|
|
|
func.func @test_reduction_implicit_copy() {
|
|
%c1_i32 = arith.constant 1 : i32
|
|
%cN = arith.constant 100 : i32
|
|
%r = fir.alloca i32 {bindc_name = "r", uniq_name = "_QFEr"}
|
|
%i = fir.alloca i32 {bindc_name = "i", uniq_name = "_QFEi"}
|
|
%r_decl = fir.declare %r {uniq_name = "_QFEr"} : (!fir.ref<i32>) -> !fir.ref<i32>
|
|
%i_decl = fir.declare %i {uniq_name = "_QFEi"} : (!fir.ref<i32>) -> !fir.ref<i32>
|
|
%c0_i32 = arith.constant 0 : i32
|
|
fir.store %c0_i32 to %r_decl : !fir.ref<i32>
|
|
|
|
acc.parallel {
|
|
%red_var = acc.reduction varPtr(%r_decl : !fir.ref<i32>) recipe(@reduction_add_ref_i32) -> !fir.ref<i32> {name = "r"}
|
|
acc.loop reduction(%red_var : !fir.ref<i32>) control(%iv : i32) = (%c1_i32 : i32) to (%cN : i32) step (%c1_i32 : i32) {
|
|
fir.store %iv to %i_decl : !fir.ref<i32>
|
|
%cur_r = fir.load %red_var : !fir.ref<i32>
|
|
%new_r = arith.addi %cur_r, %c1_i32 : i32
|
|
fir.store %new_r to %red_var : !fir.ref<i32>
|
|
acc.yield
|
|
} attributes {inclusiveUpperbound = array<i1: true>, independent = [#acc.device_type<none>]}
|
|
acc.yield
|
|
}
|
|
return
|
|
}
|
|
|
|
// When enable-implicit-reduction-copy=true: expect copyin/copyout for reduction variable
|
|
// COPY: %[[COPYIN:.*]] = acc.copyin varPtr({{.*}} : !fir.ref<i32>) -> !fir.ref<i32> {dataClause = #acc<data_clause acc_reduction>, implicit = true, name = "r"}
|
|
// COPY: acc.copyout accPtr(%[[COPYIN]] : !fir.ref<i32>) to varPtr({{.*}} : !fir.ref<i32>) {dataClause = #acc<data_clause acc_copy>, implicit = true, name = "r"}
|
|
|
|
// When enable-implicit-reduction-copy=false: expect firstprivate for reduction variable
|
|
// FIRSTPRIVATE: acc.firstprivate varPtr({{.*}} : !fir.ref<i32>) recipe({{.*}}) -> !fir.ref<i32> {implicit = true, name = "r"}
|
|
// FIRSTPRIVATE-NOT: acc.copyin
|
|
// FIRSTPRIVATE-NOT: acc.copyout
|
|
|
|
// -----
|
|
|
|
// Test case: reduction variable used both in loop and outside (should be firstprivate)
|
|
// This corresponds to Fortran code:
|
|
// integer :: r = 0, i, out
|
|
// !$acc parallel num_gangs(1)
|
|
// !$acc loop reduction(+:r) copyout(out)
|
|
// do i = 1, N
|
|
// r = r + 1
|
|
// enddo
|
|
// out = r
|
|
// !$acc end parallel
|
|
|
|
acc.reduction.recipe @reduction_add_ref_i32 : !fir.ref<i32> reduction_operator <add> init {
|
|
^bb0(%arg0: !fir.ref<i32>):
|
|
%c0_i32 = arith.constant 0 : i32
|
|
%0 = fir.alloca i32
|
|
%1 = fir.declare %0 {uniq_name = "acc.reduction.init"} : (!fir.ref<i32>) -> !fir.ref<i32>
|
|
fir.store %c0_i32 to %1 : !fir.ref<i32>
|
|
acc.yield %1 : !fir.ref<i32>
|
|
} combiner {
|
|
^bb0(%arg0: !fir.ref<i32>, %arg1: !fir.ref<i32>):
|
|
%0 = fir.load %arg0 : !fir.ref<i32>
|
|
%1 = fir.load %arg1 : !fir.ref<i32>
|
|
%2 = arith.addi %0, %1 : i32
|
|
fir.store %2 to %arg0 : !fir.ref<i32>
|
|
acc.yield %arg0 : !fir.ref<i32>
|
|
}
|
|
|
|
func.func @test_reduction_with_usage_outside_loop() {
|
|
%c1_i32 = arith.constant 1 : i32
|
|
%cN = arith.constant 100 : i32
|
|
%c0_i32 = arith.constant 0 : i32
|
|
|
|
%r = fir.alloca i32 {bindc_name = "r", uniq_name = "_QFEr"}
|
|
%i = fir.alloca i32 {bindc_name = "i", uniq_name = "_QFEi"}
|
|
%out = fir.alloca i32 {bindc_name = "out", uniq_name = "_QFEout"}
|
|
|
|
%r_decl = fir.declare %r {uniq_name = "_QFEr"} : (!fir.ref<i32>) -> !fir.ref<i32>
|
|
%i_decl = fir.declare %i {uniq_name = "_QFEi"} : (!fir.ref<i32>) -> !fir.ref<i32>
|
|
%out_decl = fir.declare %out {uniq_name = "_QFEout"} : (!fir.ref<i32>) -> !fir.ref<i32>
|
|
fir.store %c0_i32 to %r_decl : !fir.ref<i32>
|
|
|
|
%out_copyout = acc.create varPtr(%out_decl : !fir.ref<i32>) -> !fir.ref<i32> {dataClause = #acc<data_clause acc_copyout>, name = "out"}
|
|
acc.parallel dataOperands(%out_copyout : !fir.ref<i32>) {
|
|
%red_var = acc.reduction varPtr(%r_decl : !fir.ref<i32>) recipe(@reduction_add_ref_i32) -> !fir.ref<i32> {name = "r"}
|
|
acc.loop reduction(%red_var : !fir.ref<i32>) control(%iv : i32) = (%c1_i32 : i32) to (%cN : i32) step (%c1_i32 : i32) {
|
|
fir.store %iv to %i_decl : !fir.ref<i32>
|
|
%cur_r = fir.load %red_var : !fir.ref<i32>
|
|
%new_r = arith.addi %cur_r, %c1_i32 : i32
|
|
fir.store %new_r to %red_var : !fir.ref<i32>
|
|
acc.yield
|
|
} attributes {inclusiveUpperbound = array<i1: true>, independent = [#acc.device_type<none>]}
|
|
// out = r (usage of r outside the loop)
|
|
%final_r = fir.load %r_decl : !fir.ref<i32>
|
|
fir.store %final_r to %out_copyout : !fir.ref<i32>
|
|
acc.yield
|
|
}
|
|
acc.copyout accPtr(%out_copyout : !fir.ref<i32>) to varPtr(%out_decl : !fir.ref<i32>) {dataClause = #acc<data_clause acc_copyout>, name = "out"}
|
|
return
|
|
}
|
|
|
|
// In this case, r should be firstprivate regardless of the flag setting because it's used outside the reduction context
|
|
// COPY-LABEL: func.func @test_reduction_with_usage_outside_loop
|
|
// COPY: acc.firstprivate varPtr({{.*}} : !fir.ref<i32>) recipe({{.*}}) -> !fir.ref<i32> {implicit = true, name = "r"}
|
|
// COPY-NOT: acc.copyin varPtr({{.*}} : !fir.ref<i32>) -> !fir.ref<i32> {{.*}} name = "r"
|
|
|
|
// FIRSTPRIVATE-LABEL: func.func @test_reduction_with_usage_outside_loop
|
|
// FIRSTPRIVATE: acc.firstprivate varPtr({{.*}} : !fir.ref<i32>) recipe({{.*}}) -> !fir.ref<i32> {implicit = true, name = "r"}
|
|
// FIRSTPRIVATE-NOT: acc.copyin varPtr({{.*}} : !fir.ref<i32>) -> !fir.ref<i32> {{.*}} name = "r"
|
|
|