Skip to content

GitLab

Commit 9e11d3b8 authored by Bartlomiej Kocot's avatar Bartlomiej Kocot
Browse files

Add instances with smaller NPerBlock

parent 2a62df23
Hide whitespace changes
Inline Side-by-side
Showing with 2 additions and 1 deletion
library/include/ck/library/tensor_operation_instance/gpu/grouped_conv_bwd_data/device_grouped_conv_bwd_data_wmma_instance.hpp
View file @ 9e11d3b8
......@@ -53,10 +53,11 @@ using device_grouped_conv_bwd_data_wmma_f16_instances = std::tuple<
DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout, F16, F16, F32, F16, Empty_Tuple, F16, PassThrough, PassThrough, CDEElementOp, ConvSpec, 256, 128, 256, 8, 8, 16, 16, 4, 4, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 8, 8, 1, 1, 1, S<1, 32, 1, 8>, 8>,
DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout, F16, F16, F32, F16, Empty_Tuple, F16, PassThrough, PassThrough, CDEElementOp, ConvSpec, 256, 64, 256, 8, 8, 16, 16, 2, 4, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 8, 8, 1, 1, 1, S<1, 32, 1, 8>, 8>,
DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout, F16, F16, F32, F16, Empty_Tuple, F16, PassThrough, PassThrough, CDEElementOp, ConvSpec, 256, 128, 256, 8, 8, 16, 16, 4, 4, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 8, 8, 1, 1, 1, S<1, 32, 1, 8>, 8>,
DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout, F16, F16, F32, F16, Empty_Tuple, F16, PassThrough, PassThrough, CDEElementOp, ConvSpec, 256, 128, 64, 8, 8, 16, 16, 4, 1, S<4, 64, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<8, 32, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, 1, 1, S<1, 32, 1, 8>, 8>,
// blocksize=128
DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout, F16, F16, F32, F16, Empty_Tuple, F16, PassThrough, PassThrough, CDEElementOp, ConvSpec, 128, 64, 128, 8, 8, 16, 16, 2, 4, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<8, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 8, 8, 1, 1, 1, S<1, 32, 1, 4>, 8>,
DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout, F16, F16, F32, F16, Empty_Tuple, F16, PassThrough, PassThrough, CDEElementOp, ConvSpec, 128, 64, 128, 8, 8, 16, 16, 2, 4, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<8, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 8, 8, 1, 1, 1, S<1, 32, 1, 4>, 8>,
DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout, F16, F16, F32, F16, Empty_Tuple, F16, PassThrough, PassThrough, CDEElementOp, ConvSpec, 128, 128, 128, 8, 8, 16, 16, 4, 4, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<8, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 8, 1, 1, 1, S<1, 32, 1, 4>, 8>,
DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout, F16, F16, F32, F16, Empty_Tuple, F16, PassThrough, PassThrough, CDEElementOp, ConvSpec, 128, 128, 64, 8, 8, 16, 16, 4, 2, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<8, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 2, 8, 1, 1, 1, S<1, 32, 1, 4>, 8>,
DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout, F16, F16, F32, F16, Empty_Tuple, F16, PassThrough, PassThrough, CDEElementOp, ConvSpec, 128, 128, 128, 8, 8, 16, 16, 4, 4, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<8, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 4, 8, 1, 1, 1, S<1, 32, 1, 4>, 8>,
DeviceGroupedConvBwdDataMultipleD_Wmma_CShuffle<NDSpatial, ALayout, BLayout, DsLayout, ELayout, F16, F16, F32, F16, Empty_Tuple, F16, PassThrough, PassThrough, CDEElementOp, ConvSpec, 128, 32, 256, 8, 8, 16, 16, 1, 8, S<4, 32, 1>, S<1, 0, 2>, S<1, 0, 2>, 2, 8, 8, 1, S<8, 16, 1>, S<0, 2, 1>, S<0, 2, 1>, 1, 8, 8, 1, 1, 1, S<1, 32, 1, 4>, 8>,
// // blocksize=64
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment