6ca1a09f03
This is a purely mechanical change that introduces an enum attribute in the GPU dialect to represent the various memref memory spaces as opposed to the hard-coded integer attributes that are currently used. The following steps were taken to make the transition across the codebase: 1. Introduce a pass "gpu-lower-memory-space-attributes": The pass updates all memref types that have a memory space attribute that is a `gpu::AddressSpaceAttr`. These attributes are changed to `IntegerAttr`'s using a mapping that is given by the caller. This pass is based on the "map-memref-spirv-storage-class" pass and the common functions can probably be refactored into a set of utilities under the MemRef dialect. 2. Update the verifiers of GPU/NVGPU dialect operations. If a verifier currently checks the address space of an operand using e.g.`getWorkspaceAddressSpace`, then it can continue to do so. However, the checks are changed to only fail if the memory space is either missing or a wrong value of type `gpu::AddressSpaceAttr`. Otherwise, it just assumes the address space is correct because it was specifically lowered to something other than a `gpu::AddressSpaceAttr`. 3. Update existing gpu-to-llvm conversion infrastructure. In the existing gpu-to-X passes, we add a full conversion equivalent to `gpu-lower-memory-space-attributes` just before doing the conversion to the LLVMDialect. This is done because currently both the gpu-to-llvm passes (rocdl,nvvm) run gpu-to-gpu rewrites within the pass, which introduce `AddressSpaceAttr` memory space annotations. Therefore, I inserted the memory space conversion between the gpu-to-gpu rewrites and the LLVM conversion. For more context see the below discourse discussion: https://discourse.llvm.org/t/gpu-workgroup-shared-memory-address-space-is-hard-coded/ Reviewed By: ftynse Differential Revision: https://reviews.llvm.org/D140644
118 lines
4.5 KiB
C++
118 lines
4.5 KiB
C++
//===- GPUOpsLowering.h - GPU FuncOp / ReturnOp lowering -------*- C++ -*--===//
|
|
//
|
|
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
|
|
// See https://llvm.org/LICENSE.txt for license information.
|
|
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
#ifndef MLIR_CONVERSION_GPUCOMMON_GPUOPSLOWERING_H_
|
|
#define MLIR_CONVERSION_GPUCOMMON_GPUOPSLOWERING_H_
|
|
|
|
#include "mlir/Conversion/LLVMCommon/Pattern.h"
|
|
#include "mlir/Dialect/GPU/IR/GPUDialect.h"
|
|
#include "mlir/Dialect/LLVMIR/LLVMDialect.h"
|
|
|
|
namespace mlir {
|
|
|
|
struct GPUFuncOpLowering : ConvertOpToLLVMPattern<gpu::GPUFuncOp> {
|
|
GPUFuncOpLowering(LLVMTypeConverter &converter, unsigned allocaAddrSpace,
|
|
unsigned workgroupAddrSpace, StringAttr kernelAttributeName)
|
|
: ConvertOpToLLVMPattern<gpu::GPUFuncOp>(converter),
|
|
allocaAddrSpace(allocaAddrSpace),
|
|
workgroupAddrSpace(workgroupAddrSpace),
|
|
kernelAttributeName(kernelAttributeName) {}
|
|
|
|
LogicalResult
|
|
matchAndRewrite(gpu::GPUFuncOp gpuFuncOp, OpAdaptor adaptor,
|
|
ConversionPatternRewriter &rewriter) const override;
|
|
|
|
private:
|
|
/// The address space to use for `alloca`s in private memory.
|
|
unsigned allocaAddrSpace;
|
|
/// The address space to use declaring workgroup memory.
|
|
unsigned workgroupAddrSpace;
|
|
|
|
/// The attribute name to use instead of `gpu.kernel`.
|
|
StringAttr kernelAttributeName;
|
|
};
|
|
|
|
/// The lowering of gpu.printf to a call to HIP hostcalls
|
|
///
|
|
/// Simplifies llvm/lib/Transforms/Utils/AMDGPUEmitPrintf.cpp, as we don't have
|
|
/// to deal with %s (even if there were first-class strings in MLIR, they're not
|
|
/// legal input to gpu.printf) or non-constant format strings
|
|
struct GPUPrintfOpToHIPLowering : public ConvertOpToLLVMPattern<gpu::PrintfOp> {
|
|
using ConvertOpToLLVMPattern<gpu::PrintfOp>::ConvertOpToLLVMPattern;
|
|
|
|
LogicalResult
|
|
matchAndRewrite(gpu::PrintfOp gpuPrintfOp, gpu::PrintfOpAdaptor adaptor,
|
|
ConversionPatternRewriter &rewriter) const override;
|
|
};
|
|
|
|
/// The lowering of gpu.printf to a call to an external printf() function
|
|
///
|
|
/// This pass will add a declaration of printf() to the GPUModule if needed
|
|
/// and seperate out the format strings into global constants. For some
|
|
/// runtimes, such as OpenCL on AMD, this is sufficient setup, as the compiler
|
|
/// will lower printf calls to appropriate device-side code
|
|
struct GPUPrintfOpToLLVMCallLowering
|
|
: public ConvertOpToLLVMPattern<gpu::PrintfOp> {
|
|
GPUPrintfOpToLLVMCallLowering(LLVMTypeConverter &converter,
|
|
int addressSpace = 0)
|
|
: ConvertOpToLLVMPattern<gpu::PrintfOp>(converter),
|
|
addressSpace(addressSpace) {}
|
|
|
|
LogicalResult
|
|
matchAndRewrite(gpu::PrintfOp gpuPrintfOp, gpu::PrintfOpAdaptor adaptor,
|
|
ConversionPatternRewriter &rewriter) const override;
|
|
|
|
private:
|
|
int addressSpace;
|
|
};
|
|
|
|
/// Lowering of gpu.printf to a vprintf standard library.
|
|
struct GPUPrintfOpToVPrintfLowering
|
|
: public ConvertOpToLLVMPattern<gpu::PrintfOp> {
|
|
using ConvertOpToLLVMPattern<gpu::PrintfOp>::ConvertOpToLLVMPattern;
|
|
|
|
LogicalResult
|
|
matchAndRewrite(gpu::PrintfOp gpuPrintfOp, gpu::PrintfOpAdaptor adaptor,
|
|
ConversionPatternRewriter &rewriter) const override;
|
|
};
|
|
|
|
struct GPUReturnOpLowering : public ConvertOpToLLVMPattern<gpu::ReturnOp> {
|
|
using ConvertOpToLLVMPattern<gpu::ReturnOp>::ConvertOpToLLVMPattern;
|
|
|
|
LogicalResult
|
|
matchAndRewrite(gpu::ReturnOp op, OpAdaptor adaptor,
|
|
ConversionPatternRewriter &rewriter) const override {
|
|
rewriter.replaceOpWithNewOp<LLVM::ReturnOp>(op, adaptor.getOperands());
|
|
return success();
|
|
}
|
|
};
|
|
|
|
namespace impl {
|
|
/// Unrolls op if it's operating on vectors.
|
|
LogicalResult scalarizeVectorOp(Operation *op, ValueRange operands,
|
|
ConversionPatternRewriter &rewriter,
|
|
LLVMTypeConverter &converter);
|
|
} // namespace impl
|
|
|
|
/// Rewriting that unrolls SourceOp to scalars if it's operating on vectors.
|
|
template <typename SourceOp>
|
|
struct ScalarizeVectorOpLowering : public ConvertOpToLLVMPattern<SourceOp> {
|
|
public:
|
|
using ConvertOpToLLVMPattern<SourceOp>::ConvertOpToLLVMPattern;
|
|
|
|
LogicalResult
|
|
matchAndRewrite(SourceOp op, typename SourceOp::Adaptor adaptor,
|
|
ConversionPatternRewriter &rewriter) const override {
|
|
return impl::scalarizeVectorOp(op, adaptor.getOperands(), rewriter,
|
|
*this->getTypeConverter());
|
|
}
|
|
};
|
|
|
|
} // namespace mlir
|
|
|
|
#endif // MLIR_CONVERSION_GPUCOMMON_GPUOPSLOWERING_H_
|