å±±ç°ã¦ãã¿ã®æ鬱ãå®ã¯äºå¤æãã¦ããã¨ããã®ããã£ã¨å§æ«ãæªãã èªãã®åå¼·ä¸è¶³ãçæãã¦ããä»æ¥ãã®é ã®ã¯ã¿ã¯ã·ã§ãã ãã¦ãåãæ¥ãéå¬å ±åã ããæ¸ãã¦ã¶ã£åãã¦ããã¯ã¿ã¯ã·ã§ã¯ããã¾ãããããããã¬ãã¼ãã¨ããããããã¨ãæãã¤ã¤ããããã¦çãå·ã£ã¦ãã次第ã ã¤ãã¤ãã¨ã¬ãã¼ããªã© 1.GPGPU ãã®3å¹´ã§ã©ãå¤ãã£ãã ãããããã¿ã¼ããé¡ãããã話ã æ°ããæè¡ãåãå ¥ãããã¨ã¯ãè¦ãã¿ããããã©ã¢ããã³ãã¼ã¸ããããããã£ã¦è©±ã§ãã OpenACCã¨ããã¸è»å¼±ããã¼ã¾ãPTXèªãã ãã¨ãªãã®ã¼ããã¼ãï¼ããããªãããOpenCLerã§ãã 2.GPU de ããããªåé¡è§£ãã¦ã¿ã å±±ç°ä»äºãã 7970ã«ã¤ãã¦ã¯ãé»æºãå¤ãã¦ãªãã³ã¸ãã¦ã¿ã¾ãããã ã59xxã·ãªã¼ãºã§ãããã¾ãå¤ãããªãã®ã¯æããã¦â¦ï¼ ãããã¯ç¸æ§ã¨ãããããã¢ã¬ãªã®ã 3.GPGPUã¨æµä½è¨ç® æµä½ã®
é¢æ±GPGPUåå¼·ä¼ : ATND å æ¥ã®ãã¨ã§ãã åå è 層ãåã¯ããããããªãã£ãã®ã§ãå¤åå ¥éã¨ãã½ãããªæãã®åå¼·ä¼ãªãã ãããªã¨æã£ã¦ TL æµãã¦ããç¬éã«åå ãã¿ã³ãæ¼ããã®ã§ãããçºè¡¨ã¿ã¤ãã«ã ãè¦ã¦é常ã«ãã¼ããªãã¨ãæãã¾ãããå®éçºè¡¨è´ãã¦ã¦ãªããªããã¼ãã§ããã å ¨é¨æ¸ãã¨é·ãã®ã§å¹¾ã¤ãã GPGPU DE ããããªåé¡ã解ãã¦ã¿ãããã NVIDIA 㨠AMD ã® GPU ã§åãããã«åé¡ã解ããã¦ã¿ã話ãOpenCL ã§ã OpenCL ã¯ä½¿ã£ããã¨ç¡ãã®ã§ãªãã¨ãããã¾ãããããªãã AMD ã®æ¹ã¯ã«ã¼ãã«ãèµ·åããé度ããã¾ãéããªããããï¼ï¼ï¼ã®ã§ã«ã¼ãã«ãè¨ç®ä¸ã«ä½åº¦ãèµ·åãããããªã³ã¼ãã¯é ããªãããããã¨ãããããªçµè«ã ã£ãã¨æãã¾ãã ãªãã GPGPU ãããªã CUDA ã¿ãããªé¢¨æ½®ãå¼·ãæããããã®ã¯ããããã¨ããã«ãããã®ããç¥ããªããªã
å±±ç°ã§ãã 6/2ã«é¢æ±GPGPUåå¼·ä¼ãéå¬ãã¾ããã å½æ¥ã¯å¤æ°ã®æ¹ã«ãéã¾ãããã ãã¦ããªãããã大å¤ãªé¨ãã§ãããããªãã¨ãããã«ãç¡äºï¼ã«çµãããã¨ãåºæ¥ã¦ã楽ããã£ããããã¨ãã£ãã¨ããã§ãã å¾ã§ã¢ããããã¦ããè³æã¯ã¾ã¨ãã¾ãããåã®è³æãã¢ãããã¾ãããã¡ãã£ã¨ä¿®æ£å ¥ããã®ã§ããå°ãå¾ ã£ã¦ãã ããã éãéããã¾ã£ã¡ãã ããµãæ§ã«ã¯æ¬å½ã«é ããããã¾ããã ãã¨ãããéæã§ãã©ãã¼ããã¦ãã ãã£ãé¢ä¿è åä½ã«ã¯ãã ãã æè¬ã®æãè¿°ã¹ãã®ã¿ã§ãã ã¨ãã«ããçºè¡¨ãã¦ããã ããæ¹ã ã«ã¯ããã®å¿ããã¨ãã«åéã縫ã£ã¦ãã¼ã¿ãåºãã¦è³æãä½ã£ã¦ããã ãã¦ãå±±ç°ãªã«ãã£ã¦ãã¨ãã£ããããã¦ãããè¿ãè¨èããªãæãã§ã å½æ¥ã®æµããç¥ãããæ¹ã¯ã#kantogpuã§Twitterãæ¤ç´¢ããã¨ã¨ã¦ã幸ã http://togetter.com/li/314340 ãããã¯ä¸ãè¦ã¦ãã ã
6. å ¨ä½ã®å¦çã®æµã Singular Value Decomposition K-Nearest Neighbor K. Kato and T. Hosino. Multi-GPU algorithm for k-nearest neighbor problem. Concurrency and Computation: Practice and Experience, 23, 2011. K.Kato and T.Hosino, Singular Value Decomposition for Collaborative Filtering on a GPU, IOP Conference Series: Materials Science and Engineering 10 012017, 2010. K.Kato and T.Hosino, Solving k-Nearest
ä»æ¥é¢æ±GPGPUåå¼·ä¼ã«åå ãã¦ãã¾ããã GPGPUã«èå³ããã£ãã®ã¯ç¢ºãã§ãããèå³åé(æ å ±ã»ãã¥ãªãã£ãã·ã¹ãã 管çï¼ã®å°ãå¤ãè¦ããã¨ããã®ãããåå ãã¦ãã¾ããã ï¼ã¹ã¿ããã¨ãã¦ä¼å ´æä¾ã»Ustreamä¸ç¶ãããããã§ãããã®ã§ããï¼ æ£ç´ãGPGPUãªãã¦ããã¹ã¯ã¼ã解æã§ä½¿ããã¤ï¼ï¼ãã¬ãã«ã§åå ãã¾ãã ãªã®ã§ãGPGPUã®è©³ç´°ãåãããã¡ã¢ãä¸ã¤ãåããªãã£ãã®ã§ããããªããªãç±ãåéã¨ãããã¨ã¯ãããã¾ããã ãã ãGPUã®ä»æ§ãå¤ãããã¨ã§ãã¹ããã¯ã¯æ¯å¹´å¤ããï¼ã©ãã©ãæ©ããªãï¼ããªããã¤é度ãå¤ãã£ããããã¨ã®ãã¨ãå®å®ä¾çµ¦ãé£ããã®ãç¾å¨ã®ç¶æ³ ä¸è¬ä¼æ¥ã§ã¯ããããªã«ã¤ãããã¼ãªãã£ã¦æãã¯ãã¾ããã å社ãä»æ§ã«æºæ ãã¦ä½ã£ã¦ãããã°ãããã®ã§ãããããæè©®GPUã¡ã¤ã³ã¯ããªã´ã³å¦çã¨ãç»åå¦çç³»ãªã®ã§ãè¨ç®ããã¼ã¹ã«èãã¦ãªãã®ãããã¿ããã§ããã ä»
ãªãªã¼ã¹ãé害æ å ±ãªã©ã®ãµã¼ãã¹ã®ãç¥ãã
ææ°ã®äººæ°ã¨ã³ããªã¼ã®é ä¿¡
j次ã®ããã¯ãã¼ã¯
kåã®ããã¯ãã¼ã¯
lãã¨ã§èªã
eã³ã¡ã³ãä¸è¦§ãéã
oãã¼ã¸ãéã
{{#tags}}- {{label}}
{{/tags}}