Towards Latency-aware DNN Optimization with GPU Runtime Analysis and Tail Effect Elimination.
Fuxun YuZirui XuTong ShenDimitrios StamoulisLongfei ShangguanDi WangRishi MadhokChunshui ZhaoXin LiNikolaos KarianakisDimitrios LymberopoulosAng LiChenchen LiuYiran ChenXiang ChenPublished in: CoRR (2020)