kernel_tuner
GPU optimizer
Automates the process of optimizing performance and energy efficiency in GPU applications.
Kernel Tuner
294 stars
10 watching
50 forks
Language: Python
last commit: 2 months ago
Linked from 1 awesome list
auto-tuningautotuningccpluspluscudacuda-kernelsgpugpu-computingkernel-tunermachine-learningopenclopencl-kernelsoptimizationpythonsoftware-developmenttesting
green-software-foundation/awesome-green-softwareRelated projects:
| Repository | Description | Stars |
|---|---|---|
 syne-tune/syne-tune | A tool for large-scale and asynchronous hyperparameter optimization in machine learning | 393 |
 jmrichardson/tuneta | Automates optimization of technical indicators for machine learning models in finance | 421 |
 gpuopen-tools/radeon_gpu_profiler | A low-level profiling tool for analyzing GPU workloads and optimizing DirectX 12 and Vulkan games on AMD GPUs. | 397 |
 arm-software/libgpucounters | A utility library providing access to performance counters on Arm GPUs. | 215 |
 liyanghart/hyperparameter-optimization-of-machine-learning-algorithms | Provides tools and techniques for tuning hyperparameters in machine learning models to improve performance. | 1,283 |
 hyperopt/hyperopt-sklearn | Automates search for optimal parameters in machine learning algorithms. | 1,594 |
 jeremymain/gpuprofiler | A tool that captures system details and resource utilization metrics to help analyze performance and size virtual GPU environments. | 289 |
 autonomio/talos | A tool for automating hyperparameter experiments for machine learning models using TensorFlow and Keras | 1,626 |
 rib/gputop | A tool for analyzing GPU performance and metrics in real-time, providing graphical and machine-readable data for developers | 162 |
 nvidia/tensorflow | An optimized version of TensorFlow to support newer hardware and libraries for NVIDIA GPU users | 1,017 |
| gpuopen-tools/radeon_gpu_analyzer | An offline compiler and code analysis tool for various GPU architectures and programming languages. | 422 |
 alan-fgr/cullminator9000 | A high-performance software optimization tool for removing unnecessary geometric data in 3D rendering pipelines | 35 |
 nebuly-ai/nos | A module to optimize GPU utilization in Kubernetes clusters through dynamic partitioning and elastic resource management. | 636 |
 google/jaxopt | An open-source project providing hardware accelerated, batchable and differentiable optimizers in JAX for deep learning. | 941 |
 adacore/cuda | A toolset that compiles Ada and SPARK code to NVIDIA GPUs | 18 |