processor oblivious parallel algorithms and scheduling illustration on parallel prefix n.
Skip this Video
Loading SlideShow in 5 Seconds..
Processor-oblivious parallel algorithms and scheduling Illustration on parallel prefix PowerPoint Presentation
Download Presentation
Processor-oblivious parallel algorithms and scheduling Illustration on parallel prefix

play fullscreen
1 / 23
Download Presentation

Processor-oblivious parallel algorithms and scheduling Illustration on parallel prefix - PowerPoint PPT Presentation

pakuna
163 Views
Download Presentation

Processor-oblivious parallel algorithms and scheduling Illustration on parallel prefix

- - - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - - -
Presentation Transcript

  1. Processor-oblivious parallel algorithms and schedulingIllustration on parallel prefix Jean-Louis Roch, Daouda Traore INRIA-CNRS Moais team - LIG Grenoble, France • Contents • I. What is a processor-oblivious parallel algorithm ? • II. Work-stealing scheduling of parallel algorithms • III. Processor-oblivious parallel prefix computation

  2. Processor-oblivious algorithms Dynamic architecture : non-fixed number of resources, variable speeds eg: grid, … but not only: SMP server in multi-users mode => motivates « processor-oblivious » parallel algorithm that : + is independent from the underlying architecture: no reference to p nori(t) = speed of processor i at time t nor … + on a given architecture, has performance guarantees : behaves as well as an optimal (off-line, non-oblivious) one Problem: often, the larger the parallel degree, the larger the #operations to perform !

  3. * * * * Prefix of size n/2 13 … n * * * 24 … n-1 Prefix computation • Prefix problem : • input : a0, a1, …, an • output : 0, 1, …, n with • Sequential algorithm:for (i= 0 ; i <= n; i++ ) [ i ] = [ i – 1 ] * a [ i ] ; • Fine grain optimal parallel algorithm [Ladner-Fischer]: performs W1= W = noperations a0 a1 a2 a3 a4 … an-1 an Critical time W =2. log n but performs W1= 2.n ops Twice more expensive   than the sequential …

  4. Prefix computation : an example where parallelism always costs • Any parallel algorithm with critical time W runs on p processors in time • strict lower bound : block algorithm + pipeline [Nicolau&al. 1996] • Question : How to design a generic parallel algorithm, independent from the architecture, that achieves optimal performance on any given architecture ? • > to design a malleable algorithm where scheduling suits the number of operations performed to the architecture

  5. Architecture model - Heterogeneous processors with changing speed => i(t) = instantaneous speed of processor i at time t in #operations per second - Average speed per processor for a computation with duration T : - Lower bound for the time of prefix computation :

  6. Work-stealing (1/2) « Work » W1= #total operations performed «Depth » W = #ops on a critical path (parallel time on resources) • Workstealing = “greedy” schedule but distributed and randomized • Each processor manages locally the tasks it creates • When idle, a processor steals the oldest ready task on a remote -non idle- victim processor (randomly chosen)

  7. Work-stealing (2/2) « Work » W1= #total operations performed «Depth » W = #ops on a critical path (parallel time on resources) • Interests : -> suited to heterogeneous architectures with slight modification [Bender-Rabin02] -> if W small enough near-optimal processor-oblivious schedule with good probability on p processors with average speeds ave NB : #succeeded steals = #task migrations < p W [Blumofe 98, Narlikar 01, Bender 02] • Implementation: work-first principle[Cilk serie-parallel, Kaapi dataflow]-> Move scheduling overhead on the steal operations (infrequent case)-> General case : “local parallelism” implemented by sequential function call

  8. How to get both optimal work W1and W small? • General approach: to mix both • a sequential algorithm with optimal work W1 • and a fine grain parallel algorithm with minimal critical time W • Folk technique : parallel, than sequential • Parallel algorithm until a certain « grain »; then use the sequential one • Drawback : W increases ;o) …and, also, the number of steals • Work-preserving speed-up technique[Bini-Pan94] sequential, then parallelCascading [Jaja92] : Careful interplay of both algorithms to build one with both W small and W1 = O( Wseq ) • Use the work-optimal sequential algorithm to reduce the size • Then use the time-optimal parallel algorithm to decrease the time Drawback : sequential at coarse grain and parallel at fine grain ;o(

  9. SeqCompute SeqCompute Extract_par LastPartComputation Alternative :concurrently sequential and parallel Based on the Work-first principle : Executes always a sequential algorithm to reduce parallelism overhead • use parallel algorithm only if a processor becomes idle (ie steals) by extracting parallelism from a sequential computation Hypothesis : two algorithms : • - 1 sequential : SeqCompute- 1 parallel : LastPartComputation : at any time, it is possible to extract parallelism from the remaining computations of the sequential algorithm • Self-adaptive granularity • Examples : - iterated product [Vernizzi 05] - gzip / compression [Kerfali 04] - MPEG-4 / H264 [Bernard 06] - prefix computation [Traore 06]

  10. 0 a1 a2 a3 a4 a5 a6 a7 a8 a9 a10 a11 a12 Main Seq.  Steal request  Work-stealer 1  Work-stealer 2 Adaptive Prefix on 3 processors Sequential 1 Parallel

  11. 0 a1 a2 a3 a4 Main Seq.  1 2 Steal request  a5 a6 a7 a8 a9 a10 a11 a12  6 Work-stealer 1 i=a5*…*ai  Work-stealer 2 Adaptive Prefix on 3 processors Sequential 3 Parallel 7

  12. 0 a1 a2 a3 a4 Main Seq.  1 2 3 4 8 8 Preempt 4  a5 a6 a7 a8  6 7 Work-stealer 1 i=a5*…*ai a9 a10 a11 a12  10 Work-stealer 2 i=a9*…*ai Sequential Adaptive Prefix on 3 processors Parallel 8

  13. 0 a1 a2 a3 a4 8 Main Seq.  1 2 3 4 11 Preempt 11 8  a5 a6 a7 a8  6 7 Work-stealer 1 i=a5*…*ai a9 a10 a11 a12  10 Work-stealer 2 i=a9*…*ai Adaptive Prefix on 3 processors Sequential 8 Parallel 5 6 8 9 11

  14. 0 a1 a2 a3 a4 8 11 a12 Main Seq.  1 2 3 4  a5 a6 a7 a8  6 7 Work-stealer 1 i=a5*…*ai a9 a10 a11 a12  10 Work-stealer 2 i=a9*…*ai Adaptive Prefix on 3 processors Sequential 8 11 12 Parallel 5 6 7 8 9 10 11

  15. 0 a1 a2 a3 a4 8 11 a12 Main Seq. 1  2 3 4 8 11 12  a5 a6 a7 a8  5 6 6 7 7 8 Work-stealer 1 i=a5*…*ai a9 a10 a11 a12  9 10 10 11 Work-stealer 2 i=a9*…*ai Adaptive Prefix on 3 processors Sequential Implicit critical path on the sequential process Parallel

  16. Analysis of the algorithm • Execution time • Scheme of the proof : • Dynamic coupling of two algorithms that completes simultaneously: • Sequential: (optimal) number of operations S on one processor • Parallel : minimal time but performs X operations on other processors • dynamic splitting always possible till finest grain BUT local sequential • Critical path small ( eg : log X) • Each non constant time task can potentially be splitted (variable speeds) • Algorithmic scheme ensures Ts = Tp + O(log X)=> enables to bound the whole number X of operations performedand the overhead of parallelism = (s+X) - #ops_optimal

  17. Optimal off-line on p procs Pure sequential Oblivious Adaptive prefix : experiments1 Prefix sum of 8.106 double on a SMP 8 procs (IA64 1.5GHz/ linux) Single user context Time (s) #processors Single-user context : processor-oblivious prefix achieves near-optimal performance : - close to the lower bound both on 1 proc and on p processors - Less sensitive to system overhead : even better than the theoretically “optimal” off-line parallel algorithm on p processors :

  18. Off-line parallel algorithm for p processors Oblivious Adaptive prefix : experiments 2 Prefix sum of 8.106 double on a SMP 8 procs (IA64 1.5GHz/ linux) External charge (9-p external processes) Time (s) #processors Multi-user context : Additional external charge: (9-p) additional external dummy processes are concurrently executed Processor-oblivious prefix computation is always the fastest15% benefit over a parallel algorithm for p processors with off-line schedule,

  19. Conclusion The interplay of an on-line parallel algorithm directed by work-stealing schedule useful for the design of processor-oblivious algorithms Application to prefix computation : - theoretically reaches the lower bound on heterogeneous processors with changing speeds - practically, achieves near-optimal performances on multi-user SMPs Generic adaptivescheme to implement parallel algorithms with provable performance - work in progress : parallel 3D reconstruction [oct-tree scheme with deadline constraint]

  20. Thank you

  21. Adaptative 8 proc. Parallel 8 proc. Parallel 7 proc. Parallel 6 proc. Parallel 5 proc. Parallel 4 proc. Parallel 3 proc. Parallel 2 proc. Sequential The Prefix race: sequential/parallel fixed/ adaptive On each of the 10 executions, adaptive completes first

  22. Parallel Parallel Adaptive Adaptive Adaptive prefix : some experiments Prefix of 10000 elements on a SMP 8 procs (IA64 / linux) External charge Time (s) Time (s) #processors #processors Multi-user context Adaptive is the fastest15% benefit over a static grain algorithm • Single user context • Adaptive is equivalent to: • - sequential on 1 proc • - optimal parallel-2 proc. on 2 processors • - … • - optimal parallel-8 proc. on 8 processors

  23. With * = double sum ( r[i]=r[i-1] + x[i] ) Finest “grain” limited to 1 page = 16384 octets = 2048 double Single user Processors with variable speeds Remark for n=4.096.000 doubles : - “pure” sequential : 0,20 s - minimal ”grain” = 100 doubles : 0.26s on 1 proc and 0.175 on 2 procs (close to lower bound)