CiSE-EOT-Article - Revision history

Charliep at 14:53, 24 March 2021

2021-03-24T14:53:43Z

← Older revision		Revision as of 14:53, 24 March 2021
Line 111:		Line 111:
	For the student, authenticity in the problems they face and the experience of their education is important. We use problem based learning as one approach to increase the authenticity of the student experience, through the creation of "supercomputer based labs" in which students make use of professional computing tools and libraries to solve problems related to course content and learning goals.		For the student, authenticity in the problems they face and the experience of their education is important. We use problem based learning as one approach to increase the authenticity of the student experience, through the creation of "supercomputer based labs" in which students make use of professional computing tools and libraries to solve problems related to course content and learning goals.

	The use of problems as a teaching tool in HPC is particularly interesting given the cross-disciplinary nature of the field. Students solving the same problem need to be able to ~~master~~ at least some aspect of another field, but different students will still take away and give to the problem from their own perspective.		The use of problems as a teaching tool in HPC is particularly interesting given the cross-disciplinary nature of the field. Students solving the same problem need to be able to learn at least some aspect of another field, but different students will still take away and give to the problem from their own perspective.

	We have a series of lessons based around the study of protein structure using GROMACS. Depending on the students perspective, many different questions could arise from the same problem. What is the best way to optimize compiler directives for a given hardware? What hardware configuration results in the greatest performance for a given cluster? How does that relate to computing power per dollar or per megawatt?		We have a series of lessons based around the study of protein structure using GROMACS. Depending on the students perspective, many different questions could arise from the same problem. What is the best way to optimize compiler directives for a given hardware? What hardware configuration results in the greatest performance for a given cluster? How does that relate to computing power per dollar or per megawatt?

Charliep: /* The Paper */

2008-01-19T04:25:31Z

The Paper

← Older revision		Revision as of 04:25, 19 January 2008
Line 22:		Line 22:

	==The Paper==		==The Paper==

			<b>N.B - this has been moved to LaTeX. charliep, January 18, 2008</b>

	===Title===		===Title===

Djoiner: /* Introduction */

2008-01-19T02:08:34Z

Introduction

← Older revision		Revision as of 02:08, 19 January 2008
Line 36:		Line 36:

	In the August 26, 2005 edition of HPCwire, the authors of this paper described HPC education as broken. Is it still? The definitive answer is "It depends". There have been tremendous advancements with the various science portals, while new computational science programs continue to burst forth at a snails pace. The SC educational outreach via its pathways program is doings an outstanding job, and with 100% private sector funding, at reaching new groups, but is still just introducing a trickle of new thinking and new capabilities into the broad river of the educational status quo.		In the August 26, 2005 edition of HPCwire, the authors of this paper described HPC education as broken. Is it still? The definitive answer is "It depends". There have been tremendous advancements with the various science portals, while new computational science programs continue to burst forth at a snails pace. The SC educational outreach via its pathways program is doings an outstanding job, and with 100% private sector funding, at reaching new groups, but is still just introducing a trickle of new thinking and new capabilities into the broad river of the educational status quo.

			The challenges facing the country in science education were clearly laid out in the June 2005 report to the president "Computational Science: Assuring America's Competitiveness" (http://www.nitrd.gov/pitac/reports/20050609_computational/computational.pdf). 2 years later, these challenges have been largely reaffirmed by the National Academies report "Is America Falling Off the Flat Earth?" (http://www.nap.edu/catalog.php?record_id=12021), which echoes the same concerns compounded by current trends in globalization.

	We predicted wonderful things coming down the pipe, what has come down the pipe and how has it evolved from our original ideas? We are part of the new thinking and we are part of the status quo, and we are in the thick of things. We have done a good job coming up with a low cost cluster platform, with a no cost operating environment, with some integrated curricular models. The no cost operating at times also has no cost of system administration, but we are still actively involved with making it significantly easier for us to maintain that condition of no cost system administration as we add new applications and as its underlying operating system continues to evolve. We have been wildly unsuccessful at having the breadth of curricular modules we'd like spanning disciplines and the K-grad academic range. Though there is a broad base of "good stuff" that is heavily being used. I suppose where we are all at is clutching the tail of a bucking bronco. We are making good progress in moving towards the more stable front of the horse, but we still find ourselves at the wrong end.		We predicted wonderful things coming down the pipe, what has come down the pipe and how has it evolved from our original ideas? We are part of the new thinking and we are part of the status quo, and we are in the thick of things. We have done a good job coming up with a low cost cluster platform, with a no cost operating environment, with some integrated curricular models. The no cost operating at times also has no cost of system administration, but we are still actively involved with making it significantly easier for us to maintain that condition of no cost system administration as we add new applications and as its underlying operating system continues to evolve. We have been wildly unsuccessful at having the breadth of curricular modules we'd like spanning disciplines and the K-grad academic range. Though there is a broad base of "good stuff" that is heavily being used. I suppose where we are all at is clutching the tail of a bucking bronco. We are making good progress in moving towards the more stable front of the horse, but we still find ourselves at the wrong end.
Line 43:		Line 45:
	In order to broaden participation in HPC and computational science generally, more of our EOT efforts need to be directed towards faculty and students at smaller institutions, faculty who are primarily teachers, working with the next generation of scientists. These users require materials designed for learning how to use HPC and computational methods at a variety of levels, not just as the tools of a research scientist.		In order to broaden participation in HPC and computational science generally, more of our EOT efforts need to be directed towards faculty and students at smaller institutions, faculty who are primarily teachers, working with the next generation of scientists. These users require materials designed for learning how to use HPC and computational methods at a variety of levels, not just as the tools of a research scientist.

			===The challenges of HPC Education===
	The ~~challenge and the importance~~ of HPC EOT was clearly laid out in the June 2005 report to the president "Computational Science: Assuring America's Competitiveness" (http://www.nitrd.gov/pitac/reports/20050609_computational/computational.pdf) and was reaffirmed in 2007 with the report "Is America Falling Off the Flat Earth?" (http://www.nap.edu/catalog.php?record_id=~~12021)~~



	Computational Science and Engineering is by its very nature multi- inter- and cross-disciplinary, with practitioners in the fields of mathematics, computer science, and domain specific sciences having to work together (or at least use the product of each others work) in a tight knit collaboration.		Computational Science and Engineering is by its very nature multi- inter- and cross-disciplinary, with practitioners in the fields of mathematics, computer science, and domain specific sciences having to work together (or at least use the product of each others work) in a tight knit collaboration.
Line 52:		Line 51:
	For years the traditional training of computational scientists has been left largely to		For years the traditional training of computational scientists has been left largely to
	graduate advisers and a few specialized courses, if that. However, there is a growing trend		graduate advisers and a few specialized courses, if that. However, there is a growing trend
	towards teaching computation at the undergraduate level. For over a decade, the Krell institute has strived to survey and list every computational science program; their current list shows 16 undergraduate degree programs specifically in computational science, and tens of schools with significant coursework available for undergraduate students. However, new programs are being developed and offered every year, and the current list often does not include these new programs or programs outside of traditional departments, such as multi-disciplinary centers ~~(cite private communication)~~. In New Jersey alone, there are 2 undergraduate degree programs, with a 3rd in the pipeline, that do not show up on the current list.		towards teaching computation at the undergraduate level. For over a decade, the Krell institute has strived to survey and list every computational science program; their current list shows 16 undergraduate degree programs specifically in computational science, and tens of schools with significant coursework available for undergraduate students. However, new programs are being developed and offered every year, and the current list often does not include these new programs or programs outside of traditional departments, such as multi-disciplinary centers. In New Jersey alone, there are 2 undergraduate degree programs, with a 3rd in the pipeline, that do not show up on the current list.

	~~(cite Krell survey, can we get a more recent number/reference? I know of at least 3 programs in NJ alone not on the Krell list)~~

	~~(can we contact Krell and make sure we are looking at the most recent list? Can we get their choice of a reference for the list?)~~

	Possibly the biggest challenge to getting computation into undergraduate curriculum is the politics.		Possibly the biggest challenge to getting computation into undergraduate curriculum is the politics.

Djoiner: /* Introduction */

2008-01-19T02:02:46Z

Introduction

← Older revision		Revision as of 02:02, 19 January 2008
Line 47:		Line 47:


	~~A little knowledge is said to be a dangerous thing. Imagine how dangerous you can be with a little knowledge of CS, math, AND physics.~~

	Computational Science and Engineering is by its very nature multi- inter- and cross-disciplinary, with practitioners in the fields of mathematics, computer science, and domain specific sciences having to work together (or at least use the product of each others work) in a tight knit collaboration.		Computational Science and Engineering is by its very nature multi- inter- and cross-disciplinary, with practitioners in the fields of mathematics, computer science, and domain specific sciences having to work together (or at least use the product of each others work) in a tight knit collaboration.

Djoiner at 02:01, 19 January 2008

2008-01-19T02:01:49Z

← Older revision		Revision as of 02:01, 19 January 2008
Line 43:		Line 43:
	In order to broaden participation in HPC and computational science generally, more of our EOT efforts need to be directed towards faculty and students at smaller institutions, faculty who are primarily teachers, working with the next generation of scientists. These users require materials designed for learning how to use HPC and computational methods at a variety of levels, not just as the tools of a research scientist.		In order to broaden participation in HPC and computational science generally, more of our EOT efforts need to be directed towards faculty and students at smaller institutions, faculty who are primarily teachers, working with the next generation of scientists. These users require materials designed for learning how to use HPC and computational methods at a variety of levels, not just as the tools of a research scientist.

	~~===Challenges of modern HPC EOT===~~

	The challenge and the importance of HPC EOT was clearly laid out in the June 2005 report to the president "Computational Science: Assuring America's Competitiveness" (http://www.nitrd.gov/pitac/reports/20050609_computational/computational.pdf) and was reaffirmed in 2007 with the report "Is America Falling Off the Flat Earth?" (http://www.nap.edu/catalog.php?record_id=12021)		The challenge and the importance of HPC EOT was clearly laid out in the June 2005 report to the president "Computational Science: Assuring America's Competitiveness" (http://www.nitrd.gov/pitac/reports/20050609_computational/computational.pdf) and was reaffirmed in 2007 with the report "Is America Falling Off the Flat Earth?" (http://www.nap.edu/catalog.php?record_id=12021)

	~~====Who are the stakeholders?====~~


Line 75:		Line 72:
	Finally, there are a large body of non-scientists who have a fundamental lack of computational literacy. This is not exactly new, we've been dealing with a mathematically illiterate public for some time, however, computational literacy in some ways has lower barriers than mathematical literacy. The "eye-candy" factor cannot be ignored, both of technology with blinking lights and computational products that are animated and less abstract than mathematical products. A 3D animation of the formation and motion of a cloud system, for example, can convey information the novice can immediately recognize as valuable, with little recognition going to an isocontour plot of pressures across a flattened map, or perish the thought, a table of raw data reflecting the same situation.		Finally, there are a large body of non-scientists who have a fundamental lack of computational literacy. This is not exactly new, we've been dealing with a mathematically illiterate public for some time, however, computational literacy in some ways has lower barriers than mathematical literacy. The "eye-candy" factor cannot be ignored, both of technology with blinking lights and computational products that are animated and less abstract than mathematical products. A 3D animation of the formation and motion of a cloud system, for example, can convey information the novice can immediately recognize as valuable, with little recognition going to an isocontour plot of pressures across a flattened map, or perish the thought, a table of raw data reflecting the same situation.

	~~====Broader engagement====~~

	# For the purposes of EOT the current working definition of "underserved group" is too narrow. For the next generation of EOT it not only needs to cover the traditional areas of gender and race but also geography, specifically including rural areas which generally have not been well served by either technology build-out or educational efforts. These communities are full of smaller colleges and universities which could make very good use of both EOT offerings and computational resources.		For the purposes of EOT the current working definition of "underserved group" is too narrow. For the next generation of EOT it not only needs to cover the traditional areas of gender and race but also geography, specifically including rural areas which generally have not been well served by either technology build-out or educational efforts. These communities are full of smaller colleges and universities which could make very good use of both EOT offerings and computational resources.
	# If we are to broaden access to computational methods for a wide range of traditionally underserved groups (TUGs), the next generation of HPC EOT will need to do a better job of supporting first generation HPC consumers. This audience has much more modest needs for computational power but requires more human capital in the form of support for workshops, virtual rounds, curriculum materials, and software interfaces optimized for HPC pedagogy.

	~~====New fields====~~		If we are to broaden access to computational methods for a wide range of traditionally underserved groups (TUGs), the next generation of HPC EOT will need to do a better job of supporting first generation HPC consumers. This audience has much more modest needs for computational power but requires more human capital in the form of support for workshops, virtual rounds, curriculum materials, and software interfaces optimized for HPC pedagogy.

	~~# Humanities, arts, and social sciences~~		The disciplinary focus of HPC EOT activities has largely been in the natural sciences. Going forward we should be looking to engage a much wider audience, particularly building on efforts in the humanities, arts, and social science (HASS) communities. This will require changes at both the high level, making the language and processes of Grid computing more accessible to this wider audience, and at lower levels where software interfaces, curriculum materials, and support structure will need to be provided for those disciplines.
	## The disciplinary focus of HPC EOT activities has largely been in the natural sciences. Going forward we should be looking to engage a much wider audience, particularly building on efforts in the humanities, arts, and social science (HASS) communities. This will require changes at both the high level, making the language and processes of Grid computing more accessible to this wider audience, and at lower levels where software interfaces, curriculum materials, and support structure will need to be provided for those disciplines.
	~~# Engineering~~

	===Elements===		===Elements===
Line 141:		Line 134:
	Through the NCSI/SC workshops, we have seen a number of repeat participants, with our most successful participants coming to multiple workshops and progressing in their level of participation throughout. Typically our participants will show up the first time with a desire to see a lot of things and get a lot of hands on instruction. We know, however, we have made real impact when our participants come back to the workshop and tell us that they would really just like a machine in the corner, our help when they need it, and one week not in their office in which to get work done.		Through the NCSI/SC workshops, we have seen a number of repeat participants, with our most successful participants coming to multiple workshops and progressing in their level of participation throughout. Typically our participants will show up the first time with a desire to see a lot of things and get a lot of hands on instruction. We know, however, we have made real impact when our participants come back to the workshop and tell us that they would really just like a machine in the corner, our help when they need it, and one week not in their office in which to get work done.

	====Year-round support via Virtual Rounds ~~(ref Henry's paper)~~====		====Year-round support via Virtual Rounds====

	Henry ~~Neiman~~ has done an extraordinary job applying the notion of a doctor's rounds to helping support faculty and scientists learning to apply parallel methods to the discipline problems they want to solve computationally. Instead of dragging interns from bed to bed to learn the practice of being a doctor, Henry travels from office to office to help folk where they work.		Henry Neeman has done an extraordinary job applying the notion of a doctor's rounds to helping support faculty and scientists learning to apply parallel methods to the discipline problems they want to solve computationally. Instead of dragging interns from bed to bed to learn the practice of being a doctor, Henry travels from office to office to help folk where they work.

	We are working to extend this to the notion of virtual rounds. Once we have established a relationship with a person of group, it is possible to productively interact from a distance. A hard part is assembling the right tools. There is a certain utility to a conference call, but is hard to see things. The people we are serving don't have access grid nodes, so we have to find other ways to see. Through SC funding, we are exploring using a metaverse as a content rich environment to explore collaboration. Second Life is where the action is, unfortunately it is not particularly educational. The Open Croquet Consortium is promising for it more easy supports content, but there is a ways to go before we can explore the visualization of a computational model in world.		We are working to extend this to the notion of virtual rounds. Once we have established a relationship with a person of group, it is possible to productively interact from a distance. A hard part is assembling the right tools. There is a certain utility to a conference call, but is hard to see things. The people we are serving don't have access grid nodes, so we have to find other ways to see. Through SC funding, we are exploring using a metaverse as a content rich environment to explore collaboration. Second Life is where the action is, unfortunately it is not particularly educational. The Open Croquet Consortium is promising for it more easy supports content, but there is a ways to go before we can explore the visualization of a computational model in world.

Tmurphy: /* Including undergraduate and graduate students as assistant instructors */

2008-01-18T20:10:51Z

Including undergraduate and graduate students as assistant instructors

← Older revision		Revision as of 20:10, 18 January 2008
Line 112:		Line 112:
	# Broadens our reach in terms of age, gender, racial, and discipline diversity		# Broadens our reach in terms of age, gender, racial, and discipline diversity

			One of our biggest successes has been involving undergraduate and graduate students as assistant instructors and as collaborators in our HPC projects. It ended up starting up as a natural outgrowth of our own collaboration of academic focus (PhD granting institution, masters granting institution, liberal arts college, community college), as well as distance (California, Iowa, Illinois, New Jersey.) Our students have actually become (unofficially) our students. With the four of us collaborating across distance. For instance, Jessie a grad student at University of Northern Iowa is the lead investigator of the metaverse project on which Charlie from Earlham and Tom from Contras Costa are participating. Students from all our campus have been working with us and with each other on our LittleFe portable education project. We are even starting to incorporate students from other campuses we encounter though our workshops. The most gratifying part is our students are continuing to collaborate years after they have graduated.

			There are the very practical aspects of this arrangement. We don't have to have as many faculty leaders at the workshop, which is cost effective. The students have brought improvements to presentation material and have instituted new sessions as well. The students have also broadened our age, gender, racial, and discipline diversity

			This is not a guaranteed way to create a vast quantity of HPC ready graduates, but it provides a wonderful unique learning environment, where students can wield their academic knowledge as they gain real world experience.

	====Authenticity of experience====		====Authenticity of experience====

Tmurphy: /* Year-round support via Virtual Rounds (ref Henry's paper) */

2008-01-18T19:49:19Z

Year-round support via Virtual Rounds (ref Henry's paper)

← Older revision		Revision as of 19:49, 18 January 2008
Line 138:		Line 138:
	====Year-round support via Virtual Rounds (ref Henry's paper)====		====Year-round support via Virtual Rounds (ref Henry's paper)====

			Henry Neiman has done an extraordinary job applying the notion of a doctor's rounds to helping support faculty and scientists learning to apply parallel methods to the discipline problems they want to solve computationally. Instead of dragging interns from bed to bed to learn the practice of being a doctor, Henry travels from office to office to help folk where they work.

			We are working to extend this to the notion of virtual rounds. Once we have established a relationship with a person of group, it is possible to productively interact from a distance. A hard part is assembling the right tools. There is a certain utility to a conference call, but is hard to see things. The people we are serving don't have access grid nodes, so we have to find other ways to see. Through SC funding, we are exploring using a metaverse as a content rich environment to explore collaboration. Second Life is where the action is, unfortunately it is not particularly educational. The Open Croquet Consortium is promising for it more easy supports content, but there is a ways to go before we can explore the visualization of a computational model in world.

			Related to rounds, is the goal of re-gathering workshop attendees to get status of their successes and their current struggles so we can create mini-sessions to address those needs, much as we do during our regular workshops. Re-gathering in person is expensive; the same metaverse tools allowing rounds will allow us to create a virtual conference room support a similar environment to the original workshop.

	====Participation of all stakeholder disciplines====		====Participation of all stakeholder disciplines====

Tmurphy: /* Conclusion */

2008-01-18T19:27:30Z

Conclusion

← Older revision		Revision as of 19:27, 18 January 2008
Line 166:		Line 166:

	===Conclusion===		===Conclusion===

			In the end, like success in many areas, it is going to be impossible to state what one thing was seminal to the success of HPC education, outreach, and training. We could say the seminal event will be getting enough critical mass in terms of people and programs, but that is really a circular definition. Success is coming from all of our chipping away at it. We do know helping each person, course, and program is a step towards forming that critical mass; we know these advancements are often hard fought. Unless there are a few trees we are missing, there is not a lot of low hanging fruit.

			Involving faculty across many institutions and academic levels fosters HPC, involving graduates and undergraduates with interesting real life HPC problems fosters their experience and helps us achieve more, struggling to find and understand new applications of HPC helps, instituting rounds where we can support the growth of others in person or remotely is a win, and most of all, growing community has been both the best way to shoulder the load of HPC EOT, as well as to consistently stride towards our goals. The journey is much more pleasant walking with jovial companions.

	# Unanswered questions		# Unanswered questions

Tmurphy: /* Challenges of modern HPC EOT */

2008-01-18T19:09:41Z

Challenges of modern HPC EOT

← Older revision		Revision as of 19:09, 18 January 2008
Line 44:		Line 44:

	===Challenges of modern HPC EOT===		===Challenges of modern HPC EOT===

			The challenge and the importance of HPC EOT was clearly laid out in the June 2005 report to the president "Computational Science: Assuring America's Competitiveness" (http://www.nitrd.gov/pitac/reports/20050609_computational/computational.pdf) and was reaffirmed in 2007 with the report "Is America Falling Off the Flat Earth?" (http://www.nap.edu/catalog.php?record_id=12021)

	====Who are the stakeholders?====		====Who are the stakeholders?====

Tmurphy: /* Authors */

2008-01-18T19:03:22Z

Authors

← Older revision		Revision as of 19:03, 18 January 2008
Line 29:		Line 29:
	===Authors===		===Authors===

	Dave Joiner, Charlie Peck, Tom Murphy		Dave Joiner, Charlie Peck, Tom Murphy, Paul Gray

	===Introduction===		===Introduction===