Project Difficulty
Accessible
Description
This project aims to replicate the characterisation study from “SPEC CPU2017: Performance, Event, and Energy Characterization on the Core i7-8700K” on an Arm64 platform (e.g., Ampere Altra, AWS Graviton) using different compilers and performance profiling tools. The study will analyze how compiler optimizations and architectural features affect execution time, energy efficiency, and instruction throughput on Arm-based server processors. Deliverables include a comprehensive performance analysis report, reproducible benchmarking scripts, and a dataset comparing performance across different configurations. The report should locate microarchitectural bottlenecks using the top-down methodology, compiler performance and recommendations on how to improve performance.
Estimated Project Duration
1 to 2 months
Recommended team size: 1–2 students
Hardware / Software Requirements
Hardware: Arm64-based server (Ampere Altra, AWS Graviton, Raspberry Pi for preliminary tests)
Software:
Compilers: GCC, LLVM/Clang, Arm Compiler for Linux
Profiling Tools: perf, Arm Performance Libraries
Workloads: SPEC CPU2017 (academic license required), custom workloads
Resources
Support
Support, including financial support when appropriate, to gain access to the relevant Arm systems and the relevant license for SpecINT2017.
Benefits / Prizes
-
Standout projects could be internally referred for relevant positions at Arm!
-
If your submission is approved, you will receive a recognised badge that you can list on your CV and shared on LinkedIn. A great way to stand out from the crowd!
-
It’s a great way to demonstrate your initiative and commitment to your field.
-
Develop skills relevant for careers in high-performance computing, cloud infrastructure, and embedded systems!
