Paper:Ispass2013Carlson - Revision history

Wheirman at 13:00, 29 April 2013

2013-04-29T13:00:24Z

Tcarlson: /* Presentation */

2013-04-29T12:34:09Z

Presentation

Tcarlson at 12:33, 29 April 2013

2013-04-29T12:33:44Z

Tcarlson at 12:33, 29 April 2013

2013-04-29T12:33:28Z

Tcarlson at 13:44, 25 April 2013

2013-04-25T13:44:01Z

Tcarlson at 13:43, 25 April 2013

2013-04-25T13:43:09Z

Wheirman at 09:57, 16 March 2013

2013-03-16T09:57:18Z

Wheirman at 09:14, 19 February 2013

2013-02-19T09:14:59Z

Wheirman: /* Abstract */

2013-02-13T13:03:07Z

Abstract

Tcarlson at 12:59, 11 February 2013

2013-02-11T12:59:20Z

@@ Line 21: / Line 21: @@
    title = {Sampled Simulation of Multi-Threaded Applications},
    booktitle = {International Symposium on Performance Analysis of Systems and Software (ISPASS)},
    year = {2013},
    month = apr
+}
 </pre>

@@ Line 14: / Line 14: @@
 ===Presentation===
-[http://www.snipersim.org/documents/presentations/2013-04-22%20ISPASS%20Multi-threaded%20Sampling.pdf Full paper PDF]
+[http://www.snipersim.org/documents/presentations/2013-04-22%20ISPASS%20Multi-threaded%20Sampling.pdf Presentation]
 ===Bibtex entry===

@@ Line 14: / Line 14: @@
 ===Presentation===
-[http://www.snipersim.org/documents/presentations/2013-04-22%20ISPASS%20Multi-threaded%20Sampling.pdf.pdf Full paper PDF]
+[http://www.snipersim.org/documents/presentations/2013-04-22%20ISPASS%20Multi-threaded%20Sampling.pdf Full paper PDF]
 ===Bibtex entry===

@@ Line 12: / Line 12: @@
 ===Full text===
 [http://www.exascience.com/wp-content/uploads/2013/02/Carlson-Sampled-simulation.pdf Full paper PDF]
 ===Bibtex entry===

@@ Line 2: / Line 2: @@
 Trevor E. Carlson, Wim Heirman, Lieven Eeckhout
-Won '''Best Paper Award''' at ''IEEE International Symposium on Performance Analysis of Systems and Software ([http://www.ispass.org/ispass2013/ ISPASS 2013])''
+'''Best Paper Award''' at ''IEEE International Symposium on Performance Analysis of Systems and Software ([http://www.ispass.org/ispass2013/ ISPASS 2013])''
 === Abstract ===

← Older revision		Revision as of 09:14, 19 February 2013
Line 9:		Line 9:

	The proposed multi-threaded application sampling methodology is able to derive an effective sampling strategy for candidate applications using architecture-independent metrics. Using this methodology, large input sets can now be simulated which would otherwise be infeasible, allowing for more accurate conclusions to be made than from studies using scaled-down input sets. Through the use of the proposed methodology, we can simulate less than 10% of the total application runtime in detail. On the SPEComp, NPB and PARSEC benchmarks, running on an 8-core simulated system, we achieve an average absolute error of 3.5%.		The proposed multi-threaded application sampling methodology is able to derive an effective sampling strategy for candidate applications using architecture-independent metrics. Using this methodology, large input sets can now be simulated which would otherwise be infeasible, allowing for more accurate conclusions to be made than from studies using scaled-down input sets. Through the use of the proposed methodology, we can simulate less than 10% of the total application runtime in detail. On the SPEComp, NPB and PARSEC benchmarks, running on an 8-core simulated system, we achieve an average absolute error of 3.5%.
		+
		+	===Full text===
		+	[http://www.exascience.com/wp-content/uploads/2013/02/Carlson-Sampled-simulation.pdf Full paper PDF]
		+
		+	===Bibtex entry===
		+	<pre>@INPROCEEDINGS{carlson2013ssomta,
		+	author = {Trevor E. Carlson and Wim Heirman and Lieven Eeckhout},
		+	title = {Sampled Simulation of Multi-Threaded Applications},
		+	booktitle = {International Symposium on Performance Analysis of Systems and Software (ISPASS)},
		+	year = {2013},
		+	month = apr
		+	}
		+	</pre>

← Older revision		Revision as of 13:03, 13 February 2013
Line 5:		Line 5:

	=== Abstract ===		=== Abstract ===
−	~~To appear~~	+
		+	Sampling is a well-known workload reduction technique that allows one to speed up architectural simulation while accurately predicting performance. Previous sampling methods have been shown to accurately predict single-threaded application runtime based on its overall IPC. However, these previous approaches are unsuitable for general multi-threaded applications, for which IPC is not a good proxy for runtime. Additionally, we find that issues such as application periodicity and inter-thread synchronization play a significant role in determining how best to sample these applications.
		+
		+	The proposed multi-threaded application sampling methodology is able to derive an effective sampling strategy for candidate applications using architecture-independent metrics. Using this methodology, large input sets can now be simulated which would otherwise be infeasible, allowing for more accurate conclusions to be made than from studies using scaled-down input sets. Through the use of the proposed methodology, we can simulate less than 10% of the total application runtime in detail. On the SPEComp, NPB and PARSEC benchmarks, running on an 8-core simulated system, we achieve an average absolute error of 3.5%.

← Older revision		Revision as of 12:59, 11 February 2013
Line 3:		Line 3:

	''IEEE International Symposium on Performance Analysis of Systems and Software ([http://www.ispass.org/ispass2013/ ISPASS 2013])''		''IEEE International Symposium on Performance Analysis of Systems and Software ([http://www.ispass.org/ispass2013/ ISPASS 2013])''
		+
		+	=== Abstract ===
		+	To appear