adding tall and skinny gemm

3eee1b9b · Harisankar Sadasivan · 67adf1b4 · 3eee1b9b · 3eee1b9b · 3eee1b9b
Commit 3eee1b9b authored Nov 01, 2023 by Harisankar Sadasivan
20 changed files
--- a/client_example/09_quantization/conv2d_fwd_bias_tanh_perchannel_quantization.cpp
+++ b/client_example/09_quantization/conv2d_fwd_bias_tanh_perchannel_quantization.cpp
--- a/client_example/09_quantization/conv2d_fwd_bias_tanh_perlayer_quantization.cpp
+++ b/client_example/09_quantization/conv2d_fwd_bias_tanh_perlayer_quantization.cpp
--- a/client_example/09_quantization/conv2d_fwd_perchannel_quantization.cpp
+++ b/client_example/09_quantization/conv2d_fwd_perchannel_quantization.cpp
--- a/client_example/09_quantization/conv2d_fwd_perlayer_quantization.cpp
+++ b/client_example/09_quantization/conv2d_fwd_perlayer_quantization.cpp
--- a/client_example/09_quantization/gemm_quantization.cpp
+++ b/client_example/09_quantization/gemm_quantization.cpp
--- a/client_example/10_grouped_convnd_bwd_data/CMakeLists.txt
+++ b/client_example/10_grouped_convnd_bwd_data/CMakeLists.txt
--- a/client_example/10_grouped_convnd_bwd_data/grouped_conv2d_bwd_data.cpp
+++ b/client_example/10_grouped_convnd_bwd_data/grouped_conv2d_bwd_data.cpp
--- a/client_example/10_grouped_convnd_bwd_data/grouped_conv3d_bwd_data.cpp
+++ b/client_example/10_grouped_convnd_bwd_data/grouped_conv3d_bwd_data.cpp
--- a/client_example/10_grouped_convnd_bwd_data/grouped_conv3d_bwd_data_input_fp16_comp_bf8f8.cpp
+++ b/client_example/10_grouped_convnd_bwd_data/grouped_conv3d_bwd_data_input_fp16_comp_bf8f8.cpp
--- a/client_example/11_grouped_conv_bwd_weight/CMakeLists.txt
+++ b/client_example/11_grouped_conv_bwd_weight/CMakeLists.txt
--- a/client_example/11_grouped_conv_bwd_weight/common.hpp
+++ b/client_example/11_grouped_conv_bwd_weight/common.hpp
--- a/client_example/11_grouped_conv_bwd_weight/grouped_conv1d_bwd_weight_fp16.cpp
+++ b/client_example/11_grouped_conv_bwd_weight/grouped_conv1d_bwd_weight_fp16.cpp
--- a/client_example/11_grouped_conv_bwd_weight/grouped_conv2d_bwd_weight_fp16.cpp
+++ b/client_example/11_grouped_conv_bwd_weight/grouped_conv2d_bwd_weight_fp16.cpp
--- a/client_example/11_grouped_conv_bwd_weight/grouped_conv3d_bwd_weight_fp16.cpp
+++ b/client_example/11_grouped_conv_bwd_weight/grouped_conv3d_bwd_weight_fp16.cpp
--- a/client_example/11_grouped_conv_bwd_weight/grouped_conv3d_bwd_weight_fp32.cpp
+++ b/client_example/11_grouped_conv_bwd_weight/grouped_conv3d_bwd_weight_fp32.cpp
--- a/client_example/12_elementwise_normalization/CMakeLists.txt
+++ b/client_example/12_elementwise_normalization/CMakeLists.txt
--- a/client_example/12_elementwise_normalization/elementwise_layernorm2d.cpp
+++ b/client_example/12_elementwise_normalization/elementwise_layernorm2d.cpp
--- a/client_example/13_batchnorm/CMakeLists.txt
+++ b/client_example/13_batchnorm/CMakeLists.txt
--- a/client_example/13_batchnorm/batchnorm_bwd_nhwc.cpp
+++ b/client_example/13_batchnorm/batchnorm_bwd_nhwc.cpp
--- a/client_example/13_batchnorm/batchnorm_fwd_nhwc.cpp
+++ b/client_example/13_batchnorm/batchnorm_fwd_nhwc.cpp