As part of our Performance Engineering group, you'll help analyze performance on ARM servers and create tools to enable modeling and characterization of complex workloads. You'll work across disciplines to implement, analyze and optimize existing tools where available or create them from scratch otherwise. The performance engineering group works across HW, FW, OS, tools and applications to identify trends, mine data, and help Marvell improve quality and performance of solutions based on ARM servers. This position requires basic understanding of computer architecture and modern processors, as well as performance analysis and/or modeling discipline. You will collaborate with software and hardware architects to explore SoC performance and power trade-offs. Your key responsibilities will be developing and building new tools and methodologies for analyzing and improving SoC designs for consumer-oriented devices in a pre-silicon environment. You will use simulation, emulation, and hardware profiling to build compelling analysis of new SoC designs. Required: - - Master's degree in Electrical Engineering, Computer Science or equivalent practical experience.
Experience reading and writing code in C/C++.
Experience in performance analysis, tools, and/or simulators at different abstraction levels (Cycle Accurate, TLM, and/or Functional).
Strong software engineering, architecture, and design skills experience
Self-starter with entrepreneurial experience and ability to interact with other disciplines Preferred
Solid understanding of modern processors
Experience analyzing workloads on modern servers (HPC or cloud applications) - Domain knowledge in one or more of these areas: CPU, Databases, HPC, Benchmarking, Machine learning
Passion for performance analysis and optimization #LI-TM1 #GLDR
All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, national origin, sexual orientation, gender identity, disability or protected veteran status.