Latest News

Semiconductor Engineering: Chiplets, Faster Interconnects, More Efficiency

 Arteris IP's K. Charles Janac, president and CEO, chats with Ed Sperling at Hot Chips in this latest Semiconductor Engineering article:

Chiplets, Faster Interconnects, More Efficiency

August 22nd, 2019 - By Ed Sperling

Big chipmakers are turning to architectural improvements such as chipsets, faster throughput both on-chip and off-chip, and concentrating more work per operation or cycle, in order to ramp up processing speeds and efficiency.

 

“Everyone is struggling with CCIX,” said K. Charles Janac, president and CEO of Arteris IP. “If you have an accelerator and two coherent dies, there are too many corner cases to get it to work easily. But now you can use 3D interconnects to hook together a planar CPU and a planar I/O. So this looks like one system to the software, and you have inter-chip links between the network on chip and different die. That way you can support non-coherent and coherent read/write across two die. It makes the interconnect more valuable, but it also makes it more complicated.”

“The memory controller and the NoC will have to be much more tightly integrated,” said Janac. “The problem is that neither one understands the QoS of the entire chip, and there aren’t any independent memory controller companies left. But memory traffic has to be better integrated to make this work.”

For more information, please visit our Resources page for free downloads of our technical papers; http://www.arteris.com/resources

Topics: SoC ArterisIP FlexNoC ncore cache coherent interconnect semiconductor engineering K. Charles Janac noc interconnect Hot Chips

Semiconductor Engineering: Where Should Auto Sensor Data Be Processed?

 Arteris IP's Kurt Shuler, Vice President of Marketing, comments in this latest Semiconductor Engineering article:

Where Should Auto Sensor Data Be Processed?

August 1st, 2019 - By Ann Steffora Mutschler

Fully autonomous vehicles are coming, but not as quickly as the initial hype would suggest...

 

Indeed, when it comes to processing the sensor data, a number of approaches currently point to allowing for scaling between different ADAS levels, but which the best way to do that is still up for debate.

“There must be an architecture they can do that with, and the question is, ‘How do you do that?'” said Kurt Shuler, vice president of marketing at Arteris IP. “There’s a lot of interest in getting more hardware accelerators to manage the communications in software, and directly managing the memory. For this, cache coherence is growing in importance. But how do you scale a cache coherent system? This must be done in an organized way, as well as adding a whole bunch of masters and slaves to it, such as additional clusters.”

For more information, please download the Arteris FlexNoC Interconnect IP data sheet; https://www.arteris.com/download-flexnoc-datasheet

Topics: SoC autonomous driving ArterisIP FlexNoC semiconductor engineering LIDAR noc interconnect cache coherence hardware accelerators

Join Arteris IP as a Corporate Application Architect!

Featured Position!

Corporate Application Architect in 
Campbell, CA

 


Contribute to the backbone of some of the world's most popular SoCs and be a part of our initiatives in the automotive market!

Topics: software jobs arteris ip safety culture noc interconnect job SoC designs digital design sales memory hierarchy

Join the Arteris IP Team as a Corporate Application Engineer!

Featured Position!

Corporate Application Engineer in 
Campbell, CA


We are looking for you to bring your experience and background in System design, SoC architecture and RTL, and your enthusiasm for technology!

Our current product is powering the creation of the most advanced artificial intelligence, mobile phone, and self-driving car SoCs.

Topics: software jobs ASIC design arteris ip noc interconnect job SoC designs

Arteris IP is Hiring for Multiple Positions in Austin, TX!

If you are looking for a new opportunity and the chance to build the next generation product...then join Arteris IP!

All positions are located in Austin, TX

Your experience ranges from 3 - 10 years and you want to contribute to the backbone of some of the world's most popular SoCs.

ACTION! - Check out these positions;

Solutions Architect
Performance Modeling Engineer
RTL 
Design Hardware Engineer
Senior Hardware Verification Engineer


Topics: software jobs arteris ip noc interconnect job SoC designs C++ Java

Arteris IP Ncore® Cache Coherent Interconnect Licensed by Bitmain for Sophon TPU Artificial Intelligence (AI) Chips

Network-on-chip (NoC) interconnect enables faster performance and lower die area for Tensor Processing Unit (TPU) AI/ML applications

CAMPBELL, Calif. June 9, 2019– Arteris IP, the world’s leading supplier of innovative, silicon-proven network-on-chip (NoC) interconnect intellectual property, today announced that Bitmain has licensed Arteris Ncore Cache Coherent Interconnect IP for use in its next-generation Sophon Tensor Processing Unit (TPU) systems-on-chip (SoCs) for the scalable hardware acceleration of artificial intelligence (AI) and machine learning (ML) algorithms.

Our choice of interconnect IP became more important as we continued to increase the complexity and performance of Sophon AI SoCs. The Arteris Ncore cache coherent interconnect IP allowed us to increase our on-chip bandwidth and reduce die area, while being easy to implement in the backend. The Ncore IP’s configurability helped us optimize the die area of our SoC, which permits us to offer our users more performance at lower cost.”


Haichao Wang, CEO, Bitmain

Topics: SoC NoC new customer performance AI chips ML/AI scalable hardware on-chip bandwidth

Arteris IP FlexNoC® Interconnect Implemented in Uhnder Digital Automotive Radar-on-Chip

Austin-based startup uses Arteris IP interconnect to optimize on-chip communications for automotive radar-on-chip (RoC) systems

CAMPBELL, Calif. June 25, 2019– Arteris IP, the world’s leading supplier of innovative, silicon-proven network-on-chip (NoC) interconnect intellectual property, today announced that Uhnder’s new automotive radar-on-chip (RoC) uses the Arteris FlexNoC IP as the on-chip interconnect.

Our choice of on-chip interconnect IP was very important to our success because of the unprecedented extent of on-chip integration and our huge bandwidth requirements. The Arteris FlexNoC interconnect IP helped us to surpass our performance goals while avoiding routing congestion in our tightly integrated single-chip radar.”


Manju Hedge, CEO and Cofounder, Uhnder

Topics: SoC NoC new customer machine learning autonomous driving flexnoc interconnect ML/AI on-chip communications automotive radar

Arteris® IP FlexNoC® Interconnect Licensed by Achronix for New Speedster®7t FPGA family

Network-on-chip (NoC) interconnect enables ASIC-like performance for Speedster7t FPGA family

CAMPBELL, Calif. — June. 18, 2019 — Arteris IP, the world’s leading supplier of innovative, silicon-proven network-on-chip (NoC) interconnect intellectual property, today announced that Achronix Semiconductor Corporation has licensed Arteris FlexNoC interconnect IP for use in its new Speedster7t FPGA family – based on a new, highly optimized architecture – that goes beyond traditional FPGA solutions featuring ASIC-like performance, FPGA adaptability and enhanced functionality to streamline designs.

Our new Speedster7t FPGA family requires extremely high on-chip bandwidth and advanced dataflow arbitration to make possible ASIC-class machine learning processing. The Arteris FlexNoC IP is the optimal interconnect to meet these demands, especially with the advanced process technology nodes and multi-gigahertz frequencies we are dealing with."


Steve Mensor, Vice President of Marketing, Achronix

Topics: SoC FPGA new customer machine learning artificial intelligence flexnoc interconnect ML/AI Achronix

Silicon-Proven Arteris IP Ncore ® Cache Coherent Interconnect Implemented in Toshiba ISO 26262-Compliant ADAS Chip

Toshiba tapes out next-generation automotive ADAS system-on-chip (SoC) using mature network-on-chip interconnect technology

CAMPBELL, Calif. — June. 11, 2019 — Arteris IP, the world’s leading supplier of innovative, silicon-proven network-on-chip (NoC) interconnect semiconductor intellectual property, today announced that Toshiba has taped out its next generation automotive advanced driver assistance system (ADAS) chip using the Arteris IP Ncore Cache Coherent and FlexNoC®non-coherent interconnect with the associated Resilience Package.

Our use of the uniquely flexible Ncore cache coherent interconnect IP helped us to more quickly design and implement our next generation automotive ADAS chips while allowing us to increase hardware diagnostic coverage for ISO 26262 compliance. The Arteris IP team was very helpful in guiding us on the interconnect configuration to optimize system performance and hardware diagnostic coverage using the integrated functional safety mechanisms. Working with the highly professional Arteris team and their world class interconnect IP has helped us meet our performance requirements and schedule, while adding valuable capabilities that would not be possible with other interconnects.


Nobuaki Otsuka, Technology Executive at Electronic Device & Storage Corporation, Toshiba

Topics: SoC ISO 26262 automotive semiconductors japan flexnoc resilience package ADAS cache coherent interconnect advanced driver assistance systems adas imaging processor ncore cache coherent interconnect

Arteris IP and Wave Computing Collaborate on Reference Architecture for Enterprise Dataflow Platform

The Arteris FlexNoC Artificial Intelligence (AI) Package Coupled with Wave Computing's AI Systems and IP Technology Create a Unified Platform Optimized for AI Data Processing 

CAMPBELL, Calif. — May 21, 2019  Arteris IP, the world’s leading supplier of innovative silicon-proven network-on-chip (NoC) interconnect intellectual property (IP), and Wave Computing®, the Silicon Valley company accelerating artificial intelligence (AI) from the datacenter to the edge, are collaborating to create a blueprint that can help customers overcome compute-to-memory design challenges. Additionally, Wave Computing is licensing Arteris IP’s Ncore Cache Coherent Interconnect, FlexNoC interconnect IP, and its accompanying FlexNoC AI Package for use in the AI-enabled chips that fuel Wave Computing’s data center systems products. By working together to assimilate each other’s technology attributes, Wave Computing and Arteris can ensure the seamless flow of information enterprise-wide, helping speed time-to-insight.

Wave and Arteris have complementary compute and networking technologies that, when packaged together, address some of the key challenges facing system-on-chip designers today such as shorter product cycles and rapidly increasing product complexity. The world of AI demands greater compute power. Working with Arteris allows us to design a scalable data platform with blazing-fast performance at a cost-effective price that helps customers accelerate insight from the edge to the data center.”


Steve Brightfield, Senior Director, Strategic AI IP Marketing, Wave Computing

Topics: Arteris FlexNoC new customer artificial intelligence ncore cache coherent interconnect flexnoc ai package noc interconnect SoC designs datacenters