ncnn Bad performance for int8 inference on XuanTie 906 (RISC-V)

57hvy0tb  于 3个月前  发布在  其他
关注(0)|答案(1)|浏览(46)

detail | 详细描述 | 詳細な説明

I was wondering if maybe anyone knows or might have an idea as to why the inference time on the XuanTie 906 (RISC-V) processor is so slow for int8 models?
The image can easily be reproduced by running the NCNN benchmark on the Alwinner D1 (1x XuanTie 906). The displayed numbers are the runtimes in milliseconds.

Thanks!

s1ag04yj

s1ag04yj1#

Currently ncnn lacks good optimization for int8 models using risc-v and rvv

You may be interested in contributions here
rv2036#2

相关问题