Is memory a bottleneck in matrix addition (SIMD Instructions)?

后端 未结 0 1196
小鲜肉
小鲜肉 2020-11-22 05:59

I\'m trying to optimize 2d matrix addition in C using SIMD instructions (_mm256_add_pd, store, load, etc.). However, I\'m not seeing a large speedup at all. Using some timin

相关标签:
回答
  • 消灭零回复
提交回复
热议问题