Int. J. High Speed Comput.最新文献_第4页

Non-Sequential Instruction Cache Prefetching for Multiple-Issue Processors 多问题处理器的非顺序指令缓存预取

Int. J. High Speed Comput. Pub Date : 1999-03-01 DOI: 10.1142/S0129053399000065

A. Veidenbaum, Qing Zhao, Abduhl Shameer

{"title":"Non-Sequential Instruction Cache Prefetching for Multiple-Issue Processors","authors":"A. Veidenbaum, Qing Zhao, Abduhl Shameer","doi":"10.1142/S0129053399000065","DOIUrl":"https://doi.org/10.1142/S0129053399000065","url":null,"abstract":"This paper presents a novel instruction cache prefetching mechanism for multiple-issue processors. Such processors at high clock rates often have to use a small instruction cache which can have significant miss rates. Prefetching from secondary cache or even memory can hide the instruction cache miss penalties, but only if initiated sufficiently far ahead of the current program counter. Existing instruction cache prefetching methods are strictly sequential and do not prefetch past conditional branches which may occur almost every clock cycle in wide-issue processors. In this study, multi-level branch prediction is used to overcome this limitation. By keeping branch history and target addresses, two methods are defined to predict a future PC several branches past the current branch. A prefetching architecture using such a mechanism is defined and evaluated with respect to its accuracy, the impact of the instruction prefetching on performance, and its interaction with sequential prefetching. Both PC-based and history-based predictors are used to perform a single-lookup prediction. Targeting an on-chip L2 cache with low latency, prediction for 3 branch levels is evaluated for a 4-issue processor and cache architecture patterned after the DEC Alpha-21164. It is shown that history-based predictor is more accurate, but both predictors are effective. The prefetching unit using them can be effective and succeeds when the sequential prefetcher fails. In addition, non-sequential prefetching is better at hiding latency due to earlier initiation. The two types of prefetching eliminate different types of misses and thus can be effectively combined to achieve better performance.","PeriodicalId":270006,"journal":{"name":"Int. J. High Speed Comput.","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1999-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125918655","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 11

Grouping Memory Consistency Model for Parallel-Multithreaded Shared-Memory Multiprocessor Systems 并行多线程共享内存多处理器系统的分组内存一致性模型

Int. J. High Speed Comput. Pub Date : 1999-03-01 DOI: 10.1142/S0129053399000041

Chao-Chin Wu, Cheng Chen

引用次数: 1

Fault-Tolerant Characteristics and Topological Properties of a Hierarchical Network of Hypercubes 超立方体分层网络的容错特性和拓扑性质

Int. J. High Speed Comput. Pub Date : 1999-03-01 DOI: 10.1142/S0129053399000028

A. Jayadevan, L. Patnaik

引用次数: 4

Scalability of Sparse Cholesky Factorization 稀疏Cholesky分解的可扩展性

Int. J. High Speed Comput. Pub Date : 1999-03-01 DOI: 10.1142/S012905339900003X

T. Rauber, G. Rünger, C. Scholtes

引用次数: 2

An Improved Mapping of Cyclic Elimination onto Hypercubes Using Data Replication 基于数据复制的循环消去到超立方体的改进映射

Int. J. High Speed Comput. Pub Date : 1997-12-01 DOI: 10.1142/S0129053397000180

Kartik Gopalan, C. Murthy

引用次数: 1

New Parallel Algorithms for Direct Solution of Sparse Linear Systems: Part I - Symmetric Coefficient Matrix 稀疏线性系统直接解的新并行算法:第一部分——对称系数矩阵

Int. J. High Speed Comput. Pub Date : 1997-12-01 DOI: 10.1142/S0129053397000167

Kartik Gopalan, C. Murthy

引用次数: 0

Dynamic Load Distribution on Meshes with Broadcasting 广播网格的动态负载分配

Int. J. High Speed Comput. Pub Date : 1997-12-01 DOI: 10.1142/S0129053397000192

W. Lee, S. Hong, Jong Kim

引用次数: 2

Efficient Multicast on Wormhole Switch-Based Nowp 基于虫洞交换机的高效组播技术

Int. J. High Speed Comput. Pub Date : 1997-12-01 DOI: 10.1142/S0129053397000209

Kuo-Pao Fan, C. King

引用次数: 1

Mapping Pipelined Divided-difference Computations into Hypercubes 将管道差分计算映射到超立方体

Int. J. High Speed Comput. Pub Date : 1997-09-01 DOI: 10.1142/S012905339700012X

K. Chung, Yu-Wei Chen

引用次数: 0

Two Real-Time Flow Controls in Wormhole Networks 虫洞网络中的两种实时流量控制

Int. J. High Speed Comput. Pub Date : 1997-09-01 DOI: 10.1142/S0129053397000155

Hyojeong Song, Boseob Kwon, Ji-Yun Kim, H. Yoon

引用次数: 1