A cache based stack folding technique for high performance Java processors

Sideris, I; Economakos, G; Pekmestzi, K

dc.contributor.author	Sideris, I	en
dc.contributor.author	Economakos, G	en
dc.contributor.author	Pekmestzi, K	en
dc.date.accessioned	2014-03-01T02:43:48Z
dc.date.available	2014-03-01T02:43:48Z
dc.date.issued	2006	en
dc.identifier.uri	https://dspace.lib.ntua.gr/xmlui/handle/123456789/31508
dc.subject	ilp	en
dc.subject	Java processor	en
dc.subject	Predecoded cache	en
dc.subject	RISC	en
dc.subject	Stack folding	en
dc.subject.other	Algorithms	en
dc.subject.other	Buffer storage	en
dc.subject.other	Computer applications	en
dc.subject.other	Computer hardware	en
dc.subject.other	Java programming language	en
dc.subject.other	Reduced instruction set computing	en
dc.subject.other	Java processors	en
dc.subject.other	Predecoded cache	en
dc.subject.other	Stack folding algorithms	en
dc.subject.other	Program processors	en
dc.title	A cache based stack folding technique for high performance Java processors	en
heal.type	conferenceItem	en
heal.identifier.primary	10.1145/1167999.1168009	en
heal.identifier.secondary	http://dx.doi.org/10.1145/1167999.1168009	en
heal.publicationDate	2006	en
heal.abstract	Java processors have been introduced to offer hardware acceleration for Java applications. They execute Java bytecodes directly in hardware. However, the stack nature of the Java virtual machine instruction set imposes a limitation on the achievable execution performance. If we intend to exploit instruction level parallelism, we must remove the stack completely. This can be achieved by recursive stack folding algorithms, such as OPEX, which dynamically transform groups of Java bytecodes to RISC like instructions. However, the decoding throughputs that are obtained are limited. In this paper we propose a novel stack folding technique, that uses a predecoded cache to store folded bytecodes, thus enabling reuse. The decoding throughput reaches 4 RISC instructions per cycle. With use of a superscalar backend core, the obtained IPC is approximately 2.08 instructions per cycle (or 3.02 Java bytecodes per cycle). Copyright 2006 ACM.	en
heal.journalName	ACM International Conference Proceeding Series	en
dc.identifier.doi	10.1145/1167999.1168009	en
dc.identifier.volume	177	en
dc.identifier.spage	48	en
dc.identifier.epage	57	en