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
75 lines
2.6 KiB
MLIR
75 lines
2.6 KiB
MLIR
// RUN: mlir-opt -split-input-file -convert-gpu-to-spirv -verify-diagnostics %s -o - | FileCheck %s
|
|
|
|
module attributes {
|
|
gpu.container_module,
|
|
spirv.target_env = #spirv.target_env<#spirv.vce<v1.4, [Shader, GroupNonUniformRotateKHR], []>,
|
|
#spirv.resource_limits<subgroup_size = 16>>
|
|
} {
|
|
|
|
gpu.module @kernels {
|
|
// CHECK-LABEL: spirv.func @rotate()
|
|
gpu.func @rotate() kernel
|
|
attributes {spirv.entry_point_abi = #spirv.entry_point_abi<workgroup_size = [16, 1, 1]>} {
|
|
%val = arith.constant 42.0 : f32
|
|
|
|
// CHECK: %[[VAL:.+]] = spirv.Constant 4.200000e+01 : f32
|
|
// CHECK: %[[OFFSET:.+]] = spirv.Constant 4 : i32
|
|
// CHECK: %[[WIDTH:.+]] = spirv.Constant 16 : i32
|
|
// CHECK: %{{.+}} = spirv.GroupNonUniformRotateKHR <Subgroup> %[[VAL]], %[[OFFSET]], cluster_size(%[[WIDTH]]) : f32, i32, i32 -> f32
|
|
// CHECK: %{{.+}} = spirv.Constant true
|
|
%result, %valid = gpu.rotate %val, 4, 16 : f32
|
|
gpu.return
|
|
}
|
|
}
|
|
|
|
}
|
|
|
|
// -----
|
|
|
|
module attributes {
|
|
gpu.container_module,
|
|
spirv.target_env = #spirv.target_env<#spirv.vce<v1.4, [Shader, GroupNonUniformRotateKHR], []>,
|
|
#spirv.resource_limits<subgroup_size = 16>>
|
|
} {
|
|
|
|
gpu.module @kernels {
|
|
// CHECK-LABEL: spirv.func @rotate_width_less_than_subgroup_size()
|
|
gpu.func @rotate_width_less_than_subgroup_size() kernel
|
|
attributes {spirv.entry_point_abi = #spirv.entry_point_abi<workgroup_size = [16, 1, 1]>} {
|
|
%val = arith.constant 42.0 : f32
|
|
|
|
// CHECK: %[[VAL:.+]] = spirv.Constant 4.200000e+01 : f32
|
|
// CHECK: %[[OFFSET:.+]] = spirv.Constant 4 : i32
|
|
// CHECK: %[[WIDTH:.+]] = spirv.Constant 8 : i32
|
|
// CHECK: %{{.+}} = spirv.GroupNonUniformRotateKHR <Subgroup> %[[VAL]], %[[OFFSET]], cluster_size(%[[WIDTH]]) : f32, i32, i32 -> f32
|
|
// CHECK: %[[INVOCATION_ID_ADDR:.+]] = spirv.mlir.addressof @__builtin__SubgroupLocalInvocationId__
|
|
// CHECK: %[[INVOCATION_ID:.+]] = spirv.Load "Input" %[[INVOCATION_ID_ADDR]]
|
|
// CHECK: %{{.+}} = spirv.ULessThan %[[INVOCATION_ID]], %[[WIDTH]]
|
|
%result, %valid = gpu.rotate %val, 4, 8 : f32
|
|
gpu.return
|
|
}
|
|
}
|
|
|
|
}
|
|
|
|
// -----
|
|
|
|
module attributes {
|
|
gpu.container_module,
|
|
spirv.target_env = #spirv.target_env<#spirv.vce<v1.4, [Shader, GroupNonUniformRotateKHR], []>,
|
|
#spirv.resource_limits<subgroup_size = 16>>
|
|
} {
|
|
|
|
gpu.module @kernels {
|
|
gpu.func @rotate_with_bigger_than_subgroup_size() kernel
|
|
attributes {spirv.entry_point_abi = #spirv.entry_point_abi<workgroup_size = [16, 1, 1]>} {
|
|
%val = arith.constant 42.0 : f32
|
|
|
|
// expected-error @+1 {{failed to legalize operation 'gpu.rotate'}}
|
|
%result, %valid = gpu.rotate %val, 4, 32 : f32
|
|
gpu.return
|
|
}
|
|
}
|
|
|
|
}
|