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/example/24_batched_gemm/batched_gemm_xdl_bf16.cpp
+++ b/example/24_batched_gemm/batched_gemm_xdl_bf16.cpp
--- a/example/24_batched_gemm/batched_gemm_xdl_fp16.cpp
+++ b/example/24_batched_gemm/batched_gemm_xdl_fp16.cpp
--- a/example/24_batched_gemm/batched_gemm_xdl_fp32.cpp
+++ b/example/24_batched_gemm/batched_gemm_xdl_fp32.cpp
--- a/example/24_batched_gemm/batched_gemm_xdl_int4.cpp
+++ b/example/24_batched_gemm/batched_gemm_xdl_int4.cpp
--- a/example/24_batched_gemm/batched_gemm_xdl_int8.cpp
+++ b/example/24_batched_gemm/batched_gemm_xdl_int8.cpp
--- a/example/24_batched_gemm/run_batched_gemm_example.inc
+++ b/example/24_batched_gemm/run_batched_gemm_example.inc
--- a/example/25_gemm_bias_e_permute/CMakeLists.txt
+++ b/example/25_gemm_bias_e_permute/CMakeLists.txt
--- a/example/25_gemm_bias_e_permute/gemm_bias_e_permute_g1m2n3k1_xdl_fp16.cpp
+++ b/example/25_gemm_bias_e_permute/gemm_bias_e_permute_g1m2n3k1_xdl_fp16.cpp
--- a/example/25_gemm_bias_e_permute/gemm_bias_e_permute_g1m3n2k1_xdl_fp16.cpp
+++ b/example/25_gemm_bias_e_permute/gemm_bias_e_permute_g1m3n2k1_xdl_fp16.cpp
--- a/example/26_contraction/CMakeLists.txt
+++ b/example/26_contraction/CMakeLists.txt
--- a/example/26_contraction/README.md
+++ b/example/26_contraction/README.md
--- a/example/26_contraction/contraction_bilinear_xdl_fp32.cpp
+++ b/example/26_contraction/contraction_bilinear_xdl_fp32.cpp
--- a/example/26_contraction/contraction_bilinear_xdl_fp64.cpp
+++ b/example/26_contraction/contraction_bilinear_xdl_fp64.cpp
--- a/example/26_contraction/contraction_scale_xdl_fp32.cpp
+++ b/example/26_contraction/contraction_scale_xdl_fp32.cpp
--- a/example/26_contraction/contraction_scale_xdl_fp64.cpp
+++ b/example/26_contraction/contraction_scale_xdl_fp64.cpp
--- a/example/27_layernorm/CMakeLists.txt
+++ b/example/27_layernorm/CMakeLists.txt
--- a/example/27_layernorm/common.hpp
+++ b/example/27_layernorm/common.hpp
--- a/example/27_layernorm/layernorm_fp16.cpp
+++ b/example/27_layernorm/layernorm_fp16.cpp
--- a/example/27_layernorm/layernorm_splitk_fp16.cpp
+++ b/example/27_layernorm/layernorm_splitk_fp16.cpp
--- a/example/27_layernorm/run_layernorm_example.inc
+++ b/example/27_layernorm/run_layernorm_example.inc