In our last CUDA C/C++ post we discussed how to transfer data efficiently between the host and device. In this post, we discuss how to overlap data transfers…
NVIDIA Collective Communications Library (NCCL) provides optimized implementation of inter-GPU communication operations, such as allreduce and variants.
This walkthrough summarizes the TREx workflow and highlight API features for examining data and TensorRT engines.
This is the fourth post in the CUDA Refresher series, which has the goal of refreshing key concepts in CUDA, tools, and optimization for beginning or…
There’s a new computational workhorse in town. For decades, general matrix-matrix multiply—known as GEMM in Basic Linear Algebra Subroutines (BLAS) libraries…
A CUDA pro tip about pointer aliasing and how to use the restrict keyword to avoid performance problems due to aliasing in C and C++ code on CPUs and GPUs.
NVIDIA is proud to announce Nsight Systems 2018.3! In this release, we introduce support for profiling Windows 10 target machines. For those unfamiliar with…
NVIDIA Nsight Systems 2019.3 is now available – provides support for Sqlite, Vulkan GPU trace, and DX12/Vulkan sutter analysis/frame health.
Use nvprof and NVTX to profile your MPI+CUDA application.
As GPU performance steadily ramps up, your application may be overdue for a tune-up to keep pace. Developers have used independent CPU profilers and GPU…
Try “site:nvidia.com” on: Marginalia · Mojeek · Wiby · DuckDuckGo · Bing · Google · Wikipedia · Internet Archive