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/15_grouped_gemm/README.md
+++ b/example/15_grouped_gemm/README.md
--- a/example/15_grouped_gemm/grouped_gemm_multiple_d_dl_fp16.cpp
+++ b/example/15_grouped_gemm/grouped_gemm_multiple_d_dl_fp16.cpp
--- a/example/15_grouped_gemm/grouped_gemm_xdl_bf16.cpp
+++ b/example/15_grouped_gemm/grouped_gemm_xdl_bf16.cpp
--- a/example/15_grouped_gemm/grouped_gemm_xdl_fixed_nk_bias_fp16.cpp
+++ b/example/15_grouped_gemm/grouped_gemm_xdl_fixed_nk_bias_fp16.cpp
--- a/example/15_grouped_gemm/grouped_gemm_xdl_fixed_nk_fp16.cpp
+++ b/example/15_grouped_gemm/grouped_gemm_xdl_fixed_nk_fp16.cpp
--- a/example/15_grouped_gemm/grouped_gemm_xdl_fixed_nk_fp8.cpp
+++ b/example/15_grouped_gemm/grouped_gemm_xdl_fixed_nk_fp8.cpp
--- a/example/15_grouped_gemm/grouped_gemm_xdl_fp16.cpp
+++ b/example/15_grouped_gemm/grouped_gemm_xdl_fp16.cpp
--- a/example/15_grouped_gemm/grouped_gemm_xdl_fp32.cpp
+++ b/example/15_grouped_gemm/grouped_gemm_xdl_fp32.cpp
--- a/example/15_grouped_gemm/grouped_gemm_xdl_int4.cpp
+++ b/example/15_grouped_gemm/grouped_gemm_xdl_int4.cpp
--- a/example/15_grouped_gemm/grouped_gemm_xdl_int8.cpp
+++ b/example/15_grouped_gemm/grouped_gemm_xdl_int8.cpp
--- a/example/15_grouped_gemm/grouped_gemm_xdl_splitk_fp16.cpp
+++ b/example/15_grouped_gemm/grouped_gemm_xdl_splitk_fp16.cpp
--- a/example/15_grouped_gemm/run_grouped_gemm_example.inc
+++ b/example/15_grouped_gemm/run_grouped_gemm_example.inc
--- a/example/16_gemm_multi_d_multi_reduces/CMakeLists.txt
+++ b/example/16_gemm_multi_d_multi_reduces/CMakeLists.txt
--- a/example/16_gemm_multi_d_multi_reduces/gemm_add_add_mean_meansquare_xdl_fp16.cpp
+++ b/example/16_gemm_multi_d_multi_reduces/gemm_add_add_mean_meansquare_xdl_fp16.cpp
--- a/example/16_gemm_multi_d_multi_reduces/gemm_add_addsquare_xdl_int8.cpp
+++ b/example/16_gemm_multi_d_multi_reduces/gemm_add_addsquare_xdl_int8.cpp
--- a/example/16_gemm_multi_d_multi_reduces/gemm_max_xdl_bf16.cpp
+++ b/example/16_gemm_multi_d_multi_reduces/gemm_max_xdl_bf16.cpp
--- a/example/16_gemm_multi_d_multi_reduces/gemm_max_xdl_fp16.cpp
+++ b/example/16_gemm_multi_d_multi_reduces/gemm_max_xdl_fp16.cpp
--- a/example/16_gemm_multi_d_multi_reduces/gemm_max_xdl_fp32.cpp
+++ b/example/16_gemm_multi_d_multi_reduces/gemm_max_xdl_fp32.cpp
--- a/example/16_gemm_multi_d_multi_reduces/gemm_max_xdl_int4.cpp
+++ b/example/16_gemm_multi_d_multi_reduces/gemm_max_xdl_int4.cpp
--- a/example/16_gemm_multi_d_multi_reduces/gemm_max_xdl_int8.cpp
+++ b/example/16_gemm_multi_d_multi_reduces/gemm_max_xdl_int8.cpp