logo

For the Inventor, By the Inventor

Santa Clara, CA, United States of America

Aayush Ankit

This inventor holds 5 USPTO granted patents and 4 published patent applications. Top assignee: D-Matrix Corporation. Active years: 2024-2026.

IDiyas Innovation Intelligence. (2026). Inventor Profile: Aayush Ankit. Retrieved from https://idiyas.com/inventor/aayush-ankit-jh7x6z0t

Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile

Calculating rank
USPTO Granted Patents = 5 

% Patents Active = 60.0

Average Co-Inventor Count = 3.1

ph-index = 1


Company Filing History:

goldMedal5 out of 12 
 
D-Matrix Corporation
 patents

Years Active: 2024-2026

Loading Chart...
5 patents (USPTO):Explore Patents
1. 12748715 - Digital switch between chiplet devices for handling transformer workloads (2026-09-29),
2. 12639253 - Methods and systems for allreduce optimization on small tensors (2026-05-26),
3. 12386774 - AI accelerator apparatus using full mesh connectivity chiplet devices for transformer workloads (2025-08-12),
4. 12353985 - Server system with AI accelerator apparatuses using in-memory compute chiplet devices for transformer workloads (2025-07-08),
5. 12182028 - Method and apparatus to cache key-value data in low-precision numerics for efficient generative transformer execution (2024-12-31),

Title: Innovations by Aayush Ankit

Introduction

Aayush Ankit is a prominent inventor based in Santa Clara, CA. He has made significant contributions to the field of artificial intelligence and computing. With a total of 5 patents, Aayush is recognized for his innovative approaches to enhancing computational efficiency.

Latest Patents

Aayush Ankit's latest patents include groundbreaking technologies aimed at improving AI processing capabilities. One of his notable inventions is an AI accelerator apparatus using full mesh connectivity chiplet devices for transformer workloads. This apparatus features a first semiconductor substrate with multiple chiplets, each containing a variety of tiles. Each tile is equipped with a central processing unit (CPU) and a hardware dispatch device, along with digital in-memory compute (DIMC) devices designed for high throughput computations. The DIMC devices are specifically configured to accelerate attention functions for transformer-based models, which are essential in machine learning applications.

Another significant patent is a server system that incorporates AI accelerator apparatuses using in-memory compute chiplet devices. This system consists of several multiprocessors, each with a first and second server CPU connected to multiple switch devices. These switch devices link to various AI accelerator apparatuses, enhancing the overall processing power and efficiency of machine learning tasks.

Career Highlights

Aayush Ankit is currently employed at D-Matrix Corporation, where he continues to develop innovative solutions in AI and computing. His work focuses on creating advanced systems that leverage in-memory computing to optimize performance in machine learning applications.

Collaborations

Aayush collaborates with talented individuals such as Jayaprakash Balachandran and Akhil Arunkumar. Together, they contribute to the advancement of technology in their respective fields.

Conclusion

Aayush Ankit's contributions to the field of artificial intelligence and computing are noteworthy. His innovative patents and collaborative efforts position him as a key figure in the ongoing evolution of technology.

Profile summary based on public USPTO records.
Data Sources: USPTO Patent Grant XML, Patent Center, EPO & CIPO • Normalized by IDiyas Innovation Graph. Methodology & provenance architecturePlease report any incorrect information to [email protected]
Loading…