e2310704d8
Create the memref dialect and move dialect-specific ops from std dialect to this dialect. Moved ops: AllocOp -> MemRef_AllocOp AllocaOp -> MemRef_AllocaOp AssumeAlignmentOp -> MemRef_AssumeAlignmentOp DeallocOp -> MemRef_DeallocOp DimOp -> MemRef_DimOp MemRefCastOp -> MemRef_CastOp MemRefReinterpretCastOp -> MemRef_ReinterpretCastOp GetGlobalMemRefOp -> MemRef_GetGlobalOp GlobalMemRefOp -> MemRef_GlobalOp LoadOp -> MemRef_LoadOp PrefetchOp -> MemRef_PrefetchOp ReshapeOp -> MemRef_ReshapeOp StoreOp -> MemRef_StoreOp SubViewOp -> MemRef_SubViewOp TransposeOp -> MemRef_TransposeOp TensorLoadOp -> MemRef_TensorLoadOp TensorStoreOp -> MemRef_TensorStoreOp TensorToMemRefOp -> MemRef_BufferCastOp ViewOp -> MemRef_ViewOp The roadmap to split the memref dialect from std is discussed here: https://llvm.discourse.group/t/rfc-split-the-memref-dialect-from-std/2667 Differential Revision: https://reviews.llvm.org/D98041
56 lines
2.1 KiB
C++
56 lines
2.1 KiB
C++
//===- TestGPUMemoryPromotionPass.cpp - Test pass for GPU promotion -------===//
|
|
//
|
|
// 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
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// This file implements the pass testing the utilities for moving data across
|
|
// different levels of the GPU memory hierarchy.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#include "mlir/Dialect/Affine/IR/AffineOps.h"
|
|
#include "mlir/Dialect/GPU/GPUDialect.h"
|
|
#include "mlir/Dialect/GPU/MemoryPromotion.h"
|
|
#include "mlir/Dialect/MemRef/IR/MemRef.h"
|
|
#include "mlir/Dialect/SCF/SCF.h"
|
|
#include "mlir/Dialect/SPIRV/IR/SPIRVDialect.h"
|
|
#include "mlir/Dialect/StandardOps/IR/Ops.h"
|
|
#include "mlir/IR/Attributes.h"
|
|
#include "mlir/Pass/Pass.h"
|
|
|
|
using namespace mlir;
|
|
|
|
namespace {
|
|
/// Simple pass for testing the promotion to workgroup memory in GPU functions.
|
|
/// Promotes all arguments with "gpu.test_promote_workgroup" attribute. This
|
|
/// does not check whether the promotion is legal (e.g., amount of memory used)
|
|
/// or beneficial (e.g., makes previously uncoalesced loads coalesced).
|
|
class TestGpuMemoryPromotionPass
|
|
: public PassWrapper<TestGpuMemoryPromotionPass,
|
|
OperationPass<gpu::GPUFuncOp>> {
|
|
void getDependentDialects(DialectRegistry ®istry) const override {
|
|
registry.insert<AffineDialect, memref::MemRefDialect, StandardOpsDialect,
|
|
scf::SCFDialect>();
|
|
}
|
|
|
|
void runOnOperation() override {
|
|
gpu::GPUFuncOp op = getOperation();
|
|
for (unsigned i = 0, e = op.getNumArguments(); i < e; ++i) {
|
|
if (op.getArgAttrOfType<UnitAttr>(i, "gpu.test_promote_workgroup"))
|
|
promoteToWorkgroupMemory(op, i);
|
|
}
|
|
}
|
|
};
|
|
} // end namespace
|
|
|
|
namespace mlir {
|
|
void registerTestGpuMemoryPromotionPass() {
|
|
PassRegistration<TestGpuMemoryPromotionPass>(
|
|
"test-gpu-memory-promotion",
|
|
"Promotes the annotated arguments of gpu.func to workgroup memory.");
|
|
}
|
|
} // namespace mlir
|