1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
|
# Sample source code from the Tutorial Introduction in the documentation.
import pycuda.driver as cuda
import pycuda.autoinit
from pycuda.compiler import SourceModule
import numpy
a = numpy.random.randn(4,4)
a = a.astype(numpy.float32)
a_gpu = cuda.mem_alloc(a.size * a.dtype.itemsize)
cuda.memcpy_htod(a_gpu, a)
mod = SourceModule("""
__global__ void doublify(float *a)
{
int idx = threadIdx.x + threadIdx.y*4;
a[idx] *= 2;
}
""")
func = mod.get_function("doublify")
func(a_gpu, block=(4,4,1), grid=(1,1), shared=0)
a_doubled = numpy.empty_like(a)
cuda.memcpy_dtoh(a_doubled, a_gpu)
print "original array:"
print a
print "doubled with kernel:"
print a_doubled
# alternate kernel invocation -------------------------------------------------
func(cuda.InOut(a), block=(4, 4, 1))
print "doubled with InOut:"
print a
# part 2 ----------------------------------------------------------------------
import pycuda.gpuarray as gpuarray
a_gpu = gpuarray.to_gpu(numpy.random.randn(4,4).astype(numpy.float32))
a_doubled = (2*a_gpu).get()
print "original array:"
print a_gpu
print "doubled with gpuarray:"
print a_doubled
|
