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
83 lines
4.4 KiB
MLIR
83 lines
4.4 KiB
MLIR
// RUN: not mlir-opt %s --split-input-file -convert-amdgpu-to-rocdl=chipset=gfx942 2>&1 | FileCheck %s --check-prefix=GFX942
|
|
// RUN: mlir-opt %s --split-input-file -convert-amdgpu-to-rocdl=chipset=gfx950 | FileCheck %s --check-prefix=GFX950
|
|
|
|
// GFX950-LABEL: func @fat_buffer_load_to_rocdl_f96
|
|
// GFX950-SAME: (%[[ARG0:.*]]: memref<128x72xf32, #amdgpu.address_space<fat_raw_buffer>>)
|
|
func.func @fat_buffer_load_to_rocdl_f96(%global : memref<128x72xf32, #amdgpu.address_space<fat_raw_buffer>>) {
|
|
%c0 = arith.constant 0 : index
|
|
%c12 = arith.constant 12 : index
|
|
%c32 = arith.constant 32 : index
|
|
%alloc = memref.alloc() : memref<64x64xf32, #gpu.address_space<workgroup>>
|
|
// GFX950: %[[BUFFER_DESC:.*]] = builtin.unrealized_conversion_cast %[[ARG0]]
|
|
|
|
// GFX950: %[[C0:.*]] = arith.constant 0 : index
|
|
// GFX950: %[[IC0:.*]] = builtin.unrealized_conversion_cast %c0 : index to i64
|
|
// GFX950: %[[C12:.*]] = arith.constant 12 : index
|
|
// GFX950: %[[IC12:.*]] = builtin.unrealized_conversion_cast %[[C12]]
|
|
// GFX950: %[[C32:.*]] = arith.constant 32 : index
|
|
// GFX950: %[[IC32:.*]] = builtin.unrealized_conversion_cast %[[C32]]
|
|
|
|
// GFX950: %[[ALLOC:.*]] = memref.alloc()
|
|
// GFX950: %[[LDS_DESC:.*]] = builtin.unrealized_conversion_cast
|
|
// GFX950: %[[GLOBAL_BASE:.*]] = llvm.extractvalue %[[BUFFER_DESC]][1]
|
|
|
|
// GFX950: %[[C72:.*]] = llvm.mlir.constant(72 : index) : i64
|
|
// GFX950: %[[MUL:.*]] = llvm.mul %[[IC12]], %[[C72]] : i64
|
|
// GFX950: %[[SRC_OFFSET:.*]] = llvm.add %[[MUL]], %[[IC0]] : i64
|
|
|
|
// GFX950: %[[GLOBAL_PTR:.*]] = llvm.getelementptr %[[GLOBAL_BASE]][%[[SRC_OFFSET]]]
|
|
// GFX950: %[[LDS_BASE:.*]] = llvm.extractvalue %[[LDS_DESC]][1]
|
|
|
|
// GFX950: %[[C64:.*]] = llvm.mlir.constant(64 : index) : i64
|
|
// GFX950: %[[MUL_2:.*]] = llvm.mul %[[IC32]], %[[C64]] : i64
|
|
// GFX950: %[[DST_OFFSET:.*]] = llvm.add %[[MUL_2]], %[[IC0]] : i64
|
|
|
|
// GFX950: %[[LDS_PTR:.*]] = llvm.getelementptr %[[LDS_BASE]][%[[DST_OFFSET]]]
|
|
// GFX950: rocdl.load.to.lds %[[GLOBAL_PTR]], %[[LDS_PTR]], 12
|
|
// GFX942: error: 'amdgpu.gather_to_lds' op Gather to LDS instructions with 12-byte and 16-byte load widths are only supported on gfx950
|
|
amdgpu.gather_to_lds %global[%c12, %c0], %alloc[%c32, %c0]
|
|
: vector<16xf6E3M2FN>, memref<128x72xf32, #amdgpu.address_space<fat_raw_buffer>>, memref<64x64xf32, #gpu.address_space<workgroup>>
|
|
func.return
|
|
}
|
|
|
|
// -----
|
|
|
|
// GFX950-LABEL: func @fat_buffer_load_to_rocdl_f128
|
|
// GFX950-SAME: (%[[ARG0:.*]]: memref<128x72xf32, #amdgpu.address_space<fat_raw_buffer>>)
|
|
func.func @fat_buffer_load_to_rocdl_f128(%global : memref<128x72xf32, #amdgpu.address_space<fat_raw_buffer>>) {
|
|
%c0 = arith.constant 0 : index
|
|
%c12 = arith.constant 12 : index
|
|
%c32 = arith.constant 32 : index
|
|
%alloc = memref.alloc() : memref<64x64xf32, #gpu.address_space<workgroup>>
|
|
// GFX950: %[[BUFFER_DESC:.*]] = builtin.unrealized_conversion_cast %[[ARG0]]
|
|
|
|
// GFX950: %[[C0:.*]] = arith.constant 0 : index
|
|
// GFX950: %[[IC0:.*]] = builtin.unrealized_conversion_cast %c0 : index to i64
|
|
// GFX950: %[[C12:.*]] = arith.constant 12 : index
|
|
// GFX950: %[[IC12:.*]] = builtin.unrealized_conversion_cast %[[C12]]
|
|
// GFX950: %[[C32:.*]] = arith.constant 32 : index
|
|
// GFX950: %[[IC32:.*]] = builtin.unrealized_conversion_cast %[[C32]]
|
|
|
|
// GFX950: %[[ALLOC:.*]] = memref.alloc()
|
|
// GFX950: %[[LDS_DESC:.*]] = builtin.unrealized_conversion_cast
|
|
// GFX950: %[[GLOBAL_BASE:.*]] = llvm.extractvalue %[[BUFFER_DESC]][1]
|
|
|
|
// GFX950: %[[C72:.*]] = llvm.mlir.constant(72 : index) : i64
|
|
// GFX950: %[[MUL:.*]] = llvm.mul %[[IC12]], %[[C72]] : i64
|
|
// GFX950: %[[SRC_OFFSET:.*]] = llvm.add %[[MUL]], %[[IC0]] : i64
|
|
|
|
// GFX950: %[[GLOBAL_PTR:.*]] = llvm.getelementptr %[[GLOBAL_BASE]][%[[SRC_OFFSET]]]
|
|
// GFX950: %[[LDS_BASE:.*]] = llvm.extractvalue %[[LDS_DESC]][1]
|
|
|
|
// GFX950: %[[C64:.*]] = llvm.mlir.constant(64 : index) : i64
|
|
// GFX950: %[[MUL_2:.*]] = llvm.mul %[[IC32]], %[[C64]] : i64
|
|
// GFX950: %[[DST_OFFSET:.*]] = llvm.add %[[MUL_2]], %[[IC0]] : i64
|
|
|
|
// GFX950: %[[LDS_PTR:.*]] = llvm.getelementptr %[[LDS_BASE]][%[[DST_OFFSET]]]
|
|
// GFX950: rocdl.load.to.lds %[[GLOBAL_PTR]], %[[LDS_PTR]], 16
|
|
// GFX942: error: 'amdgpu.gather_to_lds' op Gather to LDS instructions with 12-byte and 16-byte load widths are only supported on gfx950
|
|
amdgpu.gather_to_lds %global[%c12, %c0], %alloc[%c32, %c0]
|
|
: f128, memref<128x72xf32, #amdgpu.address_space<fat_raw_buffer>>, memref<64x64xf32, #gpu.address_space<workgroup>>
|
|
func.return
|
|
}
|