https://gcc.gnu.org/bugzilla/show_bug.cgi?id=125800
--- Comment #5 from Zhongyao Chen <chenzhongyao.hit at gmail dot com> --- Created attachment 64824 --> https://gcc.gnu.org/bugzilla/attachment.cgi?id=64824&action=edit patch for test Hi Josef, I suspect the SubMtx function in CalculiX is the issue. It seems to generate very bad vectorized code, maybe because the upthread swappable condition in my commit is too loose. I attached a small patch only for test. Could you help run a performance test and see if it fixes this issue?
