NobleBlocks
Public

Thread-level speculation with kernel support

Published • Mar 14, 2016
NobleIDNI8P07W04R55S40
Authors:
Clemens Hammacher
,
Kevin Streit
,
Andreas Zeller

Abstract

Runtime systems for speculative parallelization can be substantially sped up by implementing them with kernel support. We describe a novel implementation of a thread-level speculation (TLS) system using virtual memory to isolate speculative state, implemented in a Linux kernel module. This design ch...

Finding related papers...

Discussions

(0)

No comments yet

Be the first to share your thoughts!