# CLBlast: A Tuned OpenCL BLAS Library

arXiv: https://arxiv.org/abs/1705.05249 · HTML: https://mlsanity.com/paper/1705.05249/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 May 2017.

## Built on by (most cited first, 9 of 9)

- [Dissecting the Impact of Mobile DVFS Governors on LLM Inference Performance and Energy Efficiency](https://mlsanity.com/paper/2507.02135/) (2025)
- [Llamas on the Web: Memory-Efficient, Performance-Portable, and Multi-Precision LLM Inference with WebGPU](https://mlsanity.com/paper/2605.20706/) (2026)
- [Using hardware performance counters to speed up autotuning convergence on GPUs](https://mlsanity.com/paper/2102.05297/) (2021)
- [Searching CUDA code autotuning spaces with hardware performance counters: data from benchmarks running on various GPU architectures](https://mlsanity.com/paper/2102.05299/) (2021)
- [Tuning the Tuner: Introducing Hyperparameter Optimization for Auto-Tuning](https://mlsanity.com/paper/2509.26300/) (2025)
- [DPUV3INT8: A Compiler View to programmable FPGA Inference Engines](https://mlsanity.com/paper/2110.04327/) (2021)
- [SmartSplit: Latency-Energy-Memory Optimisation for CNN Splitting on Smartphone Environment](https://mlsanity.com/paper/2111.01077/) (2021)
- [Mobiprox: Supporting Dynamic Approximate Computing on Mobiles](https://mlsanity.com/paper/2303.11291/) (2023)
- [GPU Goldmines: Tunable WebGPU Kernels for Edge LLM Inference](https://mlsanity.com/paper/2610.17321/) (2026)

## Abstract (arXiv)

This work introduces CLBlast, an open-source BLAS library providing optimized OpenCL routines to accelerate dense linear algebra for a wide variety of devices. It is targeted at machine learning and HPC applications and thus provides a fast matrix-multiplication routine (GEMM) to accelerate the core of many applications (e.g. deep learning, iterative solvers, astrophysics, computational fluid dynamics, quantum chemistry). CLBlast has five main advantages over other OpenCL BLAS libraries: 1) it is optimized for and tested on a large variety of OpenCL devices including less commonly used devices such as embedded and low-power GPUs, 2) it can be explicitly tuned for specific problem-sizes on specific hardware platforms, 3) it can perform operations in half-precision floating-point FP16 saving bandwidth, time and energy, 4) it has an optional CUDA back-end, 5) and it can combine multiple operations in a single batched routine, accelerating smaller problems significantly. This paper describes the library and demonstrates the advantages of CLBlast experimentally for different use-cases on a wide variety of OpenCL hardware.