https://gcc.gnu.org/bugzilla/show_bug.cgi?id=95341
--- Comment #3 from rsandifo at gcc dot gnu.org <rsandifo at gcc dot gnu.org> --- (In reply to ktkachov from comment #2) > Interestingly, -msve-vector-bits gives good codegen for 128, 256, 512 but > bad for 1024, 2048 and VLA code That's because addition is the one operation that we currently support on unpacked vectors. For subtraction it's a different story (just 128-bit and 256-bit is good, as expected). But the surprising thing for me was that we didn't fall back to Advanced SIMD in VLA mode...
