Search Results for "arm-aonly"
Sort By:
Showing 20 open source projects for "arm-aonly"
View related business solutions-
Ship Agents FasterGemini Enterprise Agent Platform lets you rapidly build, scale, govern and optimize production-ready agents grounded in your organization's data. The platform enables developers to build custom or pre-built agents for virtually any use case. New customers get $300 in free credits.
-
Stop Storing Third-Party Tokens in Your DatabaseRolling your own OAuth token storage can be a security liability. Token Vault securely stores access and refresh tokens from federated providers and handles exchange and renewal automatically. Connected accounts, refresh exchange, and privileged worker flows included.
-
1
opencv-mobile
The minimal opencv for Android, iOS, ARM Linux, Windows, Linux, MacOS
The minimal opencv for Android, iOS, ARM Linux, Windows, Linux, MacOS, WebAssembly. This project provides the minimal build of opencv library for the Android, iOS and ARM Linux platforms. Packages for Windows, Linux, MacOS, and WebAssembly are available now. We provide prebuild binary packages for opencv 2.4.13.7, 3.4.18, and 4.6.0. We also provide prebuild binary package for iOS with bitcode enabled, that the official package lacks. -
2
MNN
MNN is a blazing fast, lightweight deep learning framework
MNN is a highly efficient and lightweight deep learning framework. It supports inference and training of deep learning models, and has industry leading performance for inference and training on-device. At present, MNN has been integrated in more than 20 apps of Alibaba Inc, such as Taobao, Tmall, Youku, Dingtalk, Xianyu and etc., covering more than 70 usage scenarios such as live broadcast, short video capture, search recommendation, product searching by image, interactive marketing, equity... -
3
Halide
A language for fast, portable data-parallel computation
...It was designed to make writing high-performance image and array processing code much easier on modern machines. It works on all major operating systems and with several CPU architectures (X86, ARM, MIPS, Hexagon, PowerPC) and GPU Compute APIs (CUDA, OpenCL, OpenGL, among others). It isn't a standalone programming language however; rather it is embedded in C++ which means that you write C++ code, building an in-memory representation of a Halide pipeline using Halide's C++ API. This representation can then be compiled to an object file, or a JIT-compile and run in the same process. ... -
4
CPU Features
A cross platform C99 library to get cpu features at runtime
...It enables applications to determine which instruction sets (such as SSE, AVX, or NEON) are supported on the host machine, allowing developers to optimize performance dynamically. The library supports numerous architectures—including x86, ARM, AArch64, MIPS, POWER, RISCV, LoongArch, and s390x—and works on major operating systems like Linux, macOS, Windows, FreeBSD, Android, and iOS. Implemented in portable C99, it is thread-safe, has no memory allocations, and raises no exceptions, making it suitable even for use in low-level system libraries. The design emphasizes portability, extensibility, and compatibility with sandboxed or restricted environments where direct CPU access may be limited. -
$300 Free Credits for Your Google Cloud ProjectsLaunch your next project with $300 in free Google Cloud credits—no strings attached. Test, build, and deploy without risk. Use your credits across the entire Google Cloud platform to find what works best for your needs. After your credits are used, continue with always-free tier services. Only pay when you're ready to scale. Sign up in minutes and start exploring.
-
5
XNNPACK
High-efficiency floating-point neural network inference operators
XNNPACK is a highly optimized, low-level neural network inference library developed by Google for accelerating deep learning workloads across a variety of hardware architectures, including ARM, x86, WebAssembly, and RISC-V. Rather than serving as a standalone ML framework, XNNPACK provides high-performance computational primitives—such as convolutions, pooling, activation functions, and arithmetic operations—that are integrated into higher-level frameworks like TensorFlow Lite, PyTorch Mobile, ONNX Runtime, TensorFlow.js, and MediaPipe. ... -
6
ncnn
High-performance neural network inference framework for mobile
ncnn is a high-performance neural network inference computing framework designed specifically for mobile platforms. It brings artificial intelligence right at your fingertips with no third-party dependencies, and speeds faster than all other known open source frameworks for mobile phone cpu. ncnn allows developers to easily deploy deep learning algorithm models to the mobile platform and create intelligent APPs. It is cross-platform and supports most commonly used CNN networks, including... -
7
TBOX
A glib-like multi-platform c library
...Implements the static buffer stream for parsing data. Supports coroutine and implements asynchronous operation. The coroutine library. Provides high-performance coroutine switch. Supports arm, arm64, x86, x86_64. Provides channel interfaces. Provides semaphore and lock interfaces. Supports io socket and stream operation in coroutine. Provides some io servers (http ..) using coroutine. Provides stackfull and stackless coroutines. -
8
Hippy
Tool to build cross-platform and high-performance awesome apps
...Hippy is now applied in 27+ Tencent apps such as Mobile QQ, Mobile QQ Browser, Tencent Video App, QQ Music App, Tencent News, reaching hundreds of millions of ordinary users. For Android, we recommend using the real cellphone for better develop experience, because Hippy is using X5 JS engine which can't support x86 simulator, as well as ARM simulator has a low performance. For iOS, we recommend to use iOS simulator when first try. However, you can change the Xcode configuration to install the app to iPhone if you are an iOS expert. -
9
LiteGapps
https://ps2bios.dev/
LiteGapps is a custom Google Apps on the Android operating system, an open source project that focuses on small, efficient, and comprehensive. https://ps2bios.dev -
Custom VMs From 1 to 96 vCPUs With 99.95% UptimeLive migration and automatic failover keep workloads online through maintenance. One free e2-micro VM every month.
-
10
Wildcat- Simple "C" XML reader
Wildcat: Simple "C" XML reader
A simple in C writen XML-Parser. Don't use macros or other non standard C-language extension. Object Oriented implementation. Support only single byte character sets. Tested with ARM-gcc 7.5 and Visual Studio 2019 C compiler. -
11
libjpeg-turbo
SIMD-accelerated libjpeg-compatible JPEG codec library
libjpeg-turbo is a JPEG image codec that uses SIMD instructions (MMX, SSE2, NEON, AltiVec) to accelerate baseline JPEG compression and decompression on x86, x86-64, ARM, and PowerPC systems. On such systems, libjpeg-turbo is generally 2-6x as fast as libjpeg, all else being equal. On other types of systems, libjpeg-turbo can still outperform libjpeg by a significant amount, by virtue of its highly-optimized Huffman coding routines. In many cases, the performance of libjpeg-turbo rivals that of proprietary high-speed JPEG codecs. ... -
12
Mixed Reality Toolkit
Accelerate cross-platform MR app development in Unity
...With the MRTK Examples Hub, you can try various example scenes in MRTK without building and deploying each scene. You can download pre-built app packages for HoloLens(x86), HoloLens 2(ARM), and Windows Mixed Reality immersive headsets(x64) by selecting the "Mixed Reality Toolkit Examples" package in the MR Feature Tool. MRTK provides example scenes that demonstrate how to use MRTK's features. You can find the example scenes under Assets/MRTK/Examples/Demos folder. -
13
OpenGApps
OpenGApps daily releases
The Open GApps Project is an open-source initiative that automates the creation of up-to-date Google Apps packages for Android devices. It provides pre-built packages that are compatible with all major Android versions and hardware platforms. Open GApps packages are DPI-optimized, ensuring better performance and consistency across different screen densities. The project updates Google Apps frequently, with new builds generated nightly when updates are available. Strong compression keeps... -
14
MACE
Deep learning inference framework optimized for mobile platforms
Mobile AI Compute Engine (or MACE for short) is a deep learning inference framework optimized for mobile heterogeneous computing on Android, iOS, Linux and Windows devices. Runtime is optimized with NEON, OpenCL and Hexagon, and Winograd algorithm is introduced to speed up convolution operations. The initialization is also optimized to be faster. Chip-dependent power options like big.LITTLE scheduling, Adreno GPU hints are included as advanced APIs. UI responsiveness guarantee is sometimes... -
15
Linux Deploy
Install and run GNU/Linux on Android
This application is open source software for quick and easy installation of the operating system (OS) GNU/Linux on your Android device. The application creates a disk image or a directory on a flash card or uses a partition or RAM, mounts it and installs an OS distribution. Applications of the new system are run in a chroot environment and working together with the Android platform. All changes made on the device are reversible, i.e. the application and components can be removed completely.... -
16
Simd
High performance image processing library in C++
...In particular the library supports following CPU extensions: SSE, SSE2, SSE3, SSSE3, SSE4.1, SSE4.2, AVX, AVX2 and AVX-512 for x86/x64, VMX(Altivec) and VSX(Power7) for PowerPC, NEON for ARM. The Simd Library has C API and also contains useful C++ classes and functions to facilitate access to C API. The library supports dynamic and static linking, 32-bit and 64-bit Windows, Android and Linux, MSVS, G++ and Clang compilers, MSVS project and CMake build systems. -
17
builder
Easily build software for your Linux distro repo
...So instead of worrying about how to compile for autoconf, autogen, bootstrap, cmake, or the traditional configure, make, make install, for each software title in your repo, builder will take care of all those details so you can focus on the more important parts of your project! Currently, builder can compile for AMD/Intel 32 and 64 bit along with ARM v6/7 (most notably for the Raspberry PI). The available profiles will successfully build for the XiniX and TC Linux distros, but contributions from others for those variants or others are welcomed and will be added to the database for all to use! Profiles can be found at: http://repo.cliquesoft.org/vanilla/1.1/builder/ [TC|XiniX] -
18
FFmpeg for Android
Configure and build FFmpeg library with Android NDK
FFmpeg for Android is a set of Android makefiles which enable configuration and building FFmpeg library under Android source code tree with Android NDK. -
19
rundotso
ARM linux run shared library rundotso dlopen dlsym Inline Assembler
windows has rundll, rundotso is for linux load shared library(.so) and run the functions. rundotso.c you can load shared lib and run the function. It likes the rundll.exe in windows os. compiled and tested under the android ndk. you can use any arm compiler to try. adb push rundotso /data adb shell /data/rundotso /system/libc.so system "ls /data" adb shell /data/rundotso /system/libc.so printf "%d %c %s %d %c %s" 16 G HelloRundotsoTest 16 d end Have fun! Made by Biyong SUN Songjiang, Shanghai, China. Email: sunbiyong@163.com -
20
Android on PXA270
Android on PXA270
Porting Android to Intel(Marvell) ARM XScale PXA270. A complete build system for embedded Linux and Android on PXA270. It was open source for anyone but no responsibility for any damage resulting from any usage of the software. Demo : http://www.youtube.com/watch?v=3Ine1k4Hzy8 http://www.youtube.com/watch?v=3Xp5zMPOI1c http://www.youtube.com/watch?v=lYzRSNuUsIw http://www.youtube.com/watch?
- Previous
- You're on page 1
- Next