Chestnut: Simplifying General Purpose Graphics Processing
نویسندگان
چکیده
Graphics processing units (GPUs) are powerful devices capable of rapid parallel computation, but using them for general computing tasks can be a difficult and tedious endeavor. We have created a graphical language called Chestnut that simplifies the process of programming on the GPU. The graphical environment is supported by a readable backend language that can be translated into GPU-ready code. Our language is intuitive, discoverable, and supports common operations used in parallel computing. Runtime tests demonstrate that our code is much faster than sequential code run on the central processing unit (CPU) and is often comparable to optimized code written specifi-
منابع مشابه
Simplifying High-Performance Geospatial Computing on GPGPUs Using Parallel Primitives: A Case Study of Quadtree Constructions on Large-Scale Geospatial Rasters
The increasingly available Graphics Processing Units (GPU) hardware resources and the emerging General Purpose computing on GPU (GPGPU) technologies provide an alternative and complementary solution to existing cluster based high-performance geospatial computing. However, the complexities of the unique GPGPU hardware architectures and the steep learning curve of GPGPU programming have imposed s...
متن کاملAstrophysical Supercomputing with GPUs: Critical Decisionsfor Early Adopters*
General-purpose computing on graphics processing units (GPGPU) is dramatically changing the landscape of high performance computing in astronomy. In this paper, we identify and investigate several key decision areas, with a goal of simplifying the early adoption of GPGPU in astronomy. We consider the merits of OpenCL as an open standard in order to reduce risks associated with coding in a nativ...
متن کاملImplementation of Digital Signal Processing Algorithm in General Purpose Graphics Processing Unit (GPGPU)
In this paper, we have proposed sequential and parallel matrix and matrix-vector multiplication in compute unified device architecture (CUDA) libraries. We show the process of a class of algorithms parallelization which are used in digital signal processing. We present this approach on the instance of the Linear Convolution, Circular Convolution, and Least Mean Square (LMS) algorithm. We propos...
متن کاملGeneral-purpose Graphics Processing Units Deliver New Capabilities to the Embedded Market
Today’s graphics processors are highly programmable, massively parallel compute engines. With the development of open, industry standards, parallel programming languages such as OpenCLTM and the continued evolution of heterogeneous computing, general-purpose graphics processing units (GPGPUs) offer exciting new capabilities for the embedded market. This paper examines some of the industry facto...
متن کامل