IBM announced on April 17, 2017 that it will offer the Anaconda Open Data Science platform on IBM Cognitive Systems. "By adding Anaconda support, IBM continues to take an open, collaborative approach with like-minded tech companies pushing the limits of cognitive tech. Now Anaconda’s massive developer community have access to hardware that is tailor built to power the deep … [Read more...]
Accelerating Python and Deep Learning
Sponsored Content “For deep learning to have a meaningful impact and business value, the time to train a model must be reduced from weeks to hours,” observed Ananth Sankaranarayanan, Intel’s director of engineering, analytics and AI solutions. Demonstrating the performance benefits of Intel Xeon and Intel Xeon Phi hardware and new Intel Architecture (IA) optimized software … [Read more...]
Code Modernization Enables Pikazo’s Economics and Creates Opportunity
Sponsored Content “ is a tool that let’s anyone become an artist”, began Noah Rosenberg (CEO, Pikazo) when speaking about CPU-based artistic computing. “About grade 3-4 people begin to censor themselves and don’t give themselves permission to call what they draw art”. Pikazo changes that through an innovative blend of machine-learning and behind-the-scenes artistic knowhow to … [Read more...]
NVIDIA Moves Deeper into the Data Center with the P4 and P40 Inference GPUs
NVIDIA announced the P4 and P40 GPUs that are optimized for machine learning inference performance and efficiency. The products are positioned to gain market share for NVIDIA in the data center. (Inference, sometimes called scoring or prediction, utilizes a trained machine learning algorithm to perform some difficult or valuable task like recognizing a picture, predicting an … [Read more...]
Faster Deep Learning with the Intel® Scalable System Framework: Next Generation Processors
Sponsored Post This is the first in a multi-part series on machine-learning that examines the impact of Intel Scalable System Framework (Intel® SSF) technology on the valuable HPC field of deep-learning. In this article we will focus on Intel® Xeon® and Intel® Xeon Phi™ processors. Follow-on articles will discuss other Intel SSF components including networking and storage with … [Read more...]
NVIDIA video shows how machine-learning is redefining visual search
An NVIDIA video by Nervve shows how machine-learning is redefining visual search. The video can be viewed by clicking here. According to the meeting description: From the exabytes of user generated visual content created daily on web services to the projected 859 Petabytes created every day by surveillance cameras in 2017 - Visual content is all around us. However, huge … [Read more...]
Opening Your Computer’s Mind – Google and Microsoft Open-Source Deep-Learning Software
Both Google and Microsoft have made open-source deep-learning toolkits available for download. TechEnablement.com also has a github repository containing our machine-learning teaching code that achieved 13 PF/s average sustained performance on the ORNL Titan supercomputer. Google's TensorFlow™ is an open source software library for numerical computation using data flow … [Read more...]
Wonderful Teaching Video – The Zipf Mystery
My ten year old introduced me to the wonderful new video on YouTube, "The Zipf Mystery". It is 20 minutes well spent for all interested in information theory, computer science, computational drug design, social media, machine-learning, and a huge number of other real-world relevant areas of research and application. https://youtu.be/fCn8zs912OE Consider this a form of … [Read more...]
PGI Compiled OpenACC ILP Loop Beats CUDA-7 by 200 GF/s on Deep-learning PCA Example
The PGI OpenACC compiler beat the performance of a CUDA 7.0 NVIDIA nvcc compiled deep-learning based PCA (Principal Components Analysis) example by 200 GF/s on a K40c using an ILP (Instruction Level Parallelism) loop structure taught in the TechEnablement classes and forthcoming Farber OpenACC book. PCA is an important data analysis tool utilized by data scientists. Sign up for … [Read more...]
Facebook Open Source GPU FFT 1.5x Faster Than NVIDIA CUFFT
Facebook has written a Fast Fourier Transform (fbfft) that is 1.5x faster than the NVIDIA CUFFT implementation at sizes 8-64. The paper "Fast Convolutional Nets with fbfft: A GPU Performance Evaluation" discusses the performance increases by changing to a non-zero padded FFT layout (potentially eliminating data copies), the use of autotuning, and clipping to conditionally load … [Read more...]