Panels - Revision history

imported>Sonia at 21:56, April 29, 2014

2014-04-29T21:56:48Z

← Older revision		Revision as of 21:56, April 29, 2014
Line 1:		Line 1:
	== Runtime Systems Vision ==		== Runtime Systems Vision ==
	Moderator: Vivek Sarkar		Moderator: Vivek Sarkar

	Panelists:		Panelists:

Line 16:		Line 17:

	Moderator: Mary Hall		Moderator: Mary Hall

	Panelists:		Panelists:

Line 30:		Line 32:

	Moderator: Dan/Saman		Moderator: Dan/Saman

	Panelists:		Panelists:

Line 43:		Line 46:

	Moderator: Armando Solar-Lezama		Moderator: Armando Solar-Lezama

	Panelist:		Panelist:

Line 55:		Line 59:

	Moderator: Mattan Erez		Moderator: Mattan Erez

	Panelists:		Panelists:

Line 66:		Line 71:

	Moderator: Shekhar Borkar		Moderator: Shekhar Borkar

	Panelists:		Panelists:

imported>Sonia at 21:54, April 29, 2014

2014-04-29T21:54:40Z

← Older revision		Revision as of 21:54, April 29, 2014
Line 72:		Line 72:
	[[Simulator_Research_Questions\| Questions and Discussion]]		[[Simulator_Research_Questions\| Questions and Discussion]]
	[[media: Resilience Panel-Summary-2013.pptx\|Resilience Panel Summary)]]		[[media: Resilience Panel-Summary-2013.pptx\|Resilience Panel Summary)]]


			== X-Stack OS/R requirements ==

			Moderator: Marc Snir and Barney Maccabe
			Panelists:

			Panel description.


			[[OS/R requirements_Research_Questions\| Questions and Discussion]]

			[[media: OS/R Requirements Panel-Summary-2013.pptx\|OS/R Requirments Panel Summary)]]

imported>Sonia at 21:51, April 29, 2014

2014-04-29T21:51:51Z

← Older revision		Revision as of 21:51, April 29, 2014
Line 40:		Line 40:


	== Mapping and Optimization Framework ~~Panel~~ ==		== Mapping and Optimization Framework ==

	Moderator: Armando Solar-Lezama		Moderator: Armando Solar-Lezama

imported>Sonia at 21:51, April 29, 2014

2014-04-29T21:51:24Z

← Older revision		Revision as of 21:51, April 29, 2014
Line 7:		Line 7:
	This session will focus on getting feedback from selected panelists and the audience on our results. Panelists will first provide us with constructive criticism and suggestions, followed by the interaction with the audience.		This session will focus on getting feedback from selected panelists and the audience on our results. Panelists will first provide us with constructive criticism and suggestions, followed by the interaction with the audience.

	[[media:Runtime-Panel.pdf\|Runtime Systems Vision]]		[[Runtime_Research_Questions\| Questions and Discussion]]

			[[media:Runtime-Panel.pdf\|Runtime Systems Vision Panel Summary]]



			== Compilers and Auto-tuning ==

	~~[[Runtime_Research_Questions\| Questions and Discussion]]~~		Moderator: Mary Hall
			Panelists:

	~~== Compilers Research ==~~		Panel description.
			Mary: see description for the compilers panel and auto-tuning panel on March 2013.

	~~Moderator: Dan Quinlan~~		[[Compilers_Research_Questions\| Questions and Discussion]]
	~~Panelists (to be confirmed): Milind Kulkarni (Purdue), David Padua (UIUC), P. Sadayappan (Ohio State), Armando Solar-Lezama (MIT), Olivier Tardieu (IBM), Nicolas Vasilache (Reservoir)~~

	The panelists in this parallel session will engage the audience in discussing the advances in compiler technology that are available and needed for the X-Stack program to support exascale computing systems. To save power, exascale systems will present many new features far beyond what we face today in terms of heterogeneity, explicit memory and communications management, load balancing and throttling, imbalance, demand for concurrency, deep (e.g. 10 level) memory hierarchies, new messaging and collectives, fault tolerance and new execution models (e.g., codelets). Furthermore, at these scales, the algorithms employed by systems will change radically and existing code bases will obselete accordingly. There will be a greater emphasis on irregularity, locality and placement, asynchronity, relaxed precision, communication avoidance, combinatorics, new solvers, and in-situ analysis and uncertainty quantification. The panelists will discuss how their teams' research in the X-Stack program bridges between new exascale algorithms and new exascale hardware.

	[[media:CompilerPanel_Summary.pptx\|Compiler Panel Summary]]		[[media:CompilerPanel_Summary.pptx\|Compiler Panel Summary]]

	~~[[Compilers_Research_Questions\| Questions and Discussion]]~~

	== Languages and DSLs ==		== Languages and DSLs ==

	Moderator: ~~Kathy Yelick~~		Moderator: Dan/Saman
	~~Speakers (to be confirmed)~~: ~~John Mellor-Crummey, Andrew Lumsdaine, Armando Solar-Lezama, Emina Torlak, John Feo~~		Panelists:

	~~This session will cover the concepts used~~ in ~~various general purpose~~ and ~~domain specific programming languages (~~DSLs). ~~Members of the audience will also be encouraged to participate to provide additional perspective on how specific features of the languages involved in the X-Stack projects~~ and elsewhere are meeting various challenges. (The following questions are written assuming that a speaker is presenting a particular language, but can also be answered more generally for what an Exascale language should have. And “language” is used to refer to both general purpose and ~~domain-specific languages.~~)		Panel description. Dan/Saman: see this panel description in March of last year.

			[[Languages_Research_Questions\| Questions and Discussion]]

			[[media:GPLs and DSLs -Summary-2013.pptx\|GPLs and and DSLs Panel Summary)]]

	~~[[media:GPLs-DSLs-Summary-2013.pptx\|General Purpose and Domain Specific Languages (GPLs and DSLs)]]~~

	~~[[Languages_Research_Questions\| Questions and Discussion]]~~

	== ~~Auto tuning~~ and ~~Learning~~ ==		== Mapping and Optimization Framework Panel ==

			Moderator: Armando Solar-Lezama
			Panelist:

			Panel description. Armando we want to bring here discussions about how a high level representation is mapped and optimized to a particular platform, with as much info about automated mappings/code generation as possible. This should include Mappings, Synthesis, Optimization, and Learning

	~~Moderator: Saman Amarasinghe (MIT)~~		[[Mappling Framework Panel Questions\| Questions and Discussion]]
	~~Panelist: Cy Chan (LBNL), Sam WIlliams (LBNL), Mary Hall (Utah), Una-May O’Reily (MIT)~~

	Because of the extreme complexity of the high performance software and hardware, it is becoming impossible to model and understand the behavior of end-to-end system and manually optimize them for performance. One important solution optimizing complex high performance systems is autotuning. Autotuning uses machine learning techniques to explore the optimization space with empirical evaluation of the performance. In this panel we will discuss:

	[[~~Autotuning_Research_Questions~~\| ~~Questions and Discussion~~]]		[[media: Mapping Framework Panel-Summary-2013.pptx\|Mapping Framework Panel Summary)]]

	== Resilience ==		== Resilience ==

	Moderator: ~~Andrew A. Chien (University of Chicago/ANL)~~		Moderator: Mattan Erez
	Panelists: ~~Greg Bronevetsky (LLNL), Bob Lucas (USC/ISI), Sriram Krishnamoorthy (PNNL), Josep Torrellas (Illinois), Saman Amarasinghe (MIT)~~		Panelists:

	~~The panelists in this parallel session will engage the audience in discussing various~~ resilience ~~technologies – extant and emerging –~~ and their capabilities to address different types of resilience challenges. Panelists will also discuss how each of these technologies will be demonstrated a promising, how they might be incorporated in future x-stacks (cross program synergy), ~~or presented for direct use by applications program experiments~~.		Panel description. Mattan, we need here to include different resilience approaches and their connection, if any.

	[[Resilience_Research_Questions\| Questions and Discussion]]		[[Resilience_Research_Questions\| Questions and Discussion]]

			[[media: Resilience Panel-Summary-2013.pptx\|Resilience Panel Summary)]]

	== Simulation technology ==		== Simulation technology ==

	Moderator: Shekhar Borkar		Moderator: Shekhar Borkar
	Panelists: ~~Arun Rodrigues, John Shalf, Rishi Khan, Krste Asanovic, Greg Bronevetsky~~		Panelists:

	~~The panelists in this parallel session will engage the audience in discussing various~~ simulation ~~technologies to evaluate and mature software components of the X-Stack program. This evaluation using simulators will also provide guidance~~ for ~~the~~ hardware ~~design. Behavioral simulators are fast, capable of running~~ software ~~close to real time; on the other hand, functional simulators are slower but model the hardware more accurately~~. Time accurate simulators are even slower, but provide precise timing information much needed to evaluate certain hardware-software interactions. Emulation technology provides time accuracy as well as speed for software evaluation, but is resource and time intensive. Each of these technologies have their pluses and minus, and the panel will discuss their role in the X-Stack program to evaluate software components with hardware interaction, using metrics such as performance, energy, and implementation.		Panel description. Shekhar: I would like to have a discussion about simulation for hardware and software research...

	[[Simulator_Research_Questions\| Questions and Discussion]]		[[Simulator_Research_Questions\| Questions and Discussion]]
			[[media: Resilience Panel-Summary-2013.pptx\|Resilience Panel Summary)]]

imported>Sonia: /* Runtime Research */

2014-04-29T21:35:27Z

Runtime Research

← Older revision		Revision as of 21:35, April 29, 2014
Line 1:		Line 1:
	== Runtime ~~Research~~ ==		== Runtime Systems Vision ==
	Moderator: Vivek Sarkar		Moderator: Vivek Sarkar
	Panelists: ~~Greg Bronevetsky (LLNL), Zoran Budimlic (Rice), Paul Hargrove (LBNL) Hartmut Kaiser (LSU), Sriram Krishnamoorthy (PNNL), Olivier Tardieu (IBM), Rishi Khan (ETI)~~		Panelists:

	~~Exascale systems will impose~~ a ~~fresh~~ set of ~~requirements on~~ runtime ~~systems that include targeting nodes~~ with ~~hundreds of homogeneous and heterogeneous cores~~, ~~as well as energy~~, data movement and resiliency constraints within and across nodes. This session will focus on the fundamental research challenges that need to be addressed in the area of runtimes for exascale systems. Both panelists and ~~audience members are expected~~ to ~~play an active role in the discussion~~.		We have presented the results of the Runtime Summit, which include challenges, solutions, a set of important questions to be answered, and a vision for a runtime architecture, with major components, interfaces, and how to measure success.

	[[media:Runtime-Panel~~-v5~~.pdf\|Runtime Systems]]		This session will focus on getting feedback from selected panelists and the audience on our results. Panelists will first provide us with constructive criticism and suggestions, followed by the interaction with the audience.

			[[media:Runtime-Panel.pdf\|Runtime Systems Vision]]

	[[Runtime_Research_Questions\| Questions and Discussion]]		[[Runtime_Research_Questions\| Questions and Discussion]]

imported>Sonia: Created page with "== Runtime Research == Moderator: Vivek Sarkar Panelists: Greg Bronevetsky (LLNL), Zoran Budimlic (Rice), Paul Hargrove (LBNL) Hartmut Kaiser (LSU), Sriram Krishnamoorthy (PN..."

2014-04-29T21:14:34Z

Created page with "== Runtime Research == Moderator: Vivek Sarkar Panelists: Greg Bronevetsky (LLNL), Zoran Budimlic (Rice), Paul Hargrove (LBNL) Hartmut Kaiser (LSU), Sriram Krishnamoorthy (PN..."

New page

== Runtime Research ==
Moderator: Vivek Sarkar
Panelists: Greg Bronevetsky (LLNL), Zoran Budimlic (Rice), Paul Hargrove (LBNL) Hartmut Kaiser (LSU), Sriram Krishnamoorthy (PNNL), Olivier Tardieu (IBM), Rishi Khan (ETI)

Exascale systems will impose a fresh set of requirements on runtime systems that include targeting nodes with hundreds of homogeneous and heterogeneous cores, as well as energy, data movement and resiliency constraints within and across nodes. This session will focus on the fundamental research challenges that need to be addressed in the area of runtimes for exascale systems. Both panelists and audience members are expected to play an active role in the discussion.

[[media:Runtime-Panel-v5.pdf|Runtime Systems]]

[[Runtime_Research_Questions| Questions and Discussion]]

== Compilers Research ==

Moderator: Dan Quinlan
Panelists (to be confirmed): Milind Kulkarni (Purdue), David Padua (UIUC), P. Sadayappan (Ohio State), Armando Solar-Lezama (MIT), Olivier Tardieu (IBM), Nicolas Vasilache (Reservoir)

The panelists in this parallel session will engage the audience in discussing the advances in compiler technology that are available and needed for the X-Stack program to support exascale computing systems. To save power, exascale systems will present many new features far beyond what we face today in terms of heterogeneity, explicit memory and communications management, load balancing and throttling, imbalance, demand for concurrency, deep (e.g. 10 level) memory hierarchies, new messaging and collectives, fault tolerance and new execution models (e.g., codelets). Furthermore, at these scales, the algorithms employed by systems will change radically and existing code bases will obselete accordingly. There will be a greater emphasis on irregularity, locality and placement, asynchronity, relaxed precision, communication avoidance, combinatorics, new solvers, and in-situ analysis and uncertainty quantification. The panelists will discuss how their teams' research in the X-Stack program bridges between new exascale algorithms and new exascale hardware.

[[media:CompilerPanel_Summary.pptx|Compiler Panel Summary]]

[[Compilers_Research_Questions| Questions and Discussion]]

== Languages and DSLs ==

Moderator: Kathy Yelick
Speakers (to be confirmed): John Mellor-Crummey, Andrew Lumsdaine, Armando Solar-Lezama, Emina Torlak, John Feo

This session will cover the concepts used in various general purpose and domain specific programming languages (DSLs). Members of the audience will also be encouraged to participate to provide additional perspective on how specific features of the languages involved in the X-Stack projects and elsewhere are meeting various challenges. (The following questions are written assuming that a speaker is presenting a particular language, but can also be answered more generally for what an Exascale language should have. And “language” is used to refer to both general purpose and domain-specific languages.)

[[media:GPLs-DSLs-Summary-2013.pptx|General Purpose and Domain Specific Languages (GPLs and DSLs)]]

[[Languages_Research_Questions| Questions and Discussion]]

== Auto tuning and Learning ==

Moderator: Saman Amarasinghe (MIT)
Panelist: Cy Chan (LBNL), Sam WIlliams (LBNL), Mary Hall (Utah), Una-May O’Reily (MIT)

Because of the extreme complexity of the high performance software and hardware, it is becoming impossible to model and understand the behavior of end-to-end system and manually optimize them for performance. One important solution optimizing complex high performance systems is autotuning. Autotuning uses machine learning techniques to explore the optimization space with empirical evaluation of the performance. In this panel we will discuss:

[[Autotuning_Research_Questions| Questions and Discussion]]

== Resilience ==

Moderator: Andrew A. Chien (University of Chicago/ANL)
Panelists: Greg Bronevetsky (LLNL), Bob Lucas (USC/ISI), Sriram Krishnamoorthy (PNNL), Josep Torrellas (Illinois), Saman Amarasinghe (MIT)

The panelists in this parallel session will engage the audience in discussing various resilience technologies – extant and emerging – and their capabilities to address different types of resilience challenges. Panelists will also discuss how each of these technologies will be demonstrated a promising, how they might be incorporated in future x-stacks (cross program synergy), or presented for direct use by applications program experiments.

[[Resilience_Research_Questions| Questions and Discussion]]

== Simulation technology ==

Moderator: Shekhar Borkar
Panelists: Arun Rodrigues, John Shalf, Rishi Khan, Krste Asanovic, Greg Bronevetsky

The panelists in this parallel session will engage the audience in discussing various simulation technologies to evaluate and mature software components of the X-Stack program. This evaluation using simulators will also provide guidance for the hardware design. Behavioral simulators are fast, capable of running software close to real time; on the other hand, functional simulators are slower but model the hardware more accurately. Time accurate simulators are even slower, but provide precise timing information much needed to evaluate certain hardware-software interactions. Emulation technology provides time accuracy as well as speed for software evaluation, but is resource and time intensive. Each of these technologies have their pluses and minus, and the panel will discuss their role in the X-Stack program to evaluate software components with hardware interaction, using metrics such as performance, energy, and implementation.

[[Simulator_Research_Questions| Questions and Discussion]]