diff options
author | Mike Kelly <mike.kelly@arm.com> | 2023-01-23 19:32:06 +0000 |
---|---|---|
committer | TeresaARM <teresa.charlinreyes@arm.com> | 2023-01-24 17:01:30 +0000 |
commit | 0e3fe10bfe1b4f006f6e0c5c2fae8fb5515c7544 (patch) | |
tree | 222ff6eb1c034efa05bc5dcf4b255f80993987bf /delegate | |
parent | d134c13ec9a0585bb7656654e0e65c57958d8833 (diff) | |
download | armnn-0e3fe10bfe1b4f006f6e0c5c2fae8fb5515c7544.tar.gz |
IVGCVSW-7455 Workaround to allow CLBatchMatMul to parse some 4D models
* Added ability to reduce dimension sizes when calling BuildArmComputeTensorInfo or
BuildArmComputeTensorShapes, this will attempt to remove leading 1s in order to
squeeze the number of dimensions but retain the size.
* Changed ClBatchMatMulWorkload to attempt to squeeze the number of dimensions to 3
as the CL Gemm Kernel can only support up to 3 dimensions.
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
Change-Id: I6b3d0886c5b97fdb686838fc3dc292833ddc4643
Diffstat (limited to 'delegate')
-rw-r--r-- | delegate/src/test/BatchMatMulTest.cpp | 3 |
1 files changed, 2 insertions, 1 deletions
diff --git a/delegate/src/test/BatchMatMulTest.cpp b/delegate/src/test/BatchMatMulTest.cpp index d13d8dcf43..06ad2c3be2 100644 --- a/delegate/src/test/BatchMatMulTest.cpp +++ b/delegate/src/test/BatchMatMulTest.cpp @@ -1,5 +1,5 @@ // -// Copyright © 2022 Arm Ltd and Contributors. All rights reserved. +// Copyright © 2022-2023 Arm Ltd and Contributors. All rights reserved. // SPDX-License-Identifier: MIT // @@ -677,6 +677,7 @@ namespace armnnDelegate std::vector <armnn::BackendId> backends = {armnn::Compute::GpuAcc}; BatchMatMul2DFp32SimpleTest (backends); BatchMatMul3DFp32SimpleTest (backends); + BatchMatMul4DFp32SimpleTest (backends); BatchMatMul3DFp32BatchTest (backends); BatchMatMul3DFp32BroadcastTest (backends); BatchMatMul3D2DFp32BroadcastTest (backends); |