1. Make It So ! A Tale of Two Needs Dr. Robert W. Wisniewski Chief Software Architect Extreme Scale Computing Senior Principal Engineer, Intel Corporation Smoky Mountains Conference September 4, 2014 Copyright © 2014 Intel Corporation. All rights reserved. 1

2. Legal Disclaimer Results have been estimated based on internal Intel analysis and are provided for informational purposes only. Any difference in system hardware or software design or configuration may affect actual performance. Intel, processors, chipsets, and desktop boards may contain design defects or errors known as errata, which may cause the product to deviate from published specifications. Current characterized errata are available on request. Intel, Intel Xeon, Intel Core microarchitecture, and the Intel logo are trademarks or registered trademarks of Intel Corporation or its subsidiaries in the United States and other countries. *Other names and brands may be claimed as the property of others Copyright © 2014, Intel Corporation. All rights reserved.

3. Motivation for this Talk 3 Your Supercomputer 25 Years Ago hardware kernel compiler Application

4. Cray XC30 Software Stack 4

5. 5

6. Motivation for this Talk Building Web Pages Recent PhD talk Turtles all the way down HW and SW getting more complex 6

7. Motivation for this Talk Building Web Pages Recent PhD talk Rabbits all the way down HW and SW getting more complex 7

8. 1701D Supposition: analogous to dark silicon, let the “free” cycles do the work 8 Make It So

9. Before Proceeding Not for everyone –Consider cut through high performance Good for new applications –Biological for example –Enables new ways of approaching the problem Delivering on the needs of the next machine, the next next machine, and the exascale machine 9

10. 10 Exa Peta Zeta PEZ Exascale is only a point on the continuum

11. 11 When investigations began Challenges too great with current SW Need all new OS, compiler, language… Others advocated Enhance capability of existing Hard, drive evolutionary approach OR ?? Extreme-Scale Software Challenge

12. Revolutionary versus Evolutionary 12 Which one ?

13. Revolutionary Only 13 Imagine vendors telling their customers throw out everything you’ve done over the last 20+ years. Leverage tremendous investment in Intel Architecture ecosystem.

14. Evolutionary Only 14 But there are serious challenges getting to exascale. Drive new innovations and invigorate the x86 ecosystem.

15. The Real Extreme-Scale Software Challenge 15 The real challenge in moving software to extreme scale, and therefore the real solution, will be figuring out how to incorporate and support existing computation paradigms in an evolutionary model while simultaneously supporting new revolutionary paradigms. AND

16. 1701D Supposition: analogous to dark silicon, let the “free” cycles do the work 16 Make It So

17. Maybe not so far fetched, done this a bit already Compilers Demand paging –No –Yes 17

18. mOS : multiple Operating System 18 Run multiple OSes on node simultaneously Linux API with LWK performance Kernel is configured for the application –Provides compatibility and performance/scalability/reliability Compute Node Linux Linux I/O daemon OS Node N:1 LWK OS Linux Application HPC System Platform Software partitioned glibc/shim App Assist tools

19. Global OS Resilience Dynamic Resolve as many faults as possible –Extra nodes swapped in automatically (proactively if possible) –NVRAM accessible independent of node –Automatic checkpoint of DRAM to NVRAM –For unresolvable provide fault information to application 19 CN Linux API Argo Hobbes OSN SMC HPC network nvram CN SMC

20. Runtimes and Libraries 20 Effort Pyramid Application (100+) Runtime/Lib (10+) HW LL SW (1+) task i data in control in datacontrol task n core task n runtime Over commit –Adaptive, asynchronous, load balance, fault tolerance Building block approach

21. Data Management for Big Data Smooth and automatic representation between –Application data structure in memory –Representation and access to NVRAM –Storage to disk Moving compute to data Application makes system call –make_permanent(*data), make_durable(*data) 21 main() A[100][100][100]; graph_node { int value; edge e1; } RAM nvram main()

22. 22 It was the Best, It was the Worst of Times It was evolutionary, it was revolutionary It was research, it was development

23. Weaving the Two Tales (Needs) Together –This is possible 23 Research/Out-of-Box Development/Evolution & Revolution Single Unified Project Time Value

24. Fundamental Discovery to Gain Fundamental Insights Technical Computing Continues Its Rapid Growth Other brands, names and images may be claimed as the property of others Source: IDC: Worldwide Technical Computing Server 2013–2017 Forecast; Other brands, names, and images are the property of their respective owners. Governments & Research Commercial/IndustrialNew Users – New Uses Business Transformation Big Data Analytics Enabling Data Driven Science Better Products Faster Time to Market Reduced R&D From Diagnosis to personal- ized treatment quickly Genomics Clinical Information HPC: Transforming the world of data and information into KNOWLEDGE “My goal is simple. It is complete understanding of the universe, why it is as it is and why it exists at all” Stephen Hawking

25. Conclusion –The Best of Both Worlds –Leverage PEZ(Y) cycles to provide higher level and more productive abstractions to applications –We need to build tomorrow’s turtles/rabbits –We will get to extreme scale (PEZ) by figuring out how to incorporate existing computation paradigms in an evolutionary model while simultaneously supporting new revolutionary paradigms 25 1701D AND