Speculative reconvergence for improved SIMT efficiency
Speculative reconvergence for improved SIMT efficiency
复制标题
推测再收敛以提高 SIMT 效率
DOI：
10.1145/3368826.3377911
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
Olivier Giroux
中科院分区：
文献类型：
--
作者：
S. Damani;Daniel R. Johnson;M. Stephenson;S. Keckler;Eddie Q. Yan;Michael McKeown;Olivier Giroux
GPU最有效地执行扭曲中的所有线程，但是，当扭曲中的线程遇到不同的指令。预计最终会执行给定的代码段，但并非所有线程都同时到达，从而导致序列化执行通用代码诸如函数呼叫和循环范围之类的子序列是通过在允许执行过程中执行共同代码的线程来促进融合。提高SIMT效率并提高性能的融合机会。 SIMT效率和性能中的3倍。
GPUs perform most efficiently when all threads in a warp execute the same sequence of instructions convergently. However, when threads in a warp encounter a divergent branch, the hardware serializes the execution of diverged paths. We consider a class of convergence opportunities wherein multiple threads are expected to eventually execute a given segment of code, but not all threads arrive at the same time, resulting in serialized duplicate execution of common code subsequences such as function calls and loop bodies. Our goal is to promote convergence by helping threads that execute common code arrive together before allowing execution to proceed. We propose a new user-guided compiler mechanism, Speculative Reconvergence, to help identify and exploit previously untapped convergence opportunities that increase SIMT efficiency and improve performance. For the set of workloads we study, we see improvements ranging from 10% to 3× in both SIMT efficiency and in performance.
影响因子：
3.5
作者：
Ma, CM;Li, JS;Brain, S
通讯作者：
Brain, S