diff options
author | Gian Marco Iodice <gianmarco.iodice@arm.com> | 2018-10-18 10:21:02 +0100 |
---|---|---|
committer | Anthony Barbier <anthony.barbier@arm.com> | 2018-11-02 16:55:45 +0000 |
commit | 4b90865ab985d571f70c60583cdfb8c7a65f1670 (patch) | |
tree | f116a4ffef5f5e823689dd00c1e5c9d987f3d295 /tests/validate_examples/cl_gemm.cpp | |
parent | c55beee7ef70fa08a5d217619083b288a74fcb27 (diff) | |
download | ComputeLibrary-4b90865ab985d571f70c60583cdfb8c7a65f1670.tar.gz |
COMPMID-1413 - Improve the performance of GEMMLowp with 8 bit dot product on OpenCL
COMPMID-1424 - Add dot product support for CLDepthwise QASYMM8 3x3 NHWC non-unit stride
With this patch we are able to improve the performance of MobileNet v1-qasymm8 by 37 %
Tried to use the dot product instruction in CLDepthwise QASYMM8 3x3 NHWC non-unit stride
but I have not seen any benefit (maybe because we have few arithemtic operation and we
do not have more load instructions). However Depthwise convolution has been improved by
30%
Change-Id: Id768a99c2e53a04276707e427af5d0ec93419ada
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/155082
Tested-by: bsgcomp <bsgcomp@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Diffstat (limited to 'tests/validate_examples/cl_gemm.cpp')
-rw-r--r-- | tests/validate_examples/cl_gemm.cpp | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/tests/validate_examples/cl_gemm.cpp b/tests/validate_examples/cl_gemm.cpp index cdaa33f31a..8b3a103db7 100644 --- a/tests/validate_examples/cl_gemm.cpp +++ b/tests/validate_examples/cl_gemm.cpp @@ -193,7 +193,7 @@ public: init_sgemm_output(tmp_dst, src0, src1, DataType::S32); // Configure GEMMlowp matrix multiply function - mm_gemmlowp.configure(&src0, &src1, &tmp_dst); + mm_gemmlowp.configure(&src0, &src1, nullptr, &tmp_dst); // Configure GEMMlowp output stage mm_gemmlowp_output_stage.configure(&tmp_dst, add_bias ? &biases : nullptr, &dst, dst_multiplier, dst_shift, offset_dst); |