d84d418e2a
Add constant fold for tosa.reciprocal, which can be applied if the input is a dense constant tensor. The reciprocal is computed for every element and the result is a tensor with the same dimensions as the input tensor. As the input tensor might require a lot of memory and the folding might double the required memory, a heuristic decides when to actually apply the folding. Currently, the operation will be replaced only if the input constant is a splat (i.e. requires little memory) or has in single user (similar to the already existing fold for constant transposes). This keeps the additionally required space low. Differential Revision: https://reviews.llvm.org/D150578
67 lines
2.1 KiB
C++
67 lines
2.1 KiB
C++
//===- TosaLayerwiseConstantFoldPass.cpp ----------------------------------===//
|
|
//
|
|
// 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 constant folding transformations on TOSA operations
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#include "mlir/Dialect/Tosa/Transforms/Passes.h"
|
|
|
|
#include "mlir/Dialect/Func/IR/FuncOps.h"
|
|
#include "mlir/Dialect/Tosa/IR/TosaOps.h"
|
|
#include "mlir/Pass/Pass.h"
|
|
#include "mlir/Transforms/GreedyPatternRewriteDriver.h"
|
|
|
|
namespace mlir {
|
|
namespace tosa {
|
|
#define GEN_PASS_DEF_TOSALAYERWISECONSTANTFOLDPASS
|
|
#include "mlir/Dialect/Tosa/Transforms/Passes.h.inc"
|
|
} // namespace tosa
|
|
} // namespace mlir
|
|
|
|
using namespace mlir;
|
|
using namespace mlir::tosa;
|
|
|
|
namespace {
|
|
|
|
template <typename... Args>
|
|
void addOpsCanonicalizations(MLIRContext *ctx, RewritePatternSet &patterns) {
|
|
(Args::getCanonicalizationPatterns(patterns, ctx), ...);
|
|
}
|
|
|
|
void populateTosaOpsCanonicalizationPatterns(MLIRContext *ctx,
|
|
RewritePatternSet &patterns) {
|
|
addOpsCanonicalizations<
|
|
#define GET_OP_LIST
|
|
#include "mlir/Dialect/Tosa/IR/TosaOps.cpp.inc"
|
|
>(ctx, patterns);
|
|
}
|
|
|
|
struct TosaLayerwiseConstantFoldPass
|
|
: public tosa::impl::TosaLayerwiseConstantFoldPassBase<
|
|
TosaLayerwiseConstantFoldPass> {
|
|
void runOnOperation() override {
|
|
auto *ctx = &getContext();
|
|
RewritePatternSet patterns(ctx);
|
|
auto func = getOperation();
|
|
|
|
mlir::tosa::populateTosaFoldConstantReciprocalPatterns(ctx, patterns);
|
|
mlir::tosa::populateTosaFoldConstantTransposePatterns(ctx, patterns);
|
|
populateTosaOpsCanonicalizationPatterns(ctx, patterns);
|
|
|
|
if (applyPatternsAndFoldGreedily(func, std::move(patterns)).failed())
|
|
signalPassFailure();
|
|
}
|
|
};
|
|
|
|
} // namespace
|
|
|
|
std::unique_ptr<Pass> mlir::tosa::createTosaLayerwiseConstantFoldPass() {
|
|
return std::make_unique<TosaLayerwiseConstantFoldPass>();
|
|
}
|