Files
TheRock/compiler/amd-llvm/amd/comgr/test-lit/spirv-tests/clone-kernels.hip
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

77 lines
2.7 KiB
Plaintext

// REQUIRES: comgr-has-spirv-translator
// COM: Generate a SPIRV file from a HIP kernel
// RUN: %clang -x hip --offload-arch=amdgcnspirv -nogpulib -nogpuinc \
// RUN: --no-gpu-bundle-output --offload-device-only -O3 %s -o %t.spv
// COM: Run Comgr Translator to covert SPIRV back to LLVM IR
// RUN: spirv-translator --block-sizes "1024,512,256,64" %t.spv -o %t.translated.bc
// COM: Dissasemble LLVM IR bitcode to LLVM IR text
// RUN: %llvm-dis %t.translated.bc -o - | %FileCheck %s
// COM: Verify the expected kernels
// CHECK-DAG: define amdgpu_kernel void @kernel1
// CHECK-DAG: define amdgpu_kernel void @kernel1.bs512
// CHECK-DAG: define amdgpu_kernel void @kernel1.bs256
// CHECK-DAG: define amdgpu_kernel void @kernel1.bs64
// CHECK-DAG: define amdgpu_kernel void @kernel2
// CHECK-DAG: define amdgpu_kernel void @kernel2.bs64
// CHECK-DAG: define amdgpu_kernel void @kernel3
// CHECK-DAG: define amdgpu_kernel void @kernel3.bs512
// CHECK-DAG: define amdgpu_kernel void @kernel3.bs256
// CHECK-DAG: define amdgpu_kernel void @kernel4
// CHECK-DAG: define amdgpu_kernel void @kernel4.bs512
// CHECK-DAG: define amdgpu_kernel void @kernel4.bs256
// CHECK-DAG: define amdgpu_kernel void @kernel5
// COM: Verify that the unexpected variants are not there
// COM: Kernels should not have variants that match their maximum size (default
// COM: 1024)
// CHECK-NOT: define amdgpu_kernel void @kernel1.bs1024
// CHECK-NOT: define amdgpu_kernel void @kernel3.bs1024
// CHECK-NOT: define amdgpu_kernel void @kernel2.bs256
// CHECK-NOT: define amdgpu_kernel void @kernel4.bs728
// CHECK-NOT: define amdgpu_kernel void @kernel5.bs512
// COM: Kernels should not have variants larger than the maximum size
// CHECK-NOT: define amdgpu_kernel void @kernel2.bs1024
// CHECK-NOT: define amdgpu_kernel void @kernel2.bs512
// CHECK-NOT: define amdgpu_kernel void @kernel4.bs1024
// CHECK-NOT: define amdgpu_kernel void @kernel5.bs1024
// COM: Kernels should not have variants smaller than the minimum size
// FIXME: SPIR-V currently loses the minimum block size limit during
// FIXME: translation, so these variants are still generated:
// FIXME: kernel5.bs256, kernel3.bs64, kernel4.bs64 and kernel5.bs64
extern "C" {
__attribute__((global))
void kernel1(float* a) {
a[0] = 1.0f;
}
__attribute__((global))
__attribute__((amdgpu_flat_work_group_size(1, 256)))
void kernel2(float* a) {
a[0] = 1.0f;
}
__attribute__((global))
__attribute__((amdgpu_flat_work_group_size(256, 1024)))
void kernel3(float* a) {
a[0] = 1.0f;
}
__attribute__((global))
__attribute__((amdgpu_flat_work_group_size(128, 768)))
void kernel4(float* a) {
a[0] = 1.0f;
}
__attribute__((global))
__attribute__((amdgpu_flat_work_group_size(512, 512)))
void kernel5(float* a) {
a[0] = 1.0f;
}
}