Skip to main content

In-Place Associative Computing

 
Current Solution
Market Solution
GSI Technology's New APU Solution
APU Solution

 

GSI Technology's new patented Gemini® Associative Processing Unit (APU) changes the concept of computing from serial data processing—where data is moved back and forth between the processor and memory—to massive parallel data processing, compute, and search in-place directly in the memory array.

 

This in-place associative computing technology removes the bottleneck at the I/O between the processor and memory. Data is accessed by content and processed directly in place in the memory array without having to cross the I/O. The result is an orders of magnitude performance-over-power ratio improvement compared to conventional methods that use CPU and GPGPU (General Purpose GPU) along with DRAM.

 

Target applications include memory-bound sparse matrix-vector multiplication,
convolutional neural networks, image detection, signal detection, speech recognition,
recommender systems for e-commerce, and data mining tasks such as prediction, classification, and clustering.

For more information on this exciting new technology, please contact us at associativecomputing@gsitechnology.com.
 

Articles
Why Space Needs Artificial Intelligence--NEW!
Radiation Tolerance Meets Commercial Space--NEW!
Review of 2017 Energy Consequences of Information Conference
Sales Briefs
GSI Technology Takes On DSP With Deep Learning Molecular Search with the Gemini Associative Processing Unit Facial Recognition with the Gemini Associative Processing Unit
Whitepapers
Hamming Space Locality Preserving Neural Hashing for Similarity Search In-Memory Acceleration for Big Data Gemini APU:  Enabling High Performance Billion-Scale Similarity Search Introducing a Cheminformatics Similarity Structure Search Solution
Introducing a Facial Recognition Solution In-Place Associative Computing:  A New Concept in Processor Design In-Place Associative Computing:  An Introduction to the APU Software In-Place Computing:  Scaling to 1M Similarity Searches per Second
Blogs
The Role of Transformers in Natural Language Processing and Google's Revolutionary B.E.R.T. A Beginner's Guide to Segmentation in Satellite Images How to Benchmark ANN Algorithms Getting Started with Satellite Data Processing
High-Performance, Billion-Scale Similarity Search Similarity Search: Finding A Needle In A Haystack Leveraging Word2vec For More Than Text Linear Algebra For Graph Convolutional Networks
The New Face of Biometrics In the Era of Hacks, Fakes, Bans, and GANs Application Of AI To Cybersecurity - Part 3 Classification with Similarity Search: Fast and Accurate Radio Wave Classification Application Of AI To Cybersecurity - Part 2
Radio Wave Classifier In Python: How I Built A ResNet Radio Wave Classifier With Keras Deep Learning For Radio Waves: Using Residual Neural Networks For Signal Classification Application Of AI To Cybersecurity - Part 1 Introduction To Basic Concepts An Overview Of Signal Classification: From Fourier Transforms To Deep Neural Networks
Tanimoto vs. Mol2vec The Weizmann Institute of Science Reduces Molecular Search Time from Minutes to Milliseconds - A Case Study RDKit for Newbies My First Adventures in Similarity Search
The APU: Novel Hardware For Accelerated Similarity Search Fast Visual Search in Hamming Space Hardware Accelerated Search For Drug Discovery: Molecule Similarity in Milliseconds Integrating Textual and Visual Information into a Powerful Visual Search Engine
Molecular Similarity Search: A Simple but Powerful Drug Discovery Tool Seven Tips for Visual Search at Scale Visualizing Embeddings Using t-SNE Getting Started with Clarifai's SDK
Wayfair's Visual Search and the Latest in Similarity Search Research ML in Visual Search: Part I The Visual Similarity Search Revolution Visual Search: The Future of Search
Case Study
Weizmann Institute of Science Drives Drug Discovery with Ultra-Fast Molecular Similarity Search
Presentations
Associative Based Similarity Search
for Few Shot Training
Stanford EE Computer Systems Colloquium
In-Place Deep Learning
Interviews
Dr. Avidan Akerib Interview at
Global Predictive Analytics Conference
In-Place Associative Computing Interview
with RE*WORK