Jul 21 2017
Wave Computing, the Silicon Valley start-up that is revolutionizing machine learning through WaveFlow compute appliances, today announced it has received two prestigious honors recognizing the company’s contribution to the artificial intelligence (AI) industry with its pioneering dataflow technology that enables breakthrough levels of innovation.
Wave Computing has been named by CIO Application Magazine as one of the Top 25 Artificial Intelligence Solution Providers in 2017, with special recognition for the company’s “new kind of hardware acceleration that can do machine learning training and inferencing faster by orders of magnitude compared to current offerings.”
Wave Computing was also highlighted in a comprehensive new report by AT&T Foundry, Ericsson and RocketSpace, “The Future of Artificial Intelligence in Consumer Experiences,” as one of the cutting-edge startups shaping the future of AI. The Wave compute appliance is driving the next generation of hardware solutions that allows devices to be in constant conversation, enabling real-time interaction with neural networks for optimized end-user experiences.
“We’re honored to be recognized by these industry-leading organizations for our unique dataflow-based approach to machine learning, and our ability to accelerate new levels of neural network training, inferencing and connectivity for AI applications,” said Derek Meyer, CEO of Wave Computing. “This is an exciting time for the AI industry as new solutions, such as the WaveFlow compute appliance, offer the promise to unlock new business models and revenue streams not possible with traditional hardware acceleration offerings.”
Wave Computing’s dataflow-based compute appliance is redefining machine learning by accelerating the performance and scalability of training and inferencing for deep and shallow neural networks. The solution overcomes the limitations of traditional machine learning approaches that rely on CPUs or co-processors, such as GPUs and FPGAs. By natively executing dataflow graphs, the Wave compute appliance speeds the training of neural networks up to 1,000x and enables support for much larger datasets in a single data center node. Initially optimized for the data center, each Wave compute appliance can deliver up to 2.9 PetaOps per second of performance, more than 250,000 processing elements, more than 2 TB of high-speed memories, and can be combined into even higher performance configurations.
Wave’s Early Access Program
Wave Computing is currently offering cloud-based access to a prototype of the Wave compute appliance to data scientists and developers from qualified companies. Availability is limited so interested companies should apply today.