Files
TheRock/compiler/amd-llvm/clang/test/CodeGenOpenCL/builtins-amdgcn-dl-insts.cl
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

59 lines
2.8 KiB
Common Lisp

// REQUIRES: amdgpu-registered-target
// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu gfx906 -emit-llvm -o - %s | FileCheck %s
// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu gfx1011 -emit-llvm -o - %s | FileCheck %s
// RUN: %clang_cc1 -triple amdgcn-unknown-unknown -target-cpu gfx1012 -emit-llvm -o - %s | FileCheck %s
typedef unsigned int uint;
typedef half __attribute__((ext_vector_type(2))) half2;
typedef short __attribute__((ext_vector_type(2))) short2;
typedef unsigned short __attribute__((ext_vector_type(2))) ushort2;
// CHECK-LABEL: @builtins_amdgcn_dl_insts
// CHECK: call float @llvm.amdgcn.fdot2(<2 x half> %v2hA, <2 x half> %v2hB, float %fC, i1 false)
// CHECK: call float @llvm.amdgcn.fdot2(<2 x half> %v2hA, <2 x half> %v2hB, float %fC, i1 true)
// CHECK: call i32 @llvm.amdgcn.sdot2(<2 x i16> %v2ssA, <2 x i16> %v2ssB, i32 %siC, i1 false)
// CHECK: call i32 @llvm.amdgcn.sdot2(<2 x i16> %v2ssA, <2 x i16> %v2ssB, i32 %siC, i1 true)
// CHECK: call i32 @llvm.amdgcn.udot2(<2 x i16> %v2usA, <2 x i16> %v2usB, i32 %uiC, i1 false)
// CHECK: call i32 @llvm.amdgcn.udot2(<2 x i16> %v2usA, <2 x i16> %v2usB, i32 %uiC, i1 true)
// CHECK: call i32 @llvm.amdgcn.sdot4(i32 %siA, i32 %siB, i32 %siC, i1 false)
// CHECK: call i32 @llvm.amdgcn.sdot4(i32 %siA, i32 %siB, i32 %siC, i1 true)
// CHECK: call i32 @llvm.amdgcn.udot4(i32 %uiA, i32 %uiB, i32 %uiC, i1 false)
// CHECK: call i32 @llvm.amdgcn.udot4(i32 %uiA, i32 %uiB, i32 %uiC, i1 true)
// CHECK: call i32 @llvm.amdgcn.sdot8(i32 %siA, i32 %siB, i32 %siC, i1 false)
// CHECK: call i32 @llvm.amdgcn.sdot8(i32 %siA, i32 %siB, i32 %siC, i1 true)
// CHECK: call i32 @llvm.amdgcn.udot8(i32 %uiA, i32 %uiB, i32 %uiC, i1 false)
// CHECK: call i32 @llvm.amdgcn.udot8(i32 %uiA, i32 %uiB, i32 %uiC, i1 true)
kernel void builtins_amdgcn_dl_insts(
global float *fOut, global int *siOut, global uint *uiOut,
half2 v2hA, half2 v2hB, float fC,
short2 v2ssA, short2 v2ssB, int siA, int siB, int siC,
ushort2 v2usA, ushort2 v2usB, uint uiA, uint uiB, uint uiC) {
fOut[0] = __builtin_amdgcn_fdot2(v2hA, v2hB, fC, false);
fOut[1] = __builtin_amdgcn_fdot2(v2hA, v2hB, fC, true);
siOut[0] = __builtin_amdgcn_sdot2(v2ssA, v2ssB, siC, false);
siOut[1] = __builtin_amdgcn_sdot2(v2ssA, v2ssB, siC, true);
uiOut[0] = __builtin_amdgcn_udot2(v2usA, v2usB, uiC, false);
uiOut[1] = __builtin_amdgcn_udot2(v2usA, v2usB, uiC, true);
siOut[2] = __builtin_amdgcn_sdot4(siA, siB, siC, false);
siOut[3] = __builtin_amdgcn_sdot4(siA, siB, siC, true);
uiOut[2] = __builtin_amdgcn_udot4(uiA, uiB, uiC, false);
uiOut[3] = __builtin_amdgcn_udot4(uiA, uiB, uiC, true);
siOut[4] = __builtin_amdgcn_sdot8(siA, siB, siC, false);
siOut[5] = __builtin_amdgcn_sdot8(siA, siB, siC, true);
uiOut[4] = __builtin_amdgcn_udot8(uiA, uiB, uiC, false);
uiOut[5] = __builtin_amdgcn_udot8(uiA, uiB, uiC, true);
}