1. [Home ](/) [CUDA](/cuda) CompileIQ # NVIDIA CompileIQ NVIDIA CompileIQ™ is an AI-powered compiler auto-tuning framework that uses evolutionary and genetic algorithms to optimize NVIDIA GPU compilers for individual workloads. Instead of accepting one generic compiler configuration for all workloads, CompileIQ flips the script: It generates optimal configurations for NVIDIA compiler options based on the specific workload in question. [Try CompileIQ](https://github.com/NVIDIA/CompileIQ "Try CompileIQ")[Documentation](https://nvidia.github.io/CompileIQ/stable/index.html "Documentation")[Forum](https://github.com/NVIDIA/CompileIQ/issues "Forum") * * * ## How CompileIQ Works Tune your compiler to the kernel, not the other way around. NVIDIA GPU compilers use default heuristics designed to produce strong results across a wide range of applications. That broad default is valuable, but the best configuration for one workload is not always the best configuration for another. CompileIQ turns Compiler Search Spaces into candidate configurations, evaluates these candidates against a developer-defined objective function, and uses evolutionary search to find the optimal candidate for specific kernels that matter to you. Also, there are some known configurations that work well for specific workloads. We call these premade configurations “Booster Packs,” and they’re available to use in your application without any tuning. CompileIQ works best for: - Teams that already have highly optimized source code for their kernels - Applications that follow the 80/20 rule: 80% of the compute budget is spent on 20% of the code - New kernel developers developing variations of kernels for which a Booster Pack is provided ![CompileIQ diagram](https://developer.download.nvidia.com/images/cuda/hpc-compile-iq-digram.svg) ### GitHub Repository Browse source code, search space definitions, and discover usage examples. Includes compiler tuning scripts and reference implementations for NVIDIA® CUDA® C++, NVIDIA Triton, and Helion kernels. [Learn More](https://github.com/NVIDIA/CompileIQ/) ### CUDA Programming Guide Learn how to use the --apply-controls flag introduced in CUDA Toolkit 13.3+ to apply Advanced Control Files directly to NVCC and PTXAS for kernel compilation. [Learn More](https://docs.nvidia.com/cuda/cuda-compiler-driver-nvcc/index.html#apply-controls-apply-controls) ### Search Space Downloads Download predefined compiler search spaces for PTXAS and NVCC. These define the tuning parameters CompileIQ will explore when searching for an optimal configuration for your kernel. [Learn More](https://github.com/NVIDIA/CompileIQ/releases?q=search-spaces&expanded=true) ### Booster Pack Downloads Pre-built Advanced Control Files are optimized for common workloads. Use these without running a search. Drop them into your build pipeline and benchmark immediately. [Learn More](https://github.com/NVIDIA/CompileIQ/releases?q=booster-packs&expanded=true) * * * ## Get Started With CompileIQ CompileIQ supports CUDA C++, OpenAI Triton, and PyTorch Helion—pick your environment to get started. ![decorative icon](https://developer.download.nvidia.com/icons/m48-accelerate-computing-with-cuda-c-c++.svg) ### CUDA C++ Apply an ACF to your kernel at compile time using the --apply-controls flag with NVCC 13.3+. Ideal for teams benchmarking with nvcc-compiled kernels. [NVCC Documentation](https://docs.nvidia.com/cuda/cuda-compiler-driver-nvcc/index.html#apply-controls-apply-controls) ![decorative icon](https://developer.download.nvidia.com/icons/m48-quantum-calibration-256px-blk.png) ### OpenAI Triton Pass an ACF via the PTX\_OPTIONS environment variable for global scope, or set ptx\_options directly in your kernel call for per-kernel control. [Triton Integration Guide](https://nvidia.github.io/CompileIQ/stable/triton_example.html) ![decorative icon](https://developer.download.nvidia.com/icons/m48-neural-network-3.svg) ### PyTorch Helion Specify an ACF directly via helion.Config, or use autotune\_search\_acf to let the autotuner select the best configuration from a list of candidates. [Helion Documentation](https://helionlang.com/examples/acfs/softmax_acf.html) * * * ## CompileIQ Learning Library Guide ACF Booster Pack Downloads Pre-built Advanced Control Files are optimized for specific workloads. Use these without running a search—drop them into your build pipeline and benchmark immediately. Documentation Ray and Multi-GPU Worker Docs Learn how to scale CompileIQ searches across multiple GPUs using RayWorker for distributed tuning or MultiProcessWorker for local parallel execution. Tutorial Experiment Tracking Docs Track and compare tuning runs, log objective function scores, and manage ACF artifacts across search sessions to ensure reproducible and auditable results. * * * ## More Resources ![Decorative image representing Community](https://developer.download.nvidia.com/icons/m48-people-group.svg) ### Explore Developer Forums ![Decorative image](https://developer.download.nvidia.com/icons/m48-certification-ribbon-2.svg) ### Get Training and Certification ![Decorative image representing Developer Newsletter](https://developer.download.nvidia.com/icons/m48-email-settings.svg) ### Sign Up for the Developer Newsletter * * * ## Ethical AI NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their supporting model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse. For more detailed information on ethical considerations for this model, please see the Model Card++ Explainability, Bias, Safety & Security, and Privacy Subcards. Please report security vulnerabilities or NVIDIA AI Concerns [here](https://www.nvidia.com/en-us/support/submit-security-vulnerability/). Get started with CompileIQ today. [Try CompileIQ](https://github.com/NVIDIA/CompileIQ)