Puget Systems News
TensorFlow is on it's way to becoming the "standard" framework for machine learning. There are many reasons for that, and, it is not just for machine learning! In this post I'll give a descriptive introduction to TensorFlow. This is the first post in a series on how to work with TensorFlow. Hopefully after reading thsi you will have a better understanding of the What? and Why? of TensorFlow.
It's been a few years since a game caught the interest of my family. I worked in sales at Puget Systems when I began hearing customers mention a game called Minecraft. The simple, blocky nature of the game carried over to the hardware requirements. Minecraft didn't require a high-end gaming rig. My three oldest couldn't get enough of building homes, trying to stay alive and setting anything they could find on fire with lava.
Linux is often considered the operating system of choice for power users, but does DaVinci Resolve actually perform any better in it than in Windows? Even if it does, is it enough to compensate for Linux's much higher learning curve?
Puget Systems will be exhibiting at this year's GPU Technology Conference, March 26th - 29th. We will be displaying our new GPU accelerated workstations including those for photogrammetry, rendering, virtual reality and machine learning. Come meet with us at Booth #705!
This post will look at the molecular dynamics program, NAMD. NAMD has good GPU acceleration but is heavily dependent on CPU performance as well. It achieves best performance when there is a proper balance between CPU and GPU. The system under test has 2 Xeon 8180 28-core CPU's. That's the current top of the line Intel processor. We'll see how many GPU's we can add to those Xeon 8180 CPU's to get optimal CPU/GPU compute balance with NAMD.
After Effects is a tricky application when it comes to choosing a CPU as there are many factors that come into play. Not only is there raw rendering performance, but the new integration with Cinema4D and even the amount of system RAM you need all play a role in determining what CPU is the ideal choice for your workflow.
Following up on our previous article about SOLIDWORKS 2018 GPU performance, we have been provided with an extremely complex assembly that finally shows some performance difference between low- and high-end video cards within the same family. Armed with this 4372 part, 40.9 million triangle model we ran through testing on multiple Quadro and Radeon Pro graphics cards to see how they handle such a monstrously large project.
Blackmagic's DaVinci Resolve is known for how well it utilizes multiple GPUs to improve performance, but is this still true with cards like the new NVIDIA Titan V? And do you really need a Xeon or Dual Xeon setup to get the best performance possible?
Designed and built specifically for professional workstations, NVIDIA Quadro GPUs power more than 200 professional applications across a broad range of industries including manufacturing, media and entertainment, sciences, and energy. Professionals trust them to realize their most ambitious visions
TensorFlow Scaling on 8 1080Ti GPUs - Billion Words Benchmark with LSTM on a Docker Workstation Configuration
In this post I present some Multi-GPU scaling tests running TensorFlow on a very nice system with 8 1080Ti GPU's. I use the Docker Workstation setup that I have recently written about. The job I ran for this testing was the "Billion Words Benchmark" using an LSTM model. Results were very good and better than expected.
How-To Setup NVIDIA Docker and NGC Registry on your Workstation - Part 5 Docker Performance and Resource Tuning
This should be the last post in this series dealing with the Docker setup for accessing the NVIDIA NCG Docker registry on your workstation. There are a couple of configuration tuning changes that you may want to make. These will improve performance and ensure that you have proper system "user limit" resources to handle large application and job runs with docker.
Despite how popular SOLIDWORKS is, there is a lot of outdated and simply inaccurate information on the web regarding what video card you should use. For this article I tested multiple graphics cards from the Quadro, GeForce, and Radeon Pro families at both 1080p and 4K resolutions - and quickly found that either things are now a lot simpler than in my past experience, or else something is no longer up to snuff regarding how we have tested SOLIDWORKS GPU performance in the past.
Posted in Featured Systems on 02/20/2018
Our NVIDIA DIGITS machine learning configurations are single CPU, multi-GPU workstations optimized for deep-learning workloads. These are great platforms for working with Tensorflow, Caffe and Torch and the DIGITS web interfacea as well as other frameworks like CNTK, MXNet, etc.. We have two base recommendations to meet performance and budget requirements.
If your workflow depends on having 10-bit color support on your primary display, using a workstation graphics card is typically the only way to do so since most consumer cards do not support displaying 10-bit color. But do you really need a Quadro P6000 or can you use a much less expensive card like the Quadro P4000 or Radeon Pro WX 9100 without sacrificing very much performance?
This post will go through how to get access to the NVIDIA NGC container registry on your workstation. The first 3 posts in this series gave instructions on how to install and configure a base Ubuntu 16.04 workstation system with Docker and NVIDIA-Docker for a usable work-flow. With that taken care of we can get setup to use the many useful docker images in the NGC container registry for your local system.
The NVIDIA Titan V has many the features that are not useful in DaVinci Resolve, but it's raw power allows it to give the highest single GPU playback performance of any GPU we have every tested.
In this post I'll go through setting up Docker to use User-Namespaces. This is a very important step to achieving a comfortable docker work-flow on a personal Workstation. I will show you how to configure Docker so that instead of files and processes being owned by root they will be owned by your personal user account. This will make using Docker containers on your system safer and feel much the same as a "normally" installed application.
The initial release of Lightroom Classic CC gave us some great performance gains, but the Lightroom team is not done yet. With the new 7.2 update, we once again get some terrific performance improvements, this time with an emphasis on improved multi-core performance using high core count CPUs in a number of tasks.
The NVIDIA Titan V is an interesting and powerful card with a mix of features that should improve performance and features that are completely unused by Premiere Pro. The raw power of this card makes it the fastest GPU we've testing for Exporting, but it unfortunately is not quite as impressive when it comes to Live Playback performance.
Dassault Systemes launched the initial version of SOLIDWORKS 2018 (SP0.1) late last year, but with the recent release of SP1 we expect that customers will soon be using it in production environments. In preparation for that, we have tested the field of current Intel Core i7 and i9 processors to see how they stack up in SW 2018. We hadn't yet had a chance to test AMD's Threadripper processors in SOLIDWORKS either, so they are also included in this round of benchmarks.
How-To Setup NVIDIA Docker and NGC Registry on your Workstation - Part 2 Docker and NVIDIA-Docker-v2
This post will build on top of the base systems setup described in Part1. We will go through installing,configuring and testing Docker and NVIDIA-Docker version 2.