https://gcc.gnu.org/bugzilla/show_bug.cgi?id=121767
Bug ID: 121767
Summary: [16 Regression] Vectorizer ICE at
tree-vect-slp.cc:2857
Product: gcc
Version: 16.0
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: tree-optimization
Assignee: unassigned at gcc dot gnu.org
Reporter: dhruvc at nvidia dot com
Target Milestone: ---
Created attachment 62291
--> https://gcc.gnu.org/bugzilla/attachment.cgi?id=62291&action=edit
Min-repro from creduce
Compile flags: -O2 -mcpu=neoverse-v2
This is likely occurring due to r16-3488-gb3355804c7054b which introduced this
code (started two days ago).
Min repro attached, reduced from Kokkos (https://github.com/kokkos/kokkos),
file TestSerial_AtomicOperations_int.cpp.
