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
67 lines
4.5 KiB
Common Lisp
67 lines
4.5 KiB
Common Lisp
// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py
|
|
// RUN: %clang_cc1 -cl-std=CL2.0 -O0 -triple amdgcn-unknown-unknown -target-cpu gfx900 -emit-llvm -o - %s | FileCheck %s
|
|
// RUN: %clang_cc1 -cl-std=CL2.0 -O0 -triple amdgcn-unknown-unknown -target-cpu gfx942 -emit-llvm -o - %s | FileCheck %s
|
|
// RUN: %clang_cc1 -cl-std=CL2.0 -O0 -triple amdgcn-unknown-unknown -target-cpu gfx1010 -emit-llvm -o - %s | FileCheck %s
|
|
// REQUIRES: amdgpu-registered-target
|
|
|
|
typedef unsigned int u32;
|
|
typedef unsigned short u16;
|
|
typedef unsigned char u8;
|
|
|
|
// CHECK-LABEL: @test_global_load_lds_u32(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[SRC_ADDR:%.*]] = alloca ptr addrspace(1), align 8, addrspace(5)
|
|
// CHECK-NEXT: [[DST_ADDR:%.*]] = alloca ptr addrspace(3), align 4, addrspace(5)
|
|
// CHECK-NEXT: store ptr addrspace(1) [[SRC:%.*]], ptr addrspace(5) [[SRC_ADDR]], align 8
|
|
// CHECK-NEXT: store ptr addrspace(3) [[DST:%.*]], ptr addrspace(5) [[DST_ADDR]], align 4
|
|
// CHECK-NEXT: [[TMP0:%.*]] = load ptr addrspace(1), ptr addrspace(5) [[SRC_ADDR]], align 8
|
|
// CHECK-NEXT: [[TMP1:%.*]] = load ptr addrspace(3), ptr addrspace(5) [[DST_ADDR]], align 4
|
|
// CHECK-NEXT: call void @llvm.amdgcn.global.load.lds(ptr addrspace(1) [[TMP0]], ptr addrspace(3) [[TMP1]], i32 4, i32 0, i32 0)
|
|
// CHECK-NEXT: [[TMP2:%.*]] = load ptr addrspace(1), ptr addrspace(5) [[SRC_ADDR]], align 8
|
|
// CHECK-NEXT: [[TMP3:%.*]] = load ptr addrspace(3), ptr addrspace(5) [[DST_ADDR]], align 4
|
|
// CHECK-NEXT: call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) [[TMP2]], ptr addrspace(3) [[TMP3]], i32 4, i32 0, i32 0)
|
|
// CHECK-NEXT: ret void
|
|
//
|
|
void test_global_load_lds_u32(global u32* src, local u32 *dst) {
|
|
__builtin_amdgcn_global_load_lds(src, dst, /*size=*/4, /*offset=*/0, /*aux=*/0);
|
|
__builtin_amdgcn_global_load_async_lds(src, dst, /*size=*/4, /*offset=*/0, /*aux=*/0);
|
|
}
|
|
|
|
// CHECK-LABEL: @test_global_load_lds_u16(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[SRC_ADDR:%.*]] = alloca ptr addrspace(1), align 8, addrspace(5)
|
|
// CHECK-NEXT: [[DST_ADDR:%.*]] = alloca ptr addrspace(3), align 4, addrspace(5)
|
|
// CHECK-NEXT: store ptr addrspace(1) [[SRC:%.*]], ptr addrspace(5) [[SRC_ADDR]], align 8
|
|
// CHECK-NEXT: store ptr addrspace(3) [[DST:%.*]], ptr addrspace(5) [[DST_ADDR]], align 4
|
|
// CHECK-NEXT: [[TMP0:%.*]] = load ptr addrspace(1), ptr addrspace(5) [[SRC_ADDR]], align 8
|
|
// CHECK-NEXT: [[TMP1:%.*]] = load ptr addrspace(3), ptr addrspace(5) [[DST_ADDR]], align 4
|
|
// CHECK-NEXT: call void @llvm.amdgcn.global.load.lds(ptr addrspace(1) [[TMP0]], ptr addrspace(3) [[TMP1]], i32 2, i32 0, i32 0)
|
|
// CHECK-NEXT: [[TMP2:%.*]] = load ptr addrspace(1), ptr addrspace(5) [[SRC_ADDR]], align 8
|
|
// CHECK-NEXT: [[TMP3:%.*]] = load ptr addrspace(3), ptr addrspace(5) [[DST_ADDR]], align 4
|
|
// CHECK-NEXT: call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) [[TMP2]], ptr addrspace(3) [[TMP3]], i32 2, i32 0, i32 0)
|
|
// CHECK-NEXT: ret void
|
|
//
|
|
void test_global_load_lds_u16(global u16* src, local u16 *dst) {
|
|
__builtin_amdgcn_global_load_lds(src, dst, /*size=*/2, /*offset=*/0, /*aux=*/0);
|
|
__builtin_amdgcn_global_load_async_lds(src, dst, /*size=*/2, /*offset=*/0, /*aux=*/0);
|
|
}
|
|
|
|
// CHECK-LABEL: @test_global_load_lds_u8(
|
|
// CHECK-NEXT: entry:
|
|
// CHECK-NEXT: [[SRC_ADDR:%.*]] = alloca ptr addrspace(1), align 8, addrspace(5)
|
|
// CHECK-NEXT: [[DST_ADDR:%.*]] = alloca ptr addrspace(3), align 4, addrspace(5)
|
|
// CHECK-NEXT: store ptr addrspace(1) [[SRC:%.*]], ptr addrspace(5) [[SRC_ADDR]], align 8
|
|
// CHECK-NEXT: store ptr addrspace(3) [[DST:%.*]], ptr addrspace(5) [[DST_ADDR]], align 4
|
|
// CHECK-NEXT: [[TMP0:%.*]] = load ptr addrspace(1), ptr addrspace(5) [[SRC_ADDR]], align 8
|
|
// CHECK-NEXT: [[TMP1:%.*]] = load ptr addrspace(3), ptr addrspace(5) [[DST_ADDR]], align 4
|
|
// CHECK-NEXT: call void @llvm.amdgcn.global.load.lds(ptr addrspace(1) [[TMP0]], ptr addrspace(3) [[TMP1]], i32 1, i32 0, i32 0)
|
|
// CHECK-NEXT: [[TMP2:%.*]] = load ptr addrspace(1), ptr addrspace(5) [[SRC_ADDR]], align 8
|
|
// CHECK-NEXT: [[TMP3:%.*]] = load ptr addrspace(3), ptr addrspace(5) [[DST_ADDR]], align 4
|
|
// CHECK-NEXT: call void @llvm.amdgcn.global.load.async.lds(ptr addrspace(1) [[TMP2]], ptr addrspace(3) [[TMP3]], i32 1, i32 0, i32 0)
|
|
// CHECK-NEXT: ret void
|
|
//
|
|
void test_global_load_lds_u8(global u8* src, local u8 *dst) {
|
|
__builtin_amdgcn_global_load_lds(src, dst, /*size=*/1, /*offset=*/0, /*aux=*/0);
|
|
__builtin_amdgcn_global_load_async_lds(src, dst, /*size=*/1, /*offset=*/0, /*aux=*/0);
|
|
}
|