Age | Commit message (Expand) | Author |
---|---|---|
2019-04-16 | COMPMID-2110: Enable CLGEMMLowpMatrixMultiplyReshapeOnlyRHSKernel in CLGEMMLowp | Gian Marco Iodice |
2019-03-15 | COMPMID-1694: Fuse offset contribution with the output stage when we use NEGE... | George Wort |
2019-01-25 | COMPMID-1698: Implementing CLGEMMLowpMatrixMultiplyReshapedKernel | Gian Marco Iodice |
2019-01-14 | Issue COMPMID-1835: Remove CLGEMMInterleave4x4Kernel and replace with CLGEMMR... | giuros01 |
2018-12-21 | COMPMID-1836: Remove CLGEMMTranspose1xWKernel and replace with CLGEMMReshapeR... | giuros01 |
2018-11-02 | COMPMID-1413 - Improve the performance of GEMMLowp with 8 bit dot product on ... | Gian Marco Iodice |
2018-11-02 | COMPMID-1145: (API) Introduce prepare() stage (NEON/CL/GLES) | Georgios Pinitas |
2018-11-02 | COMPMID-617: Adds CLFullyConnectionLayer validation support | Georgios Pinitas |
2018-11-02 | COMPMID-661: Convolution quantized (#32) | Chunosov |
2018-11-02 | COMPMID-697 - Rework GEMMLowp interface on OpenCL | Gian Marco |