Optimizing Reaching Definitions Overhead in Queue Processors

Optimizing Reaching Definitions Overhead in Queue Processors
复制标题

DOI:
--
复制
发表时间:
2007
期刊:
J. Convergence Inf. Technol.
影响因子:
--
通讯作者:
Y. Nakanishi;A. Canedo;B. Abderazek;M. Sowa
Y. Nakanishi;A. Canedo;B. Abderazek;M. Sowa
中科院分区:
其他
文献类型:
--
作者:
Y. Nakanishi;A. Canedo;B. Abderazek;M. Sowa

文献摘要

相似文献

队列计算机是嵌入式系统设计的可行选择。队列计算机具有指令集密集、并行性高、硬件复杂度低的特点。在本文中,我们提出了一种优化技术来减少队列处理器中变量的长期定义的开销。长距离定义与处理器的队列寄存器文件利用率有直接关系,也与指令集中保留给参考操作数的位有直接关系。使用整数和嵌入式基准,我们证明我们的技术有效地将达到定义的时间缩短了 90%。
Queue computers are a viable option for embedded systems design. Queue computers feature a dense instruction set, high parallelism, low hardware complexity. In this paper we propose an optimization technique to reduce the overhead of long reaching definitions of variables in queue processors. Long reaching definitions have direct relationship with the queue register file utilization of the processor, and also to the bits in the instruction set reserved to reference operands. Using integer and embedded benchmarks, we demonstrate that our technique effectively reduces the length of reaching definitions up to 90%.