Topic
Concurrent overlap
About: Concurrent overlap is a research topic. Over the lifetime, 2 publications have been published within this topic receiving 72 citations.
Papers
Patent•
6 Jul 2018
TL;DR: In this paper, a server performance measuring method is proposed, which relates to the field of processor performance measurement, comprising a CPU, a Cache, an MSHR and a concurrent monitoring device, wherein the Cache is respectively connected with the CPU and the MSHR; the concurrent monitoring devices include a hit-hit concurrent access monitor, a Hit-miss concurrent Access Monitor and a miss-miss Concurrent Access Monitor.
Abstract: The invention discloses a server performance measuring method, and relates to the field of processor performance measurement, comprising a CPU, a Cache, an MSHR and a concurrent monitoring device, wherein the Cache is respectively connected with the CPU and the MSHR; the concurrent monitoring device is respectively connected with the Cache and the MSHR; The concurrent monitoring device includes aHit-Hit concurrent access monitor, a Hit-miss concurrent access monitor and a miss-miss concurrent access monitor. Put the corresponding overlap amount measured by the three concurrent access monitorsinto the formula: hit time HT+ (absence rate MR-three concurrent overlap amounts) *miss cost MP to calculate the actual server performance. By adopting the three cache concurrent access monitors added in the cache, the concurrent phenomena of hit and miss are measured, the cache concurrency condition is accurately analyzed, the concurrent overlap phenomenon is removed, the actual memory pause time is obtained in real time, and the server performance is accurately measured.
TL;DR: In this paper, the authors identify a similar sequential-type of processing overlap in prospective memory (ProM) situations and show that performance was higher when the ongoing task and the ProM task required the same kind of processing rather than different kinds of processing.
Abstract: Transfer appropriate processing (TAP) is the assumption that retrospective memory test performance reflects the overlap between study and test phase processing. In a task analysis, we identify a similar sequential-type of processing overlap in prospective memory (ProM) situations. In addition, ProM test performance can also involve a concurrent overlap between processes engaged for an ongoing task and those required for recognizing relevant cues. A review of the ProM literature shows consistent TAP effects due to sequential processing overlap manipulations, but inconclusive findings for concurrent processing overlap manipulations. We examined the latter in a new experiment with young adult participants. The ongoing task required either semantic or perceptual processing of words, and the ProM task required either semantic or perceptual processing of words. Consistent with TAP, performance was higher when the ongoing task and the ProM task required the same kind of processing (i.e. semantic–semantic, perceptual–perceptual) rather than different kinds of processing (i.e. semantic–perceptual, perceptual–semantic). Copyright © 2000 John Wiley & Sons, Ltd.
Related Topics (5)
Performance Metrics
| Year | Papers |
|---|---|
| 2018 | 1 |
| 2000 | 1 |