[#RVM-188] BURS in the DaCapo Jython benchmark is more expensive than normal

RVM

BURS in the DaCapo Jython benchmark is more expensive than normal

Created: 22/Aug/07 03:44 AM Updated: 11/Apr/08 09:29 AM

Component/s:

Compiler: Optimizing

Affects Version/s:

2.9.0, 2.9.0.1, 2.9.1

Fix Version/s:

1000

Time Tracking:

Not Specified

Issue Links:

Related

This issue relates to:

~~RVM-212~~ Opt compiler memory usage

Description

« Hide

Profiling DaCapo Jython shows that we at least spend 3.7% of execution time in the opt compiler's BURS instruction selector:

344.0 (3.6953485873885485%)
Lorg/jikesrvm/compilers/opt/OPT_NormalBURS;.reachableChild
(Lorg/jikesrvm/ArchitectureSpecific$OPT_BURS_TreeNode;Lorg/jikesrvm/compilers/opt/OPT_SpaceEffGraphNode;I)Z

Measuring compilation phase time in DaCapo Jython (-s large -n 3) shows that 74.80% of compilation time is spent in BURS. Compared to other DaCapo benchmarks where BURS accounts for:
antlr - 12.30%
bloat - 7.82%
eclipse - 11.09%
fop - 10.85%
hsqldb - 11.20%
luindex - 9.49%
lusearch - 10.55%
pmd - 7.94%
xalan - 11.02%

All

Comments

Work Log

Change History

Sort Order:

[ Permlink | « Hide ]

Ian Rogers added a comment - 25/Aug/07 10:42 AM

SPEC JVM '98's ray trace benchmarks also show a greater percentage of execution time spent in BURS:
_205_raytrace - 34.77%
_227_mtrt - 40.56%
compared to:
_201_compress - 11.13%
_202_jess - 12.02%
_209_db - 9.52%
_213_javac - 12.01%
_222_mpegaudio - 19.58% (quite high)
_228_jack - 8.35%

[ Permlink | « Hide ]

Ian Rogers added a comment - 07/Sep/07 11:37 AM

Testing on a different machine shows commit r13517 has lowered the BURS overhead in jython to under 45%. Still very high.

[ Permlink | « Hide ]

Ian Rogers added a comment - 12/Sep/07 03:42 AM

We may be seeing expensive BURS phases for certain benchmarks as these benchmarks have large basic blocks (but still under our 300 instruction super large limit) and BURS is some what memory hungry.