Skip to content

GitLab

"src/include/gridwise_convolution_wrapper.hpp" did not exist on "0b41ca2d9e20ad41dc522942aaffb2ebc8ef9b92"
Unverified Commit 11e4082d authored by Bartłomiej Kocot's avatar Bartłomiej Kocot Committed by GitHub
Browse files

Fix duplication of pk_add_f16 symbols (#1858)

parent 9ee69dd2
Hide whitespace changes
Inline Side-by-side
Showing with 2 additions and 2 deletions
include/ck_tile/core/numeric/vector_type.hpp
View file @ 11e4082d
...@@ -200,7 +200,7 @@ using bf8x32_t = bf8_t __attribute((ext_vector_type(32))); ...@@ -200,7 +200,7 @@ using bf8x32_t = bf8_t __attribute((ext_vector_type(32)));
using bf8x64_t = bf8_t __attribute((ext_vector_type(64))); using bf8x64_t = bf8_t __attribute((ext_vector_type(64)));
#endif #endif
__host__ fp16x2_t pk_add_f16(const fp16x2_t& x, const fp16x2_t& y) CK_TILE_HOST fp16x2_t pk_add_f16(const fp16x2_t& x, const fp16x2_t& y)
{ {
fp16x2_t vector_res; fp16x2_t vector_res;
...@@ -210,7 +210,7 @@ __host__ fp16x2_t pk_add_f16(const fp16x2_t& x, const fp16x2_t& y) ...@@ -210,7 +210,7 @@ __host__ fp16x2_t pk_add_f16(const fp16x2_t& x, const fp16x2_t& y)
return vector_res; return vector_res;
} }
__device__ fp16x2_t pk_add_f16(const fp16x2_t& x, const fp16x2_t& y) CK_TILE_DEVICE fp16x2_t pk_add_f16(const fp16x2_t& x, const fp16x2_t& y)
{ {
fp16x2_t c; fp16x2_t c;
asm volatile("v_pk_add_f16 %0, %1, %2" : "=v"(c) : "v"(x), "v"(y)); asm volatile("v_pk_add_f16 %0, %1, %2" : "=v"(c) : "v"(x), "v"(y));
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment