Stack Overflow
Stack Overflow

Questions tagged [pycuda]

PyCUDA is the Python module which provides a comprehensive pythonic interface to the NVIDIA CUDA GPU computing environment.

PyCUDA provides a python module to access the NVIDIA CUDA driver API from within Python code.

The module includes interoperability with numpy, and comprehensive metaprogramming facilities for dynamically generating and JIT compiling CUDA code using Python.

417 questions
0
votes
1 answer

Calling __device__ function using PyCUDA returns error

When I try to run the following code, I get this error : Traceback (most recent call last): File "C:\temp\GPU Program Shell.py", line 28, in dev=mod.get_function("lol") File "C:\Python33\lib\site-packages\pycuda\compiler.py", line…
Hair of Slytherin
  • 397
  • 4
  • 21
0
votes
2 answers

Number of threads in GeForce GTX 560Ti

I ran the deviceQuery and got the following result ./deviceQuery Starting... CUDA Device Query (Runtime API) version (CUDART static linking) Detected 1 CUDA Capable device(s) Device 0: "GeForce GTX 560 Ti" CUDA Driver Version / Runtime…
Daniel Wonglee
  • 55
  • 8
0
votes
2 answers

How to Properly Recover from Memory Errors in GPU?

Consumer-grade Nvidia GPUs are expected to have about 1-10 soft memory errors per week. If you somehow manage to detect an error on a system without ECC (e.g. if the results were abnormal) what steps are necessary and sufficient to recover from…
MWB
  • 11,740
  • 6
  • 46
  • 91
0
votes
1 answer

PyCUDA using string but not array of strings

How do I get PyCuda to pull in the array of strings rather than one char string? If you uncomment the line within the C code, you'll see that its iterating through each character and not through each string. For now i'm just trying to calculate the…
Ricky Sahu
  • 23,455
  • 4
  • 42
  • 32
0
votes
1 answer

pycuda shared memory error "pycuda._driver.LogicError: cuLaunchKernel failed: invalid value"

I have a strange problem which origin I cannot determine: I have a working Kernel for some special Matrix-Vector-multiplication, which I want to speed up. Basically the big matrix (10^6 times 10^6) is constructed from few small matrices. So I want…
user2267896
  • 173
  • 2
  • 9
0
votes
1 answer

Output from shell_exec is no longer returned to PHP when including pyCuda

I am calling this python file: import sys if __name__ == "__main__": print sys.argv[1] From PHP like this: $param = "hello"; $result = shell_exec("python /path/to/python/file.py " . $param); echo $result; Which works great as hello is…
Joe P
  • 382
  • 7
  • 14
0
votes
1 answer

Integrating ODEs on the GPU using boost and python

I posted here not too long ago about a model I am trying to build using pycuda which solves About 9000 coupled ODEs. My model is too slow however and an SO member suggested that memory transfers from host to GPU is probably the culprit. Right now…
Hair of Slytherin
  • 397
  • 4
  • 21
0
votes
1 answer

Combining CUDA with Python's ODEInt and Parallel Reduction

I'm a graduate student in biophysics, trying to program a protein aggregation model using PyCUDA and Scipy's ODEInt. Within the past two weeks, I've gotten the code running, but it's very slow. Let me see if I can explain what my code does. I have…
Hair of Slytherin
  • 397
  • 4
  • 21
0
votes
1 answer

Working of CUDA scheduler

How do I know the behavior of CUDA scheduler? Apart from testing it by varying the grid sizes, block sizes etc. in my application is there any vendor provided documentation that explains exactly in what fashion the blocks are distributed?
Rakesh Kumar
  • 51
  • 1
  • 7
0
votes
1 answer

Change values of multiple cells in CUDA

It has to be a simple one, though I can't find an answer. I'm writing a program which has to calculate states of cellular automatons and in order to get a feeling how does CUDA works I tried to write a very simple program first. It takes a matrix,…
aga
  • 27,954
  • 13
  • 86
  • 121
0
votes
1 answer

Multiply two-dimensional matrices.‏ with pycuda

how can I iterate in two arrays? __global__ void euclidean(float *x, float *y, int dim_x, int dim_y, int ms, float *solution) { int idx = threadIdx.x + blockDim.x * blockIdx.x; int idy = threadIdx.y + blockDim.y *…
Ricardo Augusto
  • 3
  • 2
0
votes
2 answers

pycuda only block(N,1,1) works

I can't understand why the below program runs ok for block=N,1,1 but not for 1,1,N (result is invalid value ) or 1,N,1 ( result is 0,1,0.....0) or 10,50,1 (result is 0,1,0..0) (N=500). import pycuda.gpuarray as gpuarray import pycuda.driver as…
George
  • 5,808
  • 15
  • 83
  • 160
0
votes
2 answers

cuda -- out of memory (threads and blocks issue) --Address is out of bounds

I am using 63 registers/thread ,so (32768 is maximum) i can use about 520 threads.I am using now 512 threads in this example. (The parallelism is in the function "computeEvec" inside global computeEHfields function function.) The problems are: 1)…
George
  • 5,808
  • 15
  • 83
  • 160
0
votes
1 answer

Pycuda installation on Ubuntu

I'm having a difficult time installing pycuda. I am running on Ubuntu 12.04. I first installed the Enthought python distribution (even though I already had python on the computer). I added the enthought python location to the path in my .profile…
miz
  • 185
  • 2
  • 10
0
votes
1 answer

pycuda -- error: command 'x86_64-pc-linux-gnu-g++' failed with exit status 1

i installed sabayon linux and i tried to install pycuda but i am receiving the following error when i try su -c "make install" In file included from src/cpp/cuda.cpp:1:0: src/cpp/cuda.hpp:12:18: fatal error: cuda.h: No such file or directory…
George
  • 5,808
  • 15
  • 83
  • 160
1 2 3
…
27 28