论文标题
SRSP：gpularda asimetrik senkronizasyon icin yeni olceklenebilir bir cozum
sRSP: GPUlarda Asimetrik Senkronizasyon Icin Yeni Olceklenebilir Bir Cozum
论文作者
论文摘要
不对称共享是一个动态共享模型，该模型在该模型中大量访问了（本地）共享者，而其他（远程）共享者很少访问。在GPU上，没有特殊支持，不对称共享需要在每个访问中大量加载同步。随着远程范围促销（RSP）的引入，轻巧同步允许对本地共享者访问，而重量同步仅用于远程访问很少需要的远程访问。 RSP通过在远程访问上促进本地同步来确保数据一致性。不幸的是，RSP的第一个实现不是可扩展的解决方案。我们提供更有效，可扩展的RSP实现。我们称为SRSP的新设计基于对本地共享者的监视和重量同步操作的选择性执行。我们使用时间播的GEM5-APU模拟器评估了SRSP，结果表明，SRSP在64个计算单元GPU上平均提高了29％的性能。
Asymmetric sharing is a dynamic sharing model, where a shared data is heavily accessed by a (local) sharer, and rarely accessed by other (remote) sharers. On GPUs, without special support, asymmetric sharing requires heavily loaded synchronization on every access. With the introduction of Remote Scope Promotion (RSP), access to the local sharer is allowed with lightweight synchronization, while heavyweight synchronization is only used for remote accesses where it is rarely needed. RSP ensures data consistency by promoting local synchronizations on remote accesses. Unfortunately, the first implementation of RSP is not a scalable solution. We offer a more efficient and scalable RSP implementation. This new design, which we call sRSP, is based on the monitoring of the local sharer and the selective execution of heavyweight synchronization operations. We evaluated the sRSP with the time-detailed Gem5-APU simulator and the results show that the sRSP improves performance by an average of 29 percent on a 64 Compute Unit GPU.
