Instruction level parallelism of stack-code under varied issue widths, and one-level branch prediction

Chris Bailey; Huibin Shi

Instruction level parallelism of stack-code under varied issue widths, and one-level branch prediction

Computer Science

Research output: Contribution to conference › Paper › peer-review

Abstract

Stack architecture research interests have surfaced again in recent years, however stack machines are generally regarded as sequential execution architectures. By assuming that ILP (Instruction-Level Parallelism) can be exploited in a stack machine, we are able to use static analysis to uncover and measure available such instruction level parallelism as it naturally exists in the stack code of a hypothetical architecture. With increasing issue widths, a superscalar stack machine is shown to be modestly scalable, and displays improved scalability with the impact of branch prediction considered. This paper also indicates some of the limitations of the issue width expansion, which is confined by the available ILP of the stack code.

Original language	Undefined/Unknown
Pages	23-30
Publication status	Published - 2005

Bibliographical note

ISBN: 972-99353-6-X

Access to Document

http://www.iadisportal.org/digital-library/instruction-level-parallelism-of-stack-code-under-varied-issue-widths-and-one-level-branch-prediction

Cite this

@conference{ca80c81480c74d4d85d289e1b6b7274f,

title = "Instruction level parallelism of stack-code under varied issue widths, and one-level branch prediction",

abstract = "Stack architecture research interests have surfaced again in recent years, however stack machines are generally regarded as sequential execution architectures. By assuming that ILP (Instruction-Level Parallelism) can be exploited in a stack machine, we are able to use static analysis to uncover and measure available such instruction level parallelism as it naturally exists in the stack code of a hypothetical architecture. With increasing issue widths, a superscalar stack machine is shown to be modestly scalable, and displays improved scalability with the impact of branch prediction considered. This paper also indicates some of the limitations of the issue width expansion, which is confined by the available ILP of the stack code. ",

author = "Chris Bailey and Huibin Shi",

note = "ISBN: 972-99353-6-X ",

year = "2005",

language = "Undefined/Unknown",

pages = "23--30",

}

TY - CONF

T1 - Instruction level parallelism of stack-code under varied issue widths, and one-level branch prediction

AU - Bailey, Chris

AU - Shi, Huibin

N1 - ISBN: 972-99353-6-X

PY - 2005

Y1 - 2005

N2 - Stack architecture research interests have surfaced again in recent years, however stack machines are generally regarded as sequential execution architectures. By assuming that ILP (Instruction-Level Parallelism) can be exploited in a stack machine, we are able to use static analysis to uncover and measure available such instruction level parallelism as it naturally exists in the stack code of a hypothetical architecture. With increasing issue widths, a superscalar stack machine is shown to be modestly scalable, and displays improved scalability with the impact of branch prediction considered. This paper also indicates some of the limitations of the issue width expansion, which is confined by the available ILP of the stack code.

AB - Stack architecture research interests have surfaced again in recent years, however stack machines are generally regarded as sequential execution architectures. By assuming that ILP (Instruction-Level Parallelism) can be exploited in a stack machine, we are able to use static analysis to uncover and measure available such instruction level parallelism as it naturally exists in the stack code of a hypothetical architecture. With increasing issue widths, a superscalar stack machine is shown to be modestly scalable, and displays improved scalability with the impact of branch prediction considered. This paper also indicates some of the limitations of the issue width expansion, which is confined by the available ILP of the stack code.

M3 - Paper

SP - 23

EP - 30

ER -