Artificial intelligence (AI) and deep learning have generated lot of excitement over the past few years. Many semiconductor startups have emerged to build chipsets optimized for AI. They are tackling compute, communication, and memory-related problems specific to AI algorithm accelerations and building highly optimized architectures that promise low power and high performance. Nervana was perhaps the first company to build a chipset specifically for AI, which got started in 2014. Nervana wanted to sell cloud services based on its chipsets and bypass the application-specific integrated circuits (ASICs) altogether.

AI startup Wave Computing announced this week that it has acquired MIPS Tech, Inc. (formerly MIPS Technologies), a global leader in RISC processor Intellectual Property (IP) and licensable CPU cores. The acquisition will accelerate Wave's strategy of offering AI acceleration from the Datacenter to the Edge of Cloud by extending the company's products beyond AI systems to now also include AI-enabled embedded solutions. This is a major milestone not only in the history of our two companies, but also for the AI compute industry," said Derek Meyer, CEO of Wave Computing. "With working DPU commercial silicon and being in the final stages of bringing our first AI systems to market, now is the time for us to expand to the Edge of Cloud. The acquisition of MIPS allows us to combine technologies to create products that will deliver a single'Datacenter-to-Edge' platform ideal for AI and deep learning.

Wave Computing, a Silicon Valley AI startup specializing in data flow processing of Deep Neural Networks, has acquired MIPS Technologies for an undisclosed amount. Wave projects that the acquisition will be immediately cash-flow positive and accretive to its balance sheet and valuation. The deal logic is pretty sound, adding new markets such as edge AI computing while giving the company in-house RISC cores it can use for its next-generation DataFlow Processing Unit datacenter AI chip. Who is Wave Computing, and why does it need MIPS? Wave is an early innovator in AI silicon geared towards datacenter use, to train deep neural networks (DNNs) and run those networks for predictions and classifications.

When it comes to deep learning chip startups, hype moves fast but crossing the finish line to real production silicon takes an incredibly long time. There are several incumbents on the custom hardware side aiming for the AI training and inference market but outside of Google's TPU, there are very few functioning inside datacenters. From the forthcoming Nervana chips (now expected in 2019) to startups like Graphcore, Cerebras (which just ducked back into stealth mode), among several others, the pressure is on to create hardware that reflects the latest framework and algorithmic developments that so far seem to run quite well on widely available GPUs with all the requisite porting and software work handled thanks to big library and tooling investments from Nvidia over the last few years. In other words, it is going to be damn tough to beat Nvidia, especially this late in the game, but for one of the better known deep learning chip startups, Wave Computing, there is more going on in the outfield than we might readily see. This is why the company has invested in tech that might seem a bit left field--that is, until we look at how the AI hardware game of the future might play out.

Google last week unveiled the third version of its Tensor Processing Unit (TPU), which is designed to accelerate deep learning workloads developed in its TensorFlow environment. But that's just the start of a groundswell of new processors and processing architectures, including Wave Computing, which claims its soon-to-be-launched processor will dramatically lower the barrier of entry for running artificial intelligence workloads. Compared to traditional machine learning algorithms, deep learning models offer superior accuracy and the potential to achieve human-like precision across a range of tasks. That's true for both major branches in the deep learning family tree, including convolutional neural networks (CNNs), which are mostly geared toward solving computer vision-type problems, and recurrent neural network (RNNs), which are geared toward language-oriented problems. While deep learning offers better results, those results come at a cost in the form of two key ingredients that must be present to get the benefits: large amounts of data and large amounts of computing power.

Last year, the company released the DGX Station to enable software engineers to experiment with software libraries used in artificial intelligence and improve algorithms before sending them to the cloud, where the software is trained on enormous amounts of data. The workstation contains chips based on Nvidia's Volta architecture and provides 480 trillion floating-point operations per second, or teraflops. The DGX workstation shares the same software stack as the DGX-1 appliance, a miniature supercomputer that provides 960 teraflops of performance. That way, software engineers can swiftly swap software between Nvidia's workstations and appliances, which can be installed in data centers where training typically happens. Nvidia introduced both products to tighten its grip over the artificial intelligence market and promote its Volta architecture, which contains custom tensor cores for handling deep learning.

There are many established and startup companies developing deep learning chips. Google and Wave Computing have working silicon and are conducting customer trials. Chinese AI chip startup has received $100 million in funding. Cambricon Technologies aims to have one billion smart devices using its AI processor and own 30% of China's high-performance AI chip market in three years. Huawei estimates Cambricon chips are six times faster for deep-learning applications like training algorithms to identify images than a GPU.

If there is one subset of machine learning that incites the greatest excitement--that seems most like the intelligence in artificial intelligence--it is deep learning. Deep learning frameworks, also known as deep neural networks, power complex pattern-recognition systems that provide everything from automated language translation to image identification. Deep learning holds enormous promise for analysing unstructured data. There are just three problems: it is hard to do, it requires large amounts of data, and it uses lots of processing power. Naturally, great minds are at work to overcome these challenges.

If there is one subset of machine learning that spurs the most excitement, that seems most like the intelligence in artificial intelligence, it's deep learning. Deep learning frameworks--aka deep neural networks--power complex pattern-recognition systems that provide everything from automated language translation to image identification. Deep learning holds enormous promise for analyzing unstructured data. There are just three problems: It's hard to do, it requires large amounts of data, and it uses lots of processing power. Naturally, great minds are at work to overcome these challenges.

Intel has planted some solid stakes in the ground for the future of deep learning over the last month with its acquisition of deep learning chip startup, Nervana Systems, and most recently, mobile and embedded machine learning company, Movidius. These new pieces will snap into Intel's still-forming puzzle for capturing the supposed billion-plus dollar market ahead for deep learning, which is complemented by its own Knights Mill effort and software optimization work on machine learning codes and tooling. At the same time, just down the coast, Nvidia is firming up the market for its own GPU training and inference chips as well as its own hardware outfitted with the latest Pascal GPUs and requisite deep learning libraries. While Intel's efforts have garnered significant headlines recently with that surprising pair of acquisitions, a move which is pushing Nvidia harder to demonstrate GPU acceleration (thus far the dominant compute engine for model training) for deep learning, they still have some work to do to capture mindshare for this emerging market. Further complicating this is the fact that the last two years have brought a number of newcomers to the field--deep learning chip upstarts touting the idea that general purpose architectures (including GPUs) cannot compare to a low precision, fixed point, specialized approach.