diff options
| author | Cathal Corbett <cathal.corbett@arm.com> | 2022-03-03 15:13:23 +0000 |
|---|---|---|
| committer | Cathal Corbett <cathal.corbett@arm.com> | 2022-03-03 15:13:32 +0000 |
| commit | fd5bec4cc0e6ef192a580621f225c971d605c261 (patch) | |
| tree | 1547c8a37c24ea99587d604335254629754b1ab0 /src/backends/aclCommon/ArmComputeTensorUtils.hpp | |
| parent | 624b5a3b8e3978e9b3887918194d485b14674cea (diff) | |
| download | armnn-fd5bec4cc0e6ef192a580621f225c971d605c261.tar.gz | |
Revert "Revert "IVGCVSW-6268 Add support of Unidirectional Sequence Lstm fp32/fp16 to Neon""
This reverts commit f87b90e4dbb906436cf205a2a19e199bfe9224ed.
Reason for revert: 22.02 release.
Change-Id: I1ca5a79a8957908f655a6c4e79eefa24c5aec645
Diffstat (limited to 'src/backends/aclCommon/ArmComputeTensorUtils.hpp')
| -rw-r--r-- | src/backends/aclCommon/ArmComputeTensorUtils.hpp | 3 |
1 files changed, 3 insertions, 0 deletions
diff --git a/src/backends/aclCommon/ArmComputeTensorUtils.hpp b/src/backends/aclCommon/ArmComputeTensorUtils.hpp index 30df31b79d..ba6ef6a3fe 100644 --- a/src/backends/aclCommon/ArmComputeTensorUtils.hpp +++ b/src/backends/aclCommon/ArmComputeTensorUtils.hpp @@ -25,6 +25,9 @@ namespace armcomputetensorutils /// Utility function to map an armnn::DataType to corresponding arm_compute::DataType. arm_compute::DataType GetArmComputeDataType(armnn::DataType dataType, bool multiScales); +/// Utility function to map an arm_compute::DataType to corresponding armnn::DataType. +armnn::DataType GetArmNNDataType(arm_compute::DataType datatype); + /// Utility function used to set up an arm_compute::Coordinates from a vector of ArmNN Axes for reduction functions arm_compute::Coordinates BuildArmComputeReductionCoordinates(size_t inputDimensions, unsigned int originalInputRank, |