[llvm] [LV] Add support for partial reductions without a binary op (PR #133922)

[Florian Hahn via llvm-commits]

================
@@ -0,0 +1,826 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --check-globals none --filter-out-after "^scalar.ph:" --version 4
----------------
fhahn wrote:

what's the difference to llvm/test/Transforms/LoopVectorize/AArch64/partial-reduce-neon.ll? Just no dotprod feature? Would be good to have clearer name, in this test neon is also available?

https://github.com/llvm/llvm-project/pull/133922