This is an archive of the discontinued LLVM Phabricator instance.

Differential D126732

[mlir][sparse] Enable the test for operator expm1.
ClosedPublic

Authored by bixia on May 31 2022, 4:19 PM.

Details

Reviewers
aartbik
Commits
rG548f0841cd42: [mlir][sparse] Enable the test for operator expm1.

Diff Detail

Event Timeline

bixia created this revision.May 31 2022, 4:19 PM
Herald added a reviewer: aartbik. · View Herald TranscriptMay 31 2022, 4:19 PM
Herald added a project: Restricted Project. · View Herald Transcript
Herald added subscribers: bzcheeseman, sdasgup3, wenzhicui and 21 others. · View Herald Transcript
bixia requested review of this revision.May 31 2022, 4:19 PM
Herald added a project: Restricted Project. · View Herald TranscriptMay 31 2022, 4:19 PM
Herald added subscribers: stephenneuendorffer, nicolasvasilache. · View Herald Transcript
Harbormaster completed remote builds in B167147: Diff 433222.May 31 2022, 4:37 PM
aartbik accepted this revision.Jun 1 2022, 10:53 AM
This revision is now accepted and ready to land.Jun 1 2022, 10:53 AM
Closed by commit rG548f0841cd42: [mlir][sparse] Enable the test for operator expm1. (authored by bixia). · Explain WhyJun 1 2022, 11:18 AM
This revision was automatically updated to reflect the committed changes.
bixia added a commit: rG548f0841cd42: [mlir][sparse] Enable the test for operator expm1..

Revision Contents

PathSize
mlir/
test/
Integration/
Dialect/
SparseTensor/
CPU/
18 lines

Diff 433467

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_complex_ops.mlir

Show First 20 Lines • Show All 93 Lines • ▼ Show 20 Lines func.func @clog1p_expm1(%arga: tensor<?xcomplex<f64>, #SparseVector>)
%c0 = arith.constant 0 : index %c0 = arith.constant 0 : index
%d = tensor.dim %arga, %c0 : tensor<?xcomplex<f64>, #SparseVector> %d = tensor.dim %arga, %c0 : tensor<?xcomplex<f64>, #SparseVector>
%xv = sparse_tensor.init [%d] : tensor<?xcomplex<f64>, #SparseVector> %xv = sparse_tensor.init [%d] : tensor<?xcomplex<f64>, #SparseVector>
%0 = linalg.generic #trait_op1 %0 = linalg.generic #trait_op1
ins(%arga: tensor<?xcomplex<f64>, #SparseVector>) ins(%arga: tensor<?xcomplex<f64>, #SparseVector>)
outs(%xv: tensor<?xcomplex<f64>, #SparseVector>) { outs(%xv: tensor<?xcomplex<f64>, #SparseVector>) {
^bb(%a: complex<f64>, %x: complex<f64>): ^bb(%a: complex<f64>, %x: complex<f64>):
%1 = complex.log1p %a : complex<f64> %1 = complex.log1p %a : complex<f64>
// TODO(bixia): Enable this line after adding complex.expm1 to %2 = complex.expm1 %1 : complex<f64>
// complex to standard lowering. linalg.yield %2 : complex<f64>
// %2 = complex.expm1 %1 : complex<f64>
linalg.yield %1 : complex<f64>
} -> tensor<?xcomplex<f64>, #SparseVector> } -> tensor<?xcomplex<f64>, #SparseVector>
return %0 : tensor<?xcomplex<f64>, #SparseVector> return %0 : tensor<?xcomplex<f64>, #SparseVector>
} }
func.func @cdiv(%arga: tensor<?xcomplex<f64>, #SparseVector>) func.func @cdiv(%arga: tensor<?xcomplex<f64>, #SparseVector>)
-> tensor<?xcomplex<f64>, #SparseVector> { -> tensor<?xcomplex<f64>, #SparseVector> {
%c0 = arith.constant 0 : index %c0 = arith.constant 0 : index
%d = tensor.dim %arga, %c0 : tensor<?xcomplex<f64>, #SparseVector> %d = tensor.dim %arga, %c0 : tensor<?xcomplex<f64>, #SparseVector>
▲ Show 20 Lines • Show All 106 Lines • ▼ Show 20 Lines func.func @entry() {
call @dumpc(%2, %d3) : (tensor<?xcomplex<f64>, #SparseVector>, index) -> () call @dumpc(%2, %d3) : (tensor<?xcomplex<f64>, #SparseVector>, index) -> ()
// CHECK-NEXT: 0.761594 // CHECK-NEXT: 0.761594
// CHECK-NEXT: 0 // CHECK-NEXT: 0
// CHECK-NEXT: -0.964028 // CHECK-NEXT: -0.964028
// CHECK-NEXT: 0 // CHECK-NEXT: 0
// CHECK-NEXT: 0.995055 // CHECK-NEXT: 0.995055
// CHECK-NEXT: 0 // CHECK-NEXT: 0
call @dumpc(%3, %d3) : (tensor<?xcomplex<f64>, #SparseVector>, index) -> () call @dumpc(%3, %d3) : (tensor<?xcomplex<f64>, #SparseVector>, index) -> ()
// CHECK-NEXT: 1.52361 // CHECK-NEXT: -5.13
// CHECK-NEXT: 2.69061 // CHECK-NEXT: 2
// CHECK-NEXT: 1.73287 // CHECK-NEXT: 3
// CHECK-NEXT: 0.785398 // CHECK-NEXT: 4
// CHECK-NEXT: 2.13833 // CHECK-NEXT: 5
// CHECK-NEXT: 0.785398 // CHECK-NEXT: 6
call @dumpc(%4, %d3) : (tensor<?xcomplex<f64>, #SparseVector>, index) -> () call @dumpc(%4, %d3) : (tensor<?xcomplex<f64>, #SparseVector>, index) -> ()
// CHECK-NEXT: -2.565 // CHECK-NEXT: -2.565
// CHECK-NEXT: 1 // CHECK-NEXT: 1
// CHECK-NEXT: 1.5 // CHECK-NEXT: 1.5
// CHECK-NEXT: 2 // CHECK-NEXT: 2
// CHECK-NEXT: 2.5 // CHECK-NEXT: 2.5
// CHECK-NEXT: 3 // CHECK-NEXT: 3
call @dumpc(%5, %d3) : (tensor<?xcomplex<f64>, #SparseVector>, index) -> () call @dumpc(%5, %d3) : (tensor<?xcomplex<f64>, #SparseVector>, index) -> ()
Show All 16 Lines