News

PRESS RELEASE: Peer Robotics partners with Acceleration Robotics to bring hardware acceleration to their collaborative AMR

Source: Acceleration Robotics, March 16, 2023 [1]
Acceleration Robotics, which leads the ROS 2 Hardware Acceleration community efforts, will work with Peer Robotics to improve performance in the mobile robotics stack beyond prevalent market standards.

ROS 2 Hardware Acceleration Working Group #16

Source: Acceleration Robotics, March 15, 2023 [2]
Join the exciting ROS 2 Hardware Acceleration Working Group on its 16th meeting to discuss how hardware acceleration and custom compute architectures can speed up robotics. The goal of this meeting is to review the progress we have made over the last month and report on the current status of the group. The meeting is scheduled to be 30 minutes.

Acceleration robotics hosts ROS developers meet-up in Bangalore, India

Source: Acceleration Robotics, March 13, 2023 [3]
Acceleration Robotics organised another ROS Developers India Meet in Bangalore with the goal of creating a cohesive community of Indian ROS Developers.

China must rethink chip strategy in light of US sanctions

Source: E&T Magazine, March 15, 2023 [4]
China wasn’t doing that well before US sanctions on its silicon strategy; now it’s being forced to try a lot harder.

What to expect at Nvidia GTC 2023

Source: Analytics India Magazine, March 10, 2023 [5]
One of the most-awaited developer conferences, Nvidia GTC, is just around the corner. Scheduled between March 20 and 23, this year’s GTC will focus on the latest advancements from Nvidia in areas of AI computing systems, generative AI, industrial metaverse, and robotics.

Intel Agilex® 7 FPGA I-series addresses 400G IPU and networking solutions requirements

Source: Intel, March 2, 2023 [6]
Intel expands the Intel Agilex® 7 FPGAs and SoCs I-Series product offering with the AGI 041 device that delivers the right balance of capacity, power efficiency, and performance for 400G IPU and networking solutions.

Silicon Labs adds AI acceleration to wireless IoT chips

Source: EETimes, March 10, 2023 [7]
In this podcast, Sally speaks to Silicon Labs’ Matt Maupin and Dan Kozin about the company’s wireless IoT chips with AI acceleration, what use cases need this capability, how the accelerator fits into the device’s deep sleep modes and how AI works with the company’s software stack.

Embracing chaos: The imperfect art of semiconductor manufacturing and lithography

Source: SemiAnalysis, February 27, 2023 [8]
Semiconductor manufacturing is the single most complicated manufacturing process with the lowest tolerance for error. Despite this, the semiconductor industry has stacked hundreds of abstraction layers on top of each other to create a consistent device. Each chip that comes out of a fab consumes a different amount of power, and defects can lead to the chip being yield harvested with disabled "cores" and IO. This is due to the manufacturing variations embedded within billions of transistors and interconnects.

Khronos to create SYCL SC open standard for safety-critical C++ based heterogeneous compute

Source: RoboticsTomorrow, March 15, 2023 [9]
New Working Group designing derivative of the SYCL framework for high-level parallel programming to streamline safety certification in automotive, avionics, industrial, and medical markets; Open call for industry participation.

AMD flips the bird at Intel as it glides past in CPU-GPU stakes

Source: The Register, March 9, 2023 [10]
AMD is introducing its first hybrid CPU-GPU datacenter chip and Epyc products, as rival Intel confirms delays to its own GPU lineup. AMD CTO Mark Papermaster highlighted the progress made with the Instinct MI250 accelerator and its successor, the MI300, which has led to key wins in the HPC sector.

Scaling the RISC-V verification stack

Source: Semiwiki, March 15, 2023 [11]
RISC-V is taking off, but verification is still a challenge. Breker proposes a verification stack with layers from early liveness testing to system level performance and power profiling to ensure the same level of confidence as Arm.

So you want to do robots, Part 3: How to escape pilot purgatory

Source: General Robots, February 13, 2023 [12]
In this part, we’re going to dig into the most common death pattern for robotics startups: starving in pilot purgatory.

Papers

Customized FPGA design and analysis of soft-core processor for DNN

Source: sciencedirect, January 31, 2023 [13]
The proposed FPGA-based soft-core processor for deep neural network (DNN) acceleration outperforms the current general-purpose processor by 6.6 times, retaining the existing architecture's accuracy.

AutoXFPGAs: An end-to-end automated exploration framework for approximate accelerators in FPGA-based systems

Source: arXiv, March 8, 2023 [14]
AutoXFPGAs framework leverages statistical or machine learning models to explore the architecture-space of ASIC-based approximate circuits for FPGA-based systems.

Previous Hardware Acceleration in Robotics Newsletters

Past ROS 2 Hardware Acceleration Working Group meetings

  1. Vikhe, G. (2023, March 16). PRESS release: Peer robotics partners with acceleration robotics to bring hardware acceleration to their collaborative AMR. Hardware Acceleration in Robotics. https://news.accelerationrobotics.com/press-release-peer-robotics/?ref=hardware-acceleration-in-robotics-newsletter ↩︎

  2. https://www.linkedin.com/events/ros2hardwareaccelerationworking7041688888553156608/ ↩︎

  3. https://news.accelerationrobotics.com/ros-developers-meet-bangalore/ ↩︎

  4. Edwards, C. (2023, March 15). China must rethink chip strategy in light of US sanctions. E&T Magazine. https://eandt.theiet.org/content/articles/2023/03/china-must-rethink-chip-strategy-in-light-of-us-sanctions/ ↩︎

  5. Jain, A. (2023, March 10). What to expect at Nvidia GTC 2023. Analytics India Magazine. https://analyticsindiamag.com/what-to-expect-at-nvidia-gtc-2023/ ↩︎

  6. Zou, H., Wageningen, D. V., & Tausanovitch, N. (2023, March 2). Intel Agilex® 7 FPGA I-series addresses 400G IPU and networking solutions requirements. Intel. https://www.intel.com/content/www/us/en/content-details/768467/intel-agilex-7-fpga-i-series-addresses-400g-ipu-and-networking-solutions-requirements.html?cid=em&source=elo&campid=psg_WW_dcaipsgloc_EMPU_EN_2023_FM4 Solution Brief_C-MKA-29855_T-MKA-36330&content=psg_WW_dcaipsgloc_EMPU_EN_2023_FM4 Solution Brief_C-MKA-29855_T-MKA-36330&elq_cid=9300624&em_id=90324&elqrid=30e6e63f9e2c4c80a9c6cd185e9d20e2&elqcampid=55954&erpm_id=11830396 ↩︎

  7. Ward-Foxton, S. (2023, March 10). Silicon Labs adds AI acceleration to wireless IoT chips. EETimes. https://www.eetimes.com/podcasts/ai-s2-ep2/ ↩︎

  8. Patel, D. (2023, February 27). Embracing chaos: The imperfect art of semiconductor manufacturing and lithography. SemiAnalysis | Dylan Patel | Substack. https://www.semianalysis.com/p/embracing-chaos-the-imperfect-art?r=1ne6zn&utm_medium=ios&utm_campaign=post ↩︎

  9. Khronos to create SYCL SC open standard for safety-critical C++ based heterogeneous compute. (2023, March 15). Robotics and Automation Stories, Videos, Articles, Interviews, Reviews & News | RoboticsTomorrow. https://www.roboticstomorrow.com/news/2023/03/15/khronos-to-create-sycl-sc-open-standard-for-safety-critical-c-based-heterogeneous-compute/20240/ ↩︎

  10. Robinson, D. (2023, March 9). AMD gives Intel a wave as it glides past in CPU-GPU stakes. The Register: Enterprise Technology News and Analysis. https://www.theregister.com/2023/03/09/amd_cpu_gpu_hybrids/?utm_source=daily&utm_medium=newsletter&utm_content=article ↩︎

  11. Murphy, B. (2023, March 15). Scaling the RISC-V verification stack. Semiwiki. Retrieved March 15, 2023, from https://semiwiki.com/eda/325676-scaling-the-risc-v-verification-stack/ ↩︎

  12. Holson, B. (2023, February 13). So you want to do robots, Part 3: How to escape pilot purgatory. General Robots | Benjie Holson | Substack. https://generalrobots.substack.com/p/so-you-want-to-do-robots-part-3-how ↩︎

  13. Sriraman, H., & Ravikumar, A. (2023, January 31). Customized FPGA design and analysis of soft-core processor for DNN. sciencedirect. https://www.sciencedirect.com/science/article/pii/S1877050923000297?ref=pdf_download&fr=RR-2&rr=7a86434cda0a3150 ↩︎

  14. Prabakaran, B. S., Mrazek, V., Vasicek, Z., Sekanina, L., & Shafique, M. (2023, March 8). AutoXFPGAs: An end-to-end automated exploration framework for approximate accelerators in FPGA-based systems. arXiv.org. https://arxiv.org/abs/2303.04734 ↩︎