首页> 外文期刊>IEEE transactions on very large scale integration (VLSI) systems >A separated bit-line unified cache: Conciliating small on-chipcache die-area and low miss ratio
【24h】

A separated bit-line unified cache: Conciliating small on-chipcache die-area and low miss ratio

机译:分离的位线统一高速缓存:协调小的片上高速缓存裸片区域和低丢失率

获取原文
获取原文并翻译 | 示例

摘要

This paper describes an on-chip cache, called a separated bit-linenunified cache, which minimizes the chip-area cost in high-performancenmicroprocessors. This unified cache has two ports; one for theninstruction bus and the other for the data bus. A separated bit-linenmemory hierarchy architecture realizes memory hierarchy design with onlyn10%-20% area overhead. The total cache area can be reduced by more thann20%-30% on the average at capacities of larger than 64 KB with the samenhit rate as the conventional cache. The cache latency reaches 4.2 ns atna supply voltage of 1 V. Additionally, the cache is physicallynaddressable even if the cache has a large capacity
机译:本文介绍了一种片上高速缓存,称为分离的位线统一高速缓存,它可以最大程度地降低高性能微处理器的芯片面积成本。这个统一的缓存有两个端口。一个用于指令总线,另一个用于数据总线。分离的位线内存层次结构实现了仅10%-20%的区域开销的内存层次设计。在大于64 KB的容量下,平均总缓存区域平均可减少n20%-30%以上,并且具有与常规缓存相同的命中率。在1 V的电源电压下,缓存延迟达到4.2 ns。此外,即使缓存容量较大,缓存在物理上也无法寻址

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号