Generating Energy-Efficient Code via Large-Language Models -- Where are we now?
By: Radu Apsan , Vincenzo Stoico , Michel Albonico and more
Potential Business Impact:
Human coders write greener computer programs.
Context. The rise of Large Language Models (LLMs) has led to their widespread adoption in development pipelines. Goal. We empirically assess the energy efficiency of Python code generated by LLMs against human-written code and code developed by a Green software expert. Method. We test 363 solutions to 9 coding problems from the EvoEval benchmark using 6 widespread LLMs with 4 prompting techniques, and comparing them to human-developed solutions. Energy consumption is measured on three different hardware platforms: a server, a PC, and a Raspberry Pi for a total of ~881h (36.7 days). Results. Human solutions are 16% more energy-efficient on the server and 3% on the Raspberry Pi, while LLMs outperform human developers by 25% on the PC. Prompting does not consistently lead to energy savings, where the most energy-efficient prompts vary by hardware platform. The code developed by a Green software expert is consistently more energy-efficient by at least 17% to 30% against all LLMs on all hardware platforms. Conclusions. Even though LLMs exhibit relatively good code generation capabilities, no LLM-generated code was more energy-efficient than that of an experienced Green software developer, suggesting that as of today there is still a great need of human expertise for developing energy-efficient Python code.
Similar Papers
Energy-Aware Code Generation with LLMs: Benchmarking Small vs. Large Language Models for Sustainable AI Programming
Software Engineering
Smaller AI writes code using less power.
Toward Green Code: Prompting Small Language Models for Energy-Efficient Code Generation
Software Engineering
Makes small AI code generators use less power.
Comparative Analysis of Carbon Footprint in Manual vs. LLM-Assisted Code Development
Software Engineering
AI coding tools use more energy than humans.