Results 131 to 140 of about 1,012 (185)
Some of the next articles are maybe not open access.
2009 IEEE Hot Chips 21 Symposium (HCS), 2009
Optimization is a balancing act Things to consider: - Register usage / number of wavefronts in flight - ALU to memory access rat io ■ Sometimes better re-compute something - Workgroup size a multiple of 64 - Global size at least 2560 for a single ...
openaire +2 more sources
Optimization is a balancing act Things to consider: - Register usage / number of wavefronts in flight - ALU to memory access rat io ■ Sometimes better re-compute something - Workgroup size a multiple of 64 - Global size at least 2560 for a single ...
openaire +2 more sources
Hybrid OpenCL: Connecting Different OpenCL Implementations over Network
2010 10th IEEE International Conference on Computer and Information Technology, 2010We are developing Hybrid OpenCL, which enables the connection between different OpenCL implementations over the network. Hybrid OpenCL consists of two elements, a runtime system that provides the abstraction of different OpenCL implementations and a bridge program that connects multiple OpenCL runtime systems over the network. Hybrid OpenCL enables the
Shuichi Oikawa
exaly +2 more sources
OpenCL Remote: Extending OpenCL Platform Model to Network Scale
2012 IEEE 14th International Conference on High Performance Computing and Communication & 2012 IEEE 9th International Conference on Embedded Software and Systems, 2012This paper presents OpenCL Remote framework that extends the native OpenCL platform model to network scale and utilizes the native OpenCL's support of heterogeneous computing. OpenCL Remote boosts performance by distributing computation over network to many compute devices in parallel.
Ridvan Özaydin, D. Turgay Altilar
openaire +1 more source
Expression Templates and OpenCL
2012In this paper we discuss the interaction of expression templates with OpenCL devices. We show how the expression tree of expression templates can be used to generate problem specific OpenCL kernels. In a second approach we use expression templates to optimize the data transfer between the host and the device which leads to a measurable performance ...
Uwe Bawidamann, Marco Nehmeier
openaire +1 more source
2009 IEEE Hot Chips 21 Symposium (HCS), 2009
• OpenCL 1.0 Embedded Profile is a subset of the full profile • Not an “ES” specification of its own • Easier programming of heterogeneous multi-processor • Fast multiprocessor code without portability hassle • Speedups and energy efficiency possible via parallelism • But scheduling can be ...
openaire +2 more sources
• OpenCL 1.0 Embedded Profile is a subset of the full profile • Not an “ES” specification of its own • Easier programming of heterogeneous multi-processor • Fast multiprocessor code without portability hassle • Speedups and energy efficiency possible via parallelism • But scheduling can be ...
openaire +2 more sources
Proceedings of the 3rd International Workshop on OpenCL - IWOCL '15, 2015
SYCL ([sikə l] as in sickle) is a royalty-free, cross-platform C++ abstraction layer that builds on the underlying concepts, portability and efficiency of OpenCL, while adding the ease-of-use and flexibility of modern C++11. For example, SYCL enables single source development where C++ template functions can contain both host and device code to ...
Ronan Keryell, Ruymán Reyes, Lee Howes
openaire +1 more source
SYCL ([sikə l] as in sickle) is a royalty-free, cross-platform C++ abstraction layer that builds on the underlying concepts, portability and efficiency of OpenCL, while adding the ease-of-use and flexibility of modern C++11. For example, SYCL enables single source development where C++ template functions can contain both host and device code to ...
Ronan Keryell, Ruymán Reyes, Lee Howes
openaire +1 more source
Performance Traps in OpenCL for CPUs
2013 21st Euromicro International Conference on Parallel, Distributed, and Network-Based Processing, 2013With its design concept of cross-platform portability, OpenCL can be used not only on GPUs (for which it is quite popular), but also on CPUs. Whether porting GPU programs to CPUs, or simply writing new code for CPUs, using OpenCL brings up the performance issue, usually raised in one of two forms: "OpenCL is not performance portable!" or "Why using ...
Jie Shen 0003 +3 more
openaire +2 more sources
Experiences with OpenCL in PyFR
Proceedings of the International Workshop on OpenCL, 2020PyFR is an open source high-performance computing (HPC) framework for performing scale-resolving computational fluid dynamics simulations [1]. The algorithmic core of PyFR is the flux reconstruction (FR) approach of Huynh [2], which combines the geometric flexibility of finite volume schemes with the high-order accuracy and efficiency of spectral ...
Freddie D. Witherden, Peter E. Vincent
openaire +1 more source
Optimized fast Walsh-Hadamard transform on OpenCL-GPU and OpenCL-CPU
2016 Sixth International Conference on Image Processing Theory, Tools and Applications (IPTA), 2016The Walsh-Hadamard transform plays a major role in many image and video coding algorithms. In one hand, its intensive use in these algorithms makes its acceleration a challenge, in order to speed-up the algorithm execution. On the other hand, the available fast implementations are not efficient across different platforms. In this work, a parallel-based
Pedro M. M. Pereira +4 more
openaire +1 more source