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
34 lines
2.2 KiB
Common Lisp
34 lines
2.2 KiB
Common Lisp
// REQUIRES: amdgpu-registered-target
|
|
// RUN: %clang_cc1 -O0 -cl-std=CL2.0 -triple amdgcn-amd-amdhsa -target-cpu gfx908 \
|
|
// RUN: -verify -S -o - %s
|
|
|
|
#pragma OPENCL EXTENSION cl_khr_fp64:enable
|
|
|
|
typedef float v4f __attribute__((ext_vector_type(4)));
|
|
typedef float v16f __attribute__((ext_vector_type(16)));
|
|
typedef float v32f __attribute__((ext_vector_type(32)));
|
|
typedef half v4h __attribute__((ext_vector_type(4)));
|
|
typedef half v16h __attribute__((ext_vector_type(16)));
|
|
typedef half v32h __attribute__((ext_vector_type(32)));
|
|
typedef int v4i __attribute__((ext_vector_type(4)));
|
|
typedef int v16i __attribute__((ext_vector_type(16)));
|
|
typedef int v32i __attribute__((ext_vector_type(32)));
|
|
typedef short v2s __attribute__((ext_vector_type(2)));
|
|
typedef short v4s __attribute__((ext_vector_type(4)));
|
|
typedef short v16s __attribute__((ext_vector_type(16)));
|
|
typedef short v32s __attribute__((ext_vector_type(32)));
|
|
typedef double v4d __attribute__((ext_vector_type(4)));
|
|
|
|
void test_mfma_f32_16x16x4bf16_1k(global v16f* out, global v4f* out1,
|
|
global v4d* out2, global double* out3, v4s a,
|
|
v4s b, v16f c, v4f e, double f, double g,
|
|
v4d h)
|
|
{
|
|
*out = __builtin_amdgcn_mfma_f32_16x16x4bf16_1k(a, b, c, 0, 0, 0); // expected-error{{'__builtin_amdgcn_mfma_f32_16x16x4bf16_1k' needs target feature gfx90a-insts}}
|
|
*out1 = __builtin_amdgcn_mfma_f32_4x4x4bf16_1k(a, b, e, 0, 0, 0); // expected-error{{'__builtin_amdgcn_mfma_f32_4x4x4bf16_1k' needs target feature gfx90a-insts}}
|
|
*out = __builtin_amdgcn_mfma_f32_32x32x8bf16_1k(a, b, c, 0, 0, 0); // expected-error{{'__builtin_amdgcn_mfma_f32_32x32x8bf16_1k' needs target feature gfx90a-insts}}
|
|
*out1 = __builtin_amdgcn_mfma_f32_16x16x16bf16_1k(a, b, e, 0, 0, 0); // expected-error{{'__builtin_amdgcn_mfma_f32_16x16x16bf16_1k' needs target feature gfx90a-insts}}
|
|
*out2 = __builtin_amdgcn_mfma_f64_16x16x4f64(f, g, h, 0, 0, 0); // expected-error{{'__builtin_amdgcn_mfma_f64_16x16x4f64' needs target feature gfx90a-insts}}
|
|
*out3 = __builtin_amdgcn_mfma_f64_4x4x4f64(f, g, g, 0, 0, 0); // expected-error{{'__builtin_amdgcn_mfma_f64_4x4x4f64' needs target feature gfx90a-insts}}
|
|
}
|