by Ian Macintyre, Bruno R. Preiss
http://www.pads.uwaterloo.ca/Bruno.Preiss/papers/published/1991/ccece/paper.ps
Add To MetaCart
Abstract:
This paper examines the effects of multithreaded pipelining on the CPI (cycles per instruction) of a RISC processor. The desired CPI in a conventional (single-threaded) RISC processor is one instruction per cycle. However, the CPI is typically more than one because of data hazards, control hazards, and resource hazards in the pipeline. A multi-threaded processor performs a context switch between every instruction. Multi-threaded pipelining holds out the promise of achieving a lower CPI because it can eliminate data and control hazards, and mask the effects of memory latency. However, multi-threaded pipelining reduces cache hit ratios and requires more chip area to implement. In this paper, we present a model for predicting the CPI of a multithreaded pipelined processor. We also present the results of trace-driven simulations of single- and multi-threaded processors. These data show that, for reasonable implementation technologies, and taking into account the chip area penalty, a multi-threaded processor can achieve a lower CPI than a single-threaded processor.
Citations
|
325
|
A Technique for High-Performance Data Compression
– Welch
- 1984
|
|
106
|
An analytical cache model
– AGARWAL, HOROWITZ, et al.
- 1989
|
|
65
|
A portable machine-independent global optimizer — design and measurements
– Chow
- 1983
|
|
46
|
Parallel operations in control data 6600
– Thornton
- 1964
|
|
18
|
Operating Systems: Concepts and Design
– Milenkovic
- 1987
|
|
17
|
A VLSI RISC
– Patterson, Sequin
- 1982
|
|
14
|
Parallel MIMD Computation: the HEP supercomputer and its applications
– Kowalik, editor
- 1985
|
|
10
|
Architectural tradeoffs in the design of MIPS-X
– Chow, Horowitz
- 1987
|
|
6
|
MASA: A Multithreaded Processor Architecture for Parallel Symbolic Computing
– Jr, Fujita
- 1988
|
|
6
|
And Now a Case for More Complex Instruction Sets
– Flynn, Mitchell, et al.
- 1987
|
|
5
|
A multiminiprocessor system implemented through pipelining,” Computer
– Shar, Davidson
- 1974
|
|
5
|
Intel's secret is out
– Perry
- 1989
|
|
3
|
A RISC Multiprocessor Based on Circulating Context
– Butner, Staley
- 1986
|
|
2
|
A study of horizontal pipelining in a RISC processor
– MacIntyre
- 1989
|
|
2
|
MIPS-X Instruction Set and Programmer's Manual
– Chow
- 1986
|
|
1
|
CPC (Cyclic Pipeline Computer)- An Architecture Suited for Josephson and PipelinedMemory Machines
– Shimizu, Goto, et al.
- 1989
|
|
1
|
Lisp on a Reduced-InstructionSet Processor: Characteristics and Optimization
– Steenkiske, Hennessy
- 1988
|
|
1
|
Organization and VLSI Implementation of MIPS
– L, Jouppi, et al.
- 1986
|
