这篇论文测试了GPT-5.5、Claude Opus 4.7和Qwen3-Coder-Next用智能体写并行Julia代码，在超算上跑192核，发现小规模还行，大规模容易死锁或OOM，开源模型最差。做HPC或Julia并行开发的人值得看。
一项新研究使用基于OpenCode的智能体扩展Julia文档MCP服务器，评估了OpenAI GPT-5.5、Anthropic Claude Opus 4.7和开源Qwen3-Coder-Next在三个并行问题（π近似、分块矩阵乘、分块Cholesky分解）上生成Dagger.jl代码的能力。实验在共享内存192核和分布式两节点上进行，与Base.Threads和MPI.jl基线对比。结果显示智能体能生成小规模可执行代码，但在大规模下因死锁、过订阅或内存溢出失败，其中开源模型受影响最严重。商业模型在Base.Threads和MPI.jl上可扩展性相当，但Dagger.jl实现存在任务依赖、粒度和调度方面的反复弱点。
Generated, Parallel, Scalable? A Study of Agentic AI-Generated Julia Code on Supercomputers
Julia is increasingly used in hpc as a single-language alternative to combining high-level scripting with low-level systems languages, but achieving scalable performance still requires expertise in parallel programming. llms are increasingly used for code generation and are advancing rapidly with each new version. Yet, existing studies focus on single-shot prompting rather than agentic settings, in which an llm autonomously plans, generates, and refines code through tool use. Using an OpenCode-based agent extended with a Julia-documentation mcp server, we study agentic generation of parallel Julia code, focusing on task-based execution with Dagger.jl. We evaluate three llms, OpenAI GPT-5.5, Anthropic Claude Opus 4.7, and the open-weight Qwen3-Coder-Next, on three problems with distinct parallel structures: π approximation, tiled general matrix multiplication, and tiled Cholesky decomposition. The generated Dagger.jl implementations are compared against agent-generated Base.Threads and MPI.jl baselines, with shared-memory experiments scaling to 192 cores and distributed-memory experiments on two nodes. The agents reliably produce executable code for small inputs but fail at larger scales due to deadlocks, oversubscription, or out-of-memory errors, with the open-weight model affected most severely. The two commercial models scale comparably on Base.Threads and MPI.jl, while their Dagger.jl implementations expose recurring weaknesses in task dependencies, granularity, and scheduling. Agentic AI is promising for producing parallel Julia code, but generating robust, performance-aware implementations for large-scale hpc systems remains an open challenge.