In this work, we evaluate OpenCL as a programming tool for developing performance-portable applications for GPGPU. While the Khronos group developed OpenCL with programming portability in mind, performance is not necessarily portable. OpenCL has required performance-impacting initializations that do not exist in other languages such as CUDA. Understanding these implications allows us to provide a single library with decent performance on a variety of platforms. We choose triangular solver (TRSM) and matrix multiplication (GEMM) as representative level 3 BLAS routines to implement in OpenCL. We profile TRSM to get the time distribution of the OpenCL runtime system. We then provide tuned GEMM kernels for both the NVIDIA Tesla C2050 and ATI Radeon 5870, the latest GPUs offered by both companies. We explore the benefits of using the texture cache, the performance ramifications of copying data into images, discrepancies in the OpenCL and CUDA compilers' optimizations, and other issues that affect the performance. Experimental results show that nearly 50% of peak performance can be obtained in GEMM on both GPUs in OpenCL. We also show that the performance of these kernels is not highly portable. Finally, we propose the use of auto-tuning to better explore these kernels' parameter space using search harness.

/pdf/from-cuda-to-opencl-towards-a-performance-portable-solution-d23sxkceiq.pdf

From CUDA to OpenCL: Towards a performance-portable solution for multi-platform GPU programming

This paper presents a comprehensive performance comparison between CUDA and OpenCL. We have selected 16 benchmarks ranging from synthetic applications to real-world ones. We make an extensive analysis of the performance gaps taking into account programming models, ptimization strategies, architectural details, and underlying compilers. Our results show that, for most applications, CUDA performs at most 30\% better than OpenCL. We also show that this difference is due to unfair comparisons: in fact, OpenCL can achieve similar performance to CUDA under a fair comparison. Therefore, we define a fair comparison of the two types of applications, providing guidelines for more potential analyses. We also investigate OpenCL's portability by running the benchmarks on other prevailing platforms with minor modifications. Overall, we conclude that OpenCL's portability does not fundamentally affect its performance, and OpenCL can be a good alternative to CUDA.

A Comprehensive Performance Comparison of CUDA and OpenCL

Quantum Monte Carlo and Related Approaches

Heterogeneous Computing with OpenCL teaches OpenCL and parallel programming for complex systems that may include a variety of device architectures: multi-core CPUs, GPUs, and fully-integrated Accelerated Processing Units (APUs) such as AMD Fusion technology. Designed to work on multiple platforms and with wide industry support, OpenCL will help you more effectively program for a heterogeneous future. Written by leaders in the parallel computing and OpenCL communities, this book will give you hands-on OpenCL experience to address a range of fundamental parallel algorithms. The authors explore memory spaces, optimization techniques, graphics interoperability, extensions, and debugging and profiling. Intended to support a parallel programming course, Heterogeneous Computing with OpenCL includes detailed examples throughout, plus additional online exercises and other supporting materials.Explains principles and strategies to learn parallel programming with OpenCL, from understanding the four abstraction models to thoroughly testing and debugging complete applications.Covers image processing, web plugins, particle simulations, video editing, performance optimization, and more.Shows how OpenCL maps to an example target architecture and explains some of the tradeoffs associated with mapping to various architecturesAddresses a range of fundamental programming techniques, with multiple examples and case studies that demonstrate OpenCL extensions for a variety of hardware platforms

Heterogeneous Computing with OpenCL

Motivation: The Basic Local Alignment Search Tool (BLAST) is one of the most widely used bioinformatics tools. The widespread impact of BLAST is reflected in over 53 000 citations that this software has received in the past two decades, and the use of the word ‘blast’ as a verb referring to biological sequence comparison. Any improvement in the execution speed of BLAST would be of great importance in the practice of bioinformatics, and facilitate coping with ever increasing sizes of biomolecular databases.

Results: Using a general-purpose graphics processing unit (GPU), we have developed GPU-BLAST, an accelerated version of the popular NCBI-BLAST. The implementation is based on the source code of NCBI-BLAST, thus maintaining the same input and output interface while producing identical results. In comparison to the sequential NCBI-BLAST, the speedups achieved by GPU-BLAST range mostly between 3 and 4.

Availability: The source code of GPU-BLAST is freely available at http://archimedes.cheme.cmu.edu/biosoftware.html.

Contact: sahinidis@cmu.edu

Supplementary information:Supplementary data are available at Bioinformatics online.

Gpu-blast

Multicore processors and a variety of accelerators have allowed scientific applications to scale to larger problem sizes. We present a performance, design methodology, platform, and architectural comparison of several application accelerators executing a Quantum Monte Carlo application. We compare the application's performance and programmability on a variety of platforms including CUDA with Nvidia GPUs, Brook+ with ATI graphics accelerators, OpenCL running on both multicore and graphics processors, C++ running on multicore processors, and a VHDL implementation running on a Xilinx FPGA. We show that OpenCL provides application portability between multicore processors and GPUs, but may incur a performance cost. Furthermore, we illustrate that graphics accelerators can make simulations involving large numbers of particles feasible.

Comparing Hardware Accelerators in Scientific Applications: A Case Study

Using GPUs as computational accelerators has been a growing area of research in the past several years. One particular area amenable to exploiting video card hardware is dense linear algebra. We continue this trend by generalizing the MAGMA xGEMM kernels, porting them to OpenCL and tuning them to run on the AMD 7970. Achieving up to 1.7 TFlops in SGEMM and 650 GFlops in DGEMM, we extend this performance to multiple GPUs using a parallel-for algorithm designed to run on multiple heterogeneous devices. Using 3 Radeon 7970s, our large GEMM algorithm obtains 4.37TFlops in single precision and 1.64 TFlops/s in double.

A Trip to Tahiti: Approaching a 5 TFlop SGEMM Using 3 AMD GPUs

This poster presents clUtil, a library that simplifies OpenCL's C frontend. It provides significant productivity improvements using C++11 features, such as variadic templated functions for launching kernels, while giving users a simple construct for exploiting multiple heterogeneous devices. The parallel-for construct allows developers to seamlessly use multiple OpenCL devices with automatic work distribution and load-balancing.

Poster: Improved OpenCL Programmability with clUtil

Background While multiple tools exist for the analysis and identification of spectra generated in shotgun proteomics experiments, few easily implemented tools exist that allow for the automated analysis of the quality of spectra. A researcher’s knowledge of the quality of a spectra from an experiment can be helpful in determining possible reasons for misidentification or lack of identification of spectra in a sample.

/pdf/development-of-tools-for-the-automated-analysis-of-spectra-378l3hjlb9.pdf

Rick Weber

Papers

From CUDA to OpenCL: Towards a performance-portable solution for multi-platform GPU programming

Comparing Hardware Accelerators in Scientific Applications: A Case Study

A Trip to Tahiti: Approaching a 5 TFlop SGEMM Using 3 AMD GPUs

Poster: Improved OpenCL Programmability with clUtil

Development of tools for the automated analysis of spectra generated by tandem mass spectrometry