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
38 lines
2.3 KiB
MLIR
38 lines
2.3 KiB
MLIR
// RUN: mlir-translate -mlir-to-llvmir %s | FileCheck %s --check-prefix=LLVM
|
|
// RUN: mlir-opt %s | mlir-opt | FileCheck %s
|
|
|
|
// LLVM-LABEL: @llvm_nvvm_barrier(
|
|
// LLVM-SAME: i32 %[[barId:.*]], i32 %[[numThreads:.*]], i32 %[[redOperand:.*]])
|
|
llvm.func @llvm_nvvm_barrier(%barID : i32, %numberOfThreads : i32, %redOperand : i32) {
|
|
// LLVM: call void @llvm.nvvm.barrier.cta.sync.aligned.all(i32 0)
|
|
// CHECK: nvvm.barrier
|
|
nvvm.barrier
|
|
// LLVM: call void @llvm.nvvm.barrier.cta.sync.aligned.all(i32 %[[barId]])
|
|
// CHECK: nvvm.barrier id = %{{.*}}
|
|
nvvm.barrier id = %barID
|
|
// LLVM: call void @llvm.nvvm.barrier.cta.sync.aligned.count(i32 %[[barId]], i32 %[[numThreads]])
|
|
// CHECK: nvvm.barrier id = %{{.*}} number_of_threads = %{{.*}}
|
|
nvvm.barrier id = %barID number_of_threads = %numberOfThreads
|
|
// LLVM: call void @llvm.nvvm.barrier.cta.sync.aligned.count(i32 0, i32 %[[numThreads]])
|
|
// CHECK: nvvm.barrier number_of_threads = %{{.*}}
|
|
nvvm.barrier number_of_threads = %numberOfThreads
|
|
// LLVM: %[[redOperandCmp1:.*]] = icmp ne i32 %[[redOperand]], 0
|
|
// LLVM: %{{.*}} = call i1 @llvm.nvvm.barrier.cta.red.and.aligned.all(i32 0, i1 %[[redOperandCmp1]])
|
|
// CHECK: %{{.*}} = nvvm.barrier.reduction #nvvm.reduction<and> %{{.*}} -> i32
|
|
%0 = nvvm.barrier.reduction #nvvm.reduction<and> %redOperand -> i32
|
|
// LLVM: %[[redOperandCmp2:.*]] = icmp ne i32 %[[redOperand]], 0
|
|
// LLVM: %{{.*}} = call i1 @llvm.nvvm.barrier.cta.red.or.aligned.all(i32 0, i1 %[[redOperandCmp2]])
|
|
// CHECK: %{{.*}} = nvvm.barrier.reduction #nvvm.reduction<or> %{{.*}} -> i32
|
|
%1 = nvvm.barrier.reduction #nvvm.reduction<or> %redOperand -> i32
|
|
// LLVM: %[[redOperandCmp3:.*]] = icmp ne i32 %[[redOperand]], 0
|
|
// LLVM: %{{.*}} = call i32 @llvm.nvvm.barrier.cta.red.popc.aligned.all(i32 0, i1 %[[redOperandCmp3]])
|
|
// CHECK: %{{.*}} = nvvm.barrier.reduction #nvvm.reduction<popc> %{{.*}} -> i32
|
|
%2 = nvvm.barrier.reduction #nvvm.reduction<popc> %redOperand -> i32
|
|
// LLVM: %[[redOperandCmp4:.*]] = icmp ne i32 %[[redOperand]], 0
|
|
// LLVM: %{{.*}} = call i1 @llvm.nvvm.barrier.cta.red.and.aligned.all(i32 %[[barId]], i1 %[[redOperandCmp4]])
|
|
// CHECK: %{{.*}} = nvvm.barrier.reduction #nvvm.reduction<and> %{{.*}} id = %{{.*}} -> i32
|
|
%3 = nvvm.barrier.reduction #nvvm.reduction<and> %redOperand id = %barID -> i32
|
|
|
|
llvm.return
|
|
}
|