aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorGian Marco Iodice <gianmarco.iodice@arm.com>2021-05-17 16:02:13 +0100
committerMichele Di Giorgio <michele.digiorgio@arm.com>2021-05-18 10:11:56 +0100
commit3bf76b1ade354f0b3a4d329a6e80ac4f90fcf11d (patch)
tree06eea56ecfad5a5abd801a5bacc520bfe111d5e9
parent72d62390697f478ab21117429e9fa7f8971ae183 (diff)
downloadComputeLibrary-branches/arm_compute_21_05.tar.gz
Fix heuristic in Int8 CLDirectConvolutionKernelv21.05dev/21_05_int8_optimbranches/arm_compute_21_05
- k0 should be set to 16 for quantized data types Resolves COMPMID-4497 Change-Id: I729a8e2b7cd45762df4fef8b4c8606fe6367adb5 Signed-off-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5654 Tested-by: Arm Jenkins <bsgcomp@arm.com> Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
-rw-r--r--src/core/gpu/cl/kernels/ClDirectConvolutionKernel.cpp2
1 files changed, 1 insertions, 1 deletions
diff --git a/src/core/gpu/cl/kernels/ClDirectConvolutionKernel.cpp b/src/core/gpu/cl/kernels/ClDirectConvolutionKernel.cpp
index bf26477895..18d648d2f2 100644
--- a/src/core/gpu/cl/kernels/ClDirectConvolutionKernel.cpp
+++ b/src/core/gpu/cl/kernels/ClDirectConvolutionKernel.cpp
@@ -416,7 +416,7 @@ void ClDirectConvolutionKernel::configure(const CLCompileContext &compile_contex
const unsigned int n0 = win_config.second.x().step();
const unsigned int m0 = win_config.second.y().step();
- const unsigned int k0 = adjust_vec_size(8u, src->dimension(channel_idx));
+ const unsigned int k0 = adjust_vec_size(is_data_type_quantized(data_type)? 16u : 8u, src->dimension(channel_idx));
const unsigned int partial_store_n0 = dst->dimension(channel_idx) % n0;
const unsigned int pad_left = conv_info.pad_left();
const unsigned int pad_top = conv_info.pad_top();