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
32 lines
1.9 KiB
MLIR
32 lines
1.9 KiB
MLIR
// RUN: mlir-opt %s --gpu-to-llvm="use-bare-pointers-for-kernels=1" -split-input-file | FileCheck %s
|
|
|
|
module attributes {gpu.container_module} {
|
|
gpu.module @kernels [#nvvm.target] {
|
|
llvm.func @kernel_1(%arg0: f32, %arg1: !llvm.ptr<1>) attributes {gpu.kernel, nvvm.kernel} {
|
|
%0 = llvm.mlir.undef : !llvm.struct<(ptr<1>, ptr<1>, i64, array<1 x i64>, array<1 x i64>)>
|
|
%1 = llvm.insertvalue %arg1, %0[0] : !llvm.struct<(ptr<1>, ptr<1>, i64, array<1 x i64>, array<1 x i64>)>
|
|
%2 = llvm.insertvalue %arg1, %1[1] : !llvm.struct<(ptr<1>, ptr<1>, i64, array<1 x i64>, array<1 x i64>)>
|
|
%3 = llvm.mlir.constant(0 : index) : i64
|
|
%4 = llvm.insertvalue %3, %2[2] : !llvm.struct<(ptr<1>, ptr<1>, i64, array<1 x i64>, array<1 x i64>)>
|
|
%5 = llvm.mlir.constant(10 : index) : i64
|
|
%6 = llvm.insertvalue %5, %4[3, 0] : !llvm.struct<(ptr<1>, ptr<1>, i64, array<1 x i64>, array<1 x i64>)>
|
|
%7 = llvm.mlir.constant(1 : index) : i64
|
|
%8 = llvm.insertvalue %7, %6[4, 0] : !llvm.struct<(ptr<1>, ptr<1>, i64, array<1 x i64>, array<1 x i64>)>
|
|
llvm.return
|
|
}
|
|
}
|
|
func.func @foo() {
|
|
// CHECK: [[ALLOCATED:%.*]] = llvm.call @mgpuMemAlloc({{.*}}) : (i64, !llvm.ptr, i8) -> !llvm.ptr
|
|
// CHECK: [[CAST:%.*]] = llvm.addrspacecast [[ALLOCATED]] : !llvm.ptr to !llvm.ptr<1>
|
|
// CHECK: [[DESCRIPTOR:%.*]] = llvm.insertvalue [[CAST]], {{.*}}[0] : !llvm.struct<(ptr<1>, ptr<1>, i64, array<1 x i64>, array<1 x i64>)>
|
|
// CHECK: [[PTR:%.*]] = llvm.extractvalue {{.*}}[1] : !llvm.struct<(ptr<1>, ptr<1>, i64, array<1 x i64>, array<1 x i64>)>
|
|
// CHECK: gpu.launch_func @kernels::@kernel_1 blocks in ({{.*}}) threads in ({{.*}}) : i64
|
|
// CHECK: args(%{{.*}} : f32, [[PTR]] : !llvm.ptr<1>)
|
|
%0 = arith.constant 0. : f32
|
|
%1 = gpu.alloc () : memref<10xf32, 1>
|
|
%c8 = arith.constant 8 : index
|
|
gpu.launch_func @kernels::@kernel_1 blocks in (%c8, %c8, %c8) threads in (%c8, %c8, %c8) args(%0 : f32, %1 : memref<10xf32, 1>)
|
|
return
|
|
}
|
|
}
|