Military startup launches neural processor for machine learning
Dan Goldin, who led the National Aeronautics and Space Administration (NASA) throughout its renaissance in the 1990s, is the founder and CEO.
The KnuPath processor is already in production and in use at customer sites, KnuEdge said. At the same time the company launched KnuVerse, its voice-recognition and authentication software. The company said it has been supplying the software for military applications for five years.
KnuEdge has also divided itself into multiple operations to better drive sales forward. These are: hardware operation KnuPath, software operation KnuVerse and service operation Knurld. Knurld delivers the same neuromorphic computation technologies to a broader market via Knurld.io, a public cloud API service that allows developers to incorporate voice authentication into their proprietary products.
The KnuPath processor, codenamed Hermosa, is described as a Lambda Fabric processor and is generally intended to be deployed in datacenters where its ability to scale can be used. The KnuPath Lambda Fabric is desined to scale up to 512k devices and offers a rack-to-rack latency of 400ns, approaching half that of existing high-speed interconnects, the company said.
Each KnuPath processor includes 256 tDSP cores, 64 programmable DMA engines, an integrated L1 router to provide a maximum performance of 256-Gflops/s and 3,702Gbytes/s of memory bandwidth. There are 16 bi-directional I/O paths per processor chip delivering 320 Gbps-per processor and the chip consumes 34W.
Despite this hefty power consumption KnuEdge claims that when compared to the alternative processors available today its first-generation Lambda Fabric processors demonstrate an efficiency performance per watt advantage of between a factor of 2 and 6.
Put another way on its website KnuPath claims: “Hermosa outperforms the newest competing GPUs by 2.7 to 8.1x, as measured by key benchmarks like FFT, Sparse Matrix-Vector Multiply and k-means Clustering.”
“Many of today’s CPUs, GPUs and FPGAs force system designers to either create workarounds with last-generation chip sets or reduce their requirements for advanced-compute projects,” said Goldin, in a statement. “After ten years of stealth development and rigorous testing, Lambda Fabric enters the market as mature technology which enables system designers to meet the most demanding requirements now, and also helps them rethink what is possible with neural computing in the future.”
As can be seen from the package photograph ARM is involved in the KnuPath. However it is not clear from the sparse technical description at the KnuPath how it is involved. The KnuPath subsidiary of KnuEdge is based in Austin, Texas, which is a major site for ARM in North America.
The need for the KnuPath processor was revealed when KnuEdge encountered problem developing its neural network based voice recognition and authentication technology. The company created a chip design team to build an ASIC that would not only support that application but could be deployed more widely.
KnuEdge said the production platforms and systems based on KnuPath processor would be delivered in the second half of 2016.
KnuVerse voice-recognition and authentication software has been used in “mission-critical battlefield conditions” for five years, KnuEdge said, and is now being made available for enterprise applications where it is expected to enhance voice-command consumer electronics.
Voice-assisted applications have become popular in the form of Siri, Cortana and Alexa but such systems are not completely reliable in noisy environments. At the core of KnuVerse are authentication techniques that improve the security of human-voice biometrics
“KnuVerse has already driven millions [of dollars] in revenue, and although we have just begun selling commercially, we have significant interest from Fortune 500 companies in the banking, healthcare and entertainment industries,” said Kate Dilligan, executive vice president of KnuVerse, in a statement. “When our enterprise customers realize that they can instantly recognize and authenticate users on any device or platform without friction, the innovation wheels start turning. They stop worrying about fundamental tech issues and begin looking at higher-order opportunities such as improving the customer experience and establishing new competitive advantages.”
Goldin said: “At KnuEdge, we are not in business to create incremental technology improvements on what already exists. Our mission is fundamental transformation.”
Neural network stick promises new smart applications, products
Lawrence Livermore, IBM partner on brain-like supercomputer
BrainChip CEO gives details of neural network architecture
Startup plans neural network circuit for low-power wireless sensors
Machine-learning radars may be coming to automotive