+ vsetvli t0, a2, e8, m2, tu, ma + vle8.v v0, (a0) + sub a2, a2, t0 + vsetvli zero, t0, e16, m4, tu, ma + vle16.v v8, (a1) + vsetvli zero, t0, e8, m2, tu, ma + vwsub.wv v16, v8, v0 + vsetvli zero, t0, e16, m4, tu, ma
It looks to me like the second vsetvli is unnecessary, and consequently the third as well. As for the later ones, please use `vsetvli zero, zero` if you intend to change SEW while preserving VL and the LMUL:SEW ratio. -- 雷米‧德尼-库尔蒙 http://www.remlab.net/ _______________________________________________ ffmpeg-devel mailing list ffmpeg-devel@ffmpeg.org https://ffmpeg.org/mailman/listinfo/ffmpeg-devel To unsubscribe, visit link above, or email ffmpeg-devel-requ...@ffmpeg.org with subject "unsubscribe".