Skip to content
adanalis edited this page Mar 2, 2012 · 7 revisions

Quality Threshold Clustering (QTC)

Description: Measures performance of the Quality Threshold Clustering algorithm.

Problem Sizes (number of points, threshold)

  • s=1 (8192, 3)
  • s=2 (20000, 3)
  • s=3 (32768, 1)
  • s=4 (65536, 1)

With these sizes, a run on a Tesla C2070, will take approximately: 0.1, 2, 20, or 200 seconds

Precision: float

Includes PCIe Transfer Time: Yes, in [testName]_PCIe measurements

Parameters

  • -s, sample problem sizes (overrides all other parameters)
  • --PointCount, point count
  • --DataFile, BLAST data input file name
  • --Threshold, cluster diameter threshold
  • --SaveOutput, BLAST data input file name
  • --Verbose, Print cluster cardinalities (duplicates verbose? -s? -K)
  • --TextureMem, Use Texture memory for distance matrix
  • --Dense, Enable the use of a dense distance matrix regardless of problem size

Specific Tests

  • TBD - achieved GFLOPS?
  • TBD - achieved GFLOPS
Clone this wiki locally