1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
|
//===- ParallelLoopTiling.cpp - Tiles scf.parallel ---------------===//
//
// 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 loop tiling on parallel loops.
//
//===----------------------------------------------------------------------===//
#include "PassDetail.h"
#include "mlir/Dialect/Affine/IR/AffineOps.h"
#include "mlir/Dialect/SCF/Passes.h"
#include "mlir/Dialect/SCF/SCF.h"
#include "mlir/Dialect/SCF/Transforms.h"
#include "mlir/Dialect/SCF/Utils.h"
#include "mlir/Dialect/StandardOps/IR/Ops.h"
using namespace mlir;
using namespace mlir::scf;
/// Tile a parallel loop of the form
/// scf.parallel (%i0, %i1) = (%arg0, %arg1) to (%arg2, %arg3)
/// step (%arg4, %arg5)
///
/// into
/// scf.parallel (%i0, %i1) = (%arg0, %arg1) to (%arg2, %arg3)
/// step (%arg4*tileSize[0],
/// %arg5*tileSize[1])
/// scf.parallel (%j0, %j1) = (0, 0) to (min(%arg4*tileSize[0], %arg2-%i0)
/// min(%arg5*tileSize[1], %arg3-%i1))
/// step (%arg4, %arg5)
///
/// where the uses of %i0 and %i1 in the loop body are replaced by
/// %i0 + j0 and %i1 + %j1.
//
/// The old loop is replaced with the new one.
std::pair<ParallelOp, ParallelOp>
mlir::scf::tileParallelLoop(ParallelOp op, ArrayRef<int64_t> tileSizes) {
OpBuilder b(op);
auto zero = b.create<ConstantIndexOp>(op.getLoc(), 0);
SmallVector<Value, 2> tileSizeConstants;
tileSizeConstants.reserve(op.upperBound().size());
for (size_t i = 0, end = op.upperBound().size(); i != end; ++i) {
if (i < tileSizes.size())
tileSizeConstants.push_back(
b.create<ConstantIndexOp>(op.getLoc(), tileSizes[i]));
else
// Just pick 1 for the remaining dimensions.
tileSizeConstants.push_back(b.create<ConstantIndexOp>(op.getLoc(), 1));
}
// Create the outer loop with adjusted steps.
SmallVector<Value, 2> newSteps;
newSteps.reserve(op.step().size());
for (auto step : llvm::zip(op.step(), tileSizeConstants)) {
newSteps.push_back(
b.create<MulIOp>(op.getLoc(), std::get<0>(step), std::get<1>(step)));
}
auto outerLoop = b.create<ParallelOp>(op.getLoc(), op.lowerBound(),
op.upperBound(), newSteps);
b.setInsertionPointToStart(outerLoop.getBody());
// Compute min(size, dim - offset) to avoid out-of-bounds accesses.
// FIXME: Instead of using min, we want to replicate the tail. This would give
// the inner loop constant bounds for easy vectorization.
auto minMap = AffineMap::get(
/*dimCount=*/3, /*symbolCount=*/0,
{getAffineDimExpr(/*position=*/0, b.getContext()),
getAffineDimExpr(/*position=*/1, b.getContext()) -
getAffineDimExpr(/*position=*/2, b.getContext())},
b.getContext());
// Create the inner loop with adjusted bounds.
SmallVector<Value, 2> newBounds;
newBounds.reserve(op.upperBound().size());
for (auto dim : llvm::zip(outerLoop.lowerBound(), outerLoop.upperBound(),
outerLoop.step(), outerLoop.getInductionVars(),
op.step(), tileSizeConstants)) {
Value lowerBound, upperBound, newStep, iv, step, tileSizeConstant;
std::tie(lowerBound, upperBound, newStep, iv, step, tileSizeConstant) = dim;
// Collect the statically known loop bounds
auto lowerBoundConstant =
dyn_cast_or_null<ConstantIndexOp>(lowerBound.getDefiningOp());
auto upperBoundConstant =
dyn_cast_or_null<ConstantIndexOp>(upperBound.getDefiningOp());
auto stepConstant = dyn_cast_or_null<ConstantIndexOp>(step.getDefiningOp());
auto tileSize =
cast<ConstantIndexOp>(tileSizeConstant.getDefiningOp()).getValue();
// If the loop bounds and the loop step are constant and if the number of
// loop iterations is an integer multiple of the tile size, we use a static
// bound for the inner loop.
if (lowerBoundConstant && upperBoundConstant && stepConstant) {
auto numIterations = llvm::divideCeil(upperBoundConstant.getValue() -
lowerBoundConstant.getValue(),
stepConstant.getValue());
if (numIterations % tileSize == 0) {
newBounds.push_back(newStep);
continue;
}
}
// Otherwise, we dynamically compute the bound for
// each iteration of the outer loop.
newBounds.push_back(
b.create<AffineMinOp>(op.getLoc(), b.getIndexType(), minMap,
ValueRange{newStep, upperBound, iv}));
}
auto innerLoop = b.create<ParallelOp>(
op.getLoc(), SmallVector<Value, 2>(newBounds.size(), zero), newBounds,
op.step());
// Steal the body of the old parallel loop and erase it.
innerLoop.region().takeBody(op.region());
// Insert computation for new index vectors and replace uses.
b.setInsertionPointToStart(innerLoop.getBody());
for (auto ivs :
llvm::zip(innerLoop.getInductionVars(), outerLoop.getInductionVars())) {
Value inner_index = std::get<0>(ivs);
AddIOp newIndex =
b.create<AddIOp>(op.getLoc(), std::get<0>(ivs), std::get<1>(ivs));
inner_index.replaceAllUsesExcept(newIndex, newIndex);
}
op.erase();
return std::make_pair(outerLoop, innerLoop);
}
namespace {
struct ParallelLoopTiling
: public SCFParallelLoopTilingBase<ParallelLoopTiling> {
ParallelLoopTiling() = default;
explicit ParallelLoopTiling(ArrayRef<int64_t> tileSizes) {
this->tileSizes = tileSizes;
}
void runOnFunction() override {
SmallVector<ParallelOp, 2> innermostPloops;
getInnermostParallelLoops(getFunction().getOperation(), innermostPloops);
for (ParallelOp ploop : innermostPloops) {
// FIXME: Add reduction support.
if (ploop.getNumReductions() == 0)
tileParallelLoop(ploop, tileSizes);
}
}
};
} // namespace
std::unique_ptr<Pass>
mlir::createParallelLoopTilingPass(ArrayRef<int64_t> tileSizes) {
return std::make_unique<ParallelLoopTiling>(tileSizes);
}
|
