ViewTube

Part of the Using Perlmutter Training, Jan 5-7, 2022. Slides and more details are available at ...

Part of the Nvidia HPC SDK Training, Jan 12-13, 2022. Slides and more details are available at ...

High-performance computing is now dominated by general-purpose graphics processing unit (GPGPU) oriented computations.

This is a solution to the classic CPU vs GPU technical interview question. Preparing for a technical interview? Checkout ...

An introduction to GPU programming using a simple SAXPY (Single-precision A*X + Y) as an example. This video is the first part ...

... in Python first and then translates it to CUDA, highlighting the significant performance gains achievable with GPU programming.

Multi-Core Computer Architecture https://onlinecourses.nptel.ac.in/noc23_cs113/preview Dr. John Jose Department of Computer ...

OpenACC is still the GPU programming is still more mature than OpenMP at this point, especially for NVidia GPUs. And here's the ...

And I'm going to talk about the debugging on GPU. So maybe I'm a civilian that underestimating the number of threads here, but I ...

A video analyzing the architectural makeup of an Nvidia Volta Tensor Core. References: Pu, J., et. al. "FPMax: a 106GFLOPS/W at ...

From the NERSC NVIDIA RAPIDS Workshop on April 14, 2020. Please see ...

The webinar AMD GPU architecture and application porting took place on 22 May 2020.

Part of the Nvidia HPC SDK Training, Jan 12-13, 2022. Slides and more details are available at ...

Don't miss out! Join us at our upcoming event: KubeCon + CloudNativeCon Europe 2023 in Amsterdam, The Netherlands from ...

Basic intro to GPU programming with CUDA, including kernels, the different memory spaces, and how to get high performance.

In this lightning talks Alex shares his experiences attempting to configure GPU hardware acceleration for tensorflow and H264 ...

A quick guide on how to enable the use of your GPU for machine learning with Jupyter Notebook, Tensorflow, Keras on the ...

WebGPU is a new Javascript API bringing more featureful access to the GPU while being more idiomatic to JavaScript. WebGPU ...

Start with an analogy. Then delve into CUDA with some pytorch code to demonstrate why we use GPUs instead of just CPUs.

Lecture 1: SIMD vs. SIMT: Thread Mapping, Scheduling, and Pipelining in NVIDIA GPUs.