J. Wang and R. W. Quong. The feasibility of using compression to increase memory system performance. In MASCOTS, pages 107--113, 1994. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
The Feasibility of Using Compression to Increase Memory System.. - Wang, Quong (1994) (1 citation) Self-citation (Wang) (Correct)
....is favorable. Because M i Gamma1 0 and M i Gamma1 is independent of compression, the only difference between the approaches is t i and i . Equation 2 indicates that t i is a function of h i , m i , and t i 1 , giving a recursive dependence down to level n. We use the following lemmas [10] to simplify the recurrence relation. Lemma 1 : m Lemma 2 : t j = t From Lemmas 1 and 2, the difference between t and t i relies only on (i) the compression ratio at the i th level, ii) the miss ratio at the i th level for compression and non compression approaches, and (iii) the ....
....is directly proportional to m i , the miss rate at level i, and t i 1 , the access time of level i 1. For example, if m i or t i 1 doubles, dmax is doubled. 3.2. 2 Case studies of memory systems Compression at the L1 cache is not feasible because of the limited decompression time is allowed[10]. At the other extreme, compression at secondary storage cannot improve memory performance because we cannot reduce the miss rate, since accesses to this level never miss. A general analysis. Figure 4 shows the maximum allowed decompression delay if compression is to be effective. Points on the ....
Wang, J-L, Quong, R. W., The Feasibility of Using Compression to Increase Memory System Performance. TR-EE-93-37, Purdue University, 1993.
Expected I-Cache Miss Rates via the Gap Model - Quong (1994) (12 citations) Self-citation (Quong) (Correct)
....be answered relatively easily and with reasonable accuracy. It is ideally suited for evaluating the relative difference between two designs. For example, our model can predict the effect on the miss rate of changing the program size, say, due to procedure inlining [5] 8] 9] or due to compression [17]. The numbers gathered by the gap model provide insight into why various misses are occurring. In particular, our model clearly indicates whether cache misses are compulsory, conflict and capacity [6] 7] Our model also shows which basic blocks are likely to account for many cache misses. 1.4 ....
Jenlong Wang and Russell W. Quong. The Feasibility of Using Compression to Increase Memory System Performance. In International Workshop on Modeling, Analysis and Simulation of Computer and Telecommunications Systems --- MASCOTS 1994.
Selective Main Memory Compression by Identifying Program Phase .. - Nakar, Weiss (2004) (Correct)
No context found.
J. Wang and R. W. Quong. The feasibility of using compression to increase memory system performance. In MASCOTS, pages 107--113, 1994.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC