Proceedings of the ACM SIGPLAN 1995 Conference on Programming Language Design and Implementation 1995
DOI: 10.1145/207110.207165
|View full text |Cite
|
Sign up to set email alerts
|

Stack caching for interpreters

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1
1

Citation Types

0
34
0

Year Published

1999
1999
2013
2013

Publication Types

Select...
3
2
2

Relationship

1
6

Authors

Journals

citations
Cited by 45 publications
(34 citation statements)
references
References 7 publications
0
34
0
Order By: Relevance
“…This is not surprising, given that more MOVEs are eliminated dynamically than statically (see figures 4,5), and thus there is more potential for intermediate values to be kept in registers in the frequently executed code.…”
Section: Local Data Memory Accessesmentioning
confidence: 97%
See 2 more Smart Citations
“…This is not surprising, given that more MOVEs are eliminated dynamically than statically (see figures 4,5), and thus there is more potential for intermediate values to be kept in registers in the frequently executed code.…”
Section: Local Data Memory Accessesmentioning
confidence: 97%
“…Many designers favour stack architectures since the location of operands is implicit in the stack pointer [5,6,19]. In contrast, the operands of register machine instructions must be specified explicitly.…”
Section: Motivationmentioning
confidence: 99%
See 1 more Smart Citation
“…Register Caching: A popular optimization among stack based virtual machines is to cache the top value(s) of the stack in machine registers [8]. An equivalent approach to caching virtual registers in machine registers is to date un- established 1 .…”
Section: Scope For Optimizationmentioning
confidence: 99%
“…Unlike in previously published stack caching techniques [14], the primary goal of stack caching for us is to reduce the dependence height in the execute part of the bytecode and not to reduce the number of operations. Unlike [14], we do not maintain how many cache elements are valid by means of interpreter state. In our case, tos contains valid data when there is at least one element on the stack, and nos contains valid data when there are at least two elements on the stack.…”
Section: Stack Cachingmentioning
confidence: 99%