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
168 lines
10 KiB
Common Lisp
168 lines
10 KiB
Common Lisp
// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --version 6
|
|
// REQUIRES: amdgpu-registered-target
|
|
// RUN: %clang_cc1 -cl-std=CL2.0 -triple amdgcn-unknown-unknown -target-cpu gfx1250 -emit-llvm -o - %s | FileCheck %s --check-prefix=CHECK-GFX1250
|
|
|
|
typedef int v2i __attribute__((ext_vector_type(2)));
|
|
typedef int v4i __attribute__((ext_vector_type(4)));
|
|
|
|
// CHECK-GFX1250-LABEL: define dso_local void @test_amdgcn_cluster_load_async_to_lds_b8(
|
|
// CHECK-GFX1250-SAME: ptr addrspace(1) noundef readonly captures(none) [[GADDR:%.*]], ptr addrspace(3) noundef writeonly captures(none) [[LADDR:%.*]], i32 noundef [[MASK:%.*]]) local_unnamed_addr #[[ATTR0:[0-9]+]] {
|
|
// CHECK-GFX1250-NEXT: [[ENTRY:.*:]]
|
|
// CHECK-GFX1250-NEXT: tail call void @llvm.amdgcn.cluster.load.async.to.lds.b8(ptr addrspace(1) [[GADDR]], ptr addrspace(3) [[LADDR]], i32 16, i32 0, i32 [[MASK]])
|
|
// CHECK-GFX1250-NEXT: ret void
|
|
//
|
|
void test_amdgcn_cluster_load_async_to_lds_b8(global char* gaddr, local char* laddr, int mask)
|
|
{
|
|
__builtin_amdgcn_cluster_load_async_to_lds_b8(gaddr, laddr, 16, 0, mask);
|
|
}
|
|
|
|
// CHECK-GFX1250-LABEL: define dso_local void @test_amdgcn_cluster_load_async_to_lds_b32(
|
|
// CHECK-GFX1250-SAME: ptr addrspace(1) noundef readonly captures(none) [[GADDR:%.*]], ptr addrspace(3) noundef writeonly captures(none) [[LADDR:%.*]], i32 noundef [[MASK:%.*]]) local_unnamed_addr #[[ATTR0]] {
|
|
// CHECK-GFX1250-NEXT: [[ENTRY:.*:]]
|
|
// CHECK-GFX1250-NEXT: tail call void @llvm.amdgcn.cluster.load.async.to.lds.b32(ptr addrspace(1) [[GADDR]], ptr addrspace(3) [[LADDR]], i32 16, i32 0, i32 [[MASK]])
|
|
// CHECK-GFX1250-NEXT: ret void
|
|
//
|
|
void test_amdgcn_cluster_load_async_to_lds_b32(global int* gaddr, local int* laddr, int mask)
|
|
{
|
|
__builtin_amdgcn_cluster_load_async_to_lds_b32(gaddr, laddr, 16, 0, mask);
|
|
}
|
|
|
|
// CHECK-GFX1250-LABEL: define dso_local void @test_amdgcn_cluster_load_async_to_lds_b64(
|
|
// CHECK-GFX1250-SAME: ptr addrspace(1) noundef readonly captures(none) [[GADDR:%.*]], ptr addrspace(3) noundef writeonly captures(none) [[LADDR:%.*]], i32 noundef [[MASK:%.*]]) local_unnamed_addr #[[ATTR0]] {
|
|
// CHECK-GFX1250-NEXT: [[ENTRY:.*:]]
|
|
// CHECK-GFX1250-NEXT: tail call void @llvm.amdgcn.cluster.load.async.to.lds.b64(ptr addrspace(1) [[GADDR]], ptr addrspace(3) [[LADDR]], i32 16, i32 0, i32 [[MASK]])
|
|
// CHECK-GFX1250-NEXT: ret void
|
|
//
|
|
void test_amdgcn_cluster_load_async_to_lds_b64(global v2i* gaddr, local v2i* laddr, int mask)
|
|
{
|
|
__builtin_amdgcn_cluster_load_async_to_lds_b64(gaddr, laddr, 16, 0, mask);
|
|
}
|
|
|
|
// CHECK-GFX1250-LABEL: define dso_local void @test_amdgcn_cluster_load_async_to_lds_b128(
|
|
// CHECK-GFX1250-SAME: ptr addrspace(1) noundef readonly captures(none) [[GADDR:%.*]], ptr addrspace(3) noundef writeonly captures(none) [[LADDR:%.*]], i32 noundef [[MASK:%.*]]) local_unnamed_addr #[[ATTR0]] {
|
|
// CHECK-GFX1250-NEXT: [[ENTRY:.*:]]
|
|
// CHECK-GFX1250-NEXT: tail call void @llvm.amdgcn.cluster.load.async.to.lds.b128(ptr addrspace(1) [[GADDR]], ptr addrspace(3) [[LADDR]], i32 16, i32 0, i32 [[MASK]])
|
|
// CHECK-GFX1250-NEXT: ret void
|
|
//
|
|
void test_amdgcn_cluster_load_async_to_lds_b128(global v4i* gaddr, local v4i* laddr, int mask)
|
|
{
|
|
__builtin_amdgcn_cluster_load_async_to_lds_b128(gaddr, laddr, 16, 0, mask);
|
|
}
|
|
|
|
// CHECK-GFX1250-LABEL: define dso_local void @test_amdgcn_global_load_async_to_lds_b8(
|
|
// CHECK-GFX1250-SAME: ptr addrspace(1) noundef readonly captures(none) [[GADDR:%.*]], ptr addrspace(3) noundef writeonly captures(none) [[LADDR:%.*]]) local_unnamed_addr #[[ATTR0]] {
|
|
// CHECK-GFX1250-NEXT: [[ENTRY:.*:]]
|
|
// CHECK-GFX1250-NEXT: tail call void @llvm.amdgcn.global.load.async.to.lds.b8(ptr addrspace(1) [[GADDR]], ptr addrspace(3) [[LADDR]], i32 16, i32 0)
|
|
// CHECK-GFX1250-NEXT: ret void
|
|
//
|
|
void test_amdgcn_global_load_async_to_lds_b8( global char* gaddr, local char* laddr)
|
|
{
|
|
__builtin_amdgcn_global_load_async_to_lds_b8(gaddr, laddr, 16, 0);
|
|
}
|
|
|
|
// CHECK-GFX1250-LABEL: define dso_local void @test_amdgcn_global_load_async_to_lds_b32(
|
|
// CHECK-GFX1250-SAME: ptr addrspace(1) noundef readonly captures(none) [[GADDR:%.*]], ptr addrspace(3) noundef writeonly captures(none) [[LADDR:%.*]]) local_unnamed_addr #[[ATTR0]] {
|
|
// CHECK-GFX1250-NEXT: [[ENTRY:.*:]]
|
|
// CHECK-GFX1250-NEXT: tail call void @llvm.amdgcn.global.load.async.to.lds.b32(ptr addrspace(1) [[GADDR]], ptr addrspace(3) [[LADDR]], i32 16, i32 0)
|
|
// CHECK-GFX1250-NEXT: ret void
|
|
//
|
|
void test_amdgcn_global_load_async_to_lds_b32(global int* gaddr, local int* laddr)
|
|
{
|
|
__builtin_amdgcn_global_load_async_to_lds_b32(gaddr, laddr, 16, 0);
|
|
}
|
|
|
|
// CHECK-GFX1250-LABEL: define dso_local void @test_amdgcn_global_load_async_to_lds_b64(
|
|
// CHECK-GFX1250-SAME: ptr addrspace(1) noundef readonly captures(none) [[GADDR:%.*]], ptr addrspace(3) noundef writeonly captures(none) [[LADDR:%.*]]) local_unnamed_addr #[[ATTR0]] {
|
|
// CHECK-GFX1250-NEXT: [[ENTRY:.*:]]
|
|
// CHECK-GFX1250-NEXT: tail call void @llvm.amdgcn.global.load.async.to.lds.b64(ptr addrspace(1) [[GADDR]], ptr addrspace(3) [[LADDR]], i32 16, i32 0)
|
|
// CHECK-GFX1250-NEXT: ret void
|
|
//
|
|
void test_amdgcn_global_load_async_to_lds_b64(global v2i* gaddr, local v2i* laddr)
|
|
{
|
|
__builtin_amdgcn_global_load_async_to_lds_b64(gaddr, laddr, 16, 0);
|
|
}
|
|
|
|
// CHECK-GFX1250-LABEL: define dso_local void @test_amdgcn_global_load_async_to_lds_b128(
|
|
// CHECK-GFX1250-SAME: ptr addrspace(1) noundef readonly captures(none) [[GADDR:%.*]], ptr addrspace(3) noundef writeonly captures(none) [[LADDR:%.*]]) local_unnamed_addr #[[ATTR0]] {
|
|
// CHECK-GFX1250-NEXT: [[ENTRY:.*:]]
|
|
// CHECK-GFX1250-NEXT: tail call void @llvm.amdgcn.global.load.async.to.lds.b128(ptr addrspace(1) [[GADDR]], ptr addrspace(3) [[LADDR]], i32 16, i32 0)
|
|
// CHECK-GFX1250-NEXT: ret void
|
|
//
|
|
void test_amdgcn_global_load_async_to_lds_b128( global v4i* gaddr, local v4i* laddr)
|
|
{
|
|
__builtin_amdgcn_global_load_async_to_lds_b128(gaddr, laddr, 16, 0);
|
|
}
|
|
|
|
// CHECK-GFX1250-LABEL: define dso_local void @test_amdgcn_global_store_async_from_lds_b8(
|
|
// CHECK-GFX1250-SAME: ptr addrspace(1) noundef writeonly captures(none) [[GADDR:%.*]], ptr addrspace(3) noundef readonly captures(none) [[LADDR:%.*]]) local_unnamed_addr #[[ATTR0]] {
|
|
// CHECK-GFX1250-NEXT: [[ENTRY:.*:]]
|
|
// CHECK-GFX1250-NEXT: tail call void @llvm.amdgcn.global.store.async.from.lds.b8(ptr addrspace(1) [[GADDR]], ptr addrspace(3) [[LADDR]], i32 16, i32 0)
|
|
// CHECK-GFX1250-NEXT: ret void
|
|
//
|
|
void test_amdgcn_global_store_async_from_lds_b8(global char* gaddr, local char* laddr)
|
|
{
|
|
__builtin_amdgcn_global_store_async_from_lds_b8(gaddr, laddr, 16, 0);
|
|
}
|
|
|
|
// CHECK-GFX1250-LABEL: define dso_local void @test_amdgcn_global_store_async_from_lds_b32(
|
|
// CHECK-GFX1250-SAME: ptr addrspace(1) noundef writeonly captures(none) [[GADDR:%.*]], ptr addrspace(3) noundef readonly captures(none) [[LADDR:%.*]]) local_unnamed_addr #[[ATTR0]] {
|
|
// CHECK-GFX1250-NEXT: [[ENTRY:.*:]]
|
|
// CHECK-GFX1250-NEXT: tail call void @llvm.amdgcn.global.store.async.from.lds.b32(ptr addrspace(1) [[GADDR]], ptr addrspace(3) [[LADDR]], i32 16, i32 0)
|
|
// CHECK-GFX1250-NEXT: ret void
|
|
//
|
|
void test_amdgcn_global_store_async_from_lds_b32(global int* gaddr, local int* laddr)
|
|
{
|
|
__builtin_amdgcn_global_store_async_from_lds_b32(gaddr, laddr, 16, 0);
|
|
}
|
|
|
|
// CHECK-GFX1250-LABEL: define dso_local void @test_amdgcn_global_store_async_from_lds_b64(
|
|
// CHECK-GFX1250-SAME: ptr addrspace(1) noundef writeonly captures(none) [[GADDR:%.*]], ptr addrspace(3) noundef readonly captures(none) [[LADDR:%.*]]) local_unnamed_addr #[[ATTR0]] {
|
|
// CHECK-GFX1250-NEXT: [[ENTRY:.*:]]
|
|
// CHECK-GFX1250-NEXT: tail call void @llvm.amdgcn.global.store.async.from.lds.b64(ptr addrspace(1) [[GADDR]], ptr addrspace(3) [[LADDR]], i32 16, i32 0)
|
|
// CHECK-GFX1250-NEXT: ret void
|
|
//
|
|
void test_amdgcn_global_store_async_from_lds_b64(global v2i* gaddr, local v2i* laddr)
|
|
{
|
|
__builtin_amdgcn_global_store_async_from_lds_b64(gaddr, laddr, 16, 0);
|
|
}
|
|
|
|
// CHECK-GFX1250-LABEL: define dso_local void @test_amdgcn_global_store_async_from_lds_b128(
|
|
// CHECK-GFX1250-SAME: ptr addrspace(1) noundef writeonly captures(none) [[GADDR:%.*]], ptr addrspace(3) noundef readonly captures(none) [[LADDR:%.*]]) local_unnamed_addr #[[ATTR0]] {
|
|
// CHECK-GFX1250-NEXT: [[ENTRY:.*:]]
|
|
// CHECK-GFX1250-NEXT: tail call void @llvm.amdgcn.global.store.async.from.lds.b128(ptr addrspace(1) [[GADDR]], ptr addrspace(3) [[LADDR]], i32 16, i32 0)
|
|
// CHECK-GFX1250-NEXT: ret void
|
|
//
|
|
void test_amdgcn_global_store_async_from_lds_b128(global v4i* gaddr, local v4i* laddr)
|
|
{
|
|
__builtin_amdgcn_global_store_async_from_lds_b128(gaddr, laddr, 16, 0);
|
|
}
|
|
|
|
// CHECK-GFX1250-LABEL: define dso_local void @test_amdgcn_ds_atomic_async_barrier_arrive_b64(
|
|
// CHECK-GFX1250-SAME: ptr addrspace(3) noundef [[ADDR:%.*]]) local_unnamed_addr #[[ATTR2:[0-9]+]] {
|
|
// CHECK-GFX1250-NEXT: [[ENTRY:.*:]]
|
|
// CHECK-GFX1250-NEXT: tail call void @llvm.amdgcn.ds.atomic.async.barrier.arrive.b64(ptr addrspace(3) [[ADDR]])
|
|
// CHECK-GFX1250-NEXT: ret void
|
|
//
|
|
void test_amdgcn_ds_atomic_async_barrier_arrive_b64(local long* addr)
|
|
{
|
|
__builtin_amdgcn_ds_atomic_async_barrier_arrive_b64(addr);
|
|
}
|
|
|
|
// CHECK-GFX1250-LABEL: define dso_local void @test_amdgcn_ds_atomic_barrier_arrive_rtn_b64(
|
|
// CHECK-GFX1250-SAME: ptr addrspace(3) noundef captures(none) [[ADDR:%.*]], i64 noundef [[DATA:%.*]], ptr noundef writeonly captures(none) initializes((0, 8)) [[OUT:%.*]]) local_unnamed_addr #[[ATTR4:[0-9]+]] {
|
|
// CHECK-GFX1250-NEXT: [[ENTRY:.*:]]
|
|
// CHECK-GFX1250-NEXT: [[TMP0:%.*]] = tail call i64 @llvm.amdgcn.ds.atomic.barrier.arrive.rtn.b64(ptr addrspace(3) [[ADDR]], i64 [[DATA]])
|
|
// CHECK-GFX1250-NEXT: store i64 [[TMP0]], ptr [[OUT]], align 8, !tbaa [[LONG_TBAA8:![0-9]+]]
|
|
// CHECK-GFX1250-NEXT: ret void
|
|
//
|
|
void test_amdgcn_ds_atomic_barrier_arrive_rtn_b64(local long* addr, long data, long *out)
|
|
{
|
|
*out = __builtin_amdgcn_ds_atomic_barrier_arrive_rtn_b64(addr, data);
|
|
}
|
|
//.
|
|
// CHECK-GFX1250: [[META6:![0-9]+]] = !{!"omnipotent char", [[META7:![0-9]+]], i64 0}
|
|
// CHECK-GFX1250: [[META7]] = !{!"Simple C/C++ TBAA"}
|
|
// CHECK-GFX1250: [[LONG_TBAA8]] = !{[[META9:![0-9]+]], [[META9]], i64 0}
|
|
// CHECK-GFX1250: [[META9]] = !{!"long", [[META6]], i64 0}
|
|
//.
|