Future Directions for NSF Advanced Computing Infrastructure to Support U.S. Science and Engineering in 2017-2020 (2016) / Chapter Skim
Currently Skimming:
2 Background
2 Background
Pages 25-51
The Chapter Skim interface presents what we've algorithmically identified as the most significant single chunk of text within every page in the chapter.
Select key terms on the right to highlight them within pages of the chapter.
From page 25... ...
. For compute-intensive research, it includes not 1 National Research Council, Future Directions for NSF Advanced Computing Infrastructure to Support U.S.
|
From page 26... ...
Others are creating ways for their researchers to pool funds into a shared computing infrastructure (creat ing what in many ways is a private cloud) , which may also be partly supported by institutional funds.
|
From page 27... ...
of data as well as modeling and simulation. Historically, and even now, NSF advanced computing centers have focused on high-performance computing primarily for simulation.
|
From page 28... ...
Today, advanced computing capabilities are involved in an even wider range of scientific fields and challenges, and the rise of data-driven science requires new approaches. The gap between 3 Task Force on the Future of the NSF Supercomputer Centers Program, Report of the Task Force on the Future of the NSF Supercomputer Centers Program, National Science Foundation, Washington, D.C., September 15, 1995, http://www.nsf.gov/pubs/1996/nsf9646/nsf9646.
|
From page 29... ...
• Capacity computing refers to computing with large numbers of applications, none of which require a "capability" platform but in their aggregate require large amounts of computing power. • High-throughput computing refers to the use of many computing resources over a period of time to attack a particular set of computational tasks.
|
From page 30... ...
This section reviews the state of the art in hardware, software, and algorithms, with a particular emphasis on the challenges created by the disruptive changes in computer architecture driven by the need to increase computing power. 2.4.1 Hardware The past decade has seen an enormous disruption in computer hardware throughout the computing industry, as processor clock speed increases have stalled and parallel processing has moved on-chip with multicore processors.6 The primary drivers have been power density and total energy consumption -- concerns that are important in portable devices and increasingly in large data and compute centers due to fundamental cooling limits of packaging and overall facility infrastructure and operations costs.
|
From page 31... ...
Box 2.2 contains further discussion of these architectural challenges. One consequence of the growth in the use of computing by all aspects of society and not just for science research is that much of the investment by both computer hardware and software vendors is directed at the larger commercial market for computing.
|
From page 32... ...
1.E+06 1.E+05 1.E+04 1.E+03 1.E+02 1.E+01 1/1/92 1/1/96 1/1/00 1/1/04 1/1/08 1/1/12 1/1/16 Heavyweight Lightweight Hybrid Trend: CAGR=1.88 FIGURE 2.2.1 Speed of Top 10 systems from TOP500 ranking. SOURCE: Updated from Peter Kogge, "Updating the Energy Model for Future Exascale Systems," in High Performance Computing: 30th International Conference, ISC High Performance 2015, Frankfurt, Germany, July 12-16, 2015, Proceedings, using data from http://top500.org.
|
From page 33... ...
SOURCE: Updated from Peter Kogge, "Updating the Energy Model for Future Exascale Systems," in High Performance Computing: 30th International Conference, ISC High Performance 2015, Frankfurt, Germany, July 12-16, 2015, Proceedings, using data from http://graph500.org. benchmark represents the solution of a large matrix equation (as does LINPACK)
|
From page 34... ...
SOURCE: Updated from Peter Kogge, "Updating the Energy Model for Future Exascale Systems," in High Performance Computing: 30th International Conference, ISC High Performance 2015, Frankfurt, Germany, July 12-16, 2015, Proceedings. The reason for this constraint goes back to architecture and the way com mercial memory chips are attached to modern processors.
|
From page 35... ...
SOURCE: Updated from Peter Kogge, "Updating the Energy Model for Future Exascale Systems" in High Performance Computing: 30th International Conference, ISC High Performance 2015, Frankfurt, Germany, July 12-16, 2015, Proceedings. the single-chip microprocessor in the early 1990s and the rise of multicore in the mid-2000s.
|
From page 36... ...
The scientific modeling and simulation community has billions of dollars invested in software based on message passing between serial programs, with only isolated examples of applications that can take advantage of accelerators. Shrinking memory size per core is a problem for some applications, and explicit data movement may require significant code rewriting because it requires careful consideration of which data structures should be allocated in each type of memory, keeping track of memory size limits, and scheduling data movement between memory spaces as needed.
|
From page 37... ...
Data storage has also undergone its own exponential improvement, with both data densities (bits per unit area) and bit per unit cost doubling every 1 to 2 years.
|
From page 38... ...
In addition to use in storage, the price, performance, persistence, and power characteristics of non-volatile memory technologies enable innovations in computer architectures to complement regular DRAM, such as in the proposed DOE pre-exascale systems. In summary, over the next few years, HDD storage capacity will continue to decrease slowly in cost, but various performance metrics will see revolutionary change as non-volatile memory technologies become even more price competitive, and eventually storage capacity itself will fall in cost once silicon technologies dominate.
|
From page 39... ...
Recently, interconnect design principles from HPC, such as more highly connected networks with better bisection bandwidth and latencies, have been adopted for commercial applications.7 Also of importance is wide-area networking, which is critical to the success of NSF's advanced computing, especially in terms of providing access and the infrastructure necessary to bring together data sources and computing resources. The size of some data sets is forcing some data offline or onto remote storage, so storage hierarchies, storage architectures, and WAN (wide area network)
|
From page 40... ...
They may use FORTRAN for numerical kernels, C++ for complex data structures, and Python to manage the steps in a software pipeline, and they may call multiple scientific libraries that are themselves written in other languages. Parallelism is typically ex pressed using message passing, typically MPI, possibly with threading used for on
|
From page 41... ...
The diversity of libraries used in scientific computing gives some indication of the software investment needed to sustain a broad program of scientific discovery using HPC. Tables 2.3.1 and 2.3.2 show the usage of some of the most popular scientific libraries and programming models in one center based on a survey of users and weighted by the number of hours each project uses.
|
From page 42... ...
Machine characteristics may also affect the choice of algorithms, as the relative costs of computation, data movement, and data storage continue to change across generations, along with the types and degrees of hardware parallelism. Minimizing the total work performed is generally a desirable metric, but on machines with very fast processing and limited bandwidth, recomputation or other seemingly expensive computations may pay off if data movement is reduced, and memory size limits can make some algorithms impractical.
|
From page 43... ...
Machine learning algorithms based on neural networks, for example, are only effective because of the performance of modern hardware, and the massive high-throughput computations of the Materials Genome Initiative would not be possible on the hardware available two decades ago. So while hardware performance gains will be increasingly difficult in the future, substantial algorithmic improvements for some problems are probably impossible.
|
From page 44... ...
44 FUTURE DIRECTIONS FOR NSF ADVANCED COMPUTING INFRASTRUCTURE BOX 2.4 Continued FIGURE 2.4.1 Top: A table of the scaling of the memory and processing requirements for the solution of the electrostatic potential equation on a uniform cubic grid of n × n × n cells for n = 64. Bottom: The relative gains of some solutions algorithms for this problem and Moore's law for the improvement of processing rates over the same period.
|
From page 45... ...
A significant fraction of ACI's investments have been for two tiers of advanced computing hardware; a petascale computing system, Blue Waters, deployed in 2013 at the University of Illinois, and a distributed set of systems deployed under the eXtreme Digital program and integrated by the Extreme Science and Engineering Discovery Environment (XSEDE)
|
From page 46... ...
Trends in the overall investment in advanced computing can be seen by looking at the spending amounts reported by federal agencies to the Networking and Information Technology Research and Development program's National Coordination Office. Figure 2.1 shows the total federal investment in all categories tracked by Networking and Information Technology Research and Development (NITRD)
|
From page 47... ...
NOTE: CSIA, Cyber Security and Information Assurance; HCIIM, Human Computer Interaction and Information Management; HCSS, High Confidence Software and Systems; HECIA, High-End Computing Infrastructure and Applications; HECRD, High-End Computing Research and Development; LSN, Large Scale Networking; SDP, Software Design and Productivity; SEW, Social, Economic, and Workforce Implications of IT and IT Workforce Development. SOURCE: Compiled from data provided in annual supplements to the president's budget request, prepared by the National Coordination Office for the Networking and Information Technology Research and Development program, https://www.nitrd.gov/Publications/ SupplementsAll.aspx.
|
From page 48... ...
in millions of dollars. NOTE: CSIA, Cyber Security and Information Assurance; HCIIM, Human Computer Interaction and Information Management; HCSS, High Confidence Software and Systems; HECIA, High-End Computing Infrastructure and Applications; HECRD, High End Computing Research and Development; LSN, Large Scale Networking; SDP, Software Design and Productivity; SEW, Social, Economic, and Workforce Implications of IT and IT Workforce Development.
|
From page 49... ...
SOURCE: Derived from data obtained by querying Open XDMoD database, University at Buffalo. All Others 226M Other 154M 5% 3% DOD 252M 6% NASA 312M 7% NSF 2113M None 333M 46% 7% DOE 503M 11% NIH 672M 15% FIGURE 2.4 Estimated use in XSEDE service units of NSF advanced computing by grantees of other federal agencies, based on allocations of XSEDE resources over calendar year 2014.
|
From page 50... ...
2.7 NATIONAL STRATEGIC COMPUTING INITIATIVE As this study was being completed, an executive order11 was issued establishing a National Strategic Computing Initiative. Section 3a of the order designates NSF as one of the three lead agencies for the initiative and calls for NSF to "play a central role in scientific discovery advances, the broader HPC ecosystem for scientific discovery, and workforce development." Box 2.5 compares items in the executive order with the major themes of this report.
|
From page 51... ...
NSCI calls for acceleration of the deployment of an exascale class system but says nothing about the acceleration needed for future science needs at all scales. 1 Executive Office of the President, "Executive Order -- Creating a National Strategic Com puting Initiative," July 29, 2015, https://www.whitehouse.gov/the-press-office/2015/07/29/ executive-order-creating-national-strategic-computing-initiative.
|
Key Terms
This material may be derived from roughly machine-read images, and so is provided only to facilitate research.
More
information on Chapter Skim is available.