All Projects → Oblomov → Clinfo

Oblomov / Clinfo

Licence: other
Print all known information about all available OpenCL platforms and devices in the system

Programming Languages

c
50402 projects - #5 most used programming language

Projects that are alternatives of or similar to Clinfo

Neanderthal
Fast Clojure Matrix Library
Stars: ✭ 927 (+398.39%)
Mutual labels:  gpgpu, opencl
Compute
A C++ GPU Computing Library for OpenCL
Stars: ✭ 1,192 (+540.86%)
Mutual labels:  gpgpu, opencl
Openclpapers
A Collection of Articles and other OpenCL Papers
Stars: ✭ 37 (-80.11%)
Mutual labels:  gpgpu, opencl
Compute Runtime
Intel® Graphics Compute Runtime for oneAPI Level Zero and OpenCL™ Driver
Stars: ✭ 593 (+218.82%)
Mutual labels:  gpgpu, opencl
Hashcat
World's fastest and most advanced password recovery utility
Stars: ✭ 11,014 (+5821.51%)
Mutual labels:  gpgpu, opencl
Vexcl
VexCL is a C++ vector expression template library for OpenCL/CUDA/OpenMP
Stars: ✭ 626 (+236.56%)
Mutual labels:  gpgpu, opencl
Parenchyma
An extensible HPC framework for CUDA, OpenCL and native CPU.
Stars: ✭ 71 (-61.83%)
Mutual labels:  gpgpu, opencl
Bitcracker
BitCracker is the first open source password cracking tool for memory units encrypted with BitLocker
Stars: ✭ 463 (+148.92%)
Mutual labels:  gpgpu, opencl
Amplifier.net
Amplifier allows .NET developers to easily run complex applications with intensive mathematical computation on Intel CPU/GPU, NVIDIA, AMD without writing any additional C kernel code. Write your function in .NET and Amplifier will take care of running it on your favorite hardware.
Stars: ✭ 92 (-50.54%)
Mutual labels:  gpgpu, opencl
Knlmeanscl
An optimized OpenCL implementation of the Non-local means de-noising algorithm
Stars: ✭ 92 (-50.54%)
Mutual labels:  gpgpu, opencl
Arrayfire Rust
Rust wrapper for ArrayFire
Stars: ✭ 525 (+182.26%)
Mutual labels:  gpgpu, opencl
Spoc
Stream Processing with OCaml
Stars: ✭ 115 (-38.17%)
Mutual labels:  gpgpu, opencl
John
John the Ripper jumbo - advanced offline password cracker, which supports hundreds of hash and cipher types, and runs on many operating systems, CPUs, GPUs, and even some FPGAs
Stars: ✭ 5,656 (+2940.86%)
Mutual labels:  gpgpu, opencl
Arraymancer
A fast, ergonomic and portable tensor library in Nim with a deep learning focus for CPU, GPU and embedded devices via OpenMP, Cuda and OpenCL backends
Stars: ✭ 793 (+326.34%)
Mutual labels:  gpgpu, opencl
Tornadovm
TornadoVM: A practical and efficient heterogeneous programming framework for managed languages
Stars: ✭ 479 (+157.53%)
Mutual labels:  gpgpu, opencl
Sycl Dnn
SYCL-DNN is a library implementing neural network algorithms written using SYCL
Stars: ✭ 67 (-63.98%)
Mutual labels:  gpgpu, opencl
Amgcl
C++ library for solving large sparse linear systems with algebraic multigrid method
Stars: ✭ 390 (+109.68%)
Mutual labels:  gpgpu, opencl
Chlorine
Dead Simple OpenCL
Stars: ✭ 419 (+125.27%)
Mutual labels:  gpgpu, opencl
Cekirdekler
Multi-device OpenCL kernel load balancer and pipeliner API for C#. Uses shared-distributed memory model to keep GPUs updated fast while using same kernel on all devices(for simplicity).
Stars: ✭ 76 (-59.14%)
Mutual labels:  gpgpu, opencl
Futhark
💥💻💥 A data-parallel functional programming language
Stars: ✭ 1,641 (+782.26%)
Mutual labels:  gpgpu, opencl

What is this?

clinfo is a simple command-line application that enumerates all possible (known) properties of the OpenCL platform and devices available on the system.

Inspired by AMD's program of the same name, it is coded in pure C and it tries to output all possible information, including those provided by platform-specific extensions, trying not to crash on unsupported properties (e.g. 1.2 properties on 1.1 platforms).

Usage

clinfo [options...]

Common used options are -l to show a synthetic summary of the available devices (without properties), and -a, to try and show properties even if clinfo would otherwise think they aren't supported by the platform or device.

Refer to the man page for further information.

Use cases

  • verify that your OpenCL environment is set up correctly; if clinfo cannot find any platform or devices (or fails to load the OpenCL dispatcher library), chances are high no other OpenCL application will run;
  • verify that your OpenCL development environment is set up correctly: if clinfo fails to build, chances are high no other OpenCL application will build;
  • explore/report the actual properties of the available device(s).

Segmentation faults

Some faulty OpenCL platforms may cause clinfo to crash. There isn't much clinfo itself can do about it, but you can try and isolate the platform responsible for this. On POSIX systems, you can generally find the platform responsible for the fault with the following one-liner:

find /etc/OpenCL/vendors/ -name '*.icd' | while read OPENCL_VENDOR_PATH ; do clinfo -l > /dev/null ; echo "$? ${OPENCL_VENDOR_PATH}" ; done

Missing information

If you know of device properties that are exposed in OpenCL (either as core properties or as extensions), but are not shown by clinfo, please open an issue providing as much information as you can. Patches and pull requests accepted too.

Building

Build status on Travis

Building requires an OpenCL SDK (or at least OpenCL headers and development files), and the standard build environment for the platform. No special build system is used (autotools, CMake, meson, ninja, etc), as I feel adding more dependencies for such a simple program would be excessive. Simply running make at the project root should work.

Android support

Local build via Termux

One way to build the application on Android, pioneered by truboxl and described here, requires the installation of Termux, that can be installed via Google Play as well as via F-Droid.

Inside Termux, you will first need to install some common tools:

pkg install git make clang -y

You will also need to clone the clinfo repository, and fetch the OpenCL headers (we'll use the official KhronosGroup/OpenCL-Headers repository for that):

git clone https://github.com/Oblomov/clinfo
git clone https://github.com/KhronosGroup/OpenCL-Headers

(I prefer doing this from a src directory I have created for development, but as long as clinfo and OpenCL-Headers are sibling directories, the headers will be found. If not, you will have to override CPPFLAGS with e.g. export CPPFLAGS=-I/path/to/where/headers/are before running make. Of course /path/to/where/headers/are should be replaced with the actual path to which the OpenCL-Headers repository was cloned.)

You can then cd clinfo and build the application. You can try simply running make since Android should be autodetected now, buf it this fails you can also force the detectio with

make OS=Android

If linking fails due to a missing libOpenCL.so, then your Android machine probably doesn't support OpenCL. Otherwise, you should have a working clinfo you can run. You will most probably need to set LD_LIBRARY_PATH to let the program know where the OpenCL library is at runtime: you will need at least ${ANDROID_ROOT}/vendor/lib64, but on some machine the OpenCL library actually maps to a different library (e.g., on one of my systems, it maps to the GLES library, which is in a different subdirectory).

Due to this requirement, on Android the actual binary is now called clinfo.real, and the produced clinfo is just a shell script that will run the actual binary after setting LD_LIBRARY_PATH. If this is not sufficient on your installation, please open an issue and we'll try to improve the shell script to cover your use case as well.

Windows support

The application can usually be built in Windows too (support for which required way more time than I should have spent, really, but I digress), by running make in a Developer Command Prompt for Visual Studio, provided an OpenCL SDK (such as the Intel or AMD one) is installed.

Precompiled Windows executable are available as artefacts of the AppVeyor CI.

Build status Windows binaries
Build status on AppVeyor 32-bit 64-bit
Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].