About the Author
Michael Azoff
With over 17 years analyst experience, most recently at Ovum/ Informa, Michael Azoff joined Kisaco Research, the company behind the AI Hardware and Edge AI Summit series, in 2020 as Chief Analyst.
Eitan Michael Azoff, PhD, MSc, BEng.
HQ’d in Kisaco Research’s London office, Michael's current focus is launching Kisaco Research vendor product comparison reports with the new Kisaco Leadership Chart (KLC) analyst chart. The first KLC is also the first analyst chart in the AI chip industry, with 16 vendors having participated in the research.
In his career Michael worked at Rutherford Appleton Laboratory building simulators for electron and hole transport in semiconductors for UK national and European community research projects and published papers in learned journals. He then turned to building neural networks and created a startup selling his Prognostica Microsoft Excel add-in for time series forecasting, and wrote a book on the topic for publisher John Wiley & Sons in 1994.
Since 2003 Michael has worked as an IT industry analyst covering software engineering topics, from agile and DevOps, to application lifecycle management and cloud native computing. He started covering machine learning when deep learning emerged as the most recent wave of interest in AI and left his position as Distinguished Analyst at Ovum/Informa to join Kisaco Research and help build an analyst capability within the company.
My analyst coverage areas at KR Analysis
My first research project at KR was to create the first analyst comparison chart for AI chips. We invited AI chip producers to participate and were fortunate to have 16 vendors participate from across the globe: USA, UK, France, and China, and a mix of established players (Nvidia, Imagination, Intel, and Xilinx, to startups.
Our analysis showed that the market naturally fell into three areas of hot activity:
▪ Data centers and high-performance computing environments (HPC): here large boxes are installed and the aim is to achieve maximum performance for training and inferencing AI systems. The buyers are cloud hyperscalars, national research labs and agencies, and some large enterprises with big investments in AI.
▪ Small edge: the opposite end of the spectrum, building the smallest useful chip possible to sell as cheap as possible and embed in edge devices. AI is inferencing here.
▪ Automotive: an active industry in AI but highly regulated creating hurdles and technology adoption cadences that can be challenging for suppliers. AI is mainly inferencing here (for systems installed in vehicles).
We produced four Kisaco Leadership Charts out of this research.
We are also researching the machine learning (ML) software tools space, and our first report here is ML Lifecycle Solutions. The biggest challenge for enterprises is taking the research AI systems developed by their data scientist and deploying these into production at scale. Using a host of open source tools to achieve this is possible but time consuming to build and maintain, as well as prone to breakdown. This is why the ML lifecycle solution space exists.
Finally, in our first batch of KR Analysis reports we produced the KLC on engineering application lifecycle management (ALM) solutions. While ALM has been in existence as a distinct practice since KR Analysis and Michael Azoff introduction © Kisaco Research. All rights reserved. Unauthorized reproduction prohibited. 4 around 2003, it continues to evolve. We found the engineering and highly regulated industries relying on engineering and compliance oriented ALM to help manage risk and complexity.
-
Motivation
Neuromorphic computing arises out of artificial intelligence (AI) research based on technology that has direct biological links with the human brain. The brain is an analog system that uses electrical spikes to transmit signals between neurons, similarly many vendors that choose the neuromorphic label for their processors use spiking neural networks (SNNs) in an analog system, typically electric circuits. However, other such vendors choose to use digital devices with a SNN, and yet again others use an analog device with non-spiking, continuous value signal neural networks.
Neuromorphic computing emerged in the 1990s but has had a slow evolution due to the challenges in training neural networks without use of a global learning rule, such as backpropagation. Backpropagation is critical in (non-spiking) deep learning neural networks, and it uses information at the output of the network to update neurons (more exactly the synapse weights) upstream in the network. To our best understanding at time of writing the human brain does not use a global learning rule and it has taken time for local learning rules to emerge for neuromorphic architectures, with success in the last two years, and this has given birth to a surge in startups in this space.
To find the common ground that can be pinned to the neuromorphic label there are two key characteristics: low power consumption and high efficiency, typically in the form of highly sparse connectivity – both characteristics of the human brain. We delve deeper into what exactly distinguishes neuromorphic from the traditional AI in this report. We also assess neuromorphic vendors with processors that span the range of possible architectures and learning rules. The Kisaco Leadership Chart (KLC) compares five of the pioneering vendors side by side: AIStorm, BrainChip, Innatera Nanosystems, Rain Neuromorphics, and SynSense. In addition to our in-depth profiles on these vendors, we have three more vendors profiled in-depth: Aspinity, Intel, and Inivation.
-
What you will learn
- How neuromorphic processors differ from other AI processors on the market.
- Which is the strongest market segment for neuromorphic processors.
- Our report has assessed five neuromorphic processor vendors and we provide a high-level heatmap on the key features available
- We compare the processors from the five participating vendors side by side and assess these in our Kisaco Leadership Chart.
- We provide an in-depth profile on each of the participating vendors together with three strengths and three weaknesses.
-
Contents
Kisaco Research View…………………………………..………..………......2
Motivation……………………………………………………..............2
Key findings…………......................................……..…………........2
Solution Analysis: Neuromorphic processors …………………...….....….3
Technology landscape………………………………………...........…3
Market landscape……………...................................……......….….4
Solution analysis: vendor comparisons…………….............................…..5
Kisaco Leadership Chart on Neuromorphic Processors 2020-21…5
Neuromorphic processor vendor comparisons………………5
The KLC chart for neuromorphic processors…………………6
Vendor analysis………………………………….............................…………8
AIStorm, Kisaco evaluation: Leader……………………………….…..8
Kisaco Assessment………………….............................………10
Aspinity, Kisaco evaluation: chose not to participate in KLC……...10
BrainChip, Kisaco evaluation: Leader……………………………...….13
Kisaco Assessment………………………..................….………17
iniVation, Kisaco evaluation: chose not to participate in KLC……...17
Innatera Nanosystems, Kisaco evaluation: Emerging Player…..…...20
Kisaco Assessment…………………….....................…..………24
Intel, Kisaco evaluation: chose not to participate in KLC…………...25
Rain Neuromorphics, Kisaco evaluation: Innovator……………...…..30
Introduction………………………………………………...……..30
The Rain Analog Processing Unit (APU)……………………….30
Taping out APU chips………………………………………..…..31
The Rain energy equilibrium algorithm for neural learning....32
The Rain APU 3D synaptic architecture……………………….33
Kisaco Assessment…………………………............……………34
SynSense, Kisaco evaluation: Contender……………………………..34
Kisaco Assessment………………………………………………..……..37
Appendix……………………………………...…………………………………38
Vendor solution selection……………………………..........…………..38
Inclusion criteria………………………….............………………………38
Methodology…………………………………………..………………….38
Definition of the KLC………………………………………..……………38
Kisaco Research ratings………………………………………….……….38
Further reading…………………………………………...………………………39
Acknowledgements……………………………………….……………………..39
Author……………………………………………………...………………………39
Kisaco Research Analysis Network……………………………………..………39
Copyright notice and disclaimer…………………………………………..…….39
-
Figures
Figure 1: Comparing the brain, neuromorphic chip, and GPU in AI inference mode.
Figure 2: Comparing the KLC vendors on key technology features.
Figure 3: Heat map analysis of participating vendor technical features.
Figure 4: Kisaco Leadership Chart on Neuromorphic Processors 2020-21.
Figure 5: Kisaco Leadership Chart on Neuromorphic Processors 2020-21: ranking of vendors.
Figure 6: Comparing digitization of input with AIStorm’s AI-in-Sensor.
Figure 7: AIStorm imager with “always on” cascaded wake-on approach.
Figure 8: Aspinity AnalogML typical use case.
Figure 9: Aspinity AnalogML core.
Figure 10: BrainChip Akida NPU architecture and IP solution.
Figure 11: BrainChip Akida software development environment and training workflow.
Figure 12: Inivation sensors only capture image changes.
Figure 13: Innatera spiking neural processor architecture.
Figure 14: Innatera spiking neural processor: segment zoom view.
Figure 15: Audio processing with a temporal feedforward SNN on the Innatera SNP.
Figure 16: Loihi benchmarks: Recurrent networks with bio-inspired properties give the best results.
Figure 17: Loihi Research Systems currently available.
Figure 18: Loihi projects pursued by INRC members.
Figure 19: Efficient sensing and pattern learning.
Figure 20: Rain’s Analog Processing Units (APUs).
Figure 21: Rain APU 3D architecture vs traditional 2D crossbar.
Figure 22: SynSense hardware families.
Figure 23: CNN based processing stack. Backpropagation-based training of visual features.
-
FAQs
1. What is the Kisaco Innovation Radar report (KIR)?
In this report we cover a topic that is still nascent in the vendor market and not ready for a KLC report. We introduce the topic and cover several leading vendors with profiles, and where possible we include in our coverage a heatmap of key high-level features in the technology being used. Vendors profiled are selected for their pioneering contribution to the field.
2. What is the KLC?
The Kisaco Leadership Chart (KLC) is KR Analysis’s take on the classis industry analyst chart in which vendor products are assessed and their scores plotted on a chart comprising four quadrants: Leader, Contender, Innovator, and Emerging Player. The x-axis represents strength of technical features, the y-axis the strength of market execution and strategy, and the size of plotted circle represents market revenue normalized to the strongest participating player in the research.
In researching the KLC we receive privileged information from a vendor. As explained in question 3, participating vendors are actively engaged in our research. Confidential privileged vendor information is not disclosed in our report but helps us assess vendors in our analysis.
3. What is the vendor selection process for a KLC project?
KR Analysis creates a shortlist of vendors to invite to the research project. The aim is to include the leading players as well as innovative smaller players, across startup and established vendors. KLC research can at best be representative of the market and is not designed to be exhaustive – in some markets the sheer number of players would make an exhaustive KLC unmanageable, in smaller markets we are still dependent on vendors agreeing to participate.
We do create KR Analysis Technology and Market Landscape reports in which we typically list the players in the markets with thumbnail profiles providing information such as company leadership, location, funding status, and main product(s) details. While we cannot guarantee exhaustiveness, the landscape report does aim to list the most important vendors and does not require vendor participation.
4. In a KLC what does participating entail for a vendor?
First of all, we do not charge vendors to participate in a KLC. Participating vendors need to be actively engaged in a KLC research project, this involves completing a comprehensive questionnaire, which we score and use as the basis for positioning the vendor in the report’s KLC. We also hold a deep dive briefing and engage in plenty of Q&A. Finally, we research publicly available material on the vendor and its product(s) to complete our final view of the vendor.
5. Why are some notable vendors missing from the report?
As explained in question 2, we do invite the leaders in a market segment we are researching, however not all such players agree to participate. As explained in question 3, participating involves active engagement and example reasons vendors offer for declining our invitation are, often ending with “...but please consider us next cycle of the report.”:
- We are in the midst of an event in which our relevant staff do not have the time to engage in your process.
- We are going through a major change in strategy or product re-architecture and the timing is not right for us to participate.
- We are about to have our IPO and this is not the right time to participate.
- We are about to launch our flagship product and the report timing is not right for us.
-
About the Author
Michael Azoff
Chief AnalystKisaco ResearchWith over 17 years analyst experience, most recently at Ovum/ Informa, Michael Azoff joined Kisaco Research, the company behind the AI Hardware and Edge AI Summit series, in 2020 as Chief Analyst.
Eitan Michael Azoff, PhD, MSc, BEng.
HQ’d in Kisaco Research’s London office, Michael's current focus is launching Kisaco Research vendor product comparison reports with the new Kisaco Leadership Chart (KLC) analyst chart. The first KLC is also the first analyst chart in the AI chip industry, with 16 vendors having participated in the research.
In his career Michael worked at Rutherford Appleton Laboratory building simulators for electron and hole transport in semiconductors for UK national and European community research projects and published papers in learned journals. He then turned to building neural networks and created a startup selling his Prognostica Microsoft Excel add-in for time series forecasting, and wrote a book on the topic for publisher John Wiley & Sons in 1994.
Since 2003 Michael has worked as an IT industry analyst covering software engineering topics, from agile and DevOps, to application lifecycle management and cloud native computing. He started covering machine learning when deep learning emerged as the most recent wave of interest in AI and left his position as Distinguished Analyst at Ovum/Informa to join Kisaco Research and help build an analyst capability within the company.
My analyst coverage areas at KR Analysis
My first research project at KR was to create the first analyst comparison chart for AI chips. We invited AI chip producers to participate and were fortunate to have 16 vendors participate from across the globe: USA, UK, France, and China, and a mix of established players (Nvidia, Imagination, Intel, and Xilinx, to startups.
Our analysis showed that the market naturally fell into three areas of hot activity:
▪ Data centers and high-performance computing environments (HPC): here large boxes are installed and the aim is to achieve maximum performance for training and inferencing AI systems. The buyers are cloud hyperscalars, national research labs and agencies, and some large enterprises with big investments in AI.
▪ Small edge: the opposite end of the spectrum, building the smallest useful chip possible to sell as cheap as possible and embed in edge devices. AI is inferencing here.
▪ Automotive: an active industry in AI but highly regulated creating hurdles and technology adoption cadences that can be challenging for suppliers. AI is mainly inferencing here (for systems installed in vehicles).
We produced four Kisaco Leadership Charts out of this research.
We are also researching the machine learning (ML) software tools space, and our first report here is ML Lifecycle Solutions. The biggest challenge for enterprises is taking the research AI systems developed by their data scientist and deploying these into production at scale. Using a host of open source tools to achieve this is possible but time consuming to build and maintain, as well as prone to breakdown. This is why the ML lifecycle solution space exists.
Finally, in our first batch of KR Analysis reports we produced the KLC on engineering application lifecycle management (ALM) solutions. While ALM has been in existence as a distinct practice since KR Analysis and Michael Azoff introduction © Kisaco Research. All rights reserved. Unauthorized reproduction prohibited. 4 around 2003, it continues to evolve. We found the engineering and highly regulated industries relying on engineering and compliance oriented ALM to help manage risk and complexity.
Request a sample
Please complete the form below to receive a sample of this report.
Purchase the report
Single Copy | $4,999 | Buy Online
VAT will be added for companies based in the UK. For further information or support in purchasing a report, please contact email: [email protected]