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
53 lines
2.2 KiB
MLIR
53 lines
2.2 KiB
MLIR
// RUN: mlir-opt %s -test-vulkan-runner-pipeline \
|
|
// RUN: | mlir-runner - --shared-libs=%mlir_vulkan_runtime,%mlir_runner_utils --entry-point-result=void | FileCheck %s
|
|
|
|
// CHECK-COUNT-4: [6, 6, 6, 6]
|
|
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<>>
|
|
} {
|
|
gpu.module @kernels {
|
|
gpu.func @kernel_mul(%arg0 : memref<4x4xf32>, %arg1 : memref<4x4xf32>, %arg2 : memref<4x4xf32>)
|
|
kernel attributes { spirv.entry_point_abi = #spirv.entry_point_abi<workgroup_size = [1, 1, 1]>} {
|
|
%x = gpu.block_id x
|
|
%y = gpu.block_id y
|
|
%1 = memref.load %arg0[%x, %y] : memref<4x4xf32>
|
|
%2 = memref.load %arg1[%x, %y] : memref<4x4xf32>
|
|
%3 = arith.mulf %1, %2 : f32
|
|
memref.store %3, %arg2[%x, %y] : memref<4x4xf32>
|
|
gpu.return
|
|
}
|
|
}
|
|
|
|
func.func @main() {
|
|
%arg0 = memref.alloc() : memref<4x4xf32>
|
|
%arg1 = memref.alloc() : memref<4x4xf32>
|
|
%arg2 = memref.alloc() : memref<4x4xf32>
|
|
%0 = arith.constant 0 : i32
|
|
%1 = arith.constant 1 : i32
|
|
%2 = arith.constant 2 : i32
|
|
%value0 = arith.constant 0.0 : f32
|
|
%value1 = arith.constant 2.0 : f32
|
|
%value2 = arith.constant 3.0 : f32
|
|
%arg3 = memref.cast %arg0 : memref<4x4xf32> to memref<?x?xf32>
|
|
%arg4 = memref.cast %arg1 : memref<4x4xf32> to memref<?x?xf32>
|
|
%arg5 = memref.cast %arg2 : memref<4x4xf32> to memref<?x?xf32>
|
|
call @fillResource2DFloat(%arg3, %value1) : (memref<?x?xf32>, f32) -> ()
|
|
call @fillResource2DFloat(%arg4, %value2) : (memref<?x?xf32>, f32) -> ()
|
|
call @fillResource2DFloat(%arg5, %value0) : (memref<?x?xf32>, f32) -> ()
|
|
|
|
%cst1 = arith.constant 1 : index
|
|
%cst4 = arith.constant 4 : index
|
|
gpu.launch_func @kernels::@kernel_mul
|
|
blocks in (%cst4, %cst4, %cst1) threads in(%cst1, %cst1, %cst1)
|
|
args(%arg0 : memref<4x4xf32>, %arg1 : memref<4x4xf32>, %arg2 : memref<4x4xf32>)
|
|
%arg6 = memref.cast %arg5 : memref<?x?xf32> to memref<*xf32>
|
|
call @printMemrefF32(%arg6) : (memref<*xf32>) -> ()
|
|
return
|
|
}
|
|
func.func private @fillResource2DFloat(%0 : memref<?x?xf32>, %1 : f32)
|
|
func.func private @printMemrefF32(%ptr : memref<*xf32>)
|
|
}
|
|
|