Merge pull request #209 from ROCm/andriy/merge_from_public

Update develop branch from public repository

Merge pull request #209 from ROCm/andriy/merge_from_public
Update develop branch from public repository
7d50244e · Illia Silin · GitHub · f221c2b0 · d51701d4 · 7d50244e
Unverified Commit 7d50244e authored Oct 31, 2024 by Illia Silin Committed by GitHub Oct 31, 2024
20 changed files
--- a/example/ck_tile/10_rmsnorm2d/instances/rmsnorm2d_fwd_bf16_n3072_instance.cpp
+++ b/example/ck_tile/10_rmsnorm2d/instances/rmsnorm2d_fwd_bf16_n3072_instance.cpp
--- a/example/ck_tile/10_rmsnorm2d/instances/rmsnorm2d_fwd_bf16_n4096_instance.cpp
+++ b/example/ck_tile/10_rmsnorm2d/instances/rmsnorm2d_fwd_bf16_n4096_instance.cpp
--- a/example/ck_tile/10_rmsnorm2d/instances/rmsnorm2d_fwd_bf16_n4096_tp_instance.cpp
+++ b/example/ck_tile/10_rmsnorm2d/instances/rmsnorm2d_fwd_bf16_n4096_tp_instance.cpp
--- a/example/ck_tile/10_rmsnorm2d/instances/rmsnorm2d_fwd_bf16_n512_instance.cpp
+++ b/example/ck_tile/10_rmsnorm2d/instances/rmsnorm2d_fwd_bf16_n512_instance.cpp
--- a/example/ck_tile/02_layernorm2d/instances/layernorm2d_fwd_fp16_n256_instance.cpp
+++ b/example/ck_tile/02_layernorm2d/instances/layernorm2d_fwd_fp16_n256_instance.cpp
--- a/example/ck_tile/02_layernorm2d/instances/layernorm2d_fwd_bf16_n64_n128_instance.cpp
+++ b/example/ck_tile/02_layernorm2d/instances/layernorm2d_fwd_bf16_n64_n128_instance.cpp
--- a/example/ck_tile/10_rmsnorm2d/instances/rmsnorm2d_fwd_fp16_n1024_instance.cpp
+++ b/example/ck_tile/10_rmsnorm2d/instances/rmsnorm2d_fwd_fp16_n1024_instance.cpp
--- a/example/ck_tile/10_rmsnorm2d/instances/rmsnorm2d_fwd_fp16_n1536_instance.cpp
+++ b/example/ck_tile/10_rmsnorm2d/instances/rmsnorm2d_fwd_fp16_n1536_instance.cpp
--- a/example/ck_tile/10_rmsnorm2d/instances/rmsnorm2d_fwd_fp16_n2048_instance.cpp
+++ b/example/ck_tile/10_rmsnorm2d/instances/rmsnorm2d_fwd_fp16_n2048_instance.cpp
--- a/example/ck_tile/02_layernorm2d/instances/layernorm2d_fwd_bf16_n768_instance.cpp
+++ b/example/ck_tile/02_layernorm2d/instances/layernorm2d_fwd_bf16_n768_instance.cpp
--- a/example/ck_tile/10_rmsnorm2d/instances/rmsnorm2d_fwd_fp16_n3072_instance.cpp
+++ b/example/ck_tile/10_rmsnorm2d/instances/rmsnorm2d_fwd_fp16_n3072_instance.cpp
--- a/example/ck_tile/10_rmsnorm2d/instances/rmsnorm2d_fwd_fp16_n4096_instance.cpp
+++ b/example/ck_tile/10_rmsnorm2d/instances/rmsnorm2d_fwd_fp16_n4096_instance.cpp
--- a/example/ck_tile/10_rmsnorm2d/instances/rmsnorm2d_fwd_fp16_n4096_tp_instance.cpp
+++ b/example/ck_tile/10_rmsnorm2d/instances/rmsnorm2d_fwd_fp16_n4096_tp_instance.cpp
--- 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/02_layernorm2d/instances/layernorm2d_fwd_instance_common.hpp
+++ b/example/ck_tile/02_layernorm2d/instances/layernorm2d_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