Linear scan register allocation
ACM Transactions on Programming Languages and Systems (TOPLAS)
Dynamo: a transparent dynamic optimization system
PLDI '00 Proceedings of the ACM SIGPLAN 2000 conference on Programming language design and implementation
FX!32: A Profile-Directed Binary Translator
IEEE Micro
The Performance of Runtime Data Cache Prefetching in a Dynamic Optimization System
Proceedings of the 36th annual IEEE/ACM International Symposium on Microarchitecture
Proceedings of the 36th annual IEEE/ACM International Symposium on Microarchitecture
An Event-Driven Multithreaded Dynamic Optimization Framework
Proceedings of the 14th International Conference on Parallel Architectures and Compilation Techniques
QEMU, a fast and portable dynamic translator
ATEC '05 Proceedings of the annual conference on USENIX Annual Technical Conference
Evaluating Indirect Branch Handling Mechanisms in Software Dynamic Translation Systems
Proceedings of the International Symposium on Code Generation and Optimization
Operating Systems: Internals and Design Principles
Operating Systems: Internals and Design Principles
StarDBT: an efficient multi-platform dynamic binary translation system
ACSAC'07 Proceedings of the 12th Asia-Pacific conference on Advances in Computer Systems Architecture
Hi-index | 0.00 |
Conventional optimization algorithms which are widely used in static compiler--including peephole, instruction selection, Graph coloring register allocation, and so on--cannot be effectively implemented in DBT (Dynamic Binary Translation) system since they bring too much overhead in run time.MTCrossBit is an experimental-multithreaded DBT optimization framework which utilizes an extra thread for building hot traces to test whether we can eliminate the overhead extremely caused by the algorithm itself. To make a better performance, a new threads' communication mechanism that we call ASLC is presented. According to the test results of SPECInt2000, we achieved some success using concurrent architecture as mentioned previously. In this paper, we illustrated that multithreaded dynamic optimization framework is an effective way to speed up DBT systems with a quantitative example.