(Enter summary)
Abstract: Two hardware methods for remedying the effects of true data dependences are studied. The first method, dependence speculation, is used to eliminate address generation-load dependences. This is enabled by address prediction that permits load instructions to proceed speculatively without waiting for their address operands. The second technique, dependence collapsing, is used to eliminate data dependences by combining a dependence among multiple instructions into one instruction. The potential of... (Update)
Cited by: More
Exploring the Design Space of LUT-based Transparent.. - Yehia, Clark, Mahlke.. (2005)
(Correct)
Dynamic Strands: Collapsing Speculative Dependence Chains for .. - Sassone, Wills (2004)
(Correct)
High-Performance Frontends for Trace Processors - Jacobson (1999)
(Correct)
Active bibliography (related documents): More All
1.6: The Performance Potential of Data Dependence.. - Sazeides, Vassiliadis, .. (1996)
(Correct)
0.3: Instruction Pre-Processing in Trace Processors - Jacobson, Smith (1999)
(Correct)
0.3: Fast Computation of Compound Expressions in Two's.. - Hakkennes.. (1997)
(Correct)
Similar documents based on text: More All
0.8: Implementations of Context Based Value Predictors - Sazeides, Smith (1997)
(Correct)
0.7: Implementations of Context-Based Value Predictors - Sazeides, Smith (1997)
(Correct)
0.6: Modeling Program Predictability - Sazeides, Smith (1998)
(Correct)
Related documents from co-citation: More All
24: Exceeding the Dataflow Limit via Value Prediction
- Lipasti, Shen - 1996
20: Value Locality and Load Value Prediction
- Lipasti, Wilkerson et al. - 1996
18: Multiscalar processors
- Sohi, Breach et al. - 1995
BibTeX entry: (Update)
Y. Sazeides, S. Vassiliadis and J. E. Smith. The Performance Potential of Data Dependence Speculation & Collapsing. in Proceeding of the 29 th Annual ACM/IEEE International Symposium on Microarchitecture, pp. 238-247, Dec., 1996. http://citeseer.ist.psu.edu/article/sazeides96performance.html More
@inproceedings { sazeides96performance,
author = "Yiannakis Sazeides and Stamatis Vassiliadis and James E. Smith",
title = "The Performance Potential of Data Dependence Speculation Collapsing",
booktitle = "International Symposium on Microarchitecture",
pages = "238--247",
year = "1996",
url = "citeseer.ist.psu.edu/article/sazeides96performance.html",
url = "citeseer.nj.nec.com/sazeidis96performance.html" }
Citations (may not include all citations):
230
Limits of instruction level parallelism
- Wall - 1991
214
Combining branch predictors
- McFarling - 1993
157
Limits of control flow on parallelism
- Lam, Wilson - 1992
110
Available instruction-level parallelism for superscalar and ..
- Jouppi, Wall - 1989
96
Effective hardware-based data prefetching for high performan.. (context) - Chen, Baer - 1995
69
Single instruction stream parallelism is greater than two (context) - Butler, Yeh et al. - 1991
64
Efficient program tracing (context) - Larus - 1993
58
Dynamic dependency analysis of ordinary programs
- Austin, Sohi - 1992
57
A load instruction unit for pipelined processors (context) - Eickemeyer, Vassiliadis - 1993
38
Zero-cycle loads: Microarchitecture support for reducing loa..
- Austin, Sohi - 1995
27
The SPARC Architecture Manual (context) - MICROSYSTEMS - 1992
24
Examination of a memory access classification scheme for poi..
- Mehrotra, Harrison - 1996
16
Scism: A scalable compound instruction set machine architect.. (context) - Vassiliadis, Blaner et al. - 1994
13
Value locality and data speculation (context) - Lipasti, Wilkerson et al. - 1996
11
Ibm risc system/6000processor architecture (context) - Oehler, Groves - 1990
10
Design of the ibm risc system/6000 floating-point execution .. (context) - Montoye, Hokenek et al. - 1990
8
Interlock collapsing alu's (context) - Vassiliadis, Phillips et al. - 1993
7
High performance 3-1 interlock collapsing alu's (context) - Phillips, Vassiliadis - 1994
5
Interlock collapsing alu for increased instruction-level par.. (context) - Malik, Eickemeyer et al. - 1992
3
Inside IBM Power and PowerPC (context) - Weiss, Smith - 1994
2
Increasing instruction level parallelism through instruction.. (context) - Moshovos - 1995
The graph only includes citing articles where the year of publication is known.
Documents on the same site (http://einstein.et.tudelft.nl/~stamatis/pubs/conf.html): More
Redundant Addition with Threshold Logic - Sorin Cotofana
(Correct)
Block Save Addition with Threshold Logic - Vassiliadis Cotofana (1995)
(Correct)
Fast Computation of Compound Expressions in Two's.. - Hakkennes.. (1997)
(Correct)
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC