High-performance out-of-order processors spend a significant portion of their execution time on the incorrect program path even though they employ aggressive branch pre-diction algorithms. Although memory references generated on the wrong path do not change the architectural state of the processor, they can affect the arrangement of data in the memory hierarchy. This paper examines the effects of wrong-path memory references on processor performance. It is shown that these references significantly affect the IPC (Instructions Per Cycle) performance of a processor.
Did you find this white paper useful?
28 out of 50 users found this white paper useful
Related white papers
Understanding USB Flash Drives as Portable Infrastructure
The purpose of this white paper is to briefly discuss seven important topics everyone in business needs to know about USB flash drives. More importantly, this white paper is meant...
TMS320C6000 EMIF: Overview of Support of High Performance Memory Technology
This document gives an overview of the memory technologies currently available in the semiconductor industry. It highlights the tradeoffs in memory selection in a TMS320C6000™ External Memory Interface (EMIF) based...
Performance Comparison: Intel® Itanium® 2-Based Servers Running SAS 9
The Cornell Institute for Social and Economic Research (CISER) set out to increase the performance of some of its processing- and memory-intensive SAS applications. CISER had to acquire the...
Memory Technology Evolution
The purpose of this paper is to discuss the evolution of main and graphics memory technologies in relation to Compaq products. This paper should help alleviate some of the confusion surrounding the...
The Price of Safety: Evaluating IOMMU Performance
IOMMUs, IO Memory Management Units, are hardware devices that translate device DMA addresses to machine addresses. An isolation capable IOMMU restricts a device so that it can only access parts...
Cache Filtering Techniques to Reduce the Negative Impact of Useless Speculative Memory References on Processor Performance
High-performance processors employ aggressive speculation and prefetching techniques to increase performance. Speculative memory references caused by these techniques sometimes bring data into the caches that are not needed by correct...
Efficient Runahead Execution: Power-Efficient Memory Latency Tolerance
Runahead execution improves memory latency tolerance without significantly increasing processor complexity. Unfortunately, a runahead execution processor executes significantly more instructions than a conventional processor, sometimes without providing any performance benefit,...
