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
62 lines
2.8 KiB
MLIR
62 lines
2.8 KiB
MLIR
// RUN: mlir-translate -mlir-to-llvmir %s | FileCheck %s
|
|
|
|
llvm.func @prefetch_L1(%gen_ptr: !llvm.ptr, %local_ptr: !llvm.ptr<5>, %global_ptr: !llvm.ptr<1>) {
|
|
// CHECK-LABEL: define void @prefetch_L1(ptr %0, ptr addrspace(5) %1, ptr addrspace(1) %2) {
|
|
// CHECK-NEXT: call void @llvm.nvvm.prefetch.L1(ptr %0)
|
|
// CHECK-NEXT: call void @llvm.nvvm.prefetch.local.L1(ptr addrspace(5) %1)
|
|
// CHECK-NEXT: call void @llvm.nvvm.prefetch.global.L1(ptr addrspace(1) %2)
|
|
// CHECK-NEXT: ret void
|
|
// CHECK-NEXT: }
|
|
nvvm.prefetch level = L1, %gen_ptr : !llvm.ptr<0>
|
|
nvvm.prefetch level = L1, %local_ptr : !llvm.ptr<5>
|
|
nvvm.prefetch level = L1, %global_ptr : !llvm.ptr<1>
|
|
llvm.return
|
|
}
|
|
|
|
llvm.func @prefetch_L2(%gen_ptr: !llvm.ptr, %local_ptr: !llvm.ptr<5>, %global_ptr: !llvm.ptr<1>) {
|
|
// CHECK-LABEL: define void @prefetch_L2(ptr %0, ptr addrspace(5) %1, ptr addrspace(1) %2) {
|
|
// CHECK-NEXT: call void @llvm.nvvm.prefetch.L2(ptr %0)
|
|
// CHECK-NEXT: call void @llvm.nvvm.prefetch.local.L2(ptr addrspace(5) %1)
|
|
// CHECK-NEXT: call void @llvm.nvvm.prefetch.global.L2(ptr addrspace(1) %2)
|
|
// CHECK-NEXT: ret void
|
|
// CHECK-NEXT: }
|
|
nvvm.prefetch level = L2, %gen_ptr : !llvm.ptr<0>
|
|
nvvm.prefetch level = L2, %local_ptr : !llvm.ptr<5>
|
|
nvvm.prefetch level = L2, %global_ptr : !llvm.ptr<1>
|
|
llvm.return
|
|
}
|
|
|
|
llvm.func @prefetch_L2_eviction_priority(%global_ptr: !llvm.ptr<1>) {
|
|
// CHECK-LABEL: define void @prefetch_L2_eviction_priority(ptr addrspace(1) %0) {
|
|
// CHECK-NEXT: call void @llvm.nvvm.prefetch.global.L2.evict.last(ptr addrspace(1) %0)
|
|
// CHECK-NEXT: call void @llvm.nvvm.prefetch.global.L2.evict.normal(ptr addrspace(1) %0)
|
|
// CHECK-NEXT: ret void
|
|
// CHECK-NEXT: }
|
|
nvvm.prefetch level = L2, evict_priority = evict_last, %global_ptr : !llvm.ptr<1>
|
|
nvvm.prefetch level = L2, evict_priority = evict_normal, %global_ptr : !llvm.ptr<1>
|
|
llvm.return
|
|
}
|
|
|
|
llvm.func @prefetch_L1_uniform(%gen_ptr: !llvm.ptr) {
|
|
// CHECK-LABEL: define void @prefetch_L1_uniform(ptr %0) {
|
|
// CHECK-NEXT: call void @llvm.nvvm.prefetchu.L1(ptr %0)
|
|
// CHECK-NEXT: ret void
|
|
// CHECK-NEXT: }
|
|
nvvm.prefetch level = L1 uniform, %gen_ptr : !llvm.ptr
|
|
llvm.return
|
|
}
|
|
|
|
llvm.func @prefetch_tensormap(%gen_ptr: !llvm.ptr, %const_ptr: !llvm.ptr<4>) {
|
|
// CHECK-LABEL: define void @prefetch_tensormap(ptr %0, ptr addrspace(4) %1) {
|
|
// CHECK-NEXT: call void @llvm.nvvm.prefetch.tensormap.p0(ptr %0)
|
|
// CHECK-NEXT: call void @llvm.nvvm.prefetch.tensormap.p4(ptr addrspace(4) %1)
|
|
// CHECK-NEXT: %3 = addrspacecast ptr %0 to ptr addrspace(101)
|
|
// CHECK-NEXT: call void @llvm.nvvm.prefetch.tensormap.p101(ptr addrspace(101) %3)
|
|
// CHECK-NEXT: ret void
|
|
// CHECK-NEXT: }
|
|
nvvm.prefetch tensormap, %gen_ptr : !llvm.ptr
|
|
nvvm.prefetch tensormap, %const_ptr: !llvm.ptr<4>
|
|
nvvm.prefetch tensormap in_param_space, %gen_ptr : !llvm.ptr
|
|
llvm.return
|
|
}
|