MatX
MatX copied to clipboard
NVIDIA
An efficient C++17 GPU numerical computing library with Python-like syntax
**Describe the bug** This simple `matx::sum` test case failed to compile on the latest commit. ```cpp #include int main() { auto t1 = matx::make_tensor({32, 10}); auto t2 = matx::make_tensor({32}); matx::sum(t2,...
the function GetFFTInputView will not compile for non-owning types. https://github.com/NVIDIA/MatX/blob/main/include/matx_fft.h#L706-L738 The issue is that owning/non-owning is part of the type. The output of this function will return the same owning...
**Describe the bug** If you enable this line in the unit tests the unit tests will show memory errors in compute sanitizer. In particular it will try to write to...
we should write a simple kernel that dispatches 1 sort batch per CTA using cub when the sorting dimension is small. This would increase throughput and lower latency for batched...
Unit tests take a very long time to compile on some systems. Parallelism helps, but not as much as it could given that many files have dozens of tests. This...
The goal here is to allow people to create tensors on the fly without syncing. These tensors could not use managed memory at this time. API example: auto t =...
Convolution needs more unit tests for both 1D and 2D. There are things that look like they are probably bugs but are not currently covered by unit tests. For example:...
The deriv operator will return the first derviative with respect to "X" of the underlying operation. The derivative of a constant (or tensor) will return 0. The wrt operator signifies...
1. You chose a managed memory scheme. This is good for entry level, but to consider it for actual systems it would be nice to have some more allocators implemented...
**Describe the bug** CMake generates a solution that fails to compile 11 of 20 projects on VS2022. From [#147](https://github.com/NVIDIA/MatX/issues/147#issuecomment-1072483456) : > The problem is not that nvcc is being passed...
