GPU Performance Modeling Internship Cambridge 2024

Lock Applications for this job are now closed
DEADLINE 25th January 2024
Cambridge

Do you have the desire to seek out and solve exceedingly difficult challenges rather than the easy ones? Do you believe that truly valuable and meaningful accomplishments are the result of pushing the limits of perseverance? Do you believe that a world-class team with relentless drive can surpass even their own high expectations? We do!

We are seeking highly motivated, innovative and confident individuals to join the GPU Performance Modeling Team; we work to advance exploration for the next generation of GPU architecture and micro-architecture. In this highly visible role, you will be at the centre of a chip design effort working with all disciplines, with a critical impact on getting high performant products to millions of Apple customers efficiently.

Key Qualifications

  • An interest in computer architecture and micro-architecture
  • Strong coding skills, especially in C++
  • Strong understanding of common data structures and algorithms
  • Knowledge of performance simulation environments is beneficial
  • Knowledge of software design patterns
  • Knowledge of scripting languages such as Perl, Python or Ruby
  • A motivated self starter and an ability to work with ambiguity
  • Excellent communication skills and ability to analyse data

Description

As an intern in the Performance Modeling Team, you will have impact in defining and optimising Apple's GPU micro-architecture. Through collaboration, you will seek out areas for GPU performance improvement while collecting data and measurements that either confirm new features or rule them out. You will work with experienced designers in micro-architecture and RTL to assess the feasibility of ideas, refine them and create new ones. The role requires the analysis of interesting workloads across existing and new product categories to identify bottlenecks and opportunities for improvement.

You will be architecting new simulator features and brainstorming novel ideas to boost simulation performance. We also cross-collaborate as a larger performance team to maintain and improve the simulation environment and look for ways to boost the productivity of the entire team.

In this role, you will be expected to:

  • Contribute towards performance modeling proposed architectural solutions and features
  • Gather, analyse and validate measured and simulated results to compare architectural design alternatives
  • Carefully analyse and present results to enable data specific architecture/design
  • Collaborate with multi-functional teams to develop architectural solutions

Education Experience

  • Currently enrolled in your penultimate year of studies in a CE, EE, CS or related field.
DEADLINE 25th January 2024