|
Bug ID:
|
6488532
|
|
Votes
|
0
|
|
Synopsis
|
Support allocate prefetching of several sequential cache lines
|
|
Category
|
hotspot:compiler2
|
|
Reported Against
|
|
|
Release Fixed
|
hs10(b03),
6u2(b01) (Bug ID:2146656)
, 7(b03) (Bug ID:2176796)
|
|
State
|
10-Fix Delivered,
request for enhancement
|
|
Priority:
|
4-Low
|
|
Related Bugs
|
6513855
,
6516355
,
6531227
|
|
Submit Date
|
31-OCT-2006
|
|
Description
|
I see about 3% improvement of jbb2005 score on Core2Duo with
-XX:AllocatePrefetchLines=3 vs -XX:AllocatePrefetchLines=1 (default).
The time spent in arraycopy dropped from 96 sec to 26 sec:
-XX:AllocatePrefetchLines=1 :
96.508 100.00 96.508 4.67 96.508 4.67 *arrayof_jshort_disjoint_arraycopy
-XX:AllocatePrefetchLines=3 :
25.868 100.00 25.868 1.25 25.868 1.25 *arrayof_jshort_disjoint_arraycopy
Posted Date : 2006-10-31 23:06:09.0
|
|
Work Around
|
N/A
|
|
Evaluation
|
Need the flag AllocatePrefetchLines to specify how many sequential cache lines
should be prefetched, the default is 1 as it is currently.
Need to modify vm_version files to detect cpu type and set the cache line size in bytes.
Posted Date : 2006-10-31 23:09:36.0
|
|
Comments
|
PLEASE NOTE: JDK6 is formerly known as Project Mustang
|
