1. NGS Workshop: Feb 2002PPL-Dept of Computer Science, UIUC Programming Environment and Performance Modeling for million-processor machines Laxmikant (Sanjay) Kale Parallel Programming Laboratory Department of Computer Science University of Illinois at Urbana-Champaign Http://charm.Cs.uiuc.edu

2. NGS Workshop: Feb 2002PPL-Dept of Computer Science, UIUC Context: Group Mission and Approach To enhance Performance and Productivity in programming complex parallel applications –Performance: scalable to very large number of processors –Productivity: of human programmers –Complex: irregular structure, dynamic variations Approach: Application Oriented yet CS centered research –Develop enabling technology, for a wide collection of apps. –Develop, use and test it in the context of real applications –Develop standard library of reusable parallel components

3. NGS Workshop: Feb 2002PPL-Dept of Computer Science, UIUC Project Objective and Overview Focus on extremely large parallel machines –Exemplified by Blue Gene/Cyclops Issues: –Programming Environment: Objects, threads, compiler support –Runtime performance adaptation –Performance modeling Coarse grained models Fine grained models Hybrid –Applications: Unstructured Meshes (FEM/Crack Propagation),.. David Padua Sanjay Kale Sarita Adve Phillipe Geubelle

4. NGS Workshop: Feb 2002PPL-Dept of Computer Science, UIUC Project Objective and Overview Focus on extremely large parallel machines –Exemplified by Blue Gene/Cyclops Issues: –Programming Environment –Runtime performance adaptation –Performance modeling Coarse grained models Fine grained models Hybrid –Applications: Unstructured Meshes (FEM/Crack Propagation),.. David Padua Sanjay Kale Sarita Adve Phillipe Geubelle

5. NGS Workshop: Feb 2002PPL-Dept of Computer Science, UIUC Multi-partition Decomposition Idea: divide the computation into a large number of pieces –Independent of number of processors –Typically larger than number of processors –Let the system map entities to processors Optimal division of labor between “system” and programmer: Decomposition done by programmer, Everything else automated

6. NGS Workshop: Feb 2002PPL-Dept of Computer Science, UIUC Object-based Parallelization User View System implementation User is only concerned with interaction between objects

7. NGS Workshop: Feb 2002PPL-Dept of Computer Science, UIUC Charm++ Parallel C++ with Data Driven Objects Object Arrays/ Object Collections Object Groups: –Global object with a “representative” on each PE Asynchronous method invocation Prioritized scheduling Information sharing abstractions: readonly, tables,.. Mature, robust, portable http://charm.cs.uiuc.edu

8. NGS Workshop: Feb 2002PPL-Dept of Computer Science, UIUC Data driven execution Scheduler Message Q

9. NGS Workshop: Feb 2002PPL-Dept of Computer Science, UIUC Load Balancing Framework Based on object migration –Partitions implemented as objects (or threads) are mapped to available processors by LB framework Measurement based load balancers: –Principle of persistence Computational loads and communication patterns –Runtime system measures actual computation times of every partition, as well as communication patterns Variety of “plug-in” LB strategies available –Scalable to a few thousand processors –Including those for situations when principle of persistence does not apply

10. NGS Workshop: Feb 2002PPL-Dept of Computer Science, UIUC Building on Object-based Parallelism Application induced load imbalances Environment induced performance issues: –Dealing with extraneous loads on shared m/cs –Vacating workstations –Heterogeneous clusters –Shrinking and Expanding jobs to available Pes Object “migration”: novel uses –Automatic checkpointing –Automatic prefetching for out-of-core execution Reuse: object based components

11. NGS Workshop: Feb 2002PPL-Dept of Computer Science, UIUC Applications Charm++ developed in the context of real applications Current applications we are involved with: –Molecular dynamics –Crack propagation –Rocket simulation: fluid dynamics + structures + –QM/MM: Material properties via quantum mech –Cosmology simulations: parallel analysis+viz –Cosmology: gravitational with multiple timestepping

12. NGS Workshop: Feb 2002PPL-Dept of Computer Science, UIUC Molecular Dynamics Collection of [charged] atoms, with bonds Newtonian mechanics At each time-step –Calculate forces on each atom Bonds: Non-bonded: electrostatic and van der Waal’s –Calculate velocities and advance positions 1 femtosecond time-step, millions needed! Thousands of atoms (1,000 - 100,000)

13. NGS Workshop: Feb 2002PPL-Dept of Computer Science, UIUC Object Based Parallelization for MD

14. NGS Workshop: Feb 2002PPL-Dept of Computer Science, UIUC Performance Data: SC2000

15. NGS Workshop: Feb 2002PPL-Dept of Computer Science, UIUC Charm++ Is a Good Match for M-PIM Encapsulation : objects Cost model: –Object data, read-only data, remote data Migration and resource management: automatic One sided communication: since the beginning Asynchronous global operations (reductions,..) Modularity: –see 1996 paper for why DD Objects enable modularity Acceptability: –C++ –Now also: AMPI on top of charm++

16. NGS Workshop: Feb 2002PPL-Dept of Computer Science, UIUC AMPI: Goals Runtime adaptivity for MPI programs –Based on multi-domain decomposition and dynamic load balancing features of Charm++ –Minimal changes to the original MPI code –Full MPI 1.1 standard compliance –Additional support for coupled codes –Automatic conversion of existing MPI programs: Polaris/Padua Original MPI CodeAMPI Code AMPI Runtime AMPIzer

17. NGS Workshop: Feb 2002PPL-Dept of Computer Science, UIUC How Good Is the Programmability I.E. Do programmers find it easy/good –We think so –Certainly a good intermediate level model Higher level abstractions can be built on it But what kinds of abstractions? We think domain-specific ones

18. NGS Workshop: Feb 2002PPL-Dept of Computer Science, UIUC Specialization MPI expression Scheduling Mapping Decomposition HPFCharm++ Domain specific frameworks /AMPI

19. NGS Workshop: Feb 2002PPL-Dept of Computer Science, UIUC Further Match With MPIM Ability to predict: –Which data is going to be needed and –Which code will execute –Based on the ready queue of object method invocations –So, we can: Prefetch data accurately Prefetch code if needed S S Q Q

20. NGS Workshop: Feb 2002PPL-Dept of Computer Science, UIUC So, What Are We Doing About It? How to develop any programming environment for a machine that isn’t built yet Blue Gene/C emulator using charm++ –Completed last year –Implememnts low level BG/C API Packet sends, extract packet from comm buffers –Emulation runs on machines with hundreds of “normal” processors Charm++ on blue Gene /C Emulator

21. NGS Workshop: Feb 2002PPL-Dept of Computer Science, UIUC Structure of the Emulators Blue Gene/C Low-level API Charm++ Converse Charm++BG/C low level API Charm++

22. NGS Workshop: Feb 2002PPL-Dept of Computer Science, UIUC Emulation on a Parallel Machine Simulating (Host) Processor BG/C Nodes Hardware thread

23. NGS Workshop: Feb 2002PPL-Dept of Computer Science, UIUC Extensions to Charm++ for BG/C Microtasks: –Objects may fire microtasks that can be executed by any thread on the same node –Increases parallelism –Overhead: sub-microsecond Issue: –Object affinity: map to thread or node? Thread, currently. Microtasks alleviate load balancing within a node

24. NGS Workshop: Feb 2002PPL-Dept of Computer Science, UIUC Emulation efficiency How much time does it take to run an emulation? –8 Million processors being emulated on 100 –In addition, lower cache performance –Lots of tiny messages On a Linux cluster: –Emulation shows good speedup

25. NGS Workshop: Feb 2002PPL-Dept of Computer Science, UIUC Emulation efficiency 1000 BG/C nodes (10x10x10) Each with 200 threads (total of 200,000 user-level threads) But Data is preliminary, based on one simulation

26. NGS Workshop: Feb 2002PPL-Dept of Computer Science, UIUC Emulator to Simulator Step 1: Coarse grained simulation –Simulation: performance prediction capability –Models contention for processor/thread –Also models communication delay based on distance –Doesn’t model memory access on chip, or network –How to do this in spite of out-of-order message delivery? Rely on determinism of Charm++ programs Time stamped messages and threads Parallel time-stamp correction algorithm

27. NGS Workshop: Feb 2002PPL-Dept of Computer Science, UIUC Applications on the current system Using BG Charm++ LeanMD: –Research quality Molecular Dyanmics –Version 0: only electrostatics + van der Vaal Simple AMR kernel –Adaptive tree to generate millions of objects Each holding a 3D array –Communication with “neighbors” Tree makes it harder to find nbrs, but Charm makes it easy

28. NGS Workshop: Feb 2002PPL-Dept of Computer Science, UIUC Emulator to Simulator Step 2: Add fine grained procesor simulation –Sarita Adve: RSIM based simulation of a node SMP node simulation: completed –Also: simulation of interconnection network –Millions of thread units/caches to simulate in detail? Step 3: Hybrid simulation –Instead: use detailed simulation to build model –Drive coarse simulation using model behavior –Further help from compiler and RTS

29. NGS Workshop: Feb 2002PPL-Dept of Computer Science, UIUC Modeling layers Applications Libraries/RTS Chip ArchitectureNetwork model For each: need a detailed simulation and a simpler (e.g. table-driven) “model” And methods for combining them

30. NGS Workshop: Feb 2002PPL-Dept of Computer Science, UIUC Summary Charm++ (data-driven migratable objects) – is a well-matched candidate programming model for M-PIMs We have developed an Emulator/Simulator –For BG/C –Runs on parallel machines We have Implemented multi-million object applications using Charm++ –And tested on emulated Blue Gene/C More info: http://charm.cs.uiuc.eduhttp://charm.cs.uiuc.edu –Emulator is available for download, along with Charm