summaryrefslogtreecommitdiff
path: root/benchmark.py
AgeCommit message (Collapse)Author
2011-09-10mergeStan Seibert
2011-09-10Add the ability to propagate the same photons multiple times on theStan Seibert
the GPU, and run the DAQ multiple times on the same photons in a likelihood calculation. Propagating the same photons in a warp speeds up propagation by a factor of 3 (and we could do this even better if we wanted), and this improves the statistics in a likelihood evaluation quite a bit. Running the DAQ multiple times is also an inexpensive way to improve the quality of the PDF estimates.
2011-09-10update benchmark.pyAnthony LaTorre
2011-09-08add normalize() function to transform module. ↵Anthony LaTorre
np.apply_along_axis(np.linalg.norm,...) is really slow!
2011-09-06geometry on the GPU is now a struct created in the GPUGeometry class. coding ↵Anthony LaTorre
style for cuda code is now compliant with python PEP 7 -- Style Guide for C Code.
2011-09-02update event structure. break gpu.GPU class into separate smaller ↵Anthony LaTorre
independent classes.
2011-08-22Oops, uncomment other benchmark testsStan Seibert
2011-08-22Benchmark and unit test for PDF creationStan Seibert
2011-08-19Do the hash-bang correctly at the top of the benchmark script.Stan Seibert
2011-08-19Benchmark photon load timesStan Seibert
2011-08-19ignore first kernel call in benchmarksAnthony LaTorre
2011-08-19add benchmarks for ray intersection and photon propagationAnthony LaTorre