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/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v2r4r2.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v2r4r2.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v3r1.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v3r1.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v3r2.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v3r2.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v3r3.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_gemm_xdlops_v3r3.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_gemv_splitk.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_gemv_splitk.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_permute.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_permute.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_put_element_1d.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_put_element_1d.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_set_buffer_value.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_set_buffer_value.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_set_multiple_buffer_value.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_set_multiple_buffer_value.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_softmax.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_softmax.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_sparse_embeddings_forward_layernorm.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_sparse_embeddings_forward_layernorm.hpp
--- a/composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_tall_and_skinny_gemm_splitk.hpp
+++ b/composable_kernel/include/ck/tensor_operation/gpu/grid/gridwise_tall_and_skinny_gemm_splitk.hpp
--- a/include/ck/tensor_operation/gpu/grid/gridwise_tensor_rearrange.hpp
+++ b/include/ck/tensor_operation/gpu/grid/gridwise_tensor_rearrange.hpp
--- a/include/ck/tensor_operation/gpu/grid/normalization/gridwise_normalization_naive_variance.hpp
+++ b/include/ck/tensor_operation/gpu/grid/normalization/gridwise_normalization_naive_variance.hpp
--- a/include/ck/tensor_operation/gpu/grid/normalization/gridwise_normalization_selector.hpp
+++ b/include/ck/tensor_operation/gpu/grid/normalization/gridwise_normalization_selector.hpp
--- a/include/ck/tensor_operation/gpu/grid/normalization/gridwise_normalization_splitk_1st.hpp
+++ b/include/ck/tensor_operation/gpu/grid/normalization/gridwise_normalization_splitk_1st.hpp
--- a/include/ck/tensor_operation/gpu/grid/normalization/gridwise_normalization_splitk_2nd.hpp
+++ b/include/ck/tensor_operation/gpu/grid/normalization/gridwise_normalization_splitk_2nd.hpp
--- a/include/ck/tensor_operation/gpu/grid/normalization/gridwise_normalization_welford_variance.hpp
+++ b/include/ck/tensor_operation/gpu/grid/normalization/gridwise_normalization_welford_variance.hpp
--- a/include/ck/tensor_operation/gpu/thread/reduction_functions_threadwise.hpp
+++ b/include/ck/tensor_operation/gpu/thread/reduction_functions_threadwise.hpp
--- a/include/ck/tensor_operation/gpu/thread/threadwise_contraction_dl.hpp
+++ b/include/ck/tensor_operation/gpu/thread/threadwise_contraction_dl.hpp