Revert "[mlir][AMDGPU] Support vector<2xf16> inputs to buffer atomic fadd (#108238)" #108256
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…fadd (llvm#108238)" This reverts commit 0d48d4d.
|
@llvm/pr-subscribers-mlir-amdgpu @llvm/pr-subscribers-mlir Author: Krzysztof Drewniak (krzysz00) ChangesThis reverts commit 0d48d4d. Mistakenly landed without approval Full diff: https://github.com/llvm/llvm-project/pull/108256.diff 3 Files Affected:
diff --git a/mlir/include/mlir/Dialect/AMDGPU/IR/AMDGPU.td b/mlir/include/mlir/Dialect/AMDGPU/IR/AMDGPU.td
index 64db4448bc2f2b..8a1ef94c853a58 100644
--- a/mlir/include/mlir/Dialect/AMDGPU/IR/AMDGPU.td
+++ b/mlir/include/mlir/Dialect/AMDGPU/IR/AMDGPU.td
@@ -253,8 +253,8 @@ def AMDGPU_RawBufferAtomicCmpswapOp :
// Raw buffer atomic floating point add
def AMDGPU_RawBufferAtomicFaddOp :
AMDGPU_Op<"raw_buffer_atomic_fadd", [AllElementTypesMatch<["value", "memref"]>,
- AttrSizedOperandSegments]>,
- Arguments<(ins AnyTypeOf<[F32, VectorOfLengthAndType<[2], [F16]>]>:$value,
+ AttrSizedOperandSegments]>,
+ Arguments<(ins F32:$value,
Arg<AnyMemRef, "buffer to operate on", [MemRead, MemWrite]>:$memref,
Variadic<I32>:$indices,
DefaultValuedAttr<BoolAttr, "true">:$boundsCheck,
diff --git a/mlir/lib/Conversion/AMDGPUToROCDL/AMDGPUToROCDL.cpp b/mlir/lib/Conversion/AMDGPUToROCDL/AMDGPUToROCDL.cpp
index fc5dd7c5602129..96b433294d258a 100644
--- a/mlir/lib/Conversion/AMDGPUToROCDL/AMDGPUToROCDL.cpp
+++ b/mlir/lib/Conversion/AMDGPUToROCDL/AMDGPUToROCDL.cpp
@@ -115,18 +115,15 @@ struct RawBufferOpLowering : public ConvertOpToLLVMPattern<GpuOp> {
rewriter.getIntegerType(floatType.getWidth()));
}
if (auto dataVector = dyn_cast<VectorType>(wantedDataType)) {
- uint32_t vecLen = dataVector.getNumElements();
uint32_t elemBits = dataVector.getElementTypeBitWidth();
- uint32_t totalBits = elemBits * vecLen;
- bool usePackedFp16 =
- dyn_cast_or_null<RawBufferAtomicFaddOp>(*gpuOp) && vecLen == 2;
+ uint32_t totalBits = elemBits * dataVector.getNumElements();
if (totalBits > maxVectorOpWidth)
return gpuOp.emitOpError(
"Total width of loads or stores must be no more than " +
Twine(maxVectorOpWidth) + " bits, but we call for " +
Twine(totalBits) +
" bits. This should've been caught in validation");
- else if (!usePackedFp16 && elemBits < 32) {
+ if (elemBits < 32) {
if (totalBits > 32) {
if (totalBits % 32 != 0)
return gpuOp.emitOpError("Load or store of more than 32-bits that "
diff --git a/mlir/test/Conversion/AMDGPUToROCDL/amdgpu-to-rocdl.mlir b/mlir/test/Conversion/AMDGPUToROCDL/amdgpu-to-rocdl.mlir
index cc51a8c40942f9..717667c22af800 100644
--- a/mlir/test/Conversion/AMDGPUToROCDL/amdgpu-to-rocdl.mlir
+++ b/mlir/test/Conversion/AMDGPUToROCDL/amdgpu-to-rocdl.mlir
@@ -151,17 +151,6 @@ func.func @gpu_gcn_raw_buffer_atomic_fadd_f32(%value: f32, %buf: memref<64xf32>,
func.return
}
-// CHECK-LABEL: func @gpu_gcn_raw_buffer_atomic_fadd_v2f16
-func.func @gpu_gcn_raw_buffer_atomic_fadd_v2f16(%value: vector<2xf16>, %buf: memref<64xf16>, %idx: i32) {
- // CHECK: %[[numRecords:.*]] = llvm.mlir.constant(128 : i32)
- // GFX9: %[[flags:.*]] = llvm.mlir.constant(159744 : i32)
- // RDNA: %[[flags:.*]] = llvm.mlir.constant(822243328 : i32)
- // CHECK: %[[resource:.*]] = rocdl.make.buffer.rsrc %{{.*}}, %{{.*}}, %[[numRecords]], %[[flags]]
- // CHECK: rocdl.raw.ptr.buffer.atomic.fadd %{{.*}}, %[[resource]], %{{.*}}, %{{.*}}, %{{.*}} : vector<2xf16>
- amdgpu.raw_buffer_atomic_fadd {boundsCheck = true} %value -> %buf[%idx] : vector<2xf16> -> memref<64xf16>, i32
- func.return
-}
-
// CHECK-LABEL: func @gpu_gcn_raw_buffer_atomic_fmax_f32
func.func @gpu_gcn_raw_buffer_atomic_fmax_f32(%value: f32, %buf: memref<64xf32>, %idx: i32) {
// CHECK: %[[numRecords:.*]] = llvm.mlir.constant(256 : i32)
|
|
@llvm/pr-subscribers-backend-amdgpu Author: Krzysztof Drewniak (krzysz00) ChangesThis reverts commit 0d48d4d. Mistakenly landed without approval Full diff: https://github.com/llvm/llvm-project/pull/108256.diff 3 Files Affected:
diff --git a/mlir/include/mlir/Dialect/AMDGPU/IR/AMDGPU.td b/mlir/include/mlir/Dialect/AMDGPU/IR/AMDGPU.td
index 64db4448bc2f2b..8a1ef94c853a58 100644
--- a/mlir/include/mlir/Dialect/AMDGPU/IR/AMDGPU.td
+++ b/mlir/include/mlir/Dialect/AMDGPU/IR/AMDGPU.td
@@ -253,8 +253,8 @@ def AMDGPU_RawBufferAtomicCmpswapOp :
// Raw buffer atomic floating point add
def AMDGPU_RawBufferAtomicFaddOp :
AMDGPU_Op<"raw_buffer_atomic_fadd", [AllElementTypesMatch<["value", "memref"]>,
- AttrSizedOperandSegments]>,
- Arguments<(ins AnyTypeOf<[F32, VectorOfLengthAndType<[2], [F16]>]>:$value,
+ AttrSizedOperandSegments]>,
+ Arguments<(ins F32:$value,
Arg<AnyMemRef, "buffer to operate on", [MemRead, MemWrite]>:$memref,
Variadic<I32>:$indices,
DefaultValuedAttr<BoolAttr, "true">:$boundsCheck,
diff --git a/mlir/lib/Conversion/AMDGPUToROCDL/AMDGPUToROCDL.cpp b/mlir/lib/Conversion/AMDGPUToROCDL/AMDGPUToROCDL.cpp
index fc5dd7c5602129..96b433294d258a 100644
--- a/mlir/lib/Conversion/AMDGPUToROCDL/AMDGPUToROCDL.cpp
+++ b/mlir/lib/Conversion/AMDGPUToROCDL/AMDGPUToROCDL.cpp
@@ -115,18 +115,15 @@ struct RawBufferOpLowering : public ConvertOpToLLVMPattern<GpuOp> {
rewriter.getIntegerType(floatType.getWidth()));
}
if (auto dataVector = dyn_cast<VectorType>(wantedDataType)) {
- uint32_t vecLen = dataVector.getNumElements();
uint32_t elemBits = dataVector.getElementTypeBitWidth();
- uint32_t totalBits = elemBits * vecLen;
- bool usePackedFp16 =
- dyn_cast_or_null<RawBufferAtomicFaddOp>(*gpuOp) && vecLen == 2;
+ uint32_t totalBits = elemBits * dataVector.getNumElements();
if (totalBits > maxVectorOpWidth)
return gpuOp.emitOpError(
"Total width of loads or stores must be no more than " +
Twine(maxVectorOpWidth) + " bits, but we call for " +
Twine(totalBits) +
" bits. This should've been caught in validation");
- else if (!usePackedFp16 && elemBits < 32) {
+ if (elemBits < 32) {
if (totalBits > 32) {
if (totalBits % 32 != 0)
return gpuOp.emitOpError("Load or store of more than 32-bits that "
diff --git a/mlir/test/Conversion/AMDGPUToROCDL/amdgpu-to-rocdl.mlir b/mlir/test/Conversion/AMDGPUToROCDL/amdgpu-to-rocdl.mlir
index cc51a8c40942f9..717667c22af800 100644
--- a/mlir/test/Conversion/AMDGPUToROCDL/amdgpu-to-rocdl.mlir
+++ b/mlir/test/Conversion/AMDGPUToROCDL/amdgpu-to-rocdl.mlir
@@ -151,17 +151,6 @@ func.func @gpu_gcn_raw_buffer_atomic_fadd_f32(%value: f32, %buf: memref<64xf32>,
func.return
}
-// CHECK-LABEL: func @gpu_gcn_raw_buffer_atomic_fadd_v2f16
-func.func @gpu_gcn_raw_buffer_atomic_fadd_v2f16(%value: vector<2xf16>, %buf: memref<64xf16>, %idx: i32) {
- // CHECK: %[[numRecords:.*]] = llvm.mlir.constant(128 : i32)
- // GFX9: %[[flags:.*]] = llvm.mlir.constant(159744 : i32)
- // RDNA: %[[flags:.*]] = llvm.mlir.constant(822243328 : i32)
- // CHECK: %[[resource:.*]] = rocdl.make.buffer.rsrc %{{.*}}, %{{.*}}, %[[numRecords]], %[[flags]]
- // CHECK: rocdl.raw.ptr.buffer.atomic.fadd %{{.*}}, %[[resource]], %{{.*}}, %{{.*}}, %{{.*}} : vector<2xf16>
- amdgpu.raw_buffer_atomic_fadd {boundsCheck = true} %value -> %buf[%idx] : vector<2xf16> -> memref<64xf16>, i32
- func.return
-}
-
// CHECK-LABEL: func @gpu_gcn_raw_buffer_atomic_fmax_f32
func.func @gpu_gcn_raw_buffer_atomic_fmax_f32(%value: f32, %buf: memref<64xf32>, %idx: i32) {
// CHECK: %[[numRecords:.*]] = llvm.mlir.constant(256 : i32)
|
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This reverts commit 0d48d4d.
Mistakenly landed without approval