[Mlir-commits] [mlir] [mlir][GPU] Expand LLVM function attribute copies (PR #76755)
llvmlistbot at llvm.org
llvmlistbot at llvm.org
Tue Jan 2 13:12:46 PST 2024
llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT-->
@llvm/pr-subscribers-mlir-gpu
Author: Krzysztof Drewniak (krzysz00)
<details>
<summary>Changes</summary>
Expand the copying of attributes on GPU kernel arguments during LLVM lowering.
Support copying attributes from values that are already LLVM pointers.
Support copying attributes, like `noundef`, that aren't specific to (the pointer parts of) arguments.
---
Full diff: https://github.com/llvm/llvm-project/pull/76755.diff
2 Files Affected:
- (modified) mlir/lib/Conversion/GPUCommon/GPUOpsLowering.cpp (+22-5)
- (modified) mlir/test/Conversion/GPUCommon/memref-arg-attrs.mlir (+25)
``````````diff
diff --git a/mlir/lib/Conversion/GPUCommon/GPUOpsLowering.cpp b/mlir/lib/Conversion/GPUCommon/GPUOpsLowering.cpp
index e79a02f931af2d..69d69356b1f6cf 100644
--- a/mlir/lib/Conversion/GPUCommon/GPUOpsLowering.cpp
+++ b/mlir/lib/Conversion/GPUCommon/GPUOpsLowering.cpp
@@ -194,18 +194,22 @@ GPUFuncOpLowering::matchAndRewrite(gpu::GPUFuncOp gpuFuncOp, OpAdaptor adaptor,
// Get memref type from function arguments and set the noalias to
// pointer arguments.
for (const auto &en : llvm::enumerate(gpuFuncOp.getArgumentTypes())) {
- auto memrefTy = en.value().dyn_cast<MemRefType>();
+ auto remapping = signatureConversion.getInputMapping(en.index());
NamedAttrList argAttr = argAttrs
? argAttrs[en.index()].cast<DictionaryAttr>()
: NamedAttrList();
-
+ auto copyAttribute = [&](StringRef attrName) {
+ Attribute attr = argAttr.erase(attrName);
+ if (!attr)
+ return;
+ for (size_t i = 0, e = remapping->size; i < e; ++i)
+ llvmFuncOp.setArgAttr(remapping->inputNo + i, attrName, attr);
+ };
auto copyPointerAttribute = [&](StringRef attrName) {
Attribute attr = argAttr.erase(attrName);
- // This is a proxy for the bare pointer calling convention.
if (!attr)
return;
- auto remapping = signatureConversion.getInputMapping(en.index());
if (remapping->size > 1 &&
attrName == LLVM::LLVMDialect::getNoAliasAttrName()) {
emitWarning(llvmFuncOp.getLoc(),
@@ -224,10 +228,23 @@ GPUFuncOpLowering::matchAndRewrite(gpu::GPUFuncOp gpuFuncOp, OpAdaptor adaptor,
if (argAttr.empty())
continue;
- if (memrefTy) {
+ copyAttribute(LLVM::LLVMDialect::getReturnedAttrName());
+ copyAttribute(LLVM::LLVMDialect::getNoUndefAttrName());
+ copyAttribute(LLVM::LLVMDialect::getInRegAttrName());
+ bool lowersToPointer = false;
+ for (size_t i = 0, e = remapping->size; i < e; ++i) {
+ lowersToPointer |= isa<LLVM::LLVMPointerType>(
+ llvmFuncOp.getArgument(remapping->inputNo + i).getType());
+ }
+
+ if (lowersToPointer) {
copyPointerAttribute(LLVM::LLVMDialect::getNoAliasAttrName());
+ copyPointerAttribute(LLVM::LLVMDialect::getNoCaptureAttrName());
+ copyPointerAttribute(LLVM::LLVMDialect::getNoFreeAttrName());
+ copyPointerAttribute(LLVM::LLVMDialect::getAlignAttrName());
copyPointerAttribute(LLVM::LLVMDialect::getReadonlyAttrName());
copyPointerAttribute(LLVM::LLVMDialect::getWriteOnlyAttrName());
+ copyPointerAttribute(LLVM::LLVMDialect::getReadnoneAttrName());
copyPointerAttribute(LLVM::LLVMDialect::getNonNullAttrName());
copyPointerAttribute(LLVM::LLVMDialect::getDereferenceableAttrName());
copyPointerAttribute(
diff --git a/mlir/test/Conversion/GPUCommon/memref-arg-attrs.mlir b/mlir/test/Conversion/GPUCommon/memref-arg-attrs.mlir
index 33374984eb7c91..e7c742067b4eb5 100644
--- a/mlir/test/Conversion/GPUCommon/memref-arg-attrs.mlir
+++ b/mlir/test/Conversion/GPUCommon/memref-arg-attrs.mlir
@@ -24,6 +24,17 @@ gpu.module @kernel {
// ROCDL-SAME: !llvm.ptr {llvm.writeonly}
// NVVM-SAME: !llvm.ptr {llvm.writeonly}
+// -----
+
+gpu.module @kernel {
+ gpu.func @test_func_readonly_ptr(%arg0 : !llvm.ptr {llvm.readonly} ) {
+ gpu.return
+ }
+}
+
+// CHECK-LABEL: llvm.func @test_func_readonly_ptr
+// ROCDL-SAME: !llvm.ptr {llvm.readonly}
+// NVVM-SAME: !llvm.ptr {llvm.readonly}
// -----
@@ -62,3 +73,17 @@ gpu.module @kernel {
// CHECK-LABEL: llvm.func @test_func_dereferenceable_or_null
// ROCDL-SAME: !llvm.ptr {llvm.dereferenceable_or_null = 4 : i64}
// NVVM-SAME: !llvm.ptr {llvm.dereferenceable_or_null = 4 : i64}
+
+// -----
+
+gpu.module @kernel {
+ gpu.func @test_func_noundef(%arg0 : memref<f32> {llvm.noundef} ) {
+ gpu.return
+ }
+}
+
+// CHECK-LABEL: llvm.func @test_func_noundef
+// ROCDL-SAME: !llvm.ptr {llvm.noundef}
+// ROCDL-SAME: i64 {llvm.noundef}
+// NVVM-SAME: !llvm.ptr {llvm.noundef}
+// NVVM-SAME: i64 {llvm.noundef}
``````````
</details>
https://github.com/llvm/llvm-project/pull/76755
More information about the Mlir-commits
mailing list