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
63 lines
3.2 KiB
MLIR
63 lines
3.2 KiB
MLIR
// RUN: mlir-opt --test-gpu-rewrite -split-input-file %s | FileCheck %s
|
|
|
|
module {
|
|
// CHECK-LABEL: func.func @shuffleF64
|
|
// CHECK-SAME: (%[[SZ:.*]]: index, %[[VALUE:.*]]: f64, %[[OFF:.*]]: i32, %[[WIDTH:.*]]: i32, %[[MEM:.*]]: memref<f64, 1>) {
|
|
func.func @shuffleF64(%sz : index, %value: f64, %offset: i32, %width: i32, %mem: memref<f64, 1>) {
|
|
gpu.launch blocks(%bx, %by, %bz) in (%grid_x = %sz, %grid_y = %sz, %grid_z = %sz)
|
|
threads(%tx, %ty, %tz) in (%block_x = %sz, %block_y = %sz, %block_z = %sz) {
|
|
// CHECK: %[[INTVAL:.*]] = arith.bitcast %[[VALUE]] : f64 to i64
|
|
// CHECK-NEXT: %[[LO:.*]] = arith.trunci %[[INTVAL]] : i64 to i32
|
|
// CHECK-NEXT: %[[HI64:.*]] = arith.shrui %[[INTVAL]], %[[C32:.*]] : i64
|
|
// CHECK-NEXT: %[[HI:.*]] = arith.trunci %[[HI64]] : i64 to i32
|
|
// CHECK-NEXT: %[[SH1:.*]], %[[V1:.*]] = gpu.shuffle xor %[[LO]], %[[OFF]], %[[WIDTH]] : i32
|
|
// CHECK-NEXT: %[[SH2:.*]], %[[V2:.*]] = gpu.shuffle xor %[[HI]], %[[OFF]], %[[WIDTH]] : i32
|
|
// CHECK-NEXT: %[[LOSH:.*]] = arith.extui %[[SH1]] : i32 to i64
|
|
// CHECK-NEXT: %[[HISHTMP:.*]] = arith.extui %[[SH2]] : i32 to i64
|
|
// CHECK-NEXT: %[[HISH:.*]] = arith.shli %[[HISHTMP]], %[[C32]] : i64
|
|
// CHECK-NEXT: %[[SHFLINT:.*]] = arith.ori %[[HISH]], %[[LOSH]] : i64
|
|
// CHECK-NEXT: = arith.bitcast %[[SHFLINT]] : i64 to f64
|
|
%shfl, %pred = gpu.shuffle xor %value, %offset, %width : f64
|
|
memref.store %shfl, %mem[] : memref<f64, 1>
|
|
gpu.terminator
|
|
}
|
|
return
|
|
}
|
|
}
|
|
|
|
// -----
|
|
|
|
module {
|
|
// CHECK-LABEL: func.func @shuffleI64
|
|
// CHECK-SAME: (%[[SZ:.*]]: index, %[[VALUE:.*]]: i64, %[[OFF:.*]]: i32, %[[WIDTH:.*]]: i32, %[[MEM:.*]]: memref<i64, 1>) {
|
|
func.func @shuffleI64(%sz : index, %value: i64, %offset: i32, %width: i32, %mem: memref<i64, 1>) {
|
|
gpu.launch blocks(%bx, %by, %bz) in (%grid_x = %sz, %grid_y = %sz, %grid_z = %sz)
|
|
threads(%tx, %ty, %tz) in (%block_x = %sz, %block_y = %sz, %block_z = %sz) {
|
|
// CHECK: %[[LO:.*]] = arith.trunci %[[VALUE]] : i64 to i32
|
|
// CHECK-NEXT: %[[HI64:.*]] = arith.shrui %[[VALUE]], %[[C32:.*]] : i64
|
|
// CHECK-NEXT: %[[HI:.*]] = arith.trunci %[[HI64]] : i64 to i32
|
|
// CHECK-NEXT: %[[SH1:.*]], %[[V1:.*]] = gpu.shuffle xor %[[LO]], %[[OFF]], %[[WIDTH]] : i32
|
|
// CHECK-NEXT: %[[SH2:.*]], %[[V2:.*]] = gpu.shuffle xor %[[HI]], %[[OFF]], %[[WIDTH]] : i32
|
|
// CHECK-NEXT: %[[LOSH:.*]] = arith.extui %[[SH1]] : i32 to i64
|
|
// CHECK-NEXT: %[[HISHTMP:.*]] = arith.extui %[[SH2]] : i32 to i64
|
|
// CHECK-NEXT: %[[HISH:.*]] = arith.shli %[[HISHTMP]], %[[C32]] : i64
|
|
// CHECK-NEXT: %[[SHFLINT:.*]] = arith.ori %[[HISH]], %[[LOSH]] : i64
|
|
%shfl, %pred = gpu.shuffle xor %value, %offset, %width : i64
|
|
memref.store %shfl, %mem[] : memref<i64, 1>
|
|
gpu.terminator
|
|
}
|
|
return
|
|
}
|
|
}
|
|
|
|
// -----
|
|
|
|
// CHECK-LABEL: @gpu_shuffle_unsupported
|
|
func.func @gpu_shuffle_unsupported(%arg0 : vector<4xf16>) -> vector<4xf16> {
|
|
%offset = arith.constant 4 : i32
|
|
%width = arith.constant 64 : i32
|
|
// CHECK: gpu.shuffle xor %{{.*}}, %{{.*}}, %{{.*}} : vector<4xf16>
|
|
%shfl, %pred = gpu.shuffle xor %arg0, %offset, %width : vector<4xf16>
|
|
return %shfl : vector<4xf16>
|
|
}
|