64812a56c7
unroll/unroll-and-jam more powerful; add additional affine expr builder methods
- use previously added analysis/simplification to infer multiple of unroll
factor trip counts, making loop unroll/unroll-and-jam more general.
- for loop unroll, support bounds that are single result affine map's with the
same set of operands. For unknown loop bounds, loop unroll will now work as
long as trip count can be determined to be a multiple of unroll factor.
- extend getConstantTripCount to deal with single result affine map's with the
same operands. move it to mlir/Analysis/LoopAnalysis.cpp
- add additional builder utility methods for affine expr arithmetic
(difference, mod/floordiv/ceildiv w.r.t postitive constant). simplify code to
use the utility methods.
- move affine analysis routines to AffineAnalysis.cpp/.h from
AffineStructures.cpp/.h.
- Rename LoopUnrollJam to LoopUnrollAndJam to match class name.
- add an additional simplification for simplifyFloorDiv, simplifyCeilDiv
- Rename AffineMap::getNumOperands() getNumInputs: an affine map by itself does
not have operands. Operands are passed to it through affine_apply, from loop
bounds/if condition's, etc., operands are stored in the latter.
This should be sufficiently powerful for now as far as unroll/unroll-and-jam go for TPU
code generation, and can move to other analyses/transformations.
Loop nests like these are now unrolled without any cleanup loop being generated.
for %i = 1 to 100 {
// unroll factor 4: no cleanup loop will be generated.
for %j = (d0) -> (d0) (%i) to (d0) -> (5*d0 + 3) (%i) {
%x = "foo"(%j) : (affineint) -> i32
}
}
for %i = 1 to 100 {
// unroll factor 4: no cleanup loop will be generated.
for %j = (d0) -> (d0) (%i) to (d0) -> (d0 - d mod 4 - 1) (%i) {
%y = "foo"(%j) : (affineint) -> i32
}
}
for %i = 1 to 100 {
for %j = (d0) -> (d0) (%i) to (d0) -> (d0 + 128) (%i) {
%x = "foo"() : () -> i32
}
}
TODO(bondhugula): extend this to LoopUnrollAndJam as well in the next CL (with minor
changes).
PiperOrigin-RevId: 212661212
67 lines
2.5 KiB
C++
67 lines
2.5 KiB
C++
//===- LoopUtils.cpp - Misc loop utilities for simplification //-----------===//
|
|
//
|
|
// Copyright 2019 The MLIR Authors.
|
|
//
|
|
// Licensed under the Apache License, Version 2.0 (the "License");
|
|
// you may not use this file except in compliance with the License.
|
|
// You may obtain a copy of the License at
|
|
//
|
|
// http://www.apache.org/licenses/LICENSE-2.0
|
|
//
|
|
// Unless required by applicable law or agreed to in writing, software
|
|
// distributed under the License is distributed on an "AS IS" BASIS,
|
|
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
// See the License for the specific language governing permissions and
|
|
// limitations under the License.
|
|
// =============================================================================
|
|
//
|
|
// This file implements miscellaneous loop simplification routines.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#include "mlir/Transforms/Passes.h"
|
|
|
|
#include "mlir/Analysis/LoopAnalysis.h"
|
|
#include "mlir/IR/Builders.h"
|
|
#include "mlir/IR/StandardOps.h"
|
|
#include "mlir/IR/Statements.h"
|
|
#include "mlir/IR/StmtVisitor.h"
|
|
|
|
/// Promotes the loop body of a forStmt to its containing block if the forStmt
|
|
/// was known to have a single iteration. Returns false otherwise.
|
|
// TODO(bondhugula): extend this for arbitrary affine bounds.
|
|
bool mlir::promoteIfSingleIteration(ForStmt *forStmt) {
|
|
Optional<uint64_t> tripCount = getConstantTripCount(*forStmt);
|
|
if (!tripCount.hasValue() || !forStmt->hasConstantLowerBound())
|
|
return false;
|
|
|
|
if (tripCount.getValue() != 1)
|
|
return false;
|
|
|
|
// Replaces all IV uses to its single iteration value.
|
|
auto *mlFunc = forStmt->findFunction();
|
|
MLFuncBuilder topBuilder(&mlFunc->front());
|
|
auto constOp = topBuilder.create<ConstantAffineIntOp>(
|
|
forStmt->getLoc(), forStmt->getConstantLowerBound());
|
|
forStmt->replaceAllUsesWith(constOp->getResult());
|
|
// Move the statements to the containing block.
|
|
auto *block = forStmt->getBlock();
|
|
block->getStatements().splice(StmtBlock::iterator(forStmt),
|
|
forStmt->getStatements());
|
|
forStmt->eraseFromBlock();
|
|
return true;
|
|
}
|
|
|
|
/// Promotes all single iteration for stmt's in the MLFunction, i.e., moves
|
|
/// their body into the containing StmtBlock.
|
|
void mlir::promoteSingleIterationLoops(MLFunction *f) {
|
|
// Gathers all innermost loops through a post order pruned walk.
|
|
class LoopBodyPromoter : public StmtWalker<LoopBodyPromoter> {
|
|
public:
|
|
void visitForStmt(ForStmt *forStmt) { promoteIfSingleIteration(forStmt); }
|
|
};
|
|
|
|
LoopBodyPromoter fsw;
|
|
fsw.walkPostOrder(f);
|
|
}
|