Performance Analysis Engineer

Apple

  • London
  • Permanent
  • Full-time
  • 2 months ago
As part of our Silicon Technologies group, you'll help design and manufacture our next-generation, high-performance, power-efficient processor, system-on-chip (SoC). You'll ensure Apple products and services can seamlessly handle the tasks that make them beloved by millions. Joining this group means you'll be crafting and building the technology that fuels Apple's devices. Together, we enable our customers to do all the things they love with their devices . In this role, you will be responsible for performance analysis and tuning of the GPU as used in a variety of Apple products. As a member of the Performance Analysis team, you will collaborate closely with other GPU Design and Software Engineers to analyse and improve the performance of Apple's GPUs. GPU performance analysis includes all levels of its stack: architecture, micro-architecture, logic design, compiler, driver, and applications. The team innovates to rapidly develop new ways of analysing data and visualisation techniques to aid in the analysis of performance data. You will not only be responsible of providing results but also understanding the performance and proposing potential optimisations. This is a high visibility role with opportunity to influence performance across the GPU and have far reaching impact for a variety of Apple products.DescriptionAs a GPU Performance Analysis Engineer, your responsibilities will include: - Developing performance test plans to validate GPU performance - Analysing performance issues using micro benches and real life content (games, pro-apps etc.) to identify hardware and software problems - Interacting with architecture, software and hardware engineers to identify bottlenecks and propose novel solutions for improved GPU performance - Developing studies to understand and quantify the performance benefit of features and algorithms implemented in hardware and software - Developing tools to aid in the efficient measurement, communication and improvement of GPU performanceMinimum Qualifications
  • Architecture knowledge of at least one of the main SoC components (GPU, CPU, Interconnect & Memory hierarchy).
  • Strong hardware and software debug skills.
  • Strong data analysis skills: able to relate performance data to HW architecture and behaviour.
  • Knowledge Python and/or C++
  • Ability to work well in a multi-site team, capable of planning your own tasks, estimate deadlines and meet schedules.
  • Excellent communications skills, self-motivated and well organised
  • Knowledge on hardware design.
Preferred Qualifications
  • - Previous experience in performance analysis of complex systems and understanding trade-offs

Apple