Files
TheRock/compiler/amd-llvm/mlir/test/Conversion/GPUToROCDL/gpu-to-rocdl-barriers-gfx12.mlir
T
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
Flatten subprojects into a single base monorepo
2026-09-02 16:34:47 -07:00

55 lines
2.2 KiB
MLIR

// RUN: mlir-opt %s -convert-gpu-to-rocdl='chipset=gfx1250' --mlir-print-local-scope | FileCheck %s
gpu.module @test_module {
// CHECK-LABEL: func @named_barrier
func.func @named_barrier() {
%member_count = arith.constant 4 : i32
// CHECK: %[[ADDR:.*]] = llvm.mlir.addressof @[[NB:__named_barrier[_0-9]*]] : !llvm.ptr<3>
// CHECK: rocdl.s.barrier.init %[[ADDR]] member_cnt = 4
%nb = gpu.initialize_named_barrier %member_count : i32 -> !gpu.named_barrier
// CHECK: llvm.fence syncscope("workgroup") release
// CHECK: rocdl.s.barrier.join %[[ADDR]]
// CHECK: rocdl.s.barrier.signal.var %[[ADDR]] member_cnt = 0
// CHECK: rocdl.s.barrier.wait id = 1
// CHECK: llvm.fence syncscope("workgroup") acquire
gpu.barrier named(%nb : !gpu.named_barrier)
func.return
}
// CHECK-LABEL: func @two_named_barriers
func.func @two_named_barriers() {
%c4 = arith.constant 4 : i32
%c8 = arith.constant 8 : i32
// CHECK: %[[ADDR0:.*]] = llvm.mlir.addressof @[[NB0:__named_barrier[_0-9]*]] : !llvm.ptr<3>
// CHECK: rocdl.s.barrier.init %[[ADDR0]] member_cnt = 4
%nb0 = gpu.initialize_named_barrier %c4 : i32 -> !gpu.named_barrier
// CHECK: %[[ADDR1:.*]] = llvm.mlir.addressof @[[NB1:__named_barrier[_0-9]*]] : !llvm.ptr<3>
// CHECK: rocdl.s.barrier.init %[[ADDR1]] member_cnt = 8
%nb1 = gpu.initialize_named_barrier %c8 : i32 -> !gpu.named_barrier
// CHECK: rocdl.s.barrier.join %[[ADDR0]]
// CHECK: rocdl.s.barrier.signal.var %[[ADDR0]] member_cnt = 0
// CHECK: rocdl.s.barrier.wait id = 1
gpu.barrier named(%nb0 : !gpu.named_barrier)
// CHECK: rocdl.s.barrier.join %[[ADDR1]]
// CHECK: rocdl.s.barrier.signal.var %[[ADDR1]] member_cnt = 0
// CHECK: rocdl.s.barrier.wait id = 1
gpu.barrier named(%nb1 : !gpu.named_barrier)
func.return
}
// CHECK-LABEL: func @cluster_scope
func.func @cluster_scope() {
// CHECK: llvm.fence syncscope("cluster") release
// CHECK-NEXT: rocdl.s.barrier.signal id = -3
// CHECK-NEXT: rocdl.s.barrier.wait id = -3
// CHECK-NEXT: llvm.fence syncscope("cluster") acquire
gpu.barrier scope <cluster>
func.return
}
// One LDS global per gpu.initialize_named_barrier.
// CHECK-COUNT-3: llvm.mlir.global internal @__named_barrier{{[_0-9]*}}() {addr_space = 3 : i32} : !llvm.target<"amdgcn.named.barrier", 0>
}