EDA start up Deneb Design launches performance modeling tool for AI-enabled System-on-Chips (SOC)

SUNNYVLE, Calif., Oct. 25, 2024 — (PRNewswire) —

Deneb takes the guess work out of chip architecture design and makes accurate predictions of AI-SoC performance, power, cost and safety

SUNNYVLE, Calif., Oct. 25, 2024 /PRNewswire-PRWeb/ -- Deneb Design, a Sunnyvale-based Electronic Design Automation (EDA) start just announced the availability of a performance modeling software called Deneb SOC. Deneb is an architecture modeling and exploration tool for artificial intelligence (AI)-enabled system-on-chip (SoC) products. Deneb takes the guess work out of architecture design and makes accurate assessment of SoC performance, power, cost and safety.

We are excited to offer an analytical tool to chip architects and help make evidence-based design and IP-selection choices through quantitative analysis.

Deneb includes a rich library of cycle- accurate and cycle-approximate architectural block models of an AI enabled SoC. These include CPU, memory subsystem, network-on-chip (NOC), tensor and vector processing units, GPU etc., all are parameterized and fully configurable. A typical use case of Deneb is to simulate the compute pipeline of a neural processing unit (NPU) that is executing an machine learning (ML)-model, and analyzes its throughput, latency and memory bandwidth requirements. The intelligence gathered from such exercise can be used to properly size the different components of the NPU pipeline, to achieve the desired performance at minimum power and cost.

Deneb also includes utilities to decompose ML and or non-ML workloads, such as convolutional neural models and LLMs, into task graphs consumed by the models for task-aware HW/SW co-simulation. Deneb generates analytical reports to show the efficacy of an architecture, and perform parameter sweeping to identify the sensitivity regions of the configuration space.

"SoC architecture design and IP selection is a complex task that may make or break an expensive chip project, yet we see a lot of such work conducted based-on a simple spreadsheet analysis or just people's intuitions", says Ms. Li Liu, managing director of Deneb Design, "we are excited to offer an analytical tool to chip architects and help them make evidence-based design and IP-selection choices through quantitative analysis".

About Deneb Design

Deneb Design, LLC is a San Jose based Electronic Design Automation (EDA) startup founded by a group of veterans with backgrounds from Silicon Valley EDA and SoC design and manufacturing industry. Deneb's mission is to provide analytical tools to help crafting next-generation high performance computing (HPC) and artificial intelligence (AI) enabled system-on-chip products for datacenters as well as personal devices. Deneb's approach is to use its tools to encourage early-phase architectural exploration, perform quantitative analysis and enable hardware/software codesign.

Media Contact

Li Liu, Deneb Design, LLC, 1 4086663198, Email Contact, www.deneb-design.com

Cision View original content: https://www.prweb.com/releases/eda-start-up-deneb-design-launches-performance-modeling-tool-for-ai-enabled-system-on-chips-soc-302285699.html

SOURCE Deneb Design, LLC

Contact:
Company Name: Deneb Design, LLC




© 2024 Internet Business Systems, Inc.
670 Aberdeen Way, Milpitas, CA 95035
+1 (408) 882-6554 — Contact Us
ShareCG™ is a trademark of Internet Business Systems, Inc.

Report a Bug Report Abuse Make a Suggestion About Privacy Policy Contact Us User Agreement Advertise