We study the performance portability of OpenCL across diverse architectures including NVIDIA GPU, Intel Ivy Bridge CPU, and AMD Fusion APU. We present detailed performance analysis at assembly level on three exemplar OpenCL benchmarks: SGEMM, SpMV, and FFT. We also identify a number of tuning knobs that are critical to performance portability, including threads-data mapping, data layout, tiling...

The Open Computing Language (OpenCL) can be used in conjunction with the Software Communications Architecture (SCA) to build very portable applications that execute across heterogeneous platforms consisting of General Purpose Processors (GPPs), Digital Signal Processors (DSPs), Field Programming Gate Arrays (FPGAs), and Graphics Processing Units (GPUs). This paper starts with an overview of how...

Numerical methods of physics analysis require specialized forms programming as well attention to issues implementation. PhysiCL is a Python package that aims provide general-purpose tools for performing OpenCL-accelerated simulations with ease. contains Numpy-based code units system, set generic simulation tools, built-in photon scattering, measuring light behavior, and writing new OpenCL-based...

This paper presents a webcam-based spherical coordinate conversion system using OpenCL massive parallel computing for panorama video image stitching. With multi-core architecture and its high-bandwidth data transmission rate of memory accesses, modern programmable GPU makes it possible to process multiple video images in parallel for real-time interaction. To get a panorama view of 360 degrees,...

The all-pairs shortest paths (APSP) problem finds the shortest path distances between all pairs of vertices,and is one of the most fundamental graph problems. In this paper, a parallel recursive partitioning approach to APSP problem using Open Computing Language (OpenCL) for directed and dense graphs with no negative cyclesbased on R-Kleene algorithm, is presented, which recursively partitions ...

There is interest in exploring hybrid OpenSHMEM + X programming models to extend the applicability of the OpenSHMEM interface to more hardware architectures. We present a hybrid OpenCL + OpenSHMEM programming model for device-level programming for architectures like the Adapteva Epiphany many-core RISC array processor. The Epiphany architecture comprises a 2D array of low-power RISC cores with ...

As an open, royalty-free framework for writing programs that execute across heterogeneous platforms, OpenCL gives programmers access to a variety of data parallel processors including CPUs, GPUs, the Cell and DSPs. All OpenCL-compliant implementations support a core specification, thus ensuring robust functional portabiity of any OpenCL program. This thesis presents the CUDAtoOpenCL source-to-s...

With the help of of CUDA [7], [6], many applications improved their performance by using GPUs. In our project called Matrix Algebra on GPU and Multicore Architectures (MAGMA) [10], we mainly focus on dense linear algebra routines similar to those from LAPACK [1]. Other than CUDA, there exist other frameworks that allow platformindependent programming for GPUs. The main three frameworks are: 1) ...

OpenCL has become a popular standard to leverage the unique power/performance opportunities found on heterogeneous systems. In this short contribution, we evaluate the latest parallel programming features supported in the OpenCL 2.0 standard. We explore using shared virtual memory and dynamic parallelism to accelerate two example applications.

CUDA and OpenCL are the most widely used programming models to exploit hardware accelerators. Both programming models provide a C-based programming language to write accelerator kernels and a host API used to glue the host and kernel parts. Although this model is a clear improvement over a low-level and ad-hoc programming model for each hardware accelerator, it is still too complex and cumberso...