Tenstorrent Inc. was founded in 2016 by Ivan Hamer, Ljubisa Bajic and Milos Trajkovic and is doing business in building AI silicon spanning from embedded computing to the data center. As of October 2021, Tenstorrent has a market valuation of more than $1 Billion.
Tenstorrent has a total of 31 patents globally, out of which 7 has been granted. Of these 31 patents, 100% patents are active. USA is where Tenstorrent has filed maximum number of patents followed by China and Europe and it also seems reasonable as the biggest market for Tenstorrent is the USA, it has generated an annual revenue of $2.05 million in the year 2020. Parallelly, USA seems to be the main focused R&D center and is also the origin country of Tenstorrent.
Do read about some of the most popular patents of Tenstorrent which have been covered by us in this article and also you can find Tenstorrent’s patents information, the worldwide patent filing activity and its patent filing trend over the years, and many other stats over Tenstorrent’s patent portfolio.
How many patents does Tenstorrent have?
Tenstorrent has a total of 31 patents globally. These patents belong to 7 unique patent families. Out of 31 patents, 31 patents are active.
How many Tenstorrent patents are Alive/Dead?
Worldwide Patents
Patent Families
How Many Patents did Tenstorrent File Every Year?
Are you wondering why there is a drop in patent filing for the last two years? It is because a patent application can take up to 18 months to get published. Certainly, it doesn’t suggest a decrease in the patent filing.
Years of Patent Filing or Grant | Tenstorrent Application Filed | Tenstorrent Patents Granted |
2021 | 1 | 14 |
2020 | 9 | 10 |
2019 | 8 | 3 |
2018 | 13 | 4 |
How Many Patents did Tenstorrent File in Different Countries?
Countries in which Tenstorrent Filed Patents
Country | Patents |
United States Of America | 13 |
China | 7 |
Europe | 7 |
Where are Research Centers of Tenstorrent Patents Located?
What Percentage of Tenstorrent US Patent Applications were Granted?
Tenstorrent (Excluding its subsidiaries) has filed 12 patent applications at USPTO so far (Excluding Design and PCT applications). Out of these 6 have been granted leading to a grant rate of 100%.
Which Law Firms Filed Most US Patents for Tenstorrent?
Law Firm | Total Application | Success Rate |
Daylight Law P C | 12 | 100.00% |
When compared to conventional accelerators such as CPUs, GPUs, FPGAs, and TPU-type processors, Tenstorrent’s architecture scales from datacenter servers to IoT devices with improved efficiency, flexibility, and programmability.
Founder and CEO, Ljubisa Bajic said, “Tenstorrent is a start-up company working on new computer architectures that are aiming to essentially be the right substrate for executing machine learning workloads. More data-heavy workloads have been emerging and taking over, especially the datacenter computing scene, but we want to go wider than that as well.”
Tenstorrent chips distinguish themselves by revising artificial intelligence software on the fly when programmes run on the processors. The goal is to limit the quantity of needless calculating so that critical calculations can be completed faster. It aims to build A.I. chips that beat Nvidia
List of Tenstorrent Patents
Publication Number | Title (English) |
US11113051B2 | Processing core with metadata actuated conditional graph execution |
US11010132B2 | Processing core with data associative adaptive rounding |
US10938413B2 | Processing core data compression and storage system |
US10817293B2 | Processing core with metadata actuated conditional graph execution |
US10644721B2 | Processing core data compression and storage system |
US10585679B2 | Processing core with operation suppression based on contribution estimate |
US10318317B2 | Processing core with operation suppression based on contribution estimate |
US20210271450A1 | Processing core with data associative adaptive rounding |
EP3776869A4 | Processing core data compression and storage system |
EP3616072A4 | Processing core with metadata actuated conditional graph execution |
EP3771989A3 | Overlay layer for network of processor cores |
US20210042118A1 | Processing Core with Meta Data Actuated Conditional Graph Execution |
US20210034373A1 | Overlay layer for network of processor cores |
CN112306946A | Covering layer for a network of processor cores |
CN112292816A | Processing core data compression and storage system |
EP3757813A3 | Processor cores using packet identifiers for routing and computation |
EP3635535A4 | Processing core operation suppression based on contribution estimate |
EP3607496A4 | Conditional graph execution based on prior simplified graph execution |
US20200401402A1 | Processor cores using packet identifiers for routing and computation |
CN112104574A | Processor core for routing and computing using packet identifiers |
US20200174799A1 | Processing core with operation suppression based on contribution estimate |
EP3633525A1 | Processing core with data associative adaptive rounding |
CN110969259A | A processing core data associated adaptive rounding |
CN110799957A | Processing the core condition pattern with metadata driven for execution of |
CN110770696A | Based on processing core operation suppressing contribution estimation |
CN110637306A | The condition map to perform based on previous simplified diagram of execution of |
WO2019239272A1 | Processing core data compression and storage system |
WO2018207146A1 | Processing core operation suppression based on contribution estimate |
WO2018198094A1 | Processing core with metadata actuated conditional graph execution |
US20180293486A1 | Conditional graph execution based on prior simplified graph execution |
WO2018185725A1 | Conditional graph execution based on prior simplified graph execution |