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
68 lines
4.4 KiB
MLIR
68 lines
4.4 KiB
MLIR
// RUN: mlir-opt -convert-xegpu-to-xevm -canonicalize %s | FileCheck %s
|
|
|
|
gpu.module @load_store_check {
|
|
// CHECK-LABEL: gpu.func @load_store(
|
|
gpu.func @load_store(%src: memref<8x16xf32, 1>, %dst: memref<8x16xf32, 1>) kernel {
|
|
// CHECK: %[[W_P_BYTES:.*]] = arith.constant 64 : i32
|
|
// CHECK: %[[ZERO:.*]] = arith.constant 0 : i32
|
|
// CHECK: %[[H:.*]] = arith.constant 8 : i32
|
|
%srcce = memref.memory_space_cast %src : memref<8x16xf32, 1> to memref<8x16xf32>
|
|
%dstte = memref.memory_space_cast %dst : memref<8x16xf32, 1> to memref<8x16xf32>
|
|
|
|
%src_tdesc = xegpu.create_nd_tdesc %srcce : memref<8x16xf32> -> !xegpu.tensor_desc<8x16xf32>
|
|
|
|
//CHECK: %[[LD_LOADED_I32:.*]] = xevm.blockload2d %{{.*}}, %[[W_P_BYTES]], %[[H]], %[[W_P_BYTES]], %[[ZERO]], %[[ZERO]]
|
|
//CHECK-SAME: <{cache_control = #xevm.load_cache_control<L1c_L2uc_L3c>, elem_size_in_bits = 32 : i32,
|
|
//CHECK-SAME: pack_register = false, tile_height = 8 : i32, tile_width = 16 : i32, transpose = false,
|
|
//CHECK-SAME: v_blocks = 1 : i32}> : (!llvm.ptr<1>, i32, i32, i32, i32, i32) -> vector<8xi32>
|
|
%loaded = xegpu.load_nd %src_tdesc[0, 0] <{l1_hint = #xegpu.cache_hint<cached>, l2_hint = #xegpu.cache_hint<uncached>}>
|
|
: !xegpu.tensor_desc<8x16xf32> -> vector<8xf32>
|
|
|
|
%tid_x = gpu.thread_id x
|
|
%tid_x_i32 = arith.index_cast %tid_x : index to i32
|
|
%tid_x_f32 = arith.sitofp %tid_x_i32 : i32 to f32
|
|
%loaded_modified = vector.insert %tid_x_f32, %loaded[0] : f32 into vector<8xf32>
|
|
|
|
%dst_tdesc = xegpu.create_nd_tdesc %dstte : memref<8x16xf32> -> !xegpu.tensor_desc<8x16xf32, #xegpu.block_tdesc_attr<memory_space = global>>
|
|
|
|
//CHECK: xevm.blockstore2d %{{.*}}, %[[W_P_BYTES]], %[[H]], %[[W_P_BYTES]], %[[ZERO]], %[[ZERO]], %{{.*}} <{
|
|
//CHECK-SAME: cache_control = #xevm.store_cache_control<L1wb_L2uc_L3wb>, elem_size_in_bits = 32 : i32,
|
|
//CHECK-SAME: tile_height = 8 : i32, tile_width = 16 : i32}> : (!llvm.ptr<1>, i32, i32, i32, i32, i32, vector<8xi32>)
|
|
xegpu.store_nd %loaded_modified, %dst_tdesc[0, 0] <{l1_hint = #xegpu.cache_hint<write_back>, l2_hint = #xegpu.cache_hint<uncached>}>
|
|
: vector<8xf32>, !xegpu.tensor_desc<8x16xf32, #xegpu.block_tdesc_attr<memory_space = global>>
|
|
gpu.return
|
|
}
|
|
|
|
// CHECK-LABEL: gpu.func @load_store_with_partial_cache_hints(
|
|
gpu.func @load_store_with_partial_cache_hints(%src: memref<8x16xf32, 1>, %dst: memref<8x16xf32, 1>) kernel {
|
|
// CHECK: %[[W_P_BYTES:.*]] = arith.constant 64 : i32
|
|
// CHECK: %[[ZERO:.*]] = arith.constant 0 : i32
|
|
// CHECK: %[[H:.*]] = arith.constant 8 : i32
|
|
%srcce = memref.memory_space_cast %src : memref<8x16xf32, 1> to memref<8x16xf32>
|
|
%dstte = memref.memory_space_cast %dst : memref<8x16xf32, 1> to memref<8x16xf32>
|
|
|
|
%src_tdesc = xegpu.create_nd_tdesc %srcce : memref<8x16xf32> -> !xegpu.tensor_desc<8x16xf32>
|
|
|
|
//CHECK: %[[LD_LOADED_I32:.*]] = xevm.blockload2d %{{.*}}, %[[W_P_BYTES]], %[[H]], %[[W_P_BYTES]], %[[ZERO]], %[[ZERO]]
|
|
//CHECK-SAME: <{cache_control = #xevm.load_cache_control<L1c_L2uc_L3c>, elem_size_in_bits = 32 : i32,
|
|
//CHECK-SAME: pack_register = false, tile_height = 8 : i32, tile_width = 16 : i32, transpose = false,
|
|
//CHECK-SAME: v_blocks = 1 : i32}> : (!llvm.ptr<1>, i32, i32, i32, i32, i32) -> vector<8xi32>
|
|
%loaded = xegpu.load_nd %src_tdesc[0, 0] <{l1_hint = #xegpu.cache_hint<cached>}>
|
|
: !xegpu.tensor_desc<8x16xf32> -> vector<8xf32>
|
|
|
|
%tid_x = gpu.thread_id x
|
|
%tid_x_i32 = arith.index_cast %tid_x : index to i32
|
|
%tid_x_f32 = arith.sitofp %tid_x_i32 : i32 to f32
|
|
%loaded_modified = vector.insert %tid_x_f32, %loaded[0] : f32 into vector<8xf32>
|
|
|
|
%dst_tdesc = xegpu.create_nd_tdesc %dstte : memref<8x16xf32> -> !xegpu.tensor_desc<8x16xf32, #xegpu.block_tdesc_attr<memory_space = global>>
|
|
|
|
//CHECK: xevm.blockstore2d %{{.*}}, %[[W_P_BYTES]], %[[H]], %[[W_P_BYTES]], %[[ZERO]], %[[ZERO]], %{{.*}} <{
|
|
//CHECK-SAME: cache_control = #xevm.store_cache_control<Use_Default>, elem_size_in_bits = 32 : i32,
|
|
//CHECK-SAME: tile_height = 8 : i32, tile_width = 16 : i32}> : (!llvm.ptr<1>, i32, i32, i32, i32, i32, vector<8xi32>)
|
|
xegpu.store_nd %loaded_modified, %dst_tdesc[0, 0] <{}>
|
|
: vector<8xf32>, !xegpu.tensor_desc<8x16xf32, #xegpu.block_tdesc_attr<memory_space = global>>
|
|
gpu.return
|
|
}
|
|
}
|