Boosting Application Performance with GPU Memory Prefetching
NVIDIA GPUs have enormous compute power and typically must be fed data at high speed to deploy that power. That is possible, in principle, because GPUs also...
Controlling Data Movement to Boost Performance on the NVIDIA Ampere Architecture
The NVIDIA Ampere architecture provides new mechanisms to control data movement within the GPU and CUDA 11.1 puts those controls into your hands. These...
GPU Pro Tip: Fast Histograms Using Shared Atomics on Maxwell
Histograms are an important data representation with many applications in computer vision, data analytics and medical imaging. A histogram is a graphical...
When writing parallel programs, you will often need to communicate values between parallel threads. The typical way to do this in CUDA programming is to use...
Peer-to-Peer Multi-GPU Transpose in CUDA Fortran (Book Excerpt)
This post is an excerpt from Chapter 4 of the book CUDA Fortran for Scientists and Engineers, by Gregory Ruetsch and Massimiliano Fatica. In this excerpt we...
In the previous CUDA C++ post we dove in to 3D finite difference computations in CUDA C/C++, demonstrating how to implement the x derivative part of the...
In the previous CUDA C/C++ post we investigated how we can use shared memory to optimize a matrix transpose, achieving roughly an order of magnitude improvement...
My last CUDA C++ post covered the mechanics of using shared memory, including static and dynamic allocation. In this post I will show some of the performance...
In the previous post, I looked at how global memory accesses by a group of threads can be coalesced into a single transaction, and how alignment and stride...
In the previous post, I looked at how global memory accesses by a group of threads can be coalesced into a single transaction, and how alignment and stride...
