Parallel computing with GPars
0 likes773 views
The document discusses the evolution of parallel computing, emphasizing advancements in Java's concurrency utilities and emerging technologies like map-reduce. It highlights Groovy's high-level abstractions for concurrent code, including parallel collections and asynchronous processing. Additionally, it presents multiple demos illustrating practical applications of these concepts, such as thread pool optimization and parallel data processing methods.
Parallel computing with GPars
- 1. Parallel Computing (with GPars) NOV 2011
- 2. Evolution ● Old Days ○ threads ○ synchronize ○ locks ○ wait-notify
- 3. Evolution ● Recent enhancements ○ java.util.concurrent.* ○ Future task ○ Executor Pools ○ Blocking Queues ○ ConcurrentMap
- 4. Evolution ● Emerging Technologies ○ Map-Reduce ○ API's (Google Collections, JSR-166) ○ Non-blocking I/O ○ Parallel Friendly Languages (Scala, Clojure, Groovy)
- 5. Groovy Parallel Systems High level abstractions for writing concurrent code! ● Code-level Helpers ○ Parallel Collections ○ Asynchronous Processing ○ Fork/Join - Map/Reduce ● Architecture-level Concepts ○ Dataflows ○ Actors ● Protecting Shared Mutable State ○ Agents
- 6. Groovy Parallel Systems High level abstractions for writing concurrent code! ● Code-level Helpers ○ Parallel Collections ○ Asynchronous Processing ○ Fork/Join - Map/Reduce ● Architecture-level Concepts ○ Dataflows ○ Actors (For next time...) ● Protecting Shared Mutable State ○ Agents (For next time...)
- 7. DEMO 1 (Parallel encryption)
- 8. Optimal Thread Pool Size Pool size = ???
- 9. Optimal Thread Pool Size Pool size = Ncores
- 10. Optimal Thread Pool Size Pool size = Ncores + 1
- 11. Optimal Thread Pool Size Pool size = Ncores + Block. Op. Ratio
- 12. Optimal Thread Pool Size Pool size = Ncores + wait time cpu time
- 13. DEMO 2 "Dado un rango obtener la cantidad de nr. primos agrupados por él ultimo digito"
- 14. Danger Don't mess up with mutable shared data!
- 15. DEMO 3 (Facebook Search)
- 16. Collections ● eachParallel() ● eachWithIndexParallel() ● collectParallel() ● findAllParallel() ● findAnyParallel ● findParallel() ● everyParallel() ● anyParallel() ● grepParallel() ● groupByParallel() ● foldParallel() ● minParallel() ● maxParallel() ● sumParallel() ● splitParallel() ● countParallel() ● foldParallel()
- 17. DEMO 4 (Facebook Singles)
- 19. DEMO 5 (API Calls)
- 20. DEMO 6 (Multiget)
- 21. Multiget
- 22. + Info ● http://gpars.org/0.12/guide/guide/single.html ● http://www.slideshare.net/paulk_asert/concurrency-with- gpars ● http://gee.cs.oswego.edu/dl/papers/fj.pdf ● http://static.googleusercontent. com/external_content/untrusted_dlcp/labs.google. com/en/us/papers/mapreduce-osdi04.pdf ● Java Concurrency in Practice (ISBN-0321349601) Pics Credits ● Stone age: http://tinyurl.com/bvnlv74 ● Steam train: http://tinyurl.com/6lp3krq ● Speed train: http://tinyurl.com/7jjc3v5 ● CPU: http://www.flickr.com/photos/olivander/149865626/