diff options
| author | Gian Marco Iodice <gianmarco.iodice@arm.com> | 2017-10-09 15:05:40 +0100 |
|---|---|---|
| committer | Anthony Barbier <anthony.barbier@arm.com> | 2018-11-02 16:35:24 +0000 |
| commit | ab18212dd287cc0ec9b7c1a2c72455fe75ebd13d (patch) | |
| tree | f802205d85785da671ddd1949ba61b9dc36a3035 /arm_compute/core/NEON/kernels/NEGEMMInterleaveBlockedKernel.h | |
| parent | ed194b1fbec6627896c5c12f74460b9142b98f7d (diff) | |
| download | ComputeLibrary-ab18212dd287cc0ec9b7c1a2c72455fe75ebd13d.tar.gz | |
COMPMID-616 - Optimizing GEMMLowp on NEON intrinsics
Change-Id: Ibbeff5d37249b6e8fc34ad496035a1511c9da5a3
Reviewed-on: http://mpd-gerrit.cambridge.arm.com/94072
Tested-by: Kaizen <jeremy.johnson+kaizengerrit@arm.com>
Reviewed-by: Pablo Tello <pablo.tello@arm.com>
Diffstat (limited to 'arm_compute/core/NEON/kernels/NEGEMMInterleaveBlockedKernel.h')
| -rw-r--r-- | arm_compute/core/NEON/kernels/NEGEMMInterleaveBlockedKernel.h | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/arm_compute/core/NEON/kernels/NEGEMMInterleaveBlockedKernel.h b/arm_compute/core/NEON/kernels/NEGEMMInterleaveBlockedKernel.h index aa942c40fb..cdeb11d606 100644 --- a/arm_compute/core/NEON/kernels/NEGEMMInterleaveBlockedKernel.h +++ b/arm_compute/core/NEON/kernels/NEGEMMInterleaveBlockedKernel.h @@ -46,7 +46,7 @@ public: * @param[in] input Input tensor. Data types supported: U8 * @param[out] output Output tensor which stores the interleaved matrix. Data type supported: same as @p input. * @param[in] block_height The height of the blocks to be interleaved. - * @param[in] block_width The width of the blocks to be interleved. + * @param[in] block_width The width of the blocks to be interleaved. * @param[in] transpose True if transpose operation must be performed, false otherwise. */ void configure(const ITensor *input, ITensor *output, unsigned int block_height, unsigned int block_width, bool transpose); |