AccelOpt: A Self-Improving LLM Agentic System for AI Accelerator Kernel Optimization
About
We present AccelOpt, a self-improving large language model (LLM) agentic system that autonomously optimizes kernels for emerging AI acclerators, eliminating the need for expert-provided hardware-specific optimization knowledge. AccelOpt explores the kernel optimization space through iterative generation, informed by an optimization memory that curates experiences and insights from previously encountered slow-fast kernel pairs. We build NKIBench, a new benchmark suite of AWS Trainium accelerator kernels with varying complexity extracted from real-world LLM workloads to evaluate the effectiveness of AccelOpt. Our evaluation confirms that AccelOpt's capability improves over time, boosting the average percentage of peak throughput from $49\%$ to $61\%$ on Trainium 1 and from $45\%$ to $59\%$ on Trainium 2 for NKIBench kernels. Moreover, AccelOpt is highly cost-effective: using open-source models, it matches the kernel improvements of Claude Sonnet 4 while being $26\times$ cheaper. The code is open-sourced at https://github.com/zhang677/AccelOpt.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Conv2d kernel generation | SM90 | Latency (ms)0.0658 | 4 | |
| GEMM kernel generation | SM90 | Latency (ms)0.319 | 4 | |
| Top-K kernel generation | SM90 | Latency (ms)0.1276 | 4 | |
| Conv2d kernel generation | SM120 | Latency (ms)0.0822 | 4 | |
| GEMM kernel generation | SM120 | Latency (ms)0.3933 | 4 | |
| FMHA kernel generation | SM90 | Latency (ms)5.1499 | 3 | |
| FMHA kernel generation | SM120 | FMHA Latency (ms)3.6366 | 3 | |
| Top-K kernel generation | SM120 | Latency (ms)0.0192 | 3 |