Generating Energy-efficient code with LLMs
This addresses the problem of reducing energy usage in code generation for developers and AI practitioners, but it is incremental as it explores prompt modifications without introducing new methods.
The study investigated how modifying prompts affects the energy consumption of code generated by large language models for Python problems, finding that specific combinations of prompt optimization, LLM, and problem reduced energy consumption, but no single prompt consistently lowered energy across all problems.
The increasing electricity demands of personal computers, communication networks, and data centers contribute to higher atmospheric greenhouse gas emissions, which in turn lead to global warming and climate change. Therefore the energy consumption of code must be minimized. Code can be generated by large language models. We look at the influence of prompt modification on the energy consumption of the code generated. We use three different Python code problems of varying difficulty levels. Prompt modification is done by adding the sentence ``Give me an energy-optimized solution for this problem'' or by using two Python coding best practices. The large language models used are CodeLlama-70b, CodeLlama-70b-Instruct, CodeLlama-70b-Python, DeepSeek-Coder-33b-base, and DeepSeek-Coder-33b-instruct. We find a decrease in energy consumption for a specific combination of prompt optimization, LLM, and Python code problem. However, no single optimization prompt consistently decreases energy consumption for the same LLM across the different Python code problems.