{"ID":2840558,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.13274","arxiv_id":"2511.13274","title":"KForge: Program Synthesis for Diverse AI Hardware Accelerators","abstract":"GPU kernels are critical for ML performance but difficult to optimize across diverse accelerators. We present KForge, a platform-agnostic framework built on two collaborative LLM-based agents: a generation agent that produces and iteratively refines programs through compilation and correctness feedback, and a performance analysis agent that interprets profiling data to guide optimization. This agent-based architecture requires only a single-shot example to target new platforms. We make three key contributions: (1) introducing an iterative refinement system where the generation agent and performance analysis agent collaborate through functional and optimization passes, interpreting diverse profiling data (from programmatic APIs to GUI-based tools) to generate actionable recommendations that guide program synthesis for arbitrary accelerators; (2) demonstrating that the generation agent effectively leverages cross-platform knowledge transfer, where a reference implementation from one architecture substantially improves generation quality for different hardware targets; and (3) validating the platform-agnostic nature of our approach by demonstrating effective program synthesis across fundamentally different parallel computing platforms: NVIDIA CUDA and Apple Metal.","short_abstract":"GPU kernels are critical for ML performance but difficult to optimize across diverse accelerators. We present KForge, a platform-agnostic framework built on two collaborative LLM-based agents: a generation agent that produces and iteratively refines programs through compilation and correctness feedback, and a performan...","url_abs":"https://arxiv.org/abs/2511.13274","url_pdf":"https://arxiv.org/pdf/2511.13274v1","authors":"[\"Taras Sereda\",\"Tom St. John\",\"Burak Bartan\",\"Natalie Serrino\",\"Sachin Katti\",\"Zain Asgar\"]","published":"2025-11-17T11:46:43Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\",\"cs.MA\",\"cs.PF\",\"cs.SE\"]","methods":"[\"Large Language Model\"]","has_code":false}