This Article 
 Bibliographic References 
 Add to: 
1999 International Symposium on Parallel Architectures, Algorithms and Networks (ISPAN '99)
A Decoupled Scheduled Dataflow Multithreaded Architecture
Fremantle, Australia
June 23-June 25
ISBN: 0-7695-0231-8
Krishna M. Kavi, University of Alabama in Huntsville
Hyong-Shik Kim, University of Alabama in Huntsville
Joseph Arul, University of Alabama in Huntsville
Ali R. Hurson, Pennsylvania State University
In this paper we propose a new approach to building multithreaded uniprocessors that become building blocks in high-end computing architectures. Our innovativeness stems from a multithreaded architecture with non-blocking threads where all memory accesses are decoupled from the thread execution. Data is pre-loaded into the thread context (registers), and all results are post-stored after the completion of the thread execution. The decoupling of memory accesses from thread execution requires a separate unit to perform the necessary pre-loads and post-stores, and to control the allocation of hardware thread contexts to enabled threads. This separation facilitates for achieving high locality and minimizing the impact of distribution and hierarchy in large memory systems. The non-blocking nature of threads eliminates the need for thread switching, thus improving the overhead in scheduling threads. The functional execution paradigm eliminates complex hardware required for scheduling instructions for modern superscalar architectures. We will present our preliminary results obtained from Monte Carlo simulations of the proposed architectural features.
Index Terms:
Multithreaded architecture, Dataflow architecture, Decoupling of memory access, Memory wall, Separate synchronization processor
Krishna M. Kavi, Hyong-Shik Kim, Joseph Arul, Ali R. Hurson, "A Decoupled Scheduled Dataflow Multithreaded Architecture," ispan, pp.138, 1999 International Symposium on Parallel Architectures, Algorithms and Networks (ISPAN '99), 1999
Usage of this product signifies your acceptance of the Terms of Use.