# MultiKernelBench: A Multi-Platform Benchmark for Kernel Generation

arXiv: https://arxiv.org/abs/2507.17773 · HTML: https://mlsanity.com/paper/2507.17773/

## Key facts

- Cited by 38 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 54 references that are in the map.
- First posted on arXiv 20 Jul 2025.

## Builds on (most cited first, 23 of 23)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (2021)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model](https://mlsanity.com/paper/2405.04434/) (2024)
- [WizardCoder: Empowering Code Large Language Models with Evol-Instruct](https://mlsanity.com/paper/2306.08568/) (2023)
- [RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation](https://mlsanity.com/paper/2303.12570/) (2023)
- [DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence](https://mlsanity.com/paper/2406.11931/) (2024)
- [FlashInfer: Efficient and Customizable Attention Engine for LLM Inference Serving](https://mlsanity.com/paper/2501.01005/) (2025)
- [Magicoder: Empowering Code Generation with OSS-Instruct](https://mlsanity.com/paper/2312.02120/) (2023)
- [Ansor: Generating High-Performance Tensor Programs for Deep Learning](https://mlsanity.com/paper/2006.06762/) (2020)
- [SPoC: Search-based Pseudocode to Code](https://mlsanity.com/paper/1906.04908/) (2019)
- [DocPrompting: Generating Code by Retrieving the Docs](https://mlsanity.com/paper/2207.05987/) (2022)
- [Execution-Based Evaluation for Open-Domain Code Generation](https://mlsanity.com/paper/2212.10481/) (2022)
- [Kevin: Multi-Turn RL for Generating CUDA Kernels](https://mlsanity.com/paper/2507.11948/) (2025)
- [DevEval: A Manually-Annotated Code Generation Benchmark Aligned with Real-World Code Repositories](https://mlsanity.com/paper/2405.19856/) (2024)
- [When Language Model Meets Private Library](https://mlsanity.com/paper/2210.17236/) (2022)
- [AutoTriton: Automatic Triton Programming with Reinforcement Learning in LLMs](https://mlsanity.com/paper/2507.05687/) (2025)
- [DOMAINEVAL: An Auto-Constructed Benchmark for Multi-Domain Code Generation](https://mlsanity.com/paper/2408.13204/) (2024)
- [API-guided Dataset Synthesis to Finetune Large Code Models](https://mlsanity.com/paper/2408.08343/) (2024)

## Built on by (most cited first, 30 of 38)

- [AccelOpt: A Self-Improving LLM Agentic System for AI Accelerator Kernel Optimization](https://mlsanity.com/paper/2511.15915/) (2025)
- [KernelFoundry: Hardware-aware evolutionary GPU kernel optimization](https://mlsanity.com/paper/2603.12440/) (2026)
- [Towards Automated Kernel Generation in the Era of LLMs](https://mlsanity.com/paper/2601.15727/) (2026)
- [KernelBenchX: A Comprehensive Benchmark for Evaluating LLM-Generated GPU Kernels](https://mlsanity.com/paper/2605.04956/) (2026)
- [KernelBench-Verified: Do LLM-Generated Kernels Actually Beat PyTorch?](https://mlsanity.com/paper/2607.16241/) (2026)
- [AKG kernel Agent: A Multi-Agent Framework for Cross-Platform Kernel Synthesis](https://mlsanity.com/paper/2512.23424/) (2025)
- [AscendCraft: Automatic Ascend NPU Kernel Generation via DSL-Guided Transcompilation](https://mlsanity.com/paper/2601.22760/) (2026)
- [Kernel-Smith: A Unified Recipe for Evolutionary Kernel Optimization](https://mlsanity.com/paper/2603.28342/) (2026)
- [KernelCraft: Benchmarking for Agentic Close-to-Metal Kernel Generation on Emerging Hardware](https://mlsanity.com/paper/2603.08721/) (2026)
- [Making LLMs Optimize Multi-Scenario CUDA Kernels Like Experts](https://mlsanity.com/paper/2603.07169/) (2026)
- [GPU Kernel Optimization Beyond Full Builds: An LLM Framework with Minimal Executable Programs](https://mlsanity.com/paper/2512.22147/) (2025)
- [DICE: Diffusion Large Language Models Excel at Generating CUDA Kernels](https://mlsanity.com/paper/2602.11715/) (2026)
- [Towards Cold-Start Drafting and Continual Refining: A Value-Driven Memory Approach with Application to NPU Kernel Synthesis](https://mlsanity.com/paper/2603.10846/) (2026)
- [AscendOptimizer: Episodic Agent for Ascend NPU Operator Optimization](https://mlsanity.com/paper/2603.23566/) (2026)
- [Kernel Contracts: A Specification Language for ML Kernel Correctness Across Heterogeneous Silicon](https://mlsanity.com/paper/2604.22032/) (2026)
- [FastKernels: Benchmarking GPU Kernel Generation in Production](https://mlsanity.com/paper/2605.23215/) (2026)
- [Are LLM-Generated GPU Kernels Production-Ready? A Trace-Driven Benchmark and Optimization Agent](https://mlsanity.com/paper/2607.14541/) (2026)
- [PerfAgent: Profiler-Guided Iterative Refinement for Repository-Level Code Optimization](https://mlsanity.com/paper/2607.19653/) (2026)
- [Evolution of Kernels: Automated RISC-V Kernel Optimization with Large Language Models](https://mlsanity.com/paper/2509.14265/) (2025)
- [Counting Without Running: Evaluating LLMs' Reasoning About Code Complexity](https://mlsanity.com/paper/2512.04355/) (2025)
- [AgentKernelArena: Generalization-Aware Benchmarking of GPU Kernel Optimization Agents](https://mlsanity.com/paper/2605.16819/) (2026)
- [JAXBench: Benchmarking Autonomous TPU Kernel Optimization](https://mlsanity.com/paper/2607.20466/) (2026)
- [RealisticTritonBench: A Benchmark for Triton-Kernel Generation in Real-World AI Frameworks](https://mlsanity.com/paper/2608.12004/) (2026)
- [MobileKernelBench: Can LLMs Write Efficient Kernels for Mobile Devices?](https://mlsanity.com/paper/2603.11935/) (2026)
- [Metal-Sci: A Scientific Compute Benchmark for Evolutionary LLM Kernel Search on Apple Silicon](https://mlsanity.com/paper/2605.09708/) (2026)
- [Hawk: Harnessing Hardware-Aware Knowledge for High-Performance NPU Kernel Generation](https://mlsanity.com/paper/2607.01590/) (2026)
- [MKEvolve: A Modular Multi-Agent Framework for Kernel Code Generation](https://mlsanity.com/paper/2607.20501/) (2026)
- [CANN Bench: Benchmarking Agent Generated Kernels against Real NPU and Algorithmic Limits](https://mlsanity.com/paper/2607.20518/) (2026)
- [Kernel Forge: An Agent Harness for LLM-based Generation and Optimization of CUDA Kernels](https://mlsanity.com/paper/2607.24762/) (2026)
- [Learning When to Optimize: Verified Optimization Skills from Expert GPU-Kernel Lineages](https://mlsanity.com/paper/2605.28213/) (2026)

## Abstract (arXiv)

The automatic generation of deep learning (DL) kernels using large language models (LLMs) has emerged as a promising approach to reduce the manual effort and hardware-specific expertise required for writing high-performance operator implementations. However, existing benchmarks for evaluating LLMs in this domain suffer from limited hardware support, coarse-grained kernel categorization, and imbalanced task coverage. To address these limitations, we introduce MultiKernelBench, the first comprehensive, multi-platform benchmark for LLM-based DL kernel generation. MultiKernelBench spans 285 tasks across 14 well-defined kernel categories and supports three major hardware platforms: Nvidia GPUs, Huawei NPUs, and Google TPUs. To enable future extensibility, we design a modular backend abstraction layer that decouples platform-specific logic from the core benchmarking infrastructure, allowing easy integration of new hardware platforms. We further propose a simple yet effective category-aware one-shot prompting method that improves generation quality by providing in-category exemplars. Through systematic evaluations of seven state-of-the-art LLMs, we reveal significant variation in task difficulty, poor generalization to platforms with less training exposure, and the effectiveness of targeted prompting strategies. MultiKernelBench is publicly available at https://github.com/wzzll123/MultiKernelBench.