| commit | e5d0b93b152a26faf93538eb719d03e5b477d670 | [log] [tgz] |
|---|---|---|
| author | Sadik Armagan <sadik.armagan@arm.com> | Thu Apr 09 15:48:44 2020 +0100 |
| committer | Sadik Armagan <sadik.armagan@arm.com> | Thu Apr 09 15:48:44 2020 +0100 |
| tree | 360e1d83c40459a8cbec64fc346411a1a63193ef | |
| parent | 99b57c97ef07bbbefaf655915c01bfb2f9f05e15 [diff] [blame] |
IVGCVSW-4641 Investigate Hal 1.3 VTS Failures * Add QASYMM8_SIGNED data type support to NeonTensorHandle Signed-off-by: Sadik Armagan <sadik.armagan@arm.com> Change-Id: Iae34f7d67de83642606ccd8c61a1b72df7f2bb3a
diff --git a/src/backends/neon/workloads/NeonWorkloadUtils.hpp b/src/backends/neon/workloads/NeonWorkloadUtils.hpp index c3c9d3d..860a835 100644 --- a/src/backends/neon/workloads/NeonWorkloadUtils.hpp +++ b/src/backends/neon/workloads/NeonWorkloadUtils.hpp
@@ -52,6 +52,7 @@ case DataType::QuantizedSymm8PerAxis: ARMNN_FALLTHROUGH; case DataType::QSymmS8: + case DataType::QAsymmS8: CopyArmComputeTensorData(tensor, handle->GetConstTensor<int8_t>()); break; ARMNN_NO_DEPRECATE_WARN_END