Dynamic performance tuning for speculative threads
نویسندگان
چکیده
منابع مشابه
Modeling and Optimization of Speculative Threads
Modeling and Optimization of Speculative Threads Tor M. Aamodt Doctor of Philosophy Department of Electrical and Computer Engineering University of Toronto 2006 This dissertation proposes a framework for modeling the control flow behavior of a program and the application of this framework to the optimization of speculative threads used for instruction and data prefetch. A novel form of helper t...
متن کاملSpeculative Distribution of Sub-Threads Across Processors
As multi-core architecture continues to dominate the development of new processor technology, effective utilization of processors has come to mean heavy parallelization inside of programs. However, some problems are simply not parallelizable, and these problems have been unable to make any real use of multi-core architecture. Recently, advances in algorithms used to understand the behavior of a...
متن کاملA Non-blocking Multithreaded Architecture with Support for Speculative Threads
In this paper we provide both a qualitative and a quantitative evaluation of a decoupled multithreaded architecture that uses non-blocking threads. Our architecture is based on simple in-order pipelines and complete decoupling of memory accesses from execution pipelines. We extend the architecture to support thread level speculation using snooping cache coherency protocols. We evaluate the perf...
متن کاملSupporting Large Speculative Threads for Databases and Beyond
Thread level speculation (TLS) has proven to be a promising method of extracting parallelismfrom both integer and scientific workloads. In this paper we use TLS to exploit intra-transactionparallelism in database workloads, and demonstrate that previous hardware support for TLS isinsufficient for the resulting large speculative threads (or epochs) and the complexity of the depen...
متن کاملA Performance and Power Evaluation of Speculative Dynamic Vectorization
With the end of Dennard scaling, processor clock frequencies are are no longer unbounded. Under such conditions, speculative approaches based on repetition of instructions in loops present an attractive solution to increase IPC. We consider two such approaches in this paper, speculative dynamic vectorization of all instructions, and speculative dynamic vectorization of loads only, based on load...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: ACM SIGARCH Computer Architecture News
سال: 2009
ISSN: 0163-5964
DOI: 10.1145/1555815.1555812