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
57 lines
2.8 KiB
MLIR
57 lines
2.8 KiB
MLIR
// RUN: mlir-opt %s --split-input-file -convert-amdgpu-to-rocdl=chipset=gfx950 | FileCheck %s
|
|
// RUN: not mlir-opt %s --split-input-file -convert-amdgpu-to-rocdl=chipset=gfx942 2>&1 | FileCheck %s --check-prefix=CHECK-OLD
|
|
|
|
// CHECK-LABEL: func @transpose_load_to_rocdl_4xf16
|
|
func.func @transpose_load_to_rocdl_4xf16(%idx1 : index, %idx2 : index, %wgmem : memref<128x72xf16, 3>) -> vector<4xf16> {
|
|
// CHECK: rocdl.ds.read.tr16.b64
|
|
// CHECK-OLD: error: 'amdgpu.transpose_load' op transpose_load is only supported on gfx950 and gfx1250+
|
|
%0 = amdgpu.transpose_load %wgmem[%idx1, %idx2] : memref<128x72xf16, 3> -> vector<4xf16>
|
|
return %0 : vector<4xf16>
|
|
}
|
|
|
|
// -----
|
|
|
|
// CHECK-LABEL: func @transpose_load_to_rocdl_8xi8
|
|
func.func @transpose_load_to_rocdl_8xi8(%idx1 : index, %idx2 : index, %wgmem : memref<128x128xi8, 3>) -> vector<8xi8> {
|
|
// CHECK: %[[RES:.*]] = rocdl.ds.read.tr8.b64
|
|
// CHECK-SAME: -> vector<2xi32>
|
|
// CHECK-NEXT: llvm.bitcast %[[RES]] : vector<2xi32> to vector<8xi8>
|
|
// CHECK-OLD: error: 'amdgpu.transpose_load' op transpose_load is only supported on gfx950 and gfx1250+
|
|
%0 = amdgpu.transpose_load %wgmem[%idx1, %idx2] : memref<128x128xi8, 3> -> vector<8xi8>
|
|
return %0 : vector<8xi8>
|
|
}
|
|
|
|
// -----
|
|
|
|
// CHECK-LABEL: func @transpose_load_to_rocdl_i4_memrefxi8
|
|
func.func @transpose_load_to_rocdl_i4_memrefxi8(%idx1 : index, %idx2 : index, %wgmem : memref<128x32xi8, 3>) -> vector<16xi4> {
|
|
// CHECK: %[[RES:.*]] = rocdl.ds.read.tr4.b64
|
|
// CHECK-SAME: -> vector<2xi32>
|
|
// CHECK-NEXT: llvm.bitcast %[[RES]] : vector<2xi32> to vector<16xi4>
|
|
// CHECK-OLD: error: 'amdgpu.transpose_load' op transpose_load is only supported on gfx950 and gfx1250+
|
|
%0 = amdgpu.transpose_load %wgmem[%idx1, %idx2] : memref<128x32xi8, 3> -> vector<16xi4>
|
|
return %0 : vector<16xi4>
|
|
}
|
|
|
|
// -----
|
|
|
|
// CHECK-LABEL: func @transpose_load_to_rocdl_i6_memrefxi8
|
|
func.func @transpose_load_to_rocdl_i6_memrefxi8(%idx1 : index, %idx2 : index, %wgmem : memref<128x32xi8, 3>) -> vector<16xi6> {
|
|
// CHECK: %[[RES:.*]] = rocdl.ds.read.tr6.b96
|
|
// CHECK-SAME: -> vector<3xi32>
|
|
// CHECK-NEXT: llvm.bitcast %[[RES]] : vector<3xi32> to vector<16xi6>
|
|
// CHECK-OLD: error: 'amdgpu.transpose_load' op transpose_load is only supported on gfx950 and gfx1250+
|
|
%0 = amdgpu.transpose_load %wgmem[%idx1, %idx2] : memref<128x32xi8, 3> -> vector<16xi6>
|
|
return %0 : vector<16xi6>
|
|
}
|
|
|
|
// -----
|
|
|
|
// CHECK-LABEL: func @transpose_load_to_rocdl_i16_memrefxi8
|
|
func.func @transpose_load_to_rocdl_i16_memrefxi8(%idx1 : index, %idx2 : index, %wgmem : memref<128x32xi8, 3>) -> vector<4xi16> {
|
|
// CHECK: rocdl.ds.read.tr16.b64
|
|
// CHECK-OLD: error: 'amdgpu.transpose_load' op transpose_load is only supported on gfx950 and gfx1250+
|
|
%0 = amdgpu.transpose_load %wgmem[%idx1, %idx2] : memref<128x32xi8, 3> -> vector<4xi16>
|
|
return %0 : vector<4xi16>
|
|
}
|