- Global Robot Software Market Report 2021
- Nvidia's 'medical grade' chip strategy
- AMD's Future CPUs Could Feature a 3D-Stacked ML Accelerator
- How Apple’s Monster M1 Ultra Chip Keeps Moore’s Law Alive
- NVIDIA Orin Leaps Ahead in Edge AI, Boosting Leadership in MLPerf Tests
- Nvidia Dominates MLPerf Inference, Qualcomm also Shines, Where’s Everybody Else?
- Nvidia Claims Arm Grace CPU Superchip 2X Faster, 2.3X More Efficient Than Intel Ice Lake
- Nvidia’s Next GPU Shows That Transformers Are Transforming AI
- ROS 2 Simplifies Hardware Acceleration for Robots
Global Robot Software Market Report 2021
Source: Orbis research, February 15, 2022 
In the past few years, the Robot Software market experienced a growth, the global market size of Robot Software reached 1142.0 million $ in 2020, of what is about 366.0 million $ in 2015. The global Robot Software market size will reach 7527.0 million $ in 2025.
Nvidia's 'medical grade' chip strategy
Source: Protocol, April 8, 2022 
Nvidia has become the most valuable chip company in the U.S. The company recently pursued the $10 trillion health care market and aims to deliver a 'medical grade' chip strategy.
AMD's Future CPUs Could Feature a 3D-Stacked ML Accelerator
Source: Tom's Hardware, April 8, 2022 
AMD has patented a processor featuring a machine learning accelerator that is stacked on top of its I/O die. System-on-chips (SoCs) with integrated FPGA or GPU-based machine learning accelerators. Technology could be added to future CPU SoCs for datacenter use.
How Apple’s Monster M1 Ultra Chip Keeps Moore’s Law Alive
Source: Wired, April 11, 2022 
By combining two processors into one, the company has squeezed a surprising amount of performance out of silicon.
NVIDIA Orin Leaps Ahead in Edge AI, Boosting Leadership in MLPerf Tests
Source: NVIDIA Blog, April 6, 2022 
Pre-production version of NVIDIA Orin led in five of six performance tests. Orin is a low-power system-on-chip based on the NVIDIA Ampere architecture. It ran up to 5x faster than previous generation Jetson AGX Xavier.
Nvidia Dominates MLPerf Inference, Qualcomm also Shines, Where’s Everybody Else?
Source: HPCwire, April 6, 2022 
The MLPerf Inference benchmarks primarily focus on datacenter and edge systems and submitters include Alibaba, ASUSTeK, Azure, Deci.ai, Dell, Fujitsu, FuriosaAI, Gigabyte, H3C, Inspur, Intel, Krai, Lenovo, Nettrix, Neuchips, NVIDIA, Qualcomm Technologies, Inc., Supermicro, and ZhejiangLab.
Nvidia Claims Arm Grace CPU Superchip 2X Faster, 2.3X More Efficient Than Intel Ice Lake
Source: Tom's Hardware, April 10, 2022 
Nvidia unveiled its new 144-core Grace CPU Superchip, its first CPU-only Arm chip designed for the data center, back at GTC. Nvidia shared a benchmark against AMD's EPYC to claim a 1.5X lead
Nvidia’s Next GPU Shows That Transformers Are Transforming AI
Source: IEEE Spectrum, April 11, 2022 
Transformers are the neural network behind OpenAI's GPT-3 and other big natural-language processors. Transformers pay "attention" to multiple sentences, enabling them to grasp context. Nvidia's new Hopper H100 is proof that the leading maker of chips for accelerating AI is a believer.
ROS 2 Simplifies Hardware Acceleration for Robots
Source: IEEE Spectrum, September 27, 2021 
The process of creating optimized, hardware specific, compute architectures can be time consuming and complex. The ROS 2 Hardware Acceleration Working Group (HAWG) is working to simplify hardware acceleration engineering tasks by creating acceleration kernels based on open standards.
Hardware Acceleration in Robotics Newsletters
- Hardware Acceleration in Robotics #4 - Single-Chip Processors, a technical review of NVIDIA Jetson Orin and the new ROS 2 iRobot Create 3 and more
- Hardware Acceleration in Robotics #3 - Hardware-accelerated ROS 2 Pipelines, The Robotic Processing Unit (RPU) and more
- Hardware Acceleration in Robotics #2 - Nvidia Isaac ROS GEMs, Nvidia H100, updates to CUDA-X Libraries and more
- Hardware Acceleration in Robotics #1 - ROS2 for Self-Driving Cars, Intel world fastest FPGAs, Nvidia GTC and more
ROS 2 Hardware Acceleration Working Group meetings
- Hardware Acceleration WG, meeting #7
- Hardware Acceleration WG, meeting #6
- Hardware Acceleration WG, meeting #5
- Hardware Acceleration WG, meeting #4
- Hardware Acceleration WG, meeting #3
- Hardware Acceleration WG, meeting #2
- Hardware Acceleration WG, meeting #1
Orbis. (2021, February 15). 'Global robot software market report 2021 | Orbis research. OrbisResearch.com: Market Research Reports and Industry Analysis. https://www.orbisresearch.com/reports/index/global-robot-software-market-report-2021 ↩︎
The AI chip will see you now. (2022, April 8). Protocol. https://www.protocol.com/newsletters/protocol-enterprise/nvidia-kimberly-powell-aws-ai?rebelltitem=1#rebelltitem1 ↩︎
Shilov, A. (2022, April 8). AMD's future CPUs could feature a 3D-Stacked ML accelerator. Tom's Hardware. https://www.tomshardware.com/news/amd-future-cpus-could-feature-direct-attached-accelerators ↩︎
Nast, C. (2022, April 11). How Apple’s monster M1 ultra chip keeps Moore’s law alive. Wired. https://www.wired.com/story/apple-m1-ultra-chip-moores-law/ ↩︎
Salvator, D. (2022, April 6). NVIDIA Orin leaps ahead in edge AI, boosting leadership in MLPerf tests. NVIDIA Blog. https://blogs.nvidia.com/blog/2022/04/06/mlperf-edge-ai-inference-orin/ ↩︎
Russell, J. (2022, April 6). Nvidia dominates MLPerf inference, Qualcomm also shines, where’s everybody else? HPCwire. https://www.hpcwire.com/2022/04/06/nvidia-dominates-mlperf-inference-qualcomm-also-shines-wheres-everybody-else/ ↩︎
Alcorn, P. (2022, April 10). Nvidia claims arm grace CPU Superchip 2X faster, 2.3X more efficient than Intel ice lake. Tom's Hardware. https://www.tomshardware.com/news/nvidia-claims-arm-grace-cpu-superchip-2x-faster-23x-more-efficient-than-intel-ice-lake ↩︎
Moore, S. K. (2022, April 11). Nvidia’s next GPU shows that transformers are transforming AI. IEEE Spectrum. https://spectrum.ieee.org/nvidias-next-gpu-shows-that-transformers-are-transforming-ai ↩︎
Mayoral-Vilches, V. (2021, September 28). Ros 2 simplifies hardware acceleration for Robots. Robotics Business Review. Retrieved April 15, 2022, from https://www.roboticsbusinessreview.com/opinion/ros-2-simplifies-hardware-acceleration-for-robots/ ↩︎