[Mlir-commits] [mlir] [mlir][amdgpu] Shared memory access optimization pass (PR #75627)

Mehdi Amini llvmlistbot at llvm.org
Tue Dec 19 03:00:48 PST 2023


================
@@ -0,0 +1,48 @@
+//===- Utils.cpp - Transform utilities ------------------------------------===//
+//
+// 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
+//
+//===----------------------------------------------------------------------===//
+
+#include "mlir/Dialect/AMDGPU/Transforms/Utils.h"
+
+#include "mlir/Dialect/AMDGPU/IR/AMDGPUDialect.h"
+#include "mlir/Dialect/MemRef/IR/MemRef.h"
+#include "mlir/Dialect/Vector/IR/VectorOps.h"
+
+using namespace mlir;
+using namespace mlir::amdgpu;
+
+Operation::operand_range amdgpu::getIndices(Operation *op) {
+  if (auto loadOp = dyn_cast<memref::LoadOp>(op))
+    return loadOp.getIndices();
+  if (auto storeOp = dyn_cast<memref::StoreOp>(op))
+    return storeOp.getIndices();
+  if (auto vectorReadOp = dyn_cast<vector::LoadOp>(op))
+    return vectorReadOp.getIndices();
+  if (auto vectorStoreOp = dyn_cast<vector::StoreOp>(op))
+    return vectorStoreOp.getIndices();
+  if (auto transferReadOp = dyn_cast<vector::TransferReadOp>(op))
+    return transferReadOp.getIndices();
+  if (auto transferWriteOp = dyn_cast<vector::TransferWriteOp>(op))
+    return transferWriteOp.getIndices();
+  llvm_unreachable("unsupported op type");
----------------
joker-eph wrote:

It's hard to figure how we're guaranteeing that this unreachable can't be hit right now, can you elaborate on this?

https://github.com/llvm/llvm-project/pull/75627


More information about the Mlir-commits mailing list