forresti / convolutionLinks
Communication-Minimizing 2D Convolution in GPU Registers
☆30Updated 12 years ago
Alternatives and similar repositories for convolution
Users that are interested in convolution are comparing it to the libraries listed below
Sorting:
- A portable high-level API with CUDA or OpenCL back-end☆55Updated 8 years ago
- Set of basic classes (vector, matrix, images and memory array) for CPU and GPU☆17Updated 4 years ago
- A machine vision library written in SYCL and C++ that shows performance-portable implementation of graph algorithms☆162Updated last year
- ☆68Updated 3 years ago
- Header file to translate SSE instructions to ARM NEON instructions☆48Updated 12 years ago
- Some C++ codes for computing a 1D and 2D convolution product using the FFT implemented with the GSL or FFTW☆60Updated 12 years ago
- A tiny least squares solver targeting extreme performance on repeated minimizations☆44Updated 10 years ago
- GPU Optimization and Memory Abstraction Framework☆32Updated 6 years ago
- CNNs in Halide☆23Updated 10 years ago
- Easy to run kernels using OpenCL☆187Updated 8 months ago
- A version of the AKAZE feature detection and description that has removed the OpenCV dependency☆49Updated 11 years ago
- Greentea LibDNN - a universal convolution implementation supporting CUDA and OpenCL☆137Updated 8 years ago
- TooN - Tom's Object Oriented Numerics library☆127Updated last year
- Mirror JPEG compression and decompression accelerated on GPU☆82Updated 11 years ago
- Efficient CUDA Stream Compaction Library☆35Updated 2 years ago
- Corrected source for the OpenCL in Action book (work in progress)☆64Updated 12 years ago
- Example of how to use CUDA with CMake >= 3.8☆70Updated 6 months ago
- OpenCL Integrated Performance Primitives - A library of optimized OpenCL image processing functions☆176Updated 8 years ago
- FastHOG library that has been fixed to work with CUDA 5.x on Ubuntu 12.04☆20Updated 11 years ago
- Insanely fast CUDA LATCH: fully scale- and rotation-invariant 512-bit binary descriptor for computer vision☆32Updated 4 years ago
- Fast integer division with divisor not known at compile time. To be used primarily in CUDA kernels.☆73Updated 10 years ago
- A class for performing principal component analysis using Eigen library☆30Updated 8 years ago
- Kaadugal is a parallelized multi-core C++ implementation of the random forests algorithm for classification, regression, and structured p…☆23Updated 8 years ago
- A Light-weight and Fast Template Matrix Library☆132Updated 12 years ago
- slic video segmentation☆10Updated 10 years ago
- Lock-free parallel disjoint set data structure (aka UNION-FIND) with path compression and union by rank☆67Updated 10 years ago
- C++11 Camera Models Classes.☆35Updated 7 years ago
- Proof-of-Concept CNN in Halide☆22Updated 9 years ago
- A simple tool for porting CUDA to OpenCL (DEPRECATED)☆32Updated 6 years ago
- a heterogeneous multiGPU level-3 BLAS library☆46Updated 6 years ago