experiments/STT-tensorflow
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Convolution params selection changed for Intel.

Browse Source 
PiperOrigin-RevId: 304339069
Change-Id: I9897d5d318b8bc50a99fa9a248b465bd1a74b377
This commit is contained in:
Raman Sarokin 2020-04-01 23:55:09 -07:00 committed by TensorFlower Gardener
parent b37a9572c0
commit f0412987d7
1 changed files with 2 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
tensorflow/lite/delegates/gpu/metal/kernels/conv.cc
View File

@ -920,7 +920,7 @@ ConvParams GetConvParamsForIntel(const Convolution2DAttributes& attr,
const int dst_slices = IntegralDivideRoundUp(dst_shape.c, 4);
const int src_slices = IntegralDivideRoundUp(attr.weights.shape.i, 4);
ConvParams params;
params.weights_upload_type = WeightsUploadType::PRIVATE_MEM_SIMD16_BROADCAST;
params.weights_upload_type = WeightsUploadType::PRIVATE_MEM_SIMD8_BROADCAST;
params.x_kernel_is_1 = IsKernelXIs1(attr);
params.y_kernel_is_1 = IsKernelYIs1(attr);
params.src_depth_loop_size = 1;
@ -1132,8 +1132,7 @@ std::vector<ComputeTaskDescriptorPtr> ConvolutionWino4x4To6x6(
}
} else if (device_info.IsIntelGPU()) {
params.weight_layout = WeightsInnerBlockLayout::I4O4;
params.weights_upload_type =
WeightsUploadType::PRIVATE_MEM_SIMD16_BROADCAST;
params.weights_upload_type = WeightsUploadType::PRIVATE_MEM_SIMD8_BROADCAST;
params.work_group_size = int3(16, 1, 1);
params.block_size = int3(1, 1, 4);
} else if (device_info.IsAMDGPU()) {