1996
DOI: 10.1145/248155.238773
|View full text |Cite
|
Sign up to set email alerts
|

Studies of Windows NT performance using dynamic execution traces

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
2

Citation Types

0
22
0

Year Published

1997
1997
2000
2000

Publication Types

Select...
5
3

Relationship

0
8

Authors

Journals

citations
Cited by 19 publications
(22 citation statements)
references
References 0 publications
0
22
0
Order By: Relevance
“…We have observed that the I/O problem has indeed been addressed in modern database engines, and that memory system performance is already the main bottleneck. Perl and Sites [14] study Microsoft SQL Server performance on an Alpha-based Windows NT server through trace-driven simulation. They claim that OLTP performance is mostly limited by chip pin bandwidth, since the bandwidth that would be required to maintain a CPI of 1 in the Alpha 21164 would be much greater than what is available in that processor.…”
Section: Related Workmentioning
confidence: 99%
See 1 more Smart Citation
“…We have observed that the I/O problem has indeed been addressed in modern database engines, and that memory system performance is already the main bottleneck. Perl and Sites [14] study Microsoft SQL Server performance on an Alpha-based Windows NT server through trace-driven simulation. They claim that OLTP performance is mostly limited by chip pin bandwidth, since the bandwidth that would be required to maintain a CPI of 1 in the Alpha 21164 would be much greater than what is available in that processor.…”
Section: Related Workmentioning
confidence: 99%
“…Yet, current processors have been primarily optimized to perform well on the SPEC95 [18] benchmark suite. Similarly, design of multiprocessor architectures, along with academic research in this area, have been heavily influenced by popular scientific and engineering benchmarks such as SPLASH-2 [26] and STREAMS [13], with only a handful of published architectural studies that have in some way tried to address issues specific to commercial workloads [3,7,9,12,14,16,20,21,24].…”
Section: Introductionmentioning
confidence: 99%
“…Perl and Sites [14] demonstrated that both high bandwidth and low latency are required to effectively run OLTP and other commercial applications. Their experiments assumed single-cycle instruction latencies and on-chip cache sizes of the Alpha 21064 (8KB I, 8KB D) and 21164 (8KB I, 8KB D, and 96KB unified on-chip L2).…”
Section: Related Workmentioning
confidence: 99%
“…These techniques require complex hardware and compilers, but have proven ineffective for many programs [21].…”
Section: Introductionmentioning
confidence: 99%