Merge branch 'develop' into codegen-enable-hiprtc

c2cf0733 · Po Yen Chen · GitHub · 7643c909 · c3a4800c · c2cf0733
Unverified Commit c2cf0733 authored Oct 31, 2024 by Po Yen Chen Committed by GitHub Oct 31, 2024
20 changed files
--- 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/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