#200578296-2
Architecture, Power, Performance, Silicon Validation, Thermals and Technology. The job involves analyzing and influencing key factors effecting Performance and Power of the GPU and improving on methodologies to align the model to Silicon.
Description
Join the team to play a pivotal role in Performance and Power projections of the GPU. As Apple expands on its GPU feature set, we rely on making accurate Efficiency curves for Performance per watt. You will have the opportunity to influence GPU Architecture choices and the feature set for the product. You will work with many teams including Architecture, Power, Performance, Silicon Validation, Thermals and Technology. In the highly collaborative GPU team, your main responsibilities are: - Responsible to generate and analyze GPU Efficiency Projections, Performance per watt, for each generation of GPU over the full cycle of the project, from concept to Silicon. - Drive the methodology of generating projections to improve accuracy and quality. - Responsible for System and Chip level Power team requests to the GPU for projections. - Work with Technology, Power and Static timing teams to determine the Frequency-Voltage curves for the workloads. - Work with Performance and Power teams to gather data for the Efficiency curves and analyze the impact. - Work with the Silicon Validation team to improve projections based on Silicon data. - Collaborate with GPU architecture team to set power targets and determine the impact of the features on efficiency.
Minimum Qualifications
BS + 10 years relevant experience
Experience in areas of Power and Silicon technology
Experience with Python, Perl, or other scripting/coding skills
Experience in data analysis, data mining and triage
Preferred Qualifications
Knowledge of low power design and implementation techniques
Strong communication skills and ability to work with cross-functional groups
Experience in ASIC power analysis in PowerArtist, PTPX and power projections
Experience in post-silicon power correlation
Experience in power management techniques
Familiarity with Performance modeling
Experience with GPU workloads is a plus
Additional Requirements
More