Merge branch gfx950 into andriy/lwpck-2413

e941f59f · Andriy Roshchenko · fe9d9812 · 7da48908 · e941f59f · e941f59f
Commit e941f59f authored Nov 01, 2024 by Andriy Roshchenko
20 changed files
--- a/example/ck_tile/10_rmsnorm2d/instances/rmsnorm2d_fwd_bf16_n1536_instance.cpp
+++ b/example/ck_tile/10_rmsnorm2d/instances/rmsnorm2d_fwd_bf16_n1536_instance.cpp
--- a/example/ck_tile/10_rmsnorm2d/instances/rmsnorm2d_fwd_bf16_n2048_instance.cpp
+++ b/example/ck_tile/10_rmsnorm2d/instances/rmsnorm2d_fwd_bf16_n2048_instance.cpp
--- a/example/ck_tile/10_rmsnorm2d/instances/rmsnorm2d_fwd_bf16_n256_instance.cpp
+++ b/example/ck_tile/10_rmsnorm2d/instances/rmsnorm2d_fwd_bf16_n256_instance.cpp
--- 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/10_rmsnorm2d/instances/rmsnorm2d_fwd_bf16_n64_n128_instance.cpp
+++ b/example/ck_tile/10_rmsnorm2d/instances/rmsnorm2d_fwd_bf16_n64_n128_instance.cpp
--- a/example/ck_tile/10_rmsnorm2d/instances/rmsnorm2d_fwd_bf16_n768_instance.cpp
+++ b/example/ck_tile/10_rmsnorm2d/instances/rmsnorm2d_fwd_bf16_n768_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/10_rmsnorm2d/instances/rmsnorm2d_fwd_fp16_n256_instance.cpp
+++ b/example/ck_tile/10_rmsnorm2d/instances/rmsnorm2d_fwd_fp16_n256_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/10_rmsnorm2d/instances/rmsnorm2d_fwd_instance_common.hpp
+++ b/example/ck_tile/10_rmsnorm2d/instances/rmsnorm2d_fwd_instance_common.hpp