ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-04-20 14:59:17 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add basic support for direct loads from global to LDS (#999)

Browse Source 
* Add basic support for direct loads from global to LDS

* Clean the code and comments

* Add support for fp16

* Add comments

* Add check for thread cluster lengths

* Align non-direct-load fp16 example

* Small fixes

* Extend IsSupported to check for supported GPU gens

* Build examples only on the supported HW

* Do not throw when instance not supported in 04 example

* Review: Apply review suggestions

* Review: small fix

* Review: small fix
This commit is contained in:
Bartlomiej Wroblewski
2023-11-25 13:35:22 +01:00
committed by GitHub
parent e8cddfdc3b
commit 627054b941
23 changed files with 2783 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
include/ck/host_utility/device_prop.hpp
View File

@@ -58,4 +58,11 @@ inline bool is_xdl_supported()
ck::get_device_name() == "gfx942";
}
inline bool is_lds_direct_load_supported()
{
// Check if direct loads from global memory to LDS are supported.
return ck::get_device_name() == "gfx90a" || ck::get_device_name() == "gfx940" ||
ck::get_device_name() == "gfx941" || ck::get_device_name() == "gfx942";
}
} // namespace ck