Berkeley UPC Kathy Yelick Christian Bell Dan Bonachea

Berkeley UPC Kathy Yelick Christian Bell, Dan Bonachea, Wei Chen, Jason Duell, Paul Hargrove, Parry Husbands, Costin Iancu, Rajesh Nishtala, Mike Welcome LBNL and U. C. Berkeley http: //upc. lbl. gov

Berkeley UPC Compiler Status • Recent Berkeley UPC release (v 2. 2) • Support 1. 2 language spec • Supports collectives (tuning ongoing); memory model compliance • Supports UPC I/O (naïve reference implementation) • Compiler work • Optimization phase and improved performance in v 2. 2 • Work on automated communication overlap, upc_forall, … • Large effort in quality assurance and robustness • Test suite: 600+ tests run nightly on 20+ platform configs • >30, 000 UPC compilations and >20, 000 UPC test runs per night • Test suite infrastructure extended to support any UPC compiler • now running nightly with GCC/UPC + UPCR • also has been used on HP-UPC, Cray UPC Berkeley UPC http: //upc. lbl. gov Kathy Yelick

Berkeley UPC Collaborations • GCC UPC on Berkeley UPC Runtime • Use for cluster (GASNet) implementations • Now works with pthread runtime • Source-level debugging with Totalview 7. x • Joint project with Etnus • General framework for source-to-source translators • Future work: • Cray XT 3 and other Rainier/Adams port • Possible Blue. Gene/L port • XT 3 and BG/L both run on MPI conduit Berkeley UPC http: //upc. lbl. gov Kathy Yelick

Berkeley Applications & Benchmarks • Some new applications • • • FT: . 45 TFlops on 512 proc Itanium/Quadrics (Elan 4) CG: 30 GFlops on 512 HP Alpha/Quadrics (Elan 3) LU: >2 TFlops on 512 proc Itanium/Quadrics (Elan 4) Barnes-Hut: fine-grained (based on Splash) CFG: uses to Chombo • More on LU • Towards a Sparse direct solver (Super. LU) • Currently a full (top 500 -compliant) HPL implementation • All UPC except for call to the BLAS Berkeley UPC http: //upc. lbl. gov Kathy Yelick

End of Berkeley Status

Data Movement and Synchronization

Motivation for Data Movement Synchronization • Some are (at best) hard/slow in UPC • Benchmarks highlight these • FT: communication-limited, all-to-all: want to overlap • MG: fill in ghost regions • Remote writes are often faster than remote reads • But need to synchronize: let the other proc know data is available – See Tarek and John Mellor-Crummey’s PPo. PP 05 paper – Signaling store in Split-C – Implementation issue: reordering • LU: remotely enqueue a task • GUPS and Histogram: remotely increment/XOR a value • With or without atomicity Berkeley UPC http: //upc. lbl. gov Kathy Yelick

Who Would Like to Talk? • • • Non-Blocking Memget/put (Dan) Semaphores (Dan) Semaphore example (Tarek) Remote Atomics (Phil) Floating functions (Jason) Berkeley UPC http: //upc. lbl. gov Kathy Yelick