(science demonstration phase) 2 2 l = 30 b = 0 l = 59 b = 0 5 PACS 70 µm 160 µm SPIRE 250 µm 350 µm 500 µm Hi-GAL GPU 2 GPU 3 GPU GPU

Size: px

Start display at page:

Download "(science demonstration phase) 2 2 l = 30 b = 0 l = 59 b = 0 5 PACS 70 µm 160 µm SPIRE 250 µm 350 µm 500 µm Hi-GAL GPU 2 GPU 3 GPU GPU"

榆烜严
5 years ago
Views:

1 31 4 Vol. 31, No PROGRESS IN ASTRONOMY Nov., 2013 doi: /j.issn GPU 1,2 1 ( ) (GPU) GPU GPU GPU GPU CUDA PyOpenCL GPU GPU GPU N37 P A 1 (graphics processing unit GPU) GPU (NVIDIA) CPU GPU NVIDIA AMD CPU GPU GPU CPU NVIDIA Tesla C Gflops CPU GPU Hi-GAL [1] (Herschel infrared Galactic Plane Survey) SDP (KJCX2-YW-T20)

2 (science demonstration phase) 2 2 l = 30 b = 0 l = 59 b = 0 5 PACS 70 µm 160 µm SPIRE 250 µm 350 µm 500 µm Hi-GAL GPU 2 GPU 3 GPU GPU GPU 2 GPU GPU GPU NVIDIA CUDA (Compute Unified Device Architecture) GPU CUDA C C++ C GPU CUDA [2] CUDA NVIDIA GPU GPU OpenCL [3] (Open Computing Language) NVIDIA AMD IBM Intel OpenCL OpenCL OpenCL GPU CPU CUDA OpenCL C CUDA OpenCL [2, 3] (1) CPU ( host code) (2) GPU (kernel) CUDA CPU GPU (thread) (block) OpenCL (work item) (work group) (ID) GPU GPU GPU 3 GPU Hi-GAL GPU CUDA C

3 4 GPU 471 PyOpenCL (OpenCL Python ) GPU GPU 3.1 GPU ( 0.01 µm) 50 µm [4] Hi-GAL CPU Hi-GAL l = 30 4 PACS 160 µm SPIRE 250 µm 350 µm 500 µm SPIRE 500 µm GPU GPU CLOUDY [5] GPU CUDA C 3 (1) CPU (2) CPU GPU CPU GPU CPU (3) GPU GPU CPU 1 /* GPU */ global static void pixels(float *gpudata,float *res) { long which; const int tid=threadidx.x;/* ID*/ const int bid=blockidx.x;/* ID*/

4 /* */ for(which=bid*threads_num+tid;which<line; which+=threads_num*block_num){ /* CPU */... } } /*CPU */ main() { /* */... /* GPU */... /* GPU */ cudamalloc((void**) &gpudata, sizeof(float)*width*line); cudamemcpy2d(gpudata, sizeof(float)*width, sed30, sizeof(float)*width,sizeof(float)*width, LINE, cudamemcpyhosttodevice);... /* GPU <<<...>>> GPU */ pixels<<<block_num,threads_num,parameters>>>(gpudata, res); /* GPU CPU */ cudamemcpy2d(result, sizeof(float)*width, res, sizeof(float)*width, sizeof(float)*width, LINE, cudamemcpydevicetohost);... } 1

4 GPU 473 3.1.3 GPU 87 500 NVIDIA GeForce 9400M IDL7.1 CPU (Xeon E5620 1 ) 34 h GPU (NVIDIA GeForce 9400M) 0.5 h 68 ( 1) NVIDIA GeForce 9400M GPU GPU CPU IDL7.

5 4 GPU GPU NVIDIA GeForce 9400M IDL7.1 CPU (Xeon E ) 34 h GPU (NVIDIA GeForce 9400M) 0.5 h 68 ( 1) NVIDIA GeForce 9400M GPU GPU CPU IDL7.1 CPU (Xeon E ) s l = h CUDA NVIDIA Tesla C2075 GPU 9 min ( 2) 1 CPU GPU (t/min) CPU(Xeon E ) GPU(NVIDIA GeForce 9400M) 30 2 CPU GPU (t/min) CPU(Xeon E ) GPU(NVIDIA Tesla C2075) GPU GPU 2 NVIDIA Tesla C2075 GPU l = 30 [6] 2 l = 30

6 GPU Hi-GAL 10 pc 10 pc 10 pc 10 pc (spherical coordinates) (r, θ, φ) (d, π/2 b, l) d l b GRS [7] 100 pc l = ( ) GPU CPU 100 pc CPU (Xeon E ) Python min Hi-GAL 500 µm ( 0.01 ) CPU ( ) CPU GPU GPU CPU CPU CPU GPU GPU 3 NVIDIA Tesla C2075 GPU s ( ) GPU 95% CPU 9535 ( 3) GPU GPU 10 5

7 4 GPU CPU GPU (t/s) CPU(Xeon E ) 410 GPU PyOpenCL GPU PyOpenCL Python Python OpenCL OpenCL GPU CUDA C PyOpenCL [8] (i, j, k) 0 i<max(i) 0 j<max( j) 0 k<max(k) MAX(i) MAX( j) MAX(k) GPU (500 pc, 0.4, 0.6 ) (5, 2, 3)

8 CPU GPU CPU GPU CPU GPU GPU (1) GPU CPU (2) GPU CPU GPU GPU GPU 3.3 GPU [3] (1) CPU GPU (2) (Local Memory) (Global Memory) GPU GPU NVIDIA Tesla C2075 GPU K20m GPU 0.1 s 4 4 K20m GPU C2075 GPU 40% GPU C2075 GPU 1024, GPU 2000 GPU 1000 GPU GPU GPU GPU CPU GPU GPU GPU GPU GPU GPU

9 4 GPU K20m C2075 (t/s) K20m C2075 K20m/C % % 4 GPU GPU GPU CPU GPU CPU GPU GPU GPU GPU Rainer Spurzem Peter Berczik Peter Schwekendiek NVIDIA Tesla K20m GPU [1] Molinari S, et al. A& A, 2010, 518: L100 [2] NVIDIA Corporation. NVIDIA CUDA C Programming Guide version 4.2, vicini/cuda/doc/ CUDA_C_Programming_Guide.pdf, 2012 [3] Advanced Micro Devices, Inc. AMD Accelerated Parallel Processing OpenCL Programming Guide, primeval-slayer.com/amd-accelerated-parallel-processing-opencl-programming-guide/read/41855/, 2012 [4] Draine B T. ARA&A, 2003, 41: 241 [5] Ferland G J, Korista K T, Verner D A, et al. PASP, 1998, 110: 761 [6] Zhu J L, Huang M. 2013, in preparation [7] Roman-Duval J, Jackson J M, Heyer M, et al. ApJ, 2009, 699: 1153 [8] Andreas K. PyOpenCL documentation,

10 Applying GPU Parallel Computing Technologies to Process Herschel Far Infrared Galactic Plane Survey Data ZHU Jia-li 1,2, HUANG Mao-hai 1 ( 1. National Astronomical Observatories, Chinese Academy of Sciences, Beijing , China; 2. University of Chinese Academy of Sciences, Beijing , China ) Abstract: The Hi-GAL (Herschel infrared Galactic Plane Survey) images provide data with extraordinary spatial coverage and resolution for studying the FIR emission in the Galactic Plane. Graphics processing unit (GPU) parallel computing technologies are well suitable for accelerating processing and mining of this massive data. We illustrate the application of GPU parallel computing technologies in two examples of Hi-GAL data processing. We spare the unnecessary physical details and focus on the method of using GPU in Herschel infrared data processing. In the first example, we demonstrate a simple and straightforward application of GPU parallel computing technologies by fitting the far-infrared spectral energy distribution of the dust continuum emission in the Hi-GAL l = 30 field. There are over pixels in image of the l = 30 field. The fitting procedure for every pixel is performed in parallel by a GPU. Comparing the time-cost for fitting the entire image, the acceleration factor of the build-in GPU on a low performance laptop is 68, and a specialized GPU is 5513 times faster than a Xeon E5620 with one core. In the second example, we demonstrate a more sophisticated application of GPU parallel computing technologies. Based on the Hi-GAL l = 30 field data, the distribution of molecular clouds derived from GRS (Galactic Ring Survey) data, and the properties of H II regions, we construct a 3D model of the interstellar medium to calculate the absorption of dust grains associated with molecular clouds. The resolution of the 3D model is 100 pc for a spherical grid. For this resolution, there are 4493 cells in total responsible for absorbing FUV photons. The absorption of these cells is calculated in parallel by a GPU. The resulted absorption is then compared with observations using Monte Carlo fitting method. In every iteration, CPU samples the free parameters and computes the goodness of fitting. The GPU part of the calculation is 95% of the total time. Comparing the time-cost for one iteration, NVIDIA C2075 GPU is 9535 times as fast as a Xeon E5620. Key words: GPU; parallel computing; Hi-GAL; data analysis

Microsoft Word - 201506定版

Microsoft Word - 201506定版 56 Chinese Journal of Library and Information Science for Traditional Chinese Medicine Dec. 2015 Vol. 39 No. 6 综述中医药学语言系统研究综述于彤, 贾李蓉, 刘静, 杨硕 *, 董燕, 朱玲中国中医科学院中医药信息研究所,