Four years after the introduction of Loihi, Intel’s first neuromorphic chip, the company is introducing its successor. According to Intel, the second-generation chip will provide faster processing, higher resource density and greater energy efficiency. Intel is also introducing Lava, a software framework for neuromorphic computing.
Various processors and pieces of code are often compared to brains, but neuromorphic chips work to much more directly mimic neurological systems through the use of computational “neurons” that communicate with one another. Intel’s first-generation Loihi chip, introduced in 2017, has around 128,000 of those digital neurons. Over the ensuing four years, Loihi has been packed into increasingly large systems, learned to touch and even been taught to smell.
Now, it’s getting a new family member: Loihi 2. In its press release, Intel said that years of testing with the first-generation Loihi chip helped them to design a second generation with up to ten times the processing speed; up to 15 times greater resource density; and up to a million computational neurons per chip – more than seven times those in the first generation. Intel reports that early tests have shown that Loihi 2 required more than 60 times fewer ops per inference when running deep neural networks as compared to Loihi 1 (without a loss in accuracy).
Loihi 2 also makes strides toward greater flexibility by incorporating faster, standardized I/O interfaces to support Ethernet connections, vision sensors and larger meshed networks. These changes are meant to help the chip integrate better with the robotics and sensors that have comprised many of Loihi 1’s use cases over the years.
Intel says that Loihi 2 (which is being fabricated with a pre-production version of the “Intel 4” process) supports “new classes of neuro-inspired algorithms and applications.” These improvements over Loihi 1 – which was specialized for a specific spiking neural network (SNN) – are enabled by Loihi 2’s support for programmable pipelines for the neuron models in each neuromorphic core.
To support development for this now-widened field of neuromorphic applications, Intel is also introducing its open, modular and extensible “Lava” software framework, which the company says fills the neuromorphic computing community’s need for a common development framework. Intel says that Lava is platform-agnostic: “we have intentionally structured the code so that it is not tied to our own neuromorphic chips,” Intel wrote in its technical brief. Included within Lava is Magma, an interface for mapping and executing neural network models and other processes using neuromorphic hardware. Lava also includes offline training, integration with third-party frameworks, Python interfaces and more.
“Loihi 2 and Lava harvest insights from several years of collaborative research using Loihi,” said Mike Davies, director of Intel’s Neuromorphic Computing Lab. “Our second-generation chip greatly improves the speed, programmability and capacity of neuromorphic processing, broadening its usages in power and latency constrained intelligent computing applications. We are open sourcing Lava to address the need for software convergence, benchmarking, and cross-platform collaboration in the field and to accelerate our progress toward commercial viability.”
Speaking of commercial viability, Intel sees a broad range of applications for Loihi 2 (and neuromorphic computing more generally) in the future. Apart from previewing uses of Loihi 2 in audio and video processing, Intel highlighted possible uses for neuromorphic capabilities: intelligent edge coprocessors for aerospace and robotics, datacenter accelerators, specialized consumer devices and more.
“Advances like the new Loihi-2 chip and the Lava API are important steps forward in neuromorphic computing,” said Edy Liongosari, chief research scientist and managing director for Accenture Labs. “Next-generation neuromorphic architecture will be crucial for Accenture Labs’ research on brain-inspired computer vision algorithms for intelligent edge computing that could power future extended-reality headsets or intelligent mobile robots. The new chip provides features that will make it more efficient for hyper-dimensional computing and can enable more advanced on-chip learning, while the Lava API provides developers with a simpler and more streamlined interface to build neuromorphic systems.”
However, Loihi 2 is still in its early days. Initially, Intel is offering two Loihi 2-based systems through its neuromorphic research cloud to select members of its Intel Neuromorphic Research Community (INRC). Those systems are Oheo Gulch, which uses a single Loihi 2 chip on an Intel Arria 10 FPGA and is intended for early evaluation, and Kapoho Point, which offers eight Loihi 2 chips in a stackable, “approximately 4×4-inch form factor with an Ethernet interface … ideal for portable projects” (and which will be available soon).
The Lava framework, however, is available right now on GitHub.
Header image: the Loihi 2 die on a fingertip. Image courtesy of Intel.
Read more about neuromorphic computing