[mlir][sparse] migrate integration tests to sparse_tensor.print #83357
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This is first step (of many) cleaning up our tests to use the new and exciting sparse_tensor.print operation instead of lengthy extraction + print ops.
aartbik
requested review from
PeimingLiu,
yinying-lisa-li and
matthias-springer
as code owners
|
@llvm/pr-subscribers-mlir @llvm/pr-subscribers-mlir-sparse Author: Aart Bik (aartbik) ChangesThis is first step (of many) cleaning up our tests to use the new and exciting sparse_tensor.print operation instead of lengthy extraction + print ops. Full diff: https://github.com/llvm/llvm-project/pull/83357.diff 6 Files Affected:
diff --git a/mlir/test/Integration/Dialect/SparseTensor/CPU/block.mlir b/mlir/test/Integration/Dialect/SparseTensor/CPU/block.mlir
index 6468c4b45d2479..1184d407541b6f 100644
--- a/mlir/test/Integration/Dialect/SparseTensor/CPU/block.mlir
+++ b/mlir/test/Integration/Dialect/SparseTensor/CPU/block.mlir
@@ -10,7 +10,7 @@
// DEFINE: %{compile} = mlir-opt %s --sparsifier="%{sparsifier_opts}"
// DEFINE: %{compile_sve} = mlir-opt %s --sparsifier="%{sparsifier_opts_sve}"
// DEFINE: %{run_libs} = -shared-libs=%mlir_c_runner_utils,%mlir_runner_utils
-// DEFINE: %{run_opts} = -e entry -entry-point-result=void
+// DEFINE: %{run_opts} = -e main -entry-point-result=void
// DEFINE: %{run} = mlir-cpu-runner %{run_opts} %{run_libs}
// DEFINE: %{run_sve} = %mcr_aarch64_cmd --march=aarch64 --mattr="+sve" %{run_opts} %{run_libs}
//
@@ -82,38 +82,39 @@ module {
return %0 : tensor<?x?xf64, #BSR>
}
- func.func @entry() {
+ func.func @main() {
%c0 = arith.constant 0 : index
%f0 = arith.constant 0.0 : f64
%fileName = call @getTensorFilename(%c0) : (index) -> (!Filename)
%A = sparse_tensor.new %fileName : !Filename to tensor<?x?xf64, #BSR>
- // CHECK: ( 0, 2, 3 )
- // CHECK-NEXT: ( 0, 2, 1 )
- // CHECK-NEXT: ( 1, 2, 0, 3, 4, 0, 0, 5, 6, 7, 8, 0 )
- %pos = sparse_tensor.positions %A {level = 1 : index } : tensor<?x?xf64, #BSR> to memref<?xindex>
- %vecp = vector.transfer_read %pos[%c0], %c0 : memref<?xindex>, vector<3xindex>
- vector.print %vecp : vector<3xindex>
- %crd = sparse_tensor.coordinates %A {level = 1 : index } : tensor<?x?xf64, #BSR> to memref<?xindex>
- %vecc = vector.transfer_read %crd[%c0], %c0 : memref<?xindex>, vector<3xindex>
- vector.print %vecc : vector<3xindex>
- %val = sparse_tensor.values %A : tensor<?x?xf64, #BSR> to memref<?xf64>
- %vecv = vector.transfer_read %val[%c0], %f0 : memref<?xf64>, vector<12xf64>
- vector.print %vecv : vector<12xf64>
+ // CHECK: ---- Sparse Tensor ----
+ // CHECK-NEXT: nse = 12
+ // CHECK-NEXT: pos[1] : ( 0, 2, 3,
+ // CHECK-NEXT: crd[1] : ( 0, 2, 1,
+ // CHECK-NEXT: values : ( 1, 2, 0, 3, 4, 0, 0, 5, 6, 7, 8, 0,
+ // CHECK-NEXT: ----
+ sparse_tensor.print %A : tensor<?x?xf64, #BSR>
- // CHECK-NEXT: ( 1, 2, 0, 3, 4, 0, 0, 5, 6, 7, 8, 0 )
+ // CHECK-NEXT: ---- Sparse Tensor ----
+ // CHECK-NEXT: nse = 12
+ // CHECK-NEXT: pos[1] : ( 0, 2, 3,
+ // CHECK-NEXT: crd[1] : ( 0, 2, 1
+ // CHECK-NEXT: values : ( 1, 2, 0, 3, 4, 0, 0, 5, 6, 7, 8, 0,
+ // CHECK-NEXT: ----
%t1 = sparse_tensor.reinterpret_map %A : tensor<?x?xf64, #BSR>
to tensor<?x?x2x2xf64, #DSDD>
- %vdsdd = sparse_tensor.values %t1 : tensor<?x?x2x2xf64, #DSDD> to memref<?xf64>
- %vecdsdd = vector.transfer_read %vdsdd[%c0], %f0 : memref<?xf64>, vector<12xf64>
- vector.print %vecdsdd : vector<12xf64>
+ sparse_tensor.print %t1 : tensor<?x?x2x2xf64, #DSDD>
- // CHECK-NEXT: ( 3, 6, 0, 9, 12, 0, 0, 15, 18, 21, 24, 0 )
+ // CHECK-NEXT: ---- Sparse Tensor ----
+ // CHECK-NEXT: nse = 12
+ // CHECK-NEXT: pos[1] : ( 0, 2, 3,
+ // CHECK-NEXT: crd[1] : ( 0, 2, 1,
+ // CHECK-NEXT: values : ( 3, 6, 0, 9, 12, 0, 0, 15, 18, 21, 24, 0,
+ // CHECK-NEXT: ----
%As = call @scale(%A) : (tensor<?x?xf64, #BSR>) -> (tensor<?x?xf64, #BSR>)
- %vals = sparse_tensor.values %As : tensor<?x?xf64, #BSR> to memref<?xf64>
- %vecs = vector.transfer_read %vals[%c0], %f0 : memref<?xf64>, vector<12xf64>
- vector.print %vecs : vector<12xf64>
+ sparse_tensor.print %As : tensor<?x?xf64, #BSR>
// Release the resources.
bufferization.dealloc_tensor %A: tensor<?x?xf64, #BSR>
diff --git a/mlir/test/Integration/Dialect/SparseTensor/CPU/block_majors.mlir b/mlir/test/Integration/Dialect/SparseTensor/CPU/block_majors.mlir
index cb06f099dd3703..f8e83b5019679f 100755
--- a/mlir/test/Integration/Dialect/SparseTensor/CPU/block_majors.mlir
+++ b/mlir/test/Integration/Dialect/SparseTensor/CPU/block_majors.mlir
@@ -102,9 +102,15 @@
//
module {
- // CHECK: ( 0, 1, 2 )
- // CHECK-NEXT: ( 0, 2 )
- // CHECK-NEXT: ( 1, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 3, 4, 5, 0, 0, 0, 0, 0, 0, 0, 0, 6, 7 )
+
+ //
+ // CHECK: ---- Sparse Tensor ----
+ // CHECK-NEXT: nse = 24
+ // CHECK-NEXT: pos[1] : ( 0, 1, 2,
+ // CHECK-NEXT: crd[1] : ( 0, 2,
+ // CHECK-NEXT: values : ( 1, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 3, 4, 5, 0, 0, 0, 0, 0, 0, 0, 0, 6, 7,
+ // CHECK-NEXT: ----
+ //
func.func @foo1() {
// Build.
%c0 = arith.constant 0 : index
@@ -115,23 +121,20 @@ module {
> : tensor<6x16xf64>
%s1 = sparse_tensor.convert %m : tensor<6x16xf64> to tensor<?x?xf64, #BSR_row_rowmajor>
// Test.
- %pos1 = sparse_tensor.positions %s1 {level = 1 : index } : tensor<?x?xf64, #BSR_row_rowmajor> to memref<?xindex>
- %vecp1 = vector.transfer_read %pos1[%c0], %c0 : memref<?xindex>, vector<3xindex>
- vector.print %vecp1 : vector<3xindex>
- %crd1 = sparse_tensor.coordinates %s1 {level = 1 : index } : tensor<?x?xf64, #BSR_row_rowmajor> to memref<?xindex>
- %vecc1 = vector.transfer_read %crd1[%c0], %c0 : memref<?xindex>, vector<2xindex>
- vector.print %vecc1 : vector<2xindex>
- %val1 = sparse_tensor.values %s1 : tensor<?x?xf64, #BSR_row_rowmajor> to memref<?xf64>
- %vecv1 = vector.transfer_read %val1[%c0], %f0 : memref<?xf64>, vector<24xf64>
- vector.print %vecv1 : vector<24xf64>
+ sparse_tensor.print %s1 : tensor<?x?xf64, #BSR_row_rowmajor>
// Release.
bufferization.dealloc_tensor %s1: tensor<?x?xf64, #BSR_row_rowmajor>
return
}
- // CHECK-NEXT: ( 0, 1, 2 )
- // CHECK-NEXT: ( 0, 2 )
- // CHECK-NEXT: ( 1, 0, 0, 2, 0, 0, 0, 0, 0, 0, 0, 3, 4, 0, 0, 5, 0, 0, 0, 0, 6, 0, 0, 7 )
+ //
+ // CHECK-NEXT: ---- Sparse Tensor ----
+ // CHECK-NEXT: nse = 24
+ // CHECK-NEXT: pos[1] : ( 0, 1, 2,
+ // CHECK-NEXT: crd[1] : ( 0, 2,
+ // CHECK-NEXT: values : ( 1, 0, 0, 2, 0, 0, 0, 0, 0, 0, 0, 3, 4, 0, 0, 5, 0, 0, 0, 0, 6, 0, 0, 7,
+ // CHECK-NEXT: ----
+ //
func.func @foo2() {
// Build.
%c0 = arith.constant 0 : index
@@ -142,23 +145,20 @@ module {
> : tensor<6x16xf64>
%s2 = sparse_tensor.convert %m : tensor<6x16xf64> to tensor<?x?xf64, #BSR_row_colmajor>
// Test.
- %pos2 = sparse_tensor.positions %s2 {level = 1 : index } : tensor<?x?xf64, #BSR_row_colmajor> to memref<?xindex>
- %vecp2 = vector.transfer_read %pos2[%c0], %c0 : memref<?xindex>, vector<3xindex>
- vector.print %vecp2 : vector<3xindex>
- %crd2 = sparse_tensor.coordinates %s2 {level = 1 : index } : tensor<?x?xf64, #BSR_row_colmajor> to memref<?xindex>
- %vecc2 = vector.transfer_read %crd2[%c0], %c0 : memref<?xindex>, vector<2xindex>
- vector.print %vecc2 : vector<2xindex>
- %val2 = sparse_tensor.values %s2 : tensor<?x?xf64, #BSR_row_colmajor> to memref<?xf64>
- %vecv2 = vector.transfer_read %val2[%c0], %f0 : memref<?xf64>, vector<24xf64>
- vector.print %vecv2 : vector<24xf64>
+ sparse_tensor.print %s2 : tensor<?x?xf64, #BSR_row_colmajor>
// Release.
bufferization.dealloc_tensor %s2: tensor<?x?xf64, #BSR_row_colmajor>
return
}
- // CHECK-NEXT: ( 0, 1, 1, 2, 2 )
- // CHECK-NEXT: ( 0, 1 )
- // CHECK-NEXT: ( 1, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 3, 4, 5, 0, 0, 0, 0, 0, 0, 0, 0, 6, 7 )
+ //
+ // CHECK-NEXT: ---- Sparse Tensor ----
+ // CHECK-NEXT: nse = 24
+ // CHECK-NEXT: pos[1] : ( 0, 1, 1, 2, 2,
+ // CHECK-NEXT: crd[1] : ( 0, 1,
+ // CHECK-NEXT: values : ( 1, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, 3, 4, 5, 0, 0, 0, 0, 0, 0, 0, 0, 6, 7,
+ // CHECK-NEXT: ----
+ //
func.func @foo3() {
// Build.
%c0 = arith.constant 0 : index
@@ -169,23 +169,20 @@ module {
> : tensor<6x16xf64>
%s3 = sparse_tensor.convert %m : tensor<6x16xf64> to tensor<?x?xf64, #BSR_col_rowmajor>
// Test.
- %pos3 = sparse_tensor.positions %s3 {level = 1 : index } : tensor<?x?xf64, #BSR_col_rowmajor> to memref<?xindex>
- %vecp3 = vector.transfer_read %pos3[%c0], %c0 : memref<?xindex>, vector<5xindex>
- vector.print %vecp3 : vector<5xindex>
- %crd3 = sparse_tensor.coordinates %s3 {level = 1 : index } : tensor<?x?xf64, #BSR_col_rowmajor> to memref<?xindex>
- %vecc3 = vector.transfer_read %crd3[%c0], %c0 : memref<?xindex>, vector<2xindex>
- vector.print %vecc3 : vector<2xindex>
- %val3 = sparse_tensor.values %s3 : tensor<?x?xf64, #BSR_col_rowmajor> to memref<?xf64>
- %vecv3 = vector.transfer_read %val3[%c0], %f0 : memref<?xf64>, vector<24xf64>
- vector.print %vecv3 : vector<24xf64>
+ sparse_tensor.print %s3 : tensor<?x?xf64, #BSR_col_rowmajor>
// Release.
bufferization.dealloc_tensor %s3: tensor<?x?xf64, #BSR_col_rowmajor>
return
}
- // CHECK-NEXT: ( 0, 1, 1, 2, 2 )
- // CHECK-NEXT: ( 0, 1 )
- // CHECK-NEXT: ( 1, 0, 0, 2, 0, 0, 0, 0, 0, 0, 0, 3, 4, 0, 0, 5, 0, 0, 0, 0, 6, 0, 0, 7 )
+ //
+ // CHECK-NEXT: ---- Sparse Tensor ----
+ // CHECK-NEXT: nse = 24
+ // CHECK-NEXT: pos[1] : ( 0, 1, 1, 2, 2,
+ // CHECK-NEXT: crd[1] : ( 0, 1,
+ // CHECK-NEXT: values : ( 1, 0, 0, 2, 0, 0, 0, 0, 0, 0, 0, 3, 4, 0, 0, 5, 0, 0, 0, 0, 6, 0, 0, 7,
+ // CHECK-NEXT: ----
+ //
func.func @foo4() {
// Build.
%c0 = arith.constant 0 : index
@@ -196,15 +193,7 @@ module {
> : tensor<6x16xf64>
%s4 = sparse_tensor.convert %m : tensor<6x16xf64> to tensor<?x?xf64, #BSR_col_colmajor>
// Test.
- %pos4 = sparse_tensor.positions %s4 {level = 1 : index } : tensor<?x?xf64, #BSR_col_colmajor> to memref<?xindex>
- %vecp4 = vector.transfer_read %pos4[%c0], %c0 : memref<?xindex>, vector<5xindex>
- vector.print %vecp4 : vector<5xindex>
- %crd4 = sparse_tensor.coordinates %s4 {level = 1 : index } : tensor<?x?xf64, #BSR_col_colmajor> to memref<?xindex>
- %vecc4 = vector.transfer_read %crd4[%c0], %c0 : memref<?xindex>, vector<2xindex>
- vector.print %vecc4 : vector<2xindex>
- %val4 = sparse_tensor.values %s4 : tensor<?x?xf64, #BSR_col_colmajor> to memref<?xf64>
- %vecv4 = vector.transfer_read %val4[%c0], %f0 : memref<?xf64>, vector<24xf64>
- vector.print %vecv4 : vector<24xf64>
+ sparse_tensor.print %s4 : tensor<?x?xf64, #BSR_col_colmajor>
// Release.
bufferization.dealloc_tensor %s4: tensor<?x?xf64, #BSR_col_colmajor>
return
diff --git a/mlir/test/Integration/Dialect/SparseTensor/CPU/dense_output.mlir b/mlir/test/Integration/Dialect/SparseTensor/CPU/dense_output.mlir
index 5f6524a4b7af9e..c6ee0ce0705021 100644
--- a/mlir/test/Integration/Dialect/SparseTensor/CPU/dense_output.mlir
+++ b/mlir/test/Integration/Dialect/SparseTensor/CPU/dense_output.mlir
@@ -10,7 +10,7 @@
// DEFINE: %{compile} = mlir-opt %s --sparsifier="%{sparsifier_opts}"
// DEFINE: %{compile_sve} = mlir-opt %s --sparsifier="%{sparsifier_opts_sve}"
// DEFINE: %{run_libs} = -shared-libs=%mlir_c_runner_utils,%mlir_runner_utils
-// DEFINE: %{run_opts} = -e entry -entry-point-result=void
+// DEFINE: %{run_opts} = -e main -entry-point-result=void
// DEFINE: %{run} = mlir-cpu-runner %{run_opts} %{run_libs}
// DEFINE: %{run_sve} = %mcr_aarch64_cmd --march=aarch64 --mattr="+sve" %{run_opts} %{run_libs}
//
@@ -83,12 +83,11 @@ module {
}
func.func private @getTensorFilename(index) -> (!Filename)
- func.func private @printMemref1dF64(%ptr : memref<?xf64>) attributes { llvm.emit_c_interface }
//
// Main driver that reads matrix from file and calls the kernel.
//
- func.func @entry() {
+ func.func @main() {
%d0 = arith.constant 0.0 : f64
%c0 = arith.constant 0 : index
%c1 = arith.constant 1 : index
@@ -104,14 +103,13 @@ module {
//
// Print the linearized 5x5 result for verification.
- // CHECK: 25
- // CHECK: [2, 0, 0, 2.8, 0, 0, 4, 0, 0, 5, 0, 0, 6, 0, 0, 8.2, 0, 0, 8, 0, 0, 10.4, 0, 0, 10
//
- %n = sparse_tensor.number_of_entries %0 : tensor<?x?xf64, #DenseMatrix>
- vector.print %n : index
- %m = sparse_tensor.values %0
- : tensor<?x?xf64, #DenseMatrix> to memref<?xf64>
- call @printMemref1dF64(%m) : (memref<?xf64>) -> ()
+ // CHECK: ---- Sparse Tensor ----
+ // CHECK-NEXT: nse = 25
+ // CHECK-NEXT: values : ( 2, 0, 0, 2.8, 0, 0, 4, 0, 0, 5, 0, 0, 6, 0, 0, 8.2, 0, 0, 8, 0, 0, 10.4, 0, 0, 10,
+ // CHECK-NEXT: ----
+ //
+ sparse_tensor.print %0 : tensor<?x?xf64, #DenseMatrix>
// Release the resources.
bufferization.dealloc_tensor %a : tensor<?x?xf64, #SparseMatrix>
diff --git a/mlir/test/Integration/Dialect/SparseTensor/CPU/dense_output_bf16.mlir b/mlir/test/Integration/Dialect/SparseTensor/CPU/dense_output_bf16.mlir
index 81cd2d81cbbc32..0b34ff581016da 100644
--- a/mlir/test/Integration/Dialect/SparseTensor/CPU/dense_output_bf16.mlir
+++ b/mlir/test/Integration/Dialect/SparseTensor/CPU/dense_output_bf16.mlir
@@ -10,7 +10,7 @@
// DEFINE: %{compile} = mlir-opt %s --sparsifier="%{sparsifier_opts}"
// DEFINE: %{compile_sve} = mlir-opt %s --sparsifier="%{sparsifier_opts_sve}"
// DEFINE: %{run_libs} = -shared-libs=%mlir_c_runner_utils,%mlir_runner_utils
-// DEFINE: %{run_opts} = -e entry -entry-point-result=void
+// DEFINE: %{run_opts} = -e main -entry-point-result=void
// DEFINE: %{run} = mlir-cpu-runner %{run_opts} %{run_libs}
// DEFINE: %{run_sve} = %mcr_aarch64_cmd --march=aarch64 --mattr="+sve" %{run_opts} %{run_libs}
//
@@ -67,20 +67,8 @@ module {
return %0 : tensor<?xbf16, #DenseVector>
}
- // Dumps a dense vector of type bf16.
- func.func @dump_vec(%arg0: tensor<?xbf16, #DenseVector>) {
- // Dump the values array to verify only sparse contents are stored.
- %c0 = arith.constant 0 : index
- %d0 = arith.constant -1.0 : bf16
- %0 = sparse_tensor.values %arg0 : tensor<?xbf16, #DenseVector> to memref<?xbf16>
- %1 = vector.transfer_read %0[%c0], %d0: memref<?xbf16>, vector<32xbf16>
- %f1 = arith.extf %1: vector<32xbf16> to vector<32xf32>
- vector.print %f1 : vector<32xf32>
- return
- }
-
// Driver method to call and verify the kernel.
- func.func @entry() {
+ func.func @main() {
%c0 = arith.constant 0 : index
// Setup sparse vectors.
@@ -103,8 +91,12 @@ module {
//
// Verify the result.
//
- // CHECK: ( 1, 11, 0, 2, 13, 0, 0, 0, 0, 0, 14, 3, 0, 0, 0, 0, 15, 4, 16, 0, 5, 6, 0, 0, 0, 0, 0, 0, 7, 8, 0, 9 )
- call @dump_vec(%0) : (tensor<?xbf16, #DenseVector>) -> ()
+ // CHECK: ---- Sparse Tensor ----
+ // CHECK-NEXT: nse = 32
+ // CHECK-NEXT: values : ( 1, 11, 0, 2, 13, 0, 0, 0, 0, 0, 14, 3, 0, 0, 0, 0, 15, 4, 16, 0, 5, 6, 0, 0, 0, 0, 0, 0, 7, 8, 0, 9,
+ // CHECK-NEXT: ----
+ //
+ sparse_tensor.print %0 : tensor<?xbf16, #DenseVector>
// Release the resources.
bufferization.dealloc_tensor %sv1 : tensor<?xbf16, #SparseVector>
diff --git a/mlir/test/Integration/Dialect/SparseTensor/CPU/dense_output_f16.mlir b/mlir/test/Integration/Dialect/SparseTensor/CPU/dense_output_f16.mlir
index b320afdb885842..495682169c2909 100644
--- a/mlir/test/Integration/Dialect/SparseTensor/CPU/dense_output_f16.mlir
+++ b/mlir/test/Integration/Dialect/SparseTensor/CPU/dense_output_f16.mlir
@@ -10,7 +10,7 @@
// DEFINE: %{compile} = mlir-opt %s --sparsifier="%{sparsifier_opts}"
// DEFINE: %{compile_sve} = mlir-opt %s --sparsifier="%{sparsifier_opts_sve}"
// DEFINE: %{run_libs} = -shared-libs=%mlir_c_runner_utils,%mlir_runner_utils
-// DEFINE: %{run_opts} = -e entry -entry-point-result=void
+// DEFINE: %{run_opts} = -e main -entry-point-result=void
// DEFINE: %{run} = mlir-cpu-runner %{run_opts} %{run_libs}
// DEFINE: %{run_sve} = %mcr_aarch64_cmd --march=aarch64 --mattr="+sve" %{run_opts} %{run_libs}
//
@@ -68,20 +68,8 @@ module {
return %0 : tensor<?xf16, #DenseVector>
}
- // Dumps a dense vector of type f16.
- func.func @dump_vec(%arg0: tensor<?xf16, #DenseVector>) {
- // Dump the values array to verify only sparse contents are stored.
- %c0 = arith.constant 0 : index
- %d0 = arith.constant -1.0 : f16
- %0 = sparse_tensor.values %arg0 : tensor<?xf16, #DenseVector> to memref<?xf16>
- %1 = vector.transfer_read %0[%c0], %d0: memref<?xf16>, vector<32xf16>
- %f1 = arith.extf %1: vector<32xf16> to vector<32xf32>
- vector.print %f1 : vector<32xf32>
- return
- }
-
// Driver method to call and verify the kernel.
- func.func @entry() {
+ func.func @main() {
%c0 = arith.constant 0 : index
// Setup sparse vectors.
@@ -104,8 +92,12 @@ module {
//
// Verify the result.
//
- // CHECK: ( 1, 11, 0, 2, 13, 0, 0, 0, 0, 0, 14, 3, 0, 0, 0, 0, 15, 4, 16, 0, 5, 6, 0, 0, 0, 0, 0, 0, 7, 8, 0, 9 )
- call @dump_vec(%0) : (tensor<?xf16, #DenseVector>) -> ()
+ // CHECK: ---- Sparse Tensor ----
+ // CHECK-NEXT: nse = 32
+ // CHECK-NEXT: values : ( 1, 11, 0, 2, 13, 0, 0, 0, 0, 0, 14, 3, 0, 0, 0, 0, 15, 4, 16, 0, 5, 6, 0, 0, 0, 0, 0, 0, 7, 8, 0, 9,
+ // CHECK-NEXT: ----
+ //
+ sparse_tensor.print %0 : tensor<?xf16, #DenseVector>
// Release the resources.
bufferization.dealloc_tensor %sv1 : tensor<?xf16, #SparseVector>
diff --git a/mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_re_im.mlir b/mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_re_im.mlir
index b44ffc30c3b1ee..1860fc1c7027a1 100644
--- a/mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_re_im.mlir
+++ b/mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_re_im.mlir
@@ -10,7 +10,7 @@
// DEFINE: %{compile} = mlir-opt %s --sparsifier="%{sparsifier_opts}"
// DEFINE: %{compile_sve} = mlir-opt %s --sparsifier="%{sparsifier_opts_sve}"
// DEFINE: %{run_libs} = -shared-libs=%mlir_c_runner_utils,%mlir_runner_utils
-// DEFINE: %{run_opts} = -e entry -entry-point-result=void
+// DEFINE: %{run_opts} = -e main -entry-point-result=void
// DEFINE: %{run} = mlir-cpu-runner %{run_opts} %{run_libs}
// DEFINE: %{run_sve} = %mcr_aarch64_cmd --march=aarch64 --mattr="+sve" %{run_opts} %{run_libs}
//
@@ -72,22 +72,7 @@ module {
return %0 : tensor<?xf32, #SparseVector>
}
- func.func @dump(%arg0: tensor<?xf32, #SparseVector>) {
- %c0 = arith.constant 0 : index
- %d0 = arith.constant -1.0 : f32
- %n = sparse_tensor.number_of_entries %arg0 : tensor<?xf32, #SparseVector>
- vector.print %n : index
- %values = sparse_tensor.values %arg0 : tensor<?xf32, #SparseVector> to memref<?xf32>
- %0 = vector.transfer_read %values[%c0], %d0: memref<?xf32>, vector<3xf32>
- vector.print %0 : vector<3xf32>
- %coordinates = sparse_tensor.coordinates %arg0 { level = 0 : index } : tensor<?xf32, #SparseVector> to memref<?xindex>
- %1 = vector.transfer_read %coordinates[%c0], %c0: memref<?xindex>, vector<3xindex>
- vector.print %1 : vector<3xindex>
- return
- }
-
- // Driver method to call and verify functions cim and cre.
- func.func @entry() {
+ func.func @main() {
// Setup sparse vectors.
%v1 = arith.constant sparse<
[ [0], [20], [31] ],
@@ -104,20 +89,27 @@ module {
//
// Verify the results.
//
- // CHECK: 3
- // CHECK-NEXT: ( 5.13, 3, 5 )
- // CHECK-NEXT: ( 0, 20, 31 )
- // CHECK-NEXT: 3
- // CHECK-NEXT: ( 2, 4, 6 )
- // CHECK-NEXT: ( 0, 20, 31 )
+ // CHECK: ---- Sparse Tensor ----
+ // CHECK-NEXT: nse = 3
+ // CHECK-NEXT: pos[0] : ( 0, 3,
+ // CHECK-NEXT: crd[0] : ( 0, 20, 31,
+ // CHECK-NEXT: values : ( 5.13, 3, 5,
+ // CHECK-NEXT: ----
+ //
+ // CHECK-NEXT: ---- Sparse Tensor ----
+ // CHECK-NEXT: nse = 3
+ // CHECK-NEXT: pos[0] : ( 0, 3,
+ // CHECK-NEXT: crd[0] : ( 0, 20, 31,
+ // CHECK-NEXT: values : ( 2, 4, 6,
+ // CHECK-NEXT: ----
//
- call @dump(%0) : (tensor<?xf32, #SparseVector>) -> ()
- call @dump(%1) : (tensor<?xf32, #SparseVector>) -> ()
+ sparse_tensor.print %0 : tensor<?xf32, #SparseVector>
+ sparse_tensor.print %1 : tensor<?xf32, #SparseVector>
// Release the resources.
bufferization.dealloc_tensor %sv1 : tensor<?xcomplex<f32>, #SparseVector>
- bufferization.dealloc_tensor %0 : tensor<?xf32, #SparseVector>
- bufferization.dealloc_tensor %1 : tensor<?xf32, #SparseVector>
+ bufferization.dealloc_tensor %0 : tensor<?xf32, #SparseVector>
+ bufferization.dealloc_tensor %1 : tensor<?xf32, #SparseVector>
return
}
}
|
PeimingLiu
approved these changes
Feb 29, 2024
yinying-lisa-li
added a commit
that referenced
this pull request
Feb 29, 2024
Continuous efforts following #83357.
yinying-lisa-li
added a commit
that referenced
this pull request
Mar 1, 2024
aartbik
added a commit
to aartbik/llvm-project
that referenced
this pull request
Mar 1, 2024
Continuous efforts llvm#83357 for our sparse CUDA tests
aartbik
added a commit
that referenced
this pull request
Mar 4, 2024
Continuous efforts #83357 for our sparse CUDA tests
aartbik
added a commit
to aartbik/llvm-project
that referenced
this pull request
Mar 4, 2024
Continuing the efforts started in llvm#83357
aartbik
added a commit
to aartbik/llvm-project
that referenced
this pull request
Mar 4, 2024
Continuing the efforts started in llvm#83357
aartbik
added a commit
that referenced
this pull request
Mar 4, 2024
Continuing the efforts started in #83357
aartbik
added a commit
to aartbik/llvm-project
that referenced
this pull request
Mar 5, 2024
Continuing the efforts started in llvm#83357
aartbik
added a commit
to aartbik/llvm-project
that referenced
this pull request
Mar 5, 2024
Continuing the efforts started in llvm#83357
aartbik
added a commit
that referenced
this pull request
Mar 5, 2024
Continuing the efforts started in #83357
mylai-mtk
pushed a commit
to mylai-mtk/llvm-project
that referenced
this pull request
Jul 12, 2024
…#83357) This is first step (of many) cleaning up our tests to use the new and exciting sparse_tensor.print operation instead of lengthy extraction + print ops.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This is first step (of many) cleaning up our tests to use the new and exciting sparse_tensor.print operation instead of lengthy extraction + print ops.