Download to read offline
![17High-throughput screening on BG/P[SC08] “Towards Loosely-Coupled Programming on Petascale Systems”](https://image.slidesharecdn.com/apsfosterfebruary2011-110211130654-phpapp02/75/Opportunities-for-X-Ray-science-in-future-computing-architectures-17-2048.jpg)
![Datacomplexity also increasingID MURA_BACSU STANDARD; PRT; 429 AA.DE PROBABLE UDP-N-ACETYLGLUCOSAMINE 1-CARBOXYVINYLTRANSFERASEDE (EC 2.5.1.7) (ENOYLPYRUVATE TRANSFERASE) (UDP-N-ACETYLGLUCOSAMINEDE ENOLPYRUVYL TRANSFERASE) (EPT).GN MURA OR MURZ.OS BACILLUS SUBTILIS.OC BACTERIA; FIRMICUTES; BACILLUS/CLOSTRIDIUM GROUP; BACILLACEAE;OC BACILLUS.KW PEPTIDOGLYCAN SYNTHESIS; CELL WALL; TRANSFERASE.FT ACT_SITE 116 116 BINDS PEP (BY SIMILARITY).FT CONFLICT 374 374 S -> A (IN REF. 3).SQ SEQUENCE 429 AA; 46016 MW; 02018C5C CRC32; MEKLNIAGGD SLNGTVHISG AKNSAVALIP ATILANSEVT IEGLPEISDI ETLRDLLKEI GGNVHFENGE MVVDPTSMIS MPLPNGKVKK LRASYYLMGA MLGRFKQAVI GLPGGCHLGP RPIDQHIKGF EALGAEVTNE QGAIYLRAER LRGARIYLDV VSVGATINIM LAAVLAEGKT IIENAAKEPE IIDVATLLTS MGAKIKGAGT NVIRIDGVKE LHGCKHTIIP DRIEAGTFMI[source: GlaxoSmithKline]](https://image.slidesharecdn.com/apsfosterfebruary2011-110211130654-phpapp02/75/Opportunities-for-X-Ray-science-in-future-computing-architectures-21-2048.jpg)
Uploaded byIan Foster
Opportunities for X-Ray science in future computing architectures
The document discusses advancements in computing architecture, highlighting trends such as petascale and cloud computing, with implications for x-ray science and facilities. It emphasizes the importance of massive parallelism, large data handling, and economic aggregation in future computing challenges. The document also touches on various computational methods and the necessity for automation in scientific processes to enhance discovery and efficiency.
More Related Content
Similar to Opportunities for X-Ray science in future computing architectures
More from Ian Foster
![Vibe Coding vs. Spec-Driven Development [Free Meetup]](https://cdn.slidesharecdn.com/ss_thumbnails/vibecodingvsspecdrivendevelopment-251209105622-43f455e7-thumbnail.jpg?width=640&height=640&fit=bounds)
Opportunities for X-Ray science in future computing architectures
- 1. Opportunities for X-rayscience in future computing architectureIan FosterComputation InstituteUniversity of Chicago & Argonne National Laboratory
- 2. AbstractThe world ofcomputing continues to evolve rapidly. In just the past 10 years, we have seen the emergence of petascale supercomputing, cloud computing that provides on-demand computing and storage with considerable economies of scale, software-as-a-service methods that permit outsourcing of complex processes, and grid computing that enables federation of resources across institutional boundaries. These trends shown no signs of slowing down: the next 10 years will surely see exascale, new cloud offerings, and terabit networks. In this talk I review various of these developments and discuss their potential implications for a X-ray science and X-ray facilities.
- 3. Fastest supercomputer(floating pointops/sec)1E+17multi-PetaflopPetaflopBlue Gene/L1E+14ThunderRed StormEarthBlue PacificASCI White, ASCI QSX-5ASCI Red OptionASCI RedT3ESX-4NWTCP-PACS1E+11CM-5ParagonT3DDeltaSX-3/44Doubling time = 1.5 yr.i860 (MPPs)VP2600/10SX-2CRAY-2Y-MP8S-810/20X-MP4Cyber 205Peak Speed (flops)X-MP2 (parallel vectors)1E+8CRAY-1CDC STAR-100 (vectors)CDC 7600ILLIAC IVCDC 6600 (ICs)IBM Stretch1E+5IBM 7090 (transistors)IBM 704IBM 701UNIVACENIAC (vacuum tubes)1E+219401950196019701980199020002010Year IntroducedArgonneMy laptop
- 4.
- 5. Brahe30 years? years10years6 years2 yearsKepler
- 6. Brahe30 years? years10years6 years2 yearsKepler
- 7.
- 8. Sloan Digital SkySurvey
- 10. Aggregate SkyServer monthlytraffic from 2001 to 2006. (Singh et al., 2006)Sloan Digital Sky Survey publication statistics, Chen et al., 2009.
- 11. Three discontinuities:1) Massiveparallelism2) Large data3) Economics of aggregation
- 12. Intel x86 processortrends
- 13. Gordon Bell prizewinners
- 14. ComplexityDimensionsAlgorithmsCoupled (& non-linear)equationsTimescaleOptimizationError analysisParameters or ensemble membersResolutionTimeSimple Complex1 2 31 ManyShort Long MultiscaleFew ManyNo YesCoarse Fine AdaptiveNo YesDan Katz
- 15. Rational design ofcatalytic materials(Curtis, Greely, Zapol, Kumaran)CreateSynthesis and processing methods informed by computation; generate dataDesignMaterials with desired properties based on computation and dataUnderstandRelationship between materials properties and structure1515
- 16.
- 17. 17High-throughput screening onBG/P[SC08] “Towards Loosely-Coupled Programming on Petascale Systems”
- 18. Three discontinuities:1) Massiveparallelism2) Large data3) Economics of aggregation
- 19. PC disk drivecapacity
- 20. Data generation andanalysis costs outpace Moore’s Law$900,000Wilkening et al, IEEE Cluster09
- 21. Datacomplexity also increasingID MURA_BACSU STANDARD; PRT; 429 AA.DE PROBABLE UDP-N-ACETYLGLUCOSAMINE 1-CARBOXYVINYLTRANSFERASEDE (EC 2.5.1.7) (ENOYLPYRUVATE TRANSFERASE) (UDP-N-ACETYLGLUCOSAMINEDE ENOLPYRUVYL TRANSFERASE) (EPT).GN MURA OR MURZ.OS BACILLUS SUBTILIS.OC BACTERIA; FIRMICUTES; BACILLUS/CLOSTRIDIUM GROUP; BACILLACEAE;OC BACILLUS.KW PEPTIDOGLYCAN SYNTHESIS; CELL WALL; TRANSFERASE.FT ACT_SITE 116 116 BINDS PEP (BY SIMILARITY).FT CONFLICT 374 374 S -> A (IN REF. 3).SQ SEQUENCE 429 AA; 46016 MW; 02018C5C CRC32; MEKLNIAGGD SLNGTVHISG AKNSAVALIP ATILANSEVT IEGLPEISDI ETLRDLLKEI GGNVHFENGE MVVDPTSMIS MPLPNGKVKK LRASYYLMGA MLGRFKQAVI GLPGGCHLGP RPIDQHIKGF EALGAEVTNE QGAIYLRAER LRGARIYLDV VSVGATINIM LAAVLAEGKT IIENAAKEPE IIDVATLLTS MGAKIKGAGT NVIRIDGVKE LHGCKHTIIP DRIEAGTFMI[source: GlaxoSmithKline]
- 22.
- 25.
- 26. “light sources aloneare not enough … Enormous data sets of diffracted signals in reciprocal space and across wide energy ranges mustbe collected and analyzed in real time so that they can guide the ongoing experiments.”
- 27.
- 28. Pattern recognition inx-ray spectromicroscopyKevin Boyce, U. Chicago: study of the evolution of tree types, including now-extinct species that dominated in the “coal age” (carboniferous). Acetate peel of fossilized wood.Shows how well we can separately map cellulose-derived material from lignin-derived material in plant cell walls, with implications for cellulosic ethanol production from biomass.Lignin-derived and cellulose-derived regions in 400 million year old chert: Boyce et al., Proc. Nat. Acad. Sci. 101, 17555 (2004), with subsequent pattern recognition analysis by Lerotic, Jacobsen, Schäfer, and Vogt, Ultramicroscopy100, 35 (2004).
- 29. LDRD: “Next GenerationData Exploration - Intelligence in Data Analysis, Visualization, & Mining”“Here’s a cell in this tissue. How much zinc does it have? In the rest of the tissue, how many cells are there like this, and what is their distribution of zinc content?”Fluorescence and absorption spectral imagingDatabases to combine results of multiple experiments and instrumentsMultivariate statistical analysis and pattern recognitionPeople:APS: Stefan Vogt (PI), Lydia Finney, Chris Jacobsen, Chris Roerhig, Claude Saunders, Jesse Ward; Mathematics and Computer Science, ANL: Sven Leyffer, Stefan Wild, Mark Hereld; Northwestern: Rachel Mak
- 30.
- 31. Rapid evolution of10GbE port pricesmakes campus-Scale 10 Gbps affordable$80K/port Chiaro(60 Max)$ 5KForce 10(40 max)~$1000(300+ Max)$ 500Arista48 ports$ 400Arista48 ports2005 2007 2009 2010Source: Philip Papadopoulos, SDSC, UCSD
- 34. Three discontinuities:1) Massiveparallelism2) Large data3) Economics of aggregation
- 35.
- 36. Economies of scalein operations
- 37. Time-consuming tasks inbusiness Web presenceEmail (hosted Exchange)Calendar Telephony (hosted VOIP) Human resources and payroll Accounting Customer relationship mgmt Data analytics Content distribution …SaaS
- 38. Time-consuming tasks inbusiness Web presenceEmail (hosted Exchange)Calendar Telephony (hosted VOIP) Human resources and payroll Accounting Customer relationship mgmtData analytics Content distribution …SaaSIaaS
- 39. Time-consuming tasks inscienceRun experimentsCollect dataManage dataMove dataAcquire computersAnalyze dataRun simulationsCompare experiment with simulationSearch the literatureCommunicate with colleagues
- 40.
- 41. Find, configure, installrelevant software
- 42. Find, access, analyzerelevant data
- 43.
- 44.
- 45.
- 46.
- 47.
- 48. Time-consuming tasks inscienceRun experimentsCollect dataManage dataMove dataAcquire computersAnalyze dataRun simulationsCompare experiment with simulationSearch the literatureCommunicate with colleagues
- 49.
- 50. Find, configure, installrelevant software
- 51. Find, access, analyzerelevant data
- 52.
- 53.
- 54.
- 55. …Time-consuming tasks inscienceRun experimentsCollect dataManage dataMove dataAcquire computersAnalyze dataRun simulationsCompare experiment with simulationSearch the literatureCommunicate with colleagues
- 56.
- 57. Find, configure, installrelevant software
- 58. Find, access, analyzerelevant data
- 59.
- 60.
- 61.
- 62. …A peek insideGlobus OnlineDatastoreProfiles+ stateGridFTPWorkerWorkerConsumerWorkerConsumerWorkerConsumerGridFTPWorkerConsumerRequestcollectorNotificationtarget
- 65. Task ID :bc6d776c-2af4-11e0-9a1d-12313916526cTask Type : TRANSFERParentTask ID : n/aStatus : SUCCEEDEDRequest Time : 2011-01-28 15:39:04ZDeadline : 2011-01-29 15:39:04ZCompletion Time : 2011-01-28 16:17:12ZTotal Tasks : 500TasksSuccessful : 500TasksExpired : 0TasksCanceled : 0TasksFailed : 0TasksPending : 0TasksRetrying : 0Command : transfer (+500 input lines)Files : 500Directories : 0Bytes Transferred: 1073741824000MBits/sec : 3754.342ALCF-NERSCtask summary
- 66. 11 x 125files200 MB each11 users12 sites
- 67. Keith Cheng’s phenomeprojectGordonKindlmann3000 zebra fish mutants
- 68. Penn State UniversityPhenomeProject CoordinationArgonne / U Chicago Grid Supercomputing FacilityArgonne National LabAdvancedPhoton SourceGraphics WorkstationsTomographic Reconstruction, Deringing, Segmentation, Morphometrics & VisualizationDASAPS BeamlineData AcquisitionPattern Recognition Segmentation & Visualization Software Develop.NASGridFTPServerGridFTP ServerSANGridFTPServerHPC Cluster1 Gbps Network link10 Gbps Network linkRegular Internet linkBeamline data flowGlobus Online - hosted service for high-speed, reliable, secure data movementUsers
- 69. Penn State UniversityPhenomeProject CoordinationArgonne / U Chicago Grid Supercomputing FacilityArgonne National LabAdvancedPhoton SourceGraphics WorkstationsTomographic Reconstruction, Deringing, Segmentation, Morphometrics & VisualizationDASAPS BeamlineData AcquisitionPattern Recognition Segmentation & Visualization Software Develop.NASGridFTPServerGridFTP ServerSANGridFTPServerHPC Cluster1 Gbps Network link10 Gbps Network linkRegular Internet linkBeamline data flowGlobus Online - hosted service for high-speed, reliable, secure data movementUsers
- 70. Four thesesUltrascale computingenables new problem-solving methodsResearch data management is an essential service like electricity and networkingEconomies of scale motivate highly aggregated computing and storageAutomation of science processes accelerates discovery and yields competitive advantage
- 71.
Editor's Notes
- #3 Trends: computers, storage, detectors, …It’s the ratios that matter: Cores/CPU, CPUs/computer, data/scientistExperiment and simulation
- #5 To show what I means, let’s look at the example of astronomy again.Tycho Brahe … 30 years cataloging the position of 777 stars and the known planets with great accuracyHis assistant Kepler then took the data, and from it derived his laws of planetary motion, which say that bodies sweep out equal areas in equal time. A precursor to Newton’s law of gravitation.
- #6 To show what this means, let’s look at the example of astronomy once again.Tycho Brahe … 30 years cataloging the position of 777 stars and the known planets with great accuracyHis assistant Kepler then took the data, and from it derived his laws of planetary motion, which say that bodies sweep out equal areas in equal time. A precursor to Newton’s law of gravitation.
- #7 Some allege that Kepler took unusual steps to acquire his data. Hopefully not so common.
- #8 Photographic plates We need computers!Here are some early computers in Harvard Observatory, around 1890.Computing the consequences of equations became a profession1 multiplication per 2 seconds, maybe, x 8 people, 4 multiplications per secondHowever, unreliable and hard to get to work more than 8 hours per day
- #9 By the late 1990s, in 5 years, imaged 230 million celestial objects, measuring the spectra of more than 1 million of them
- #10 “Slices through the SDSS 3-dimensional map of the distribution of galaxies. Earth is at the center, and each point represents a galaxy, typically containing about 100 billion stars. Galaxies are colored according to the ages of their stars, with the redder, more strongly clustered points showing galaxies that are made of older stars. The outer circle is at a distance of two billion light years. The region between the wedges was not mapped by the SDSS because dust in our own Galaxy obscures the view of the distant universe in these directions. Both slices contain all galaxies within -1.25 and 1.25 degrees declination.”
- #13 http://xrds.acm.org/article.cfm?aid=1836552
- #21 Sequencing volumes doubling every 4-6 months.Note the log scale!Bioinformatics cost is purely BLAST;values are in Amazon EC2Lessons: 1) Need computer scientists; 2) Need more hardware; 3) Need more collaboration on analysis.
- #23 In contrast, see SDSS—and also Google.VolumeDiversity and complexitySpeed of analysis
- #25 Research data management in 2011
- #27 Photon science recognizes the importance of computing.However, if we perform some simple textual analysis, we see that ~1% of the report talks about computing and data. 670 out of 50,676 words—1.3%
- #28 Liz Lyon, U. Bath—Associate Director, UK Digital Curation CenterGeneric Data Acquisition (GDA) software developed at Daresbury initially, now at Diamond Light Source.
- #29 Chris Jacobsen
- #31 What about networking?Difficult to price, but many experts estimate a doubling time of 9 months for network capacity thanks to WDM and optical doping.10 Gbps per User ~ 100-1000x Shared Internet Throughput
- #32 Port Pricing is Falling Density is Rising – Dramatically Cost of 10GbE Approaching Cluster HPC Interconnects
- #33 Chicago is an international networking hub
- #34 Chicago railroads, 1950 (http://www.encyclopedia.chicagohistory.org/pages/1774.html)
- #35 Motivated by enormous parallelism,massive data, complexityEnabled by networks
- #36 What’s this got to do with that cloud thing?Recall that “cloud” is a term used to mean a few different things
- #37 Next question: Where does computing happen? Massive parallelism in computing and storage. Operations costs go up.Google data center in OregonNote also variation in cost of power: factor of 5
- #38 Interestingly, if we look at the situation in business, things are quite different.There is a similarly long list of time-consuming tasks. There is a large and growing SaaS industry that addresses many of them.If I start a business today, I can do it from a coffee shop—there is no need to acquire and run any IT at all. I can outsource …
- #39 Of course, people also make effective use of IaaS, but only for more specialized tasks
- #40 So let’s look at that list again.I and my colleagues started an effort a little while ago aimed at applying SaaS to one of these tasks …
- #42 The result of this work is something called Globus Online. This is something new. Not just more of the same Globus Toolkit stuff.Globus Toolkit: hasn’t changed. Been around 15 years. Still a toolkit for building custom Grids such as LHC, TeraGrid, ESG, BIRN, LIGO, etc.Globus Online: Focused on out sourcing the time-consuming activities associated with data transfer. Register, transfer, monitor, and customize endpoints.Globus Online is a full Web 2.0-based solution. That means a few different things. First, it is architected using REST principles: important elements are exposed as resources, on which operations can be performed using HTTP operations. These operations can be used directly, or via powerful AJAX Web GUIs.
- #43 The deceptively simple task of moving data from place to another.You might ask: What could be simpler. I simply stick it in the mail, right? But we’re talking about data that is too large to email. Maybe I need to move 100,000 files totaling 10 Terabytes from a federal laboratory where they were generated to my home institution. That sort of thing which can be very difficult.Hai Ah Nam, a nuclear physicist from Oak Ridge, spoke at GlobusWorld March 2010 about her struggles with moving dataInitially transferring 1.6 TB (86 large files) from Oak Ridge to NERSCChanged from using SCP to GridFTP to reduce transfer from days to hoursReduced transferring 137 TB from months to daysBut, it was not easy...
- #44 The deceptively simple task of moving data from place to another.You might ask: What could be simpler. I simply stick it in the mail, right? But we’re talking about data that is too large to email. Maybe I need to move 100,000 files totaling 10 Terabytes from a federal laboratory where they were generated to my home institution. That sort of thing which can be very difficult.Hai Ah Nam, a nuclear physicist from Oak Ridge, spoke at GlobusWorld March 2010 about her struggles with moving dataInitially transferring 1.6 TB (86 large files) from Oak Ridge to NERSCChanged from using SCP to GridFTP to reduce transfer from days to hoursReduced transferring 137 TB from months to daysBut, it was not easy...
- #45 Under the covers: built as a scale-out web applicationHosted on Amazon Web ServicesReplicate state data over multiple storage servers.Dynamically scale number of VMs.
- #49 Explain attempts; a cornerstone of our failure mitigation strategyThrough repeated attempts GO was able to overcome transient errors at OLCF and rangerThe expired host certs on bigred were not updated until after the run had completed
- #50 3000 zebra fish mutants
- #51 Collect, move, store, index,analyze, share, update, iterate; millions of files;1000s of experiments