Merge branch 'gemm_bf16_sk_muozturk' of...

Merge branch 'gemm_bf16_sk_muozturk' of https://github.com/ROCm/composable_kernel into gemm_bf16_sk_muozturk

Merge branch 'gemm_bf16_sk_muozturk' of...
Merge branch 'gemm_bf16_sk_muozturk' of https://github.com/ROCm/composable_kernel into gemm_bf16_sk_muozturk
eca84f93 · root · 6f210155 · c256f018 · eca84f93 · eca84f93
Commit eca84f93 authored Dec 19, 2024 by root
20 changed files
--- a/example/ck_tile/10_rmsnorm2d/instances/rmsnorm2d_fwd_fp16_n512_instance.cpp
+++ b/example/ck_tile/10_rmsnorm2d/instances/rmsnorm2d_fwd_fp16_n512_instance.cpp
--- a/example/ck_tile/10_rmsnorm2d/instances/rmsnorm2d_fwd_fp16_n64_n128_instance.cpp
+++ b/example/ck_tile/10_rmsnorm2d/instances/rmsnorm2d_fwd_fp16_n64_n128_instance.cpp
--- a/example/ck_tile/10_rmsnorm2d/instances/rmsnorm2d_fwd_fp16_n768_instance.cpp
+++ b/example/ck_tile/10_rmsnorm2d/instances/rmsnorm2d_fwd_fp16_n768_instance.cpp
--- a/example/ck_tile/10_rmsnorm2d/instances/rmsnorm2d_fwd_instance_common.hpp
+++ b/example/ck_tile/10_rmsnorm2d/instances/rmsnorm2d_fwd_instance_common.hpp
--- a/example/ck_tile/10_rmsnorm2d/rmsnorm2d_fwd.cpp
+++ b/example/ck_tile/10_rmsnorm2d/rmsnorm2d_fwd.cpp
--- a/example/ck_tile/10_rmsnorm2d/rmsnorm2d_fwd.hpp
+++ b/example/ck_tile/10_rmsnorm2d/rmsnorm2d_fwd.hpp
--- a/example/ck_tile/10_rmsnorm2d/script/perf_test.sh
+++ b/example/ck_tile/10_rmsnorm2d/script/perf_test.sh
--- a/example/ck_tile/10_rmsnorm2d/script/smoke_test.sh
+++ b/example/ck_tile/10_rmsnorm2d/script/smoke_test.sh
--- a/example/ck_tile/11_add_rmsnorm2d_rdquant/CMakeLists.txt
+++ b/example/ck_tile/11_add_rmsnorm2d_rdquant/CMakeLists.txt
--- a/example/ck_tile/11_add_rmsnorm2d_rdquant/README.md
+++ b/example/ck_tile/11_add_rmsnorm2d_rdquant/README.md
--- a/example/ck_tile/11_add_rmsnorm2d_rdquant/add_rmsnorm2d_rdquant_fwd.cpp
+++ b/example/ck_tile/11_add_rmsnorm2d_rdquant/add_rmsnorm2d_rdquant_fwd.cpp
--- a/example/ck_tile/11_add_rmsnorm2d_rdquant/add_rmsnorm2d_rdquant_fwd.hpp
+++ b/example/ck_tile/11_add_rmsnorm2d_rdquant/add_rmsnorm2d_rdquant_fwd.hpp
--- a/example/ck_tile/11_add_rmsnorm2d_rdquant/example_add_rmsnorm2d_rdquant_fwd.cpp
+++ b/example/ck_tile/11_add_rmsnorm2d_rdquant/example_add_rmsnorm2d_rdquant_fwd.cpp
--- a/example/ck_tile/11_add_rmsnorm2d_rdquant/instances/add_rmsnorm2d_rdquant_fwd_api.cpp
+++ b/example/ck_tile/11_add_rmsnorm2d_rdquant/instances/add_rmsnorm2d_rdquant_fwd_api.cpp
--- a/example/ck_tile/11_add_rmsnorm2d_rdquant/instances/add_rmsnorm2d_rdquant_fwd_bf16_n1024_instance.cpp
+++ b/example/ck_tile/11_add_rmsnorm2d_rdquant/instances/add_rmsnorm2d_rdquant_fwd_bf16_n1024_instance.cpp
--- a/example/ck_tile/11_add_rmsnorm2d_rdquant/instances/add_rmsnorm2d_rdquant_fwd_bf16_n1536_instance.cpp
+++ b/example/ck_tile/11_add_rmsnorm2d_rdquant/instances/add_rmsnorm2d_rdquant_fwd_bf16_n1536_instance.cpp
--- a/example/ck_tile/11_add_rmsnorm2d_rdquant/instances/add_rmsnorm2d_rdquant_fwd_bf16_n2048_instance.cpp
+++ b/example/ck_tile/11_add_rmsnorm2d_rdquant/instances/add_rmsnorm2d_rdquant_fwd_bf16_n2048_instance.cpp
--- a/example/ck_tile/11_add_rmsnorm2d_rdquant/instances/add_rmsnorm2d_rdquant_fwd_bf16_n256_instance.cpp
+++ b/example/ck_tile/11_add_rmsnorm2d_rdquant/instances/add_rmsnorm2d_rdquant_fwd_bf16_n256_instance.cpp
--- a/example/ck_tile/11_add_rmsnorm2d_rdquant/instances/add_rmsnorm2d_rdquant_fwd_bf16_n3072_instance.cpp
+++ b/example/ck_tile/11_add_rmsnorm2d_rdquant/instances/add_rmsnorm2d_rdquant_fwd_bf16_n3072_instance.cpp
--- a/example/ck_tile/11_add_rmsnorm2d_rdquant/instances/add_rmsnorm2d_rdquant_fwd_bf16_n4096_instance.cpp
+++ b/example/ck_tile/11_add_rmsnorm2d_rdquant/instances/add_rmsnorm2d_rdquant_fwd_bf16_n4096_instance.cpp