maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/mlir/test/Dialect/Async/async-parallel-for-compute-...

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

68 lines
2.5 KiB
MLIR
Raw Normal View History

[mlir] AsyncParallelFor: sink constants into the parallel compute function With complex recursive structure of async dispatch function LLVM can't always propagate constants to the parallel_compute_fn and it often prevents optimizations like loop unrolling and vectorization. We help LLVM by pushing known constants into the parallel_compute_fn explicitly. Reviewed By: bkramer Differential Revision: https://reviews.llvm.org/D115263
2021-12-08 10:45:31 +08:00
// RUN: mlir-opt %s -split-input-file \
[mlir] Async: clone constants into async.execute functions and parallel compute functions Reviewed By: mehdi_amini Differential Revision: https://reviews.llvm.org/D107007
2021-08-02 23:40:17 +08:00
// RUN: -async-parallel-for=async-dispatch=true \
// RUN: | FileCheck %s
[mlir] AsyncParallelFor: sink constants into the parallel compute function With complex recursive structure of async dispatch function LLVM can't always propagate constants to the parallel_compute_fn and it often prevents optimizations like loop unrolling and vectorization. We help LLVM by pushing known constants into the parallel_compute_fn explicitly. Reviewed By: bkramer Differential Revision: https://reviews.llvm.org/D115263
2021-12-08 10:45:31 +08:00
// RUN: mlir-opt %s -split-input-file \
[mlir] Async: clone constants into async.execute functions and parallel compute functions Reviewed By: mehdi_amini Differential Revision: https://reviews.llvm.org/D107007
2021-08-02 23:40:17 +08:00
// RUN: -async-parallel-for=async-dispatch=false \
// RUN: -canonicalize -inline -symbol-dce \
// RUN: | FileCheck %s
// Check that constants defined outside of the `scf.parallel` body will be
// sunk into the parallel compute function to avoid blowing up the number
// of parallel compute function arguments.
// CHECK-LABEL: func @clone_constant(
func @clone_constant(%arg0: memref<?xf32>, %lb: index, %ub: index, %st: index) {
[MLIR] Replace std ops with arith dialect ops Precursor: https://reviews.llvm.org/D110200 Removed redundant ops from the standard dialect that were moved to the `arith` or `math` dialects. Renamed all instances of operations in the codebase and in tests. Reviewed By: rriddle, jpienaar Differential Revision: https://reviews.llvm.org/D110797
2021-10-13 07:14:57 +08:00
%one = arith.constant 1.0 : f32
[mlir] Async: clone constants into async.execute functions and parallel compute functions Reviewed By: mehdi_amini Differential Revision: https://reviews.llvm.org/D107007
2021-08-02 23:40:17 +08:00
scf.parallel (%i) = (%lb) to (%ub) step (%st) {
memref.store %one, %arg0[%i] : memref<?xf32>
}
return
}
// CHECK-LABEL: func private @parallel_compute_fn(
// CHECK-SAME: %[[BLOCK_INDEX:arg[0-9]+]]: index,
// CHECK-SAME: %[[BLOCK_SIZE:arg[0-9]+]]: index,
// CHECK-SAME: %[[TRIP_COUNT:arg[0-9]+]]: index,
// CHECK-SAME: %[[LB:arg[0-9]+]]: index,
// CHECK-SAME: %[[UB:arg[0-9]+]]: index,
// CHECK-SAME: %[[STEP:arg[0-9]+]]: index,
// CHECK-SAME: %[[MEMREF:arg[0-9]+]]: memref<?xf32>
// CHECK-SAME: ) {
[MLIR] Replace std ops with arith dialect ops Precursor: https://reviews.llvm.org/D110200 Removed redundant ops from the standard dialect that were moved to the `arith` or `math` dialects. Renamed all instances of operations in the codebase and in tests. Reviewed By: rriddle, jpienaar Differential Revision: https://reviews.llvm.org/D110797
2021-10-13 07:14:57 +08:00
// CHECK: %[[CST:.*]] = arith.constant 1.0{{.*}} : f32
[mlir] Async: clone constants into async.execute functions and parallel compute functions Reviewed By: mehdi_amini Differential Revision: https://reviews.llvm.org/D107007
2021-08-02 23:40:17 +08:00
// CHECK: scf.for
// CHECK: memref.store %[[CST]], %[[MEMREF]]
[mlir] AsyncParallelFor: sink constants into the parallel compute function With complex recursive structure of async dispatch function LLVM can't always propagate constants to the parallel_compute_fn and it often prevents optimizations like loop unrolling and vectorization. We help LLVM by pushing known constants into the parallel_compute_fn explicitly. Reviewed By: bkramer Differential Revision: https://reviews.llvm.org/D115263
2021-12-08 10:45:31 +08:00
// -----
// Check that constant loop bound sunk into the parallel compute function.
// CHECK-LABEL: func @sink_constant_step(
func @sink_constant_step(%arg0: memref<?xf32>, %lb: index, %ub: index) {
%one = arith.constant 1.0 : f32
%st = arith.constant 123 : index
scf.parallel (%i) = (%lb) to (%ub) step (%st) {
memref.store %one, %arg0[%i] : memref<?xf32>
}
return
}
// CHECK-LABEL: func private @parallel_compute_fn(
// CHECK-SAME: %[[BLOCK_INDEX:arg[0-9]+]]: index,
// CHECK-SAME: %[[BLOCK_SIZE:arg[0-9]+]]: index,
// CHECK-SAME: %[[TRIP_COUNT:arg[0-9]+]]: index,
// CHECK-SAME: %[[LB:arg[0-9]+]]: index,
// CHECK-SAME: %[[UB:arg[0-9]+]]: index,
// CHECK-SAME: %[[STEP:arg[0-9]+]]: index,
// CHECK-SAME: %[[MEMREF:arg[0-9]+]]: memref<?xf32>
// CHECK-SAME: ) {
// CHECK: %[[CSTEP:.*]] = arith.constant 123 : index
// CHECK-NOT: %[[STEP]]
// CHECK: scf.for %[[I:arg[0-9]+]]
// CHECK: %[[TMP:.*]] = arith.muli %[[I]], %[[CSTEP]]
// CHECK: %[[IDX:.*]] = arith.addi %[[LB]], %[[TMP]]
// CHECK: memref.store