AI 中文总结
针对新兴加速器内核生成的现有方法反复重建无关语义的问题，提出编译器介导的Zomboss框架，将语义编译为可复用接口，在20个Gemmini和36个PLENA工作负载上实现全实例正确，且性能优于基线方法、推理成本更低。
AI 中文摘要
新兴加速器往往缺乏成熟的编译器后端，这促使研究人员开发神经智能体，使其能够基于架构文档和模拟器反馈生成并修复内核。这种方法会针对每个工作负载反复重建与工作负载无关的机器语义，包括指令行为、合法性约束、同步规则和内存协议等。我们认为，这些语义应被一次性编译为持久的符号化构件，而神经推理应聚焦于依赖工作负载的映射决策。我们提出了Zomboss，一种由编译器介导的智能体内核生成框架，该框架将神经搜索置于经过验证的编译器边界内。Zomboss将机器语义和合法性约束编译为可复用的映射接口，随后使用神经智能体在已验证的映射空间内优化依赖工作负载的决策。在20个Gemmini工作负载实例和36个PLENA工作负载实例上，Zomboss在全部56个实例中都返回了正确且经过验证的内核。相较于编译器默认方案，Zomboss在Gemmini上实现了3.34倍的几何平均加速比，在PLENA上实现了1.10倍的几何平均加速比；相较于直接的智能体生成方法，它在Gemmini上减少了71.2%的推理token，在PLENA上减少了54.2%的推理token。这些结果表明，由编译器定义的符号化接口将原生内核合成转化为经过验证的设计空间探索：编译器基础设施保障了合法性和正确性，而神经指导则以更低的搜索成本和完整的覆盖范围提升了特定工作负载的性能。
英文摘要
Emerging accelerators often lack mature compiler backends, motivating neural agents that generate and repair kernels from architectural documentation and simulator feedback. This approach repeatedly reconstructs workload-invariant machine semantics--including instruction behavior, legality constraints, synchronization rules, and memory protocols--for every workload. We argue that these semantics should be compiled once into a persistent symbolic artifact, while neural reasoning should focus on workload-dependent mapping decisions. We present Zomboss, a compiler-mediated agentic framework for kernel generation that places neural search within a verified compiler boundary. Zomboss compiles machine semantics and legality constraints into a reusable mapping interface, then uses a neural agent to optimize workload-dependent decisions within the validated mapping space. Across 20 Gemmini and 36 PLENA workload instances, Zomboss returns a correct verified kernel on all 56 instances. Relative to the compiler default, Zomboss achieves geometric-mean speedups of $3.34\times$ on Gemmini and $1.10\times$ on PLENA. Relative to direct agentic generation, it reduces inference tokens by 71.2% on Gemmini and 54.2% on PLENA. These results show that a compiler-defined symbolic interface turns native kernel synthesis into verified design-space exploration: compiler infrastructure preserves legality and correctness, while neural guidance improves workload-specific performance with lower search cost and complete coverage.
Comments12 pages, 7 figures
