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
26 lines
2.3 KiB
MLIR
26 lines
2.3 KiB
MLIR
// RUN: mlir-opt %s --gpu-to-llvm="use-bare-pointers-for-kernels=1 intersperse-sizes-for-kernels=1" -split-input-file | FileCheck %s
|
|
|
|
module attributes {gpu.container_module, spirv.target_env = #spirv.target_env<#spirv.vce<v1.0, [Shader], [SPV_KHR_storage_buffer_storage_class]>, #spirv.resource_limits<>>} {
|
|
llvm.func @malloc(i64) -> !llvm.ptr
|
|
gpu.binary @kernels [#gpu.object<#spirv.target_env<#spirv.vce<v1.0, [Shader], [SPV_KHR_storage_buffer_storage_class]>, #spirv.resource_limits<>>, "">]
|
|
func.func @main() attributes {llvm.emit_c_interface} {
|
|
// CHECK: [[RANK1UMD:%.*]] = llvm.mlir.undef : !llvm.struct<(ptr, ptr, i64, array<1 x i64>, array<1 x i64>)>
|
|
%rank1UndefMemrefDescriptor = llvm.mlir.undef : !llvm.struct<(ptr, ptr, i64, array<1 x i64>, array<1 x i64>)>
|
|
// CHECK: [[RANK2UMD:%.*]] = llvm.mlir.undef : !llvm.struct<(ptr, ptr, i64, array<2 x i64>, array<2 x i64>)>
|
|
%rank2UndefMemrefDescriptor = llvm.mlir.undef : !llvm.struct<(ptr, ptr, i64, array<2 x i64>, array<2 x i64>)>
|
|
%c1 = arith.constant 1 : index
|
|
// CHECK: [[PTR1:%.*]] = llvm.extractvalue [[RANK1UMD]][1]
|
|
// CHECK: [[PTR2:%.*]] = llvm.extractvalue [[RANK2UMD]][1]
|
|
// CHECK: [[PTR3:%.*]] = llvm.extractvalue [[RANK2UMD]][1]
|
|
// CHECK: [[SIZE1:%.*]] = llvm.mlir.constant(32 : index) : i64
|
|
// CHECK: [[SIZE2:%.*]] = llvm.mlir.constant(256 : index) : i64
|
|
// CHECK: [[SIZE3:%.*]] = llvm.mlir.constant(48 : index) : i64
|
|
%6 = builtin.unrealized_conversion_cast %rank1UndefMemrefDescriptor : !llvm.struct<(ptr, ptr, i64, array<1 x i64>, array<1 x i64>)> to memref<8xf32>
|
|
%10 = builtin.unrealized_conversion_cast %rank2UndefMemrefDescriptor : !llvm.struct<(ptr, ptr, i64, array<2 x i64>, array<2 x i64>)> to memref<8x8xi32>
|
|
%14 = builtin.unrealized_conversion_cast %rank2UndefMemrefDescriptor : !llvm.struct<(ptr, ptr, i64, array<2 x i64>, array<2 x i64>)> to memref<4x12xi8>
|
|
// CHECK: gpu.launch_func @kernels::@kernel_add blocks in ({{.*}}) threads in ({{.*}}) : i64 args([[PTR1]] : !llvm.ptr, [[SIZE1]] : i64, [[PTR2]] : !llvm.ptr, [[SIZE2]] : i64, [[PTR3]] : !llvm.ptr, [[SIZE3]] : i64)
|
|
gpu.launch_func @kernels::@kernel_add blocks in (%c1, %c1, %c1) threads in (%c1, %c1, %c1) args(%6 : memref<8xf32>, %10 : memref<8x8xi32>, %14 : memref<4x12xi8>)
|
|
return
|
|
}
|
|
}
|