[llvm] Handle VECREDUCE intrinsics in NVPTX backend (PR #136253)

Durgadoss R via llvm-commits llvm-commits at lists.llvm.org
Mon Apr 21 15:58:13 PDT 2025


================
@@ -36,17 +36,19 @@ class FeaturePTX<int version>:
 
 foreach sm = [20, 21, 30, 32, 35, 37, 50, 52, 53,
               60, 61, 62, 70, 72, 75, 80, 86, 87,
-              89, 90, 100, 101, 120] in
----------------
durga4github wrote:

Yes, Artem, these are correct and expected to be available in the public docs soon..
(we will move these additions into a separate PR)

https://github.com/llvm/llvm-project/pull/136253


More information about the llvm-commits mailing list