This is an archive of the discontinued LLVM Phabricator instance.

Differential D158443

[mlir][sparse] more complicated test for dual sparse convolution kernel.
ClosedPublic

Authored by Peiming on Aug 21 2023, 11:05 AM.

Details

Reviewers
aartbik
nicolasvasilache
anlunx
yinying-lisa-li
Commits
rG6ca0b2729870: [mlir][sparse] more complicated test for dual sparse convolution kernel.

Diff Detail

Event Timeline

Peiming created this revision.Aug 21 2023, 11:05 AM
Herald added a reviewer: aartbik. · View Herald TranscriptAug 21 2023, 11:05 AM
Herald added a project: Restricted Project. · View Herald Transcript
Herald added subscribers: K-Wu, bviyer, hanchung and 24 others. · View Herald Transcript
Peiming requested review of this revision.Aug 21 2023, 11:05 AM
Herald added a reviewer: nicolasvasilache. · View Herald TranscriptAug 21 2023, 11:05 AM
Herald added a project: Restricted Project. · View Herald Transcript
Herald added subscribers: stephenneuendorffer, nicolasvasilache. · View Herald Transcript
Peiming added reviewers: anlunx, yinying-lisa-li.Aug 21 2023, 11:06 AM
anlunx accepted this revision.Aug 21 2023, 11:19 AM
This revision is now accepted and ready to land.Aug 21 2023, 11:19 AM
Harbormaster completed remote builds in B253890: Diff 552083.Aug 21 2023, 11:43 AM
Closed by commit rG6ca0b2729870: [mlir][sparse] more complicated test for dual sparse convolution kernel. (authored by Peiming). · Explain WhyAug 21 2023, 11:48 AM
This revision was automatically updated to reflect the committed changes.
Peiming added a commit: rG6ca0b2729870: [mlir][sparse] more complicated test for dual sparse convolution kernel..
aartbik added a comment.Aug 21 2023, 12:50 PM

LGTM

Revision Contents

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

Diff 552083

mlir/test/Integration/Dialect/SparseTensor/CPU/sparse_conv_2d_nchw_fchw.mlir

Show First 20 Lines • Show All 68 Lines • ▼ Show 20 Lines
func.func @conv_2d_nchw_fchw_CCCC(%arg0: tensor<?x?x?x?xf32, #CCCC>, %arg1: tensor<?x?x?x?xf32>, %arg2: tensor<?x?x?x?xf32>) -> tensor<?x?x?x?xf32> { func.func @conv_2d_nchw_fchw_CCCC(%arg0: tensor<?x?x?x?xf32, #CCCC>, %arg1: tensor<?x?x?x?xf32>, %arg2: tensor<?x?x?x?xf32>) -> tensor<?x?x?x?xf32> {
%ret = linalg.conv_2d_nchw_fchw {dilations = dense<1> : tensor<2xi64>, %ret = linalg.conv_2d_nchw_fchw {dilations = dense<1> : tensor<2xi64>,
strides = dense<1> : tensor<2xi64>} strides = dense<1> : tensor<2xi64>}
ins (%arg0, %arg1: tensor<?x?x?x?xf32, #CCCC>, tensor<?x?x?x?xf32>) ins (%arg0, %arg1: tensor<?x?x?x?xf32, #CCCC>, tensor<?x?x?x?xf32>)
outs (%arg2: tensor<?x?x?x?xf32>) -> tensor<?x?x?x?xf32> outs (%arg2: tensor<?x?x?x?xf32>) -> tensor<?x?x?x?xf32>
return %ret : tensor<?x?x?x?xf32> return %ret : tensor<?x?x?x?xf32>
} }
func.func @conv_2d_nchw_fchw_CCCC_CCCC(%arg0: tensor<?x?x?x?xf32, #CCCC>, %arg1: tensor<?x?x?x?xf32, #CCCC>, %arg2: tensor<?x?x?x?xf32>) -> tensor<?x?x?x?xf32> {
%ret = linalg.conv_2d_nchw_fchw {dilations = dense<1> : tensor<2xi64>,
strides = dense<1> : tensor<2xi64>}
ins (%arg0, %arg1: tensor<?x?x?x?xf32, #CCCC>, tensor<?x?x?x?xf32, #CCCC>)
outs (%arg2: tensor<?x?x?x?xf32>) -> tensor<?x?x?x?xf32>
return %ret : tensor<?x?x?x?xf32>
}
func.func @entry() { func.func @entry() {
%c0 = arith.constant 0 : index %c0 = arith.constant 0 : index
%c1 = arith.constant 1 : index %c1 = arith.constant 1 : index
%c3 = arith.constant 3 : index %c3 = arith.constant 3 : index
%c6 = arith.constant 6 : index %c6 = arith.constant 6 : index
%c8 = arith.constant 8 : index %c8 = arith.constant 8 : index
%f10 = arith.constant 10.00000e+00 : f32 %f10 = arith.constant 10.00000e+00 : f32
%val = arith.constant 2.00000e+00 : f32 %val = arith.constant 2.00000e+00 : f32
%zero = arith.constant 0.00000e+00 : f32 %zero = arith.constant 0.00000e+00 : f32
%filter2D_nhwc = call @alloc_4d_filled_f32(%c1, %c3, %c3, %c3, %val) :(index, index, index, index, f32) -> (tensor<?x?x?x?xf32>) %filter2D_nhwc = call @alloc_4d_filled_f32(%c1, %c3, %c3, %c3, %val) :(index, index, index, index, f32) -> (tensor<?x?x?x?xf32>)
%in2D_tmp = call @alloc_4d_filled_f32(%c3, %c3, %c8, %c8, %val) : (index, index, index, index, f32) -> (tensor<?x?x?x?xf32>) %in2D_tmp = call @alloc_4d_filled_f32(%c3, %c3, %c8, %c8, %val) : (index, index, index, index, f32) -> (tensor<?x?x?x?xf32>)
%in2D_nhwc = tensor.insert %f10 into %in2D_tmp[%c0, %c0, %c0, %c3] : tensor<?x?x?x?xf32> %in2D_nhwc = tensor.insert %f10 into %in2D_tmp[%c0, %c0, %c0, %c3] : tensor<?x?x?x?xf32>
%out2D_nhwc = call @alloc_4d_filled_f32(%c3, %c1, %c6, %c6, %zero) : (index, index, index, index, f32) -> (tensor<?x?x?x?xf32>) %out2D_nhwc = call @alloc_4d_filled_f32(%c3, %c1, %c6, %c6, %zero) : (index, index, index, index, f32) -> (tensor<?x?x?x?xf32>)
%out2D_nhwc_CCCD = call @alloc_4d_filled_f32(%c3, %c1, %c6, %c6, %zero) : (index, index, index, index, f32) -> (tensor<?x?x?x?xf32>) %out2D_nhwc_CCCD = call @alloc_4d_filled_f32(%c3, %c1, %c6, %c6, %zero) : (index, index, index, index, f32) -> (tensor<?x?x?x?xf32>)
%out2D_nhwc_CCCC = call @alloc_4d_filled_f32(%c3, %c1, %c6, %c6, %zero) : (index, index, index, index, f32) -> (tensor<?x?x?x?xf32>) %out2D_nhwc_CCCC = call @alloc_4d_filled_f32(%c3, %c1, %c6, %c6, %zero) : (index, index, index, index, f32) -> (tensor<?x?x?x?xf32>)
%in2D_nhwc_CCCD = sparse_tensor.convert %in2D_nhwc %in2D_nhwc_CCCD = sparse_tensor.convert %in2D_nhwc
: tensor<?x?x?x?xf32> to tensor<?x?x?x?xf32, #CDCD> : tensor<?x?x?x?xf32> to tensor<?x?x?x?xf32, #CDCD>
%in2D_nhwc_CCCC = sparse_tensor.convert %in2D_nhwc %in2D_nhwc_CCCC = sparse_tensor.convert %in2D_nhwc
: tensor<?x?x?x?xf32> to tensor<?x?x?x?xf32, #CCCC> : tensor<?x?x?x?xf32> to tensor<?x?x?x?xf32, #CCCC>
%filter2D_nhwc_CCCC = sparse_tensor.convert %filter2D_nhwc
: tensor<?x?x?x?xf32> to tensor<?x?x?x?xf32, #CCCC>
%dense_ret = call @conv_2d_nchw_fchw(%in2D_nhwc, %filter2D_nhwc, %out2D_nhwc) : (tensor<?x?x?x?xf32>, tensor<?x?x?x?xf32>, tensor<?x?x?x?xf32>) -> (tensor<?x?x?x?xf32>) %dense_ret = call @conv_2d_nchw_fchw(%in2D_nhwc, %filter2D_nhwc, %out2D_nhwc) : (tensor<?x?x?x?xf32>, tensor<?x?x?x?xf32>, tensor<?x?x?x?xf32>) -> (tensor<?x?x?x?xf32>)
%CCCC_ret = call @conv_2d_nchw_fchw_CDCD(%in2D_nhwc_CCCD, %filter2D_nhwc, %out2D_nhwc_CCCD) : (tensor<?x?x?x?xf32, #CDCD>, tensor<?x?x?x?xf32>, tensor<?x?x?x?xf32>) -> (tensor<?x?x?x?xf32>) %CCCC_ret = call @conv_2d_nchw_fchw_CDCD(%in2D_nhwc_CCCD, %filter2D_nhwc, %out2D_nhwc_CCCD) : (tensor<?x?x?x?xf32, #CDCD>, tensor<?x?x?x?xf32>, tensor<?x?x?x?xf32>) -> (tensor<?x?x?x?xf32>)
%CDCD_ret = call @conv_2d_nchw_fchw_CCCC(%in2D_nhwc_CCCC, %filter2D_nhwc, %out2D_nhwc_CCCC) : (tensor<?x?x?x?xf32, #CCCC>, tensor<?x?x?x?xf32>, tensor<?x?x?x?xf32>) -> (tensor<?x?x?x?xf32>) %CDCD_ret = call @conv_2d_nchw_fchw_CCCC(%in2D_nhwc_CCCC, %filter2D_nhwc, %out2D_nhwc_CCCC) : (tensor<?x?x?x?xf32, #CCCC>, tensor<?x?x?x?xf32>, tensor<?x?x?x?xf32>) -> (tensor<?x?x?x?xf32>)
%dual_CCCC_ret = call @conv_2d_nchw_fchw_CCCC_CCCC(%in2D_nhwc_CCCC, %filter2D_nhwc_CCCC, %out2D_nhwc) : (tensor<?x?x?x?xf32, #CCCC>, tensor<?x?x?x?xf32, #CCCC>, tensor<?x?x?x?xf32>) -> (tensor<?x?x?x?xf32>)
// CHECK: ( ( ( ( 108, 124, 124, 124, 108, 108 ), // CHECK: ( ( ( ( 108, 124, 124, 124, 108, 108 ),
// CHECK-SAME: ( 108, 108, 108, 108, 108, 108 ), // CHECK-SAME: ( 108, 108, 108, 108, 108, 108 ),
// CHECK-SAME: ( 108, 108, 108, 108, 108, 108 ), // CHECK-SAME: ( 108, 108, 108, 108, 108, 108 ),
// CHECK-SAME: ( 108, 108, 108, 108, 108, 108 ), // CHECK-SAME: ( 108, 108, 108, 108, 108, 108 ),
// CHECK-SAME: ( 108, 108, 108, 108, 108, 108 ), // CHECK-SAME: ( 108, 108, 108, 108, 108, 108 ),
// CHECK-SAME: ( 108, 108, 108, 108, 108, 108 ) ) ), // CHECK-SAME: ( 108, 108, 108, 108, 108, 108 ) ) ),
▲ Show 20 Lines • Show All 52 Lines • ▼ Show 20 Linesfunc.func @entry() {
// CHECK-SAME: ( 108, 108, 108, 108, 108, 108 ), // CHECK-SAME: ( 108, 108, 108, 108, 108, 108 ),
// CHECK-SAME: ( 108, 108, 108, 108, 108, 108 ), // CHECK-SAME: ( 108, 108, 108, 108, 108, 108 ),
// CHECK-SAME: ( 108, 108, 108, 108, 108, 108 ), // CHECK-SAME: ( 108, 108, 108, 108, 108, 108 ),
// CHECK-SAME: ( 108, 108, 108, 108, 108, 108 ) ) ) ) // CHECK-SAME: ( 108, 108, 108, 108, 108, 108 ) ) ) )
%v2 = vector.transfer_read %CDCD_ret[%c0, %c0, %c0, %c0], %zero %v2 = vector.transfer_read %CDCD_ret[%c0, %c0, %c0, %c0], %zero
: tensor<?x?x?x?xf32>, vector<3x1x6x6xf32> : tensor<?x?x?x?xf32>, vector<3x1x6x6xf32>
vector.print %v2 : vector<3x1x6x6xf32> vector.print %v2 : vector<3x1x6x6xf32>
// CHECK: ( ( ( ( 108, 124, 124, 124, 108, 108 ),
// CHECK-SAME: ( 108, 108, 108, 108, 108, 108 ),
// CHECK-SAME: ( 108, 108, 108, 108, 108, 108 ),
// CHECK-SAME: ( 108, 108, 108, 108, 108, 108 ),
// CHECK-SAME: ( 108, 108, 108, 108, 108, 108 ),
// CHECK-SAME: ( 108, 108, 108, 108, 108, 108 ) ) ),
// CHECK-SAME: ( ( ( 108, 108, 108, 108, 108, 108 ),
// CHECK-SAME: ( 108, 108, 108, 108, 108, 108 ),
// CHECK-SAME: ( 108, 108, 108, 108, 108, 108 ),
// CHECK-SAME: ( 108, 108, 108, 108, 108, 108 ),
// CHECK-SAME: ( 108, 108, 108, 108, 108, 108 ),
// CHECK-SAME: ( 108, 108, 108, 108, 108, 108 ) ) ),
// CHECK-SAME: ( ( ( 108, 108, 108, 108, 108, 108 ),
// CHECK-SAME: ( 108, 108, 108, 108, 108, 108 ),
// CHECK-SAME: ( 108, 108, 108, 108, 108, 108 ),
// CHECK-SAME: ( 108, 108, 108, 108, 108, 108 ),
// CHECK-SAME: ( 108, 108, 108, 108, 108, 108 ),
// CHECK-SAME: ( 108, 108, 108, 108, 108, 108 ) ) ) )
%v3 = vector.transfer_read %dual_CCCC_ret[%c0, %c0, %c0, %c0], %zero
: tensor<?x?x?x?xf32>, vector<3x1x6x6xf32>
vector.print %v3 : vector<3x1x6x6xf32>
// Free the resources // Free the resources
bufferization.dealloc_tensor %in2D_nhwc : tensor<?x?x?x?xf32> bufferization.dealloc_tensor %in2D_nhwc : tensor<?x?x?x?xf32>
bufferization.dealloc_tensor %filter2D_nhwc : tensor<?x?x?x?xf32> bufferization.dealloc_tensor %filter2D_nhwc : tensor<?x?x?x?xf32>
bufferization.dealloc_tensor %out2D_nhwc : tensor<?x?x?x?xf32> bufferization.dealloc_tensor %out2D_nhwc : tensor<?x?x?x?xf32>
bufferization.dealloc_tensor %out2D_nhwc_CCCD : tensor<?x?x?x?xf32> bufferization.dealloc_tensor %out2D_nhwc_CCCD : tensor<?x?x?x?xf32>
bufferization.dealloc_tensor %out2D_nhwc_CCCC : tensor<?x?x?x?xf32> bufferization.dealloc_tensor %out2D_nhwc_CCCC : tensor<?x?x?x?xf32>
bufferization.dealloc_tensor %in2D_nhwc_CCCC : tensor<?x?x?x?xf32, #CCCC> bufferization.dealloc_tensor %in2D_nhwc_CCCC : tensor<?x?x?x?xf32, #CCCC>
bufferization.dealloc_tensor %in2D_nhwc_CCCD : tensor<?x?x?x?xf32, #CDCD> bufferization.dealloc_tensor %in2D_nhwc_CCCD : tensor<?x?x?x?xf32, #CDCD>
bufferization.dealloc_tensor %filter2D_nhwc_CCCC : tensor<?x?x?x?xf32, #CCCC>
return return
} }