CPU Research Scientist – Platform Architecture

Summary

Posted: Oct 18, 2024

Role Number:200574211

The CPU Platform Architecture team is responsible for pushing the boundaries of both single-threaded and multi-threaded CPU performance, to enhance the user experience of many Apple products. The team is composed of experts with deep experience in microarchitecture, ISA definition, performance modeling, power modeling, and workload analysis. We are seeking a highly motivated, innovative, and confident individual to join the CPU Platform Architecture team to help drive advanced exploration for next-generation iPhone, iPad, and Mac CPU designs.

Description

In this research-centric role, you will be responsible for exploring and defining next-generation CPU architectures that seek to maintain performance and efficiency leadership. This role will challenge you to: – Discover insight into CPU performance bottlenecks and drive improvements to performance through architectural and microarchitectural enhancements – Set direction for next-generation high performance CPU’s in such areas as: branch prediction, instruction/data prefetching, memory subsystem, or other CPU areas – Build the right tools suited for performance analysis so that you can parse through the noise and focus on the real challenges – Apply AI/ML techniques as both a tool for exploration and for CPU algorithmic feature improvement – Conduct continuous research into one or more CPU areas, brainstorm ideas, and model ideas in a performance simulator to refine and prove their utility – Present analysis/findings to guide CPU architecture and design teams on features that should be implemented in future CPU’s – Work cross-functionally with software and system partners – Provide recommendations and influence the roadmap for future Apple CPU’s used in iPhone, iPad, and Mac systems

Minimum Qualifications

• B.S. degree
• Familiarity with CPU architecture or microarchitecture concepts
• Research experience and knowledge of CPU microarchitecture or AI/ML literature
• Programming experience in either Python or C/C++

Preferred Qualifications

• Expertise in one or more disciplines within CPU architecture: branch prediction, instruction or data prefetching, value prediction, caching policies, etc.
• Ability to identify performance bottlenecks in workloads in effort to craft ideas to solve them and ability to implement those ideas in a performance simulator
• Experience applying traditional or state-of-the-art machine learning techniques to novel problems. Knowledge of model development and tuning a plus
• Knowledge and experience with common industry performance benchmarks and workloads
• 10+ years of relevant experience
• PhD in Computer Science or Computer Engineering with a focus in Computer Architecture