Presentation is loading. Please wait.

Presentation is loading. Please wait.

UPC Status Report - 10/12/04 Adam Leko UPC Project, HCS Lab University of Florida Oct 12, 2004.

Similar presentations


Presentation on theme: "UPC Status Report - 10/12/04 Adam Leko UPC Project, HCS Lab University of Florida Oct 12, 2004."— Presentation transcript:

1 UPC Status Report - 10/12/04 Adam Leko UPC Project, HCS Lab University of Florida Oct 12, 2004

2 2 NSA bench9 ● Simple code – Given stream A – Two parameters ● L – number of elements in A ● N – number of bits for each element in A – Compute B i = A i “right justified” ● 1000 -> 0001 ● 1010 - > 0101 ● 1011 -> 1011 ● Removes factors of 2 from list – Compute C such that B i * C i = 1 mod 2 N ● Parameters for experiments – N=48 (recommended: N=30 or N=46) – L=5*10^6 (recommended: L = 5*10^7)

3 3 Oct 12, 2004 Program flow ● Computation section (embarrassingly parallel) – Fill up A with [rand() & (2 N -1)] + 1 – Compute B & C ● B: directly by right shifts ( >> 1) ● C: iterative algorithm – x n -> n correct bits computed – x 2j = x j * (2 – C i * x j ) mod 2 2j – Example: 12 bits, B i =127 ● x 3 = 7 mod 8 ● x 6 = 7 * (2 – 127*7) = 63 mod 64 ● x 12 = 63 * (2 – 127*63) = 3967 mod 4096 ● Check section (gather) – First node checks all values to verify B i *C i = 1 mod 2 N – Fits along with benchmark ● “Output selected values from A, B, and C”

4 4 Oct 12, 2004

5 5

6 6 Analysis for factors (user's perspective) ● Big question: where is time being spent? Which statements in source code use the most cycles? – Which statements incur remote accesses? ● Factors: network characteristics, communication patterns – Which threads are sitting idle? ● Factors: CPU utilization, parallel efficiency, synchronization overhead – How close am I to peak GFLOPS? ● Factors: all, especially lower-level cache and network/memory – How expensive and how much synchronization? ● Factors: synchronization algorithms, network/memory latency

7 7 Oct 12, 2004 Analysis strategy ● Come up with list of questions we want our performance tool to answer ● Think about possible factors in terms of which questions they answer or help answer – Split up some questions in terms of combinations of factors – Try to get as many as possible – Preliminary list from brainstorming? ● Based on important questions from above – Perform sensitivity study ● Assemble microbenchmark suite to isolate factors ● Vary parameters artificially – Also run through list of questions and catalog answers ● Can we record this factor? etc ● Combine results from sensitivity study with survey and tool study to get preliminary list of factors

8 8 Oct 12, 2004 Individual part of project ● Contacting developers – Sent out email to all developers from contact list – Purpose ● Understand “compiler weirdness” ● Get ideas for factors ● Get access to a Cray machine? ● Look at benchmarks – Get ideas for factors ● Start on next coding project – convolution ● Model-driven factor development

9 9 Oct 12, 2004 Model-driven factor development ● Start up one or more performance models that take into account major performance factors ● Tune those models to Marvel, lambda+IBA, kappa+SCI ● General idea: – If a performance model can have 90%+ accuracy, then using the model we can determine which factors are import for which architectures – And thus what to concentrate on and what to show user – Gives us a good understanding of “what's going on” – Also can be used to validate factors we have chosen ● Issues – Existing models? – Simulation or equations? – Corner cases? – Too hard?


Download ppt "UPC Status Report - 10/12/04 Adam Leko UPC Project, HCS Lab University of Florida Oct 12, 2004."

Similar presentations


Ads by Google