arrayfire
arrayfire copied to clipboard
arrayfire
ArrayFire: a general purpose GPU library.
One of the essential vectorization components of image convolution process are the `im2col` and `col2im` kernels, which in arrayfire are implemented as `af::unwrap` and `af::wrap`. However this snippet from the...
## Issue Currently `af::seq(0)` [incorrectly produces](https://github.com/arrayfire/arrayfire/blob/b05da694a3f789579af25887108a214f1a978326/src/api/cpp/seq.cpp#L47) a sequence representing "all elements along an axis", instead of an empty sequence. Demo: ```c++ auto x = af::constant(3, 3); std::cout
- workload per thread is increased to optimize for memcopy and JIT. - memcopy can now increase its unit size - JIT now can write directly into the final buffer,...
Fix the assertion to validate the input shape of the stride, padding and dilation array Description ----------- In C functions, the way the shapes of the input shapes are passed...
I am having troubles using the Unified Backend library `af.lib`, but my program is working when I am using other libraries. Description =========== My program is perfectly working if I...
I am using the QR factorization from ArrayFire in my code. My code is similar to the QR factorization example given on the ArrayFire documentation website. In my Makefile, I...
Description I want to add arrayfire into QT build in Vsiual Studio 2017, but debug error as follows 'af::operator &&': 32 overloads have similar conversions
while rendering plot on Iris XE GPU usage goes to 70 %.the system heats up for a simple plot.I propose a way to control swap interval in WGL implementation to...
What is this error?I am using your code from example on github page. static const float h_kernel[] = { 1, 1, 1, 1, 0, 1, 1, 1, 1 }; static...