[PyCUDA] numpy.sum 377x faster than gpuarray.sum

[Serra, Mr. Efren, Contractor, Code 7542]

import numpy
"""
"""
import pycuda.driver as cuda
import pycuda.tools
import pycuda.gpuarray as gpuarray
import pycuda.autoinit, pycuda.compiler

a=numpy.arange(400)
a_gpu=gpuarray.arange(400,dtype=numpy.float32)

start=cuda.Event()
end=cuda.Event()
start.record()
gpuarray.sum(a_gpu).get()/a.size
end.record()
end.synchronize()
print "GPU array time: %fs" %(start.time_till(end)*1e-3)

start.record()
numpy.sum(a)/a.size
end.record()
end.synchronize()
print "numpy array time: %fs" %(start.time_till(end)*1e-3)

GPU array time: 0.000377s
numpy array time: 0.000001s

Efren A. Serra (Contractor)
DeVine Consulting, Inc.
Naval Research Laboratory
Marine Meteorology Division
7 Grace Hopper Ave., STOP 2
Monterey, CA 93943
Code 7542
Office: 831-656-4650