[llvm] [LoopVectorize] Improve Vectorization of Low Trip Count Loops (PR #195823)

Jack Styles via llvm-commits llvm-commits at lists.llvm.org
Wed Jul 29 03:38:07 PDT 2026


================
@@ -711,6 +711,12 @@ AArch64TTIImpl::getIntrinsicInstrCost(const IntrinsicCostAttributes &ICA,
                                         MVT::nxv16i8, MVT::nxv8i16, MVT::nxv4i32,
                                         MVT::nxv2i64};
     auto LT = getTypeLegalizationCost(RetTy);
+    // Type promotion for v2i8 and v2i16 types have a heavy cost when vectorising.
----------------
Stylie777 wrote:

I've also added supporting benchmark test cases in https://github.com/llvm/llvm-test-suite/pull/404/changes/9b20f3d6c275ef73e2ce0d0c9afbe50aade4d4f8

https://github.com/llvm/llvm-project/pull/195823


More information about the llvm-commits mailing list