-
-
Save szagoruyko/440c561f7fce5f1b20e6154d801e6033 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import pycuda.autoinit | |
import pycuda.driver as drv | |
import numpy as np | |
import torch | |
x = torch.cuda.FloatTensor(8) | |
from pycuda.compiler import SourceModule | |
mod = SourceModule(""" | |
__global__ void multiply_them(float *dest, float *a, float *b) | |
{ | |
const int i = threadIdx.x; | |
dest[i] = a[i] * b[i]; | |
} | |
""") | |
multiply_them = mod.get_function("multiply_them") | |
class Holder(pycuda.driver.PointerHolderBase): | |
def __init__(self, t): | |
super(Holder, self).__init__() | |
self.t = t | |
self.gpudata = t.data_ptr() | |
def get_pointer(): | |
return self.t.data_ptr() | |
a = np.random.randn(400).astype(np.float32) | |
b = np.random.randn(400).astype(np.float32) | |
a = torch.from_numpy(a).cuda() | |
b = torch.from_numpy(b).cuda() | |
dest = torch.Tensor(a.size()).cuda() | |
multiply_them( | |
Holder(dest), | |
Holder(a), | |
Holder(b), | |
block=(400,1,1), grid=(1,1)) | |
torch.cuda.synchronize() | |
print dest-a*b |
what happens if I want to integrate it with a neural network? I want to do it in the forward, some conv2d can be applied before and after. How can I do that? how do I determine the block size etc?
@tjyuyao
@RoyAmoyal you can use pytorch's autograd.Function api, and implement forward and backward pass in separate pycuda functions.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
@timothylimyl
I have written an easy helper class for multi-dimensional pytorch tensor access here.