Accelerating Software on the Edge
The rise of edge computing has increased the need for portable hardware acceleration for AI and image processing, especially where power consumption matters or cloud connectivity is unreliable.
Automotive is driving software innovation in vehicles, particularly for driver assist and self-driving features, motivating the use of neural networks like Llama and GPT. Traditional algorithms like BLAS and FFT also benefit, running much faster on GPU-like processors than on CPUs.
However, challenges like power consumption, cost, and safety-critical requirements remain. Developers need to develop on cloud or desktop infrastructure and migrate to final hardware, increasing the demand for software portability.
This session brings together experts from the semiconductor and software industries to explore new hardware challenges and opportunities for edge computing and the crucial role of open standards. The UXL Foundation and Autoware collaboration showcases this potential.
Speaker(s)
Alex Pim - VP of Compute Software, Imagination Technologies
Alex joined Imagination in 2002, shortly after gaining an honours degree in Artificial Intelligence & Computer Science from the University of Birmingham. Since then, he has contributed to almost all areas of software engineering within the business including Digital Video, Digital Communications and Graphics Processing Units. With a personal interest in AI, and extensive knowledge of the company’s IP he now helps shape the company’s future as a member of the Technology Office.
Manuj Sabharwal - Qualcomm
With 15 years of experience in engineering, specializing in performance and power optimization, and defining APIs for open-source AI frameworks, Manuj has significantly contributed to bringing AI to Windows PCs. Currently serving as the Director of AI Software Product at Qualcomm, Manuj is at the forefront of advancing AI software to enhance the Snapdragon XElite experience.
Leveraging oneAPI, including SyCL, Manuj has accelerated AI on edge devices, demonstrating a deep understanding of cutting-edge technologies. At Qualcomm, he collaborates with cross-disciplinary teams, manages feature roadmap planning, and engages with customers to deliver top-tier AI solutions. By partnering with customers across the edge ecosystem on Windows, Manuj has helped organizations integrate state-of-the-art AI technologies into their products.
Verena Beckham - VP of Safety Engineering at Codeplay
Chair of the Safety-Critical SIG in UXL. Chair of the SYCL SC Working Group in Khronos, developing a version of SYCL specifically for Safety-Critical systems.
Christopher Rumpf - Senior Director Automotive, Arm
With over 25 years experience across systems and software, Christopher is responsible for leading Arm’s automotive software and solutions portolios. Previously Christopher has worked for a range of fabless semiconductor design companies such as Broadcom, Qualcomm and Infineon, and holds multiple Computer Science degrees.
Zain Khawaja - Senior Tech Lead, Autoware
Zain Khawaja is Senior Tech Lead at Autoware. He is driving the development of PoV autonomy based on #Autoware software and is instrumental in preparing Autoware for the prime time, ready to be used by OEMs and Tier1s in their autonomous vehicle development journey by lowering the entry barrier into the autonomous vehicle domain. Zain has a wealth of autonomy experience accumulated from his prior experience at Oxa and his startup Propelmee, which still holds the record for the longest fully recorded autonomous drive in the UK.
