使用Python写CUDA程序的方法

import numpy as np 
from timeit import default_timer as timer
from numba import vectorize

@vectorize(["float32(float32, float32)"], target='cuda')
def vectorAdd(a, b):
  return a + b

def main():
  N = 320000000

  A = np.ones(N, dtype=np.float32 )
  B = np.ones(N, dtype=np.float32 )
  C = np.zeros(N, dtype=np.float32 )

  start = timer()
  C = vectorAdd(A, B)
  vectorAdd_time = timer() - start

  print("c[:5] = " + str(C[:5]))
  print("c[-5:] = " + str(C[-5:]))

  print("vectorAdd took %f seconds " % vectorAdd_time)

if __name__ == '__main__':
  main()

import pycuda.autoinit
import pycuda.driver as drv
import numpy as np
from timeit import default_timer as timer

from pycuda.compiler import SourceModule
mod = SourceModule("""
__global__ void func(float *a, float *b, size_t N)
{
 const int i = blockIdx.x * blockDim.x + threadIdx.x;
 if (i >= N)
 {
  return;
 }
 float temp_a = a[i];
 float temp_b = b[i];
 a[i] = (temp_a * 10 + 2 ) * ((temp_b + 2) * 10 - 5 ) * 5;
 // a[i] = a[i] + b[i];
}
""")

func = mod.get_function("func")  

def test(N):
  # N = 1024 * 1024 * 90  # float: 4M = 1024 * 1024

  print("N = %d" % N)

  N = np.int32(N)

  a = np.random.randn(N).astype(np.float32)
  b = np.random.randn(N).astype(np.float32)  
  # copy a to aa
  aa = np.empty_like(a)
  aa[:] = a
  # GPU run
  nTheads = 256
  nBlocks = int( ( N + nTheads - 1 ) / nTheads )
  start = timer()
  func(
      drv.InOut(a), drv.In(b), N,
      block=( nTheads, 1, 1 ), grid=( nBlocks, 1 ) )
  run_time = timer() - start 
  print("gpu run time %f seconds " % run_time)  
  # cpu run
  start = timer()
  aa = (aa * 10 + 2 ) * ((b + 2) * 10 - 5 ) * 5
  run_time = timer() - start 

  print("cpu run time %f seconds " % run_time) 

  # check result
  r = a - aa
  print( min(r), max(r) )

def main():
 for n in range(1, 10):
  N = 1024 * 1024 * (n * 10)
  print("------------%d---------------" % n)
  test(N)

if __name__ == '__main__':
  main()