maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/mlir/test/Transforms/single-parallel-loop-collap...

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

34 lines
1.4 KiB
MLIR
Raw Normal View History

Add a flag on the context to protect against creation of operations in unregistered dialects Differential Revision: https://reviews.llvm.org/D76903
2020-03-30 06:35:38 +08:00
// RUN: mlir-opt -allow-unregistered-dialect %s -pass-pipeline='func(parallel-loop-collapsing{collapsed-indices-0=0,1}, canonicalize)' | FileCheck %s
[MLIR] Add parallel loop collapsing. This allows conversion of a ParallelLoop from N induction variables to some nuber of induction variables less than N. The first intended use of this is for the GPUDialect to convert ParallelLoops to iterate over 3 dimensions so they can be launched as GPU Kernels. To implement this: - Normalize each iteration space of the ParallelLoop - Use the same induction variable in a new ParallelLoop for multiple original iterations. - Split the new induction variable back into the original set of values inside the body of the ParallelLoop. Subscribers: mgorny, mehdi_amini, rriddle, jpienaar, burmako, shauheen, antiagainst, nicolasvasilache, arpith-jacob, mgester, lucyrfox, aartbik, liufengdb, Joonsoo, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D76363
2020-03-11 21:38:10 +08:00
func @collapse_to_single() {
%c0 = constant 3 : index
%c1 = constant 7 : index
%c2 = constant 11 : index
%c3 = constant 29 : index
%c4 = constant 3 : index
%c5 = constant 4 : index
[mlir] Change dialect namespace loop->scf All ops of the SCF dialect now use the `scf.` prefix instead of `loop.`. This is a part of dialect renaming. Differential Revision: https://reviews.llvm.org/D79844
2020-05-13 18:12:30 +08:00
scf.parallel (%i0, %i1) = (%c0, %c1) to (%c2, %c3) step (%c4, %c5) {
[MLIR] Add parallel loop collapsing. This allows conversion of a ParallelLoop from N induction variables to some nuber of induction variables less than N. The first intended use of this is for the GPUDialect to convert ParallelLoops to iterate over 3 dimensions so they can be launched as GPU Kernels. To implement this: - Normalize each iteration space of the ParallelLoop - Use the same induction variable in a new ParallelLoop for multiple original iterations. - Split the new induction variable back into the original set of values inside the body of the ParallelLoop. Subscribers: mgorny, mehdi_amini, rriddle, jpienaar, burmako, shauheen, antiagainst, nicolasvasilache, arpith-jacob, mgester, lucyrfox, aartbik, liufengdb, Joonsoo, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D76363
2020-03-11 21:38:10 +08:00
%result = "magic.op"(%i0, %i1): (index, index) -> index
}
return
}
[MLIR] Rename collapsePLoops -> collapseParallelLoops Summary: Additionally, NFC code cleanups were done. This is to address additional comments on https://reviews.llvm.org/D76363 Differential Revision: https://reviews.llvm.org/D77052
2020-03-30 19:26:46 +08:00
// CHECK-LABEL: func @collapse_to_single() {
// CHECK: [[C7:%.*]] = constant 7 : index
// CHECK: [[C4:%.*]] = constant 4 : index
// CHECK: [[C18:%.*]] = constant 18 : index
// CHECK: [[C3:%.*]] = constant 3 : index
// CHECK: [[C0:%.*]] = constant 0 : index
// CHECK: [[C1:%.*]] = constant 1 : index
[mlir] Change dialect namespace loop->scf All ops of the SCF dialect now use the `scf.` prefix instead of `loop.`. This is a part of dialect renaming. Differential Revision: https://reviews.llvm.org/D79844
2020-05-13 18:12:30 +08:00
// CHECK: scf.parallel ([[NEW_I:%.*]]) = ([[C0]]) to ([[C18]]) step ([[C1]]) {
[MLIR] Rename collapsePLoops -> collapseParallelLoops Summary: Additionally, NFC code cleanups were done. This is to address additional comments on https://reviews.llvm.org/D76363 Differential Revision: https://reviews.llvm.org/D77052
2020-03-30 19:26:46 +08:00
// CHECK: [[I0_COUNT:%.*]] = remi_signed [[NEW_I]], [[C3]] : index
[mlir] fix off-by-one error in collapseParallelLoops Summary: The patch fixes an off by one error in the method collapseParallelLoops. It ensures the same normalized bound is used for the computation of the division and the remainder. Reviewers: herhut Reviewed By: herhut Subscribers: mehdi_amini, rriddle, jpienaar, shauheen, antiagainst, nicolasvasilache, arpith-jacob, mgester, lucyrfox, aartbik, liufengdb, stephenneuendorffer, Joonsoo, grosul1, Kayjukh, jurahul, msifontes Tags: #mlir Differential Revision: https://reviews.llvm.org/D82634
2020-06-26 19:46:37 +08:00
// CHECK: [[I1_COUNT:%.*]] = divi_signed [[NEW_I]], [[C3]] : index
// CHECK: [[V0:%.*]] = muli [[I1_COUNT]], [[C4]] : index
// CHECK: [[I1:%.*]] = addi [[V0]], [[C7]] : index
// CHECK: [[V1:%.*]] = muli [[I0_COUNT]], [[C3]] : index
// CHECK: [[I0:%.*]] = addi [[V1]], [[C3]] : index
[MLIR] Rename collapsePLoops -> collapseParallelLoops Summary: Additionally, NFC code cleanups were done. This is to address additional comments on https://reviews.llvm.org/D76363 Differential Revision: https://reviews.llvm.org/D77052
2020-03-30 19:26:46 +08:00
// CHECK: "magic.op"([[I0]], [[I1]]) : (index, index) -> index
[mlir] Change dialect namespace loop->scf All ops of the SCF dialect now use the `scf.` prefix instead of `loop.`. This is a part of dialect renaming. Differential Revision: https://reviews.llvm.org/D79844
2020-05-13 18:12:30 +08:00
// CHECK: scf.yield
[MLIR] Rename collapsePLoops -> collapseParallelLoops Summary: Additionally, NFC code cleanups were done. This is to address additional comments on https://reviews.llvm.org/D76363 Differential Revision: https://reviews.llvm.org/D77052
2020-03-30 19:26:46 +08:00
// CHECK-NEXT: }
// CHECK-NEXT: return