Speculative multithreading

From Wikipedia, the free encyclopedia

This is an old revision of this page, as edited by 149.170.117.182 (talk) at 17:09, 16 March 2018. The present address (URL) is a permanent link to this revision, which may differ significantly from the current revision.

Thread Level Speculation (TLS), also known as Speculative Multithreading (SpMT) is a runtime parallelization technique which uncovers parallelism that static (compile-time) parallelization techniques fail to exploit. This particular case of speculative execution occurs at the thread level as opposed to the instruction level and can be implemented both in hardware as well as in software.

Further reading

  • Yiapanis, Paraskevas; Brown, Gavin; Lujan, Mikel (2016). "Compiler-Driven Software Speculation for Thread-Level Parallelism". ACM Transactions on Programming Languages and Systems (TOPLAS). 38 (2). doi:10.1145/2821505.