[r16-6988 Regression] FAIL: gcc.dg/vect/costmodel/x86_64/costmodel-vect-epil-1.c scan-tree-dump vect "optimized: loop vectorized using 64 byte vectors" on Linux/x86_64
Haochen Jiang <[email protected]>
| Newsgroups | gmane.comp.gcc.patches,gmane.comp.gcc.regression |
|---|---|
| Message-ID | <[email protected]> |
On Linux/x86_64, 523b01b022f74f73f0e20a40950536c06f538910 is the first bad commit commit 523b01b022f74f73f0e20a40950536c06f538910 Author: Richard Biener <[email protected]> Date: Thu Jan 22 14:06:50 2026 +0100 Avoid selecting masked epilogs for in-order reduction vectorization caused FAIL: gcc.dg/vect/costmodel/x86_64/costmodel-vect-epil-1.c scan-tree-dump vect "optimized: epilogue loop vectorized using 32 byte vectors" FAIL: gcc.dg/vect/costmodel/x86_64/costmodel-vect-epil-1.c scan-tree-dump vect "optimized: loop vectorized using 64 byte vectors" with GCC configured with ../../gcc/configure --prefix=/export/users3/haochenj/src/gcc-bisect/master/master/r16-6988/usr --enable-clocale=gnu --with-system-zlib --with-demangler-in-ld --with-fpmath=sse --enable-languages=c,c++,fortran --enable-cet --without-isl --enable-libmpx x86_64-linux --disable-bootstrap To reproduce: $ cd {build_dir}/gcc && make check RUNTESTFLAGS="x86_64-costmodel-vect.exp=gcc.dg/vect/costmodel/x86_64/costmodel-vect-epil-1.c --target_board='unix{-m64\ -march=cascadelake}'" (Please directly reply to this email for question about this report.) (If you met problems with cascadelake related, disabling AVX512F in command line might save that.) (However, please make sure that there is no potential problems with AVX512.)