[ANN] return value prediction

Hi,

We've published a paper on our return value prediction work in SableVM. 
  The code is not merged into staging yet (or fully released as a 
separate module), but you can get it from my sandbox.  It does need some 
cleanup.

Christopher J.F. Pickett and Clark Verbrugge, "Return Value Prediction 
in a Java Virtual Machine", Second Value-Prediction and Value-Based 
Optimization Workshop (VPW2) at ASPLOS XI, pp. 40-47, October 2004.

Abstract
We present the design and implementation of return value prediction in 
SableVM, a Java Virtual Machine.  We give detailed results for the full 
SPEC JVM98 benchmark suite, and compare our results with previous, more 
limited data.  At the performance limit of existing last value, stride, 
2-delta stride, parameter stride, and context (FCM) sub-predictors in a 
hybrid, we achieve an average accuracy of 72%.  We describe and 
characterize a new table-based memoization predictor that complements 
these predictors nicely, yielding an increased average hybrid accuracy 
of 81%.  VM level information about data widths provides a 35% reduction 
in space, and dynamic allocation and expansion of per-callsite 
hashtables allows for highly accurate prediction with an average 
per-benchmark requirement of 119 MB for the context predictor and 43 MB 
for the memoization predictor.  As far as we know, the is the first 
implementation of non-trace-based return value prediction within a JVM.

http://www.sable.mcgill.ca/publications/papers/#vpw2

Comments are welcome.

Cheers,
Chris