[llvm] LSV: document hang reported in #37865 (PR #102479)

Matt Arsenault via llvm-commits llvm-commits at lists.llvm.org
Thu Aug 8 10:31:47 PDT 2024


================
@@ -0,0 +1,14 @@
+; REQUIRES: asserts
+; RUN: not --crash opt -mtriple=aarch64 -passes=load-store-vectorizer -disable-output %s
+
+define i32 @load_cycle(ptr %x) {
+; CHECK: Unexpected cycle while re-ordering instructions
+entry:
+  %gep.x.1 = getelementptr inbounds [2 x i32], ptr %x, i32 0, i32 1
+  %load.x.1 = load i32, ptr %gep.x.1
+  %rem = urem i32 %load.x.1, 1
+  %gep.x.2 = getelementptr inbounds [2 x i32], ptr %x, i32 %rem, i32 0
----------------
arsenm wrote:

I think this just failed to check that one of the vectorization pointer candidates actually depends on the other load, so these shouldn't be vectorization candidates 

https://github.com/llvm/llvm-project/pull/102479


More information about the llvm-commits mailing list