llvmorg-github-actions[bot] wrote:

<!--LLVM PR SUMMARY COMMENT-->

@llvm/pr-subscribers-offload

Author: Robert Imschweiler (ro-i)

<details>
<summary>Changes</summary>

The default cross-team reduction algorithm benefits from larger and fewer 
teams. Implement that by using 2 x the default number of threads and 1/2 x the 
default number of teams for reduction kernels.  This doesn't change the default 
total number of threads, it just redistributes them.

This is a first, rather simple heuristic, derived from (a subset of) what AOMP 
does.
The performance benefits I observed for the reduction tests in 
https://github.com/ro-i/xteam-test on a gfx942
(c71339705091500f731e2a39f247d2660bacbdce) are up to a few percent, with no 
regressions.

Claude assisted with this patch.

---
Full diff: https://github.com/llvm/llvm-project/pull/208253.diff


3 Files Affected:

- (modified) clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp (+22) 
- (modified) offload/plugins-nextgen/common/include/PluginInterface.h (+5) 
- (modified) offload/plugins-nextgen/common/src/PluginInterface.cpp (+22-4) 


``````````diff
The server is unavailable at this time. Please wait a few minutes before you 
try again.
``````````

</details>


https://github.com/llvm/llvm-project/pull/208253
_______________________________________________
cfe-commits mailing list
[email protected]
https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits

Reply via email to