|
|
This is only a preview of the paper
Click here to register and get the full text.
Existing members click here to login
|
|
|
1 Introduction
Memory speeds in today’s computers have fundamentally lagged behind processor speeds [7]. Todays
memory systems incur access latencies that are up to three orders of magnitude larger than the latency of a
single arithmetic operation. To alleviate the processor/memory performance gap, computer designers
employ a hierarchy of cache memories (e. ... As database applications
become increasingly memory-intensive, high performance database systems must maximize cache utiliza-tion
by keeping data that are likely to be referenced in the cache hierarchy. ... , the processor should never be idle due
to main memory latency. ... According to earlier studies
[1][3], when running commercial DBMSs on a modern processor, data misses in the cache hierarchy are a
key memory bottleneck and a major reason for processor stalls. Choosing a data placement scheme that
follows the workload’s memory access patterns improves spatial locality, which in turn improves cache
space utilization and performance. More specifically, the inter-record locality eliminates delays due to
unnecessary memory accesses when evaluating a predicate using a fraction of each record. ... When running queries that involve few attributes from each relation, DSM saves I/O
and improves main memory utilization.
Approximate Word count = 904
Approximate Pages = 3.6
(250 words per page double spaced)
|
|
|
|
|
|