A Burst Scheduling Access Reordering Mechanism
- 1 January 2007
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 285-294
- https://doi.org/10.1109/hpca.2007.346206
Abstract
Utilizing the nonuniform latencies of SDRAM devices, access reordering mechanisms alter the sequence of main memory access streams to reduce the observed access latency. Using a revised M5 simulator with an accurate SDRAM module, the burst scheduling access reordering mechanism is proposed and compared to conventional in order memory scheduling as well as existing academic and industrial access reordering mechanisms. With burst scheduling, memory accesses to the same rows of the same banks are clustered into bursts to maximize bus utilization of the SDRAM device. Subject to a static threshold, memory reads are allowed to preempt ongoing writes for reduced read latency, while qualified writes are piggybacked at the end of bursts to exploit row locality in writes and prevent write queue saturation. Performance improvements contributed by read preemption and write piggybacking are identified. Simulation results show that burst scheduling reduces the average execution time of selected SPEC CPU2000 benchmarks by 21% over conventional bank in order memory scheduling. Burst scheduling also outperforms Intel's patented out of order memory scheduling and the row hit access reordering mechanism by 11% and 6% respectivelyKeywords
This publication has 10 references indexed in Scilit:
- Adaptive History-Based Memory Schedulers for Modern ProcessorsIEEE Micro, 2006
- Memory Controller Optimizations for Web ServersPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- The bit-reversal SDRAM address mappingPublished by Association for Computing Machinery (ACM) ,2005
- Efficient use of memory bandwidth to improve network processor throughputPublished by Association for Computing Machinery (ACM) ,2003
- Design issues and tradeoffs for write buffersPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Reducing DRAM latencies with an integrated memory hierarchy designPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- High-performance DRAMs in workstation environmentsIEEE Transactions on Computers, 2001
- A permutation-based page interleaving scheme to reduce row-buffer conflicts and exploit data localityPublished by Association for Computing Machinery (ACM) ,2000
- Dynamic access ordering for streamed computationsIEEE Transactions on Computers, 2000
- Hitting the memory wallACM SIGARCH Computer Architecture News, 1995