GPT-5.6 found an Intel CPU microcode bug causing a performance regression

GPT-5.6 identified an Intel CPU microcode bug causing a performance regression, which was resolved by building with the -mbranches-within-32B-boundaries flag. The workaround slows conditional jumps straddling a 32-byte boundary, requiring specific program layout to restore speed.

Had a strange performance regression from a seemingly innocuous code change, and GPT-5.6 tracked it down to a microcode workaround for an Intel CPU bug. The workaround can make conditional jumps that straddle a 32-byte boundary much slower, so programs have to be laid out around it. Tried building with -mbranches-within-32B-boundaries and wouldn't you know it, we're fast again The future is so fucking cool