ãµã¤ã³ã¤ã³ããç¶æ ã§ããããããæ¼ãã¨ããã¤ãã¼ã¸ã® ããããå±¥æ´ãã«ä¸è¦§ã¨ãã¦ä¿åããã¦ããã®ã§ã å度èªã¿ãããªã£ãæãããã¨ã§ãã£ããèªã¿ããã¨ãã«ä¾¿å©ã§ãã
ãpovoã¯éå®¢è£ ç½®ããpovoããã¯ãââãauã·ã§ãããå¶ã代çåºã«å¯¾ãKDDIãé å¸ãã¦ãã販ä¿ããã¥ã¢ã«ã«ã¯ããããªæè¨ã並ã¶ã æºå¸¯é»è©±å¤§æã®KDDIï¼auï¼ããªã³ã©ã¤ã³å°ç¨æ ¼å®ãã©ã³ãpovoï¼ãã´ã©ï¼ããå·¡ããä¸è¨ã®ä»£çåºåãããã¥ã¢ã«ã§ãpovoã宣ä¼ã«æ´»ç¨ãã¦å®¢ãéããauã®å¤§å®¹éãã©ã³çã«ãã®å ´ã§å¥ç´ãããããã«ãã¨æ示ãã¦ãããã¨ããæ±æ´çµæ¸ã®åæã§ããã£ããå社ã®ææ³ã¯æ¯å表示æ³ãç¬å ç¦æ¢æ³ãé»æ°éä¿¡äºæ¥æ³ã«éåãã¦ããããããããã povoã¯KDDIã3æ23æ¥ã«éå§ãããæéãã¼ã¿å®¹é20GBã§æé¡ç¨å¥2480åã®ãã©ã³ã ãæ±æ´çµæ¸ãªã³ã©ã¤ã³ã§ã¯åæ26æ¥ãNTTãã³ã¢ããªã³ã©ã¤ã³å°ç¨æ ¼å®ãã©ã³ãahamoï¼ã¢ãã¢ï¼ãããã¨ãã«å社ã®å¤§å®¹éãã©ã³ã«èªå°ãããã¢ãã¢ããã¯ãã®åé¡ç¹ãææããï¼è©³ç´°ã¯ããã³ã¢ï½¤ãã¢ãã¢ã§ã®ã¬ãå§èªãæ¯è¡¨æ³éåããï¼ã æ¿åºè¦è«ã«ã
è¿å¹´ã®AIã¯ã人éãæãå ããªãã¦ãã³ã³ãã¥ã¼ã¿ã¼ãèªåçã«å¤§éã®ãã¼ã¿ãããã®ãã¼ã¿ã®ç¹å¾´ãçºè¦ããããã£ã¼ãã©ã¼ãã³ã°(深層å¦ç¿)ãã¨ããå¦ç¿ææ³ã§åãã¦ãã¾ãããã®ãã£ã¼ãã©ã¼ãã³ã°ã¯ãã³ã³ãã¥ã¼ã¿ã¼ã²ã¼ã ã«ä»£è¡¨ããããªã¢ã«ã¿ã¤ã ç»åå¦çã«ç¹åããæ¼ç®è£ ç½®ã»ããã»ããµã§ããGPUã§å¦çãããã¨ããã®ãéä¾ã§ãããã©ã¤ã¹å¤§å¦ã®ã³ã³ãã¥ã¼ã¿ã¼ç§å¦è ãIntelã¨å ±åã§ãGPUã«æ¯ã¹ã¦æ大15åãé«éã«ãã£ã¼ãã©ã¼ãã³ã°ã§ããCPUåãã½ããã¦ã§ã¢ããéçºãã¾ããã ACCELERATING SLIDE DEEP LEARNING ON MODERN CPUS:VECTORIZATION, QUANTIZATIONS, MEMORY OPTIMIZATIONS, AND MORE (PDFãã¡ã¤ã«)https://proceedings.mlsys.org/paper/2021/file/
ãªãªã¼ã¹ãé害æ å ±ãªã©ã®ãµã¼ãã¹ã®ãç¥ãã
ææ°ã®äººæ°ã¨ã³ããªã¼ã®é ä¿¡
å¦çãå®è¡ä¸ã§ã
j次ã®ããã¯ãã¼ã¯
kåã®ããã¯ãã¼ã¯
lãã¨ã§èªã
eã³ã¡ã³ãä¸è¦§ãéã
oãã¼ã¸ãéã
{{#tags}}- {{label}}
{{/tags}}