• Àüü
  • ÀüÀÚ/Àü±â
  • Åë½Å
  • ÄÄÇ»ÅÍ
´Ý±â

»çÀÌÆ®¸Ê

Loading..

Please wait....

±¹³» ³í¹®Áö

Ȩ Ȩ > ¿¬±¸¹®Çå > ±¹³» ³í¹®Áö > Çѱ¹Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö > Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö ¼ÒÇÁÆ®¿þ¾î ¹× µ¥ÀÌÅÍ °øÇÐ

Á¤º¸Ã³¸®ÇÐȸ ³í¹®Áö ¼ÒÇÁÆ®¿þ¾î ¹× µ¥ÀÌÅÍ °øÇÐ

Current Result Document :

ÇѱÛÁ¦¸ñ(Korean Title) ºí·Ï Á᫐ ±×·¡ÇÁ ó¸® ½Ã½ºÅÛÀÇ ºÎÇÏ ºÐ»êÀ» À§ÇÑ µ¿Àû ºí·Ï Àç¹èÄ¡ ±â¹ý
¿µ¹®Á¦¸ñ(English Title) Dynamic Block Reassignment for Load Balancing of Block Centric Graph Processing Systems
ÀúÀÚ(Author) ±è¿¹¿ø   ¹è¹ÎÈ£   ¿À»óÀ±   Yewon Kim   Minho Bae   Sangyoon Oh  
¿ø¹®¼ö·Ïó(Citation) VOL 07 NO. 05 PP. 0177 ~ 0188 (2018. 05)
Çѱ۳»¿ë
(Korean Abstract)
ÃÖ±Ù À¥, ¼Ò¼È ³×Æ®¿öÅ© ¼­ºñ½º, ¸ð¹ÙÀÏ, »ç¹°ÀÎÅÍ³Ý µîÀÇ ICT ±â¼úÀÇ ¹ßÀüÀ¸·Î ÀÎÇØ Ã³¸® ¹× ºÐ¼®ÀÌ ÇÊ¿äÇÑ ±×·¡ÇÁ µ¥ÀÌÅÍÀÇ ±Ô¸ð°¡ ±Þ¼ÓÇÏ°Ô Áõ°¡ÇÏ¿´´Ù. ÀÌ·¯ÇÑ ´ë±Ô¸ð ±×·¡ÇÁ µ¥ÀÌÅÍ´Â ´ÜÀÏ ±â±â¿¡¼­ÀÇ Ã³¸®°¡ ¾î·Æ±â ¶§¹®¿¡ ¿©·¯ ±â±â¿¡ ³ª´©¾î ºÐ»ê/º´·Ä ó¸®ÇÏ´Â °ÍÀÌ ÇÊ¿äÇÏ´Ù. ±âÁ¸ ±×·¡ÇÁ ó¸® ¾Ë°í¸®ÁòµéÀº ´ÜÀÏ ¸Þ¸ð¸® ȯ°æÀ» ±â¹ÝÀ¸·Î ¿¬±¸µÇ¾î ºÐ»ê/º´·Ä ó¸®È¯°æ¿¡ Àû¿ëµÇ±â Èûµé´Ù. ÀÌ¿¡ ´ë±Ô¸ð ±×·¡ÇÁÀÇ º¸´Ù È¿°úÀûÀÎ ºÐ»ê/º´·Ä 󸮸¦ À§ÇØ Á¤Á¡ Á᫐ ¹æ½ÄÀÇ ±×·¡ÇÁ ó¸® ½Ã½ºÅÛµé°ú, Á¤Á¡ Á᫐ ¹æ½ÄÀÇ ´ÜÁ¡À» º¸¿ÏÇÑ ºí·Ï Á᫐ ¹æ½ÄÀÇ ±×·¡ÇÁ 󸮽ýºÅÛµéÀÌ µîÀåÇÏ¿´´Ù. ÀÌ·¯ÇÑ ½Ã½ºÅÛµéÀº Ãʱ⠱׷¡ÇÁ ºÐÇÒ »óÅ°¡ Àüü ó¸® ¼º´É¿¡ »ó´çÇÑ ¿µÇâÀ» ¹ÌÄ£´Ù. ÇÑ ¹ø¿¡ ÃÖÀûÀÇ »óÅ·Π±×·¡ÇÁ¸¦ ºÐÇÒÇÏ´Â °ÍÀº ¸Å¿ì ¾î·Á¿î ¹®Á¦À̹ǷÎ, ±×·¡ÇÁ ó¸® ½Ã°£¿¡ Á¡ÁøÀûÀ¸·Î ±×·¡ÇÁ ºÐÇÒ »óŸ¦ °³¼±ÇÏ´Â ¿©·¯ ·Îµå ¹ë·±½Ì ±â¹ýµéÀÌ ¿¬±¸µÇ¾ú´Ù. ±×·¯³ª ±âÁ¸ ±â¹ýµéÀº ´ëºÎºÐ Á¤Á¡ Á᫐ ±×·¡ÇÁ ó¸® ½Ã½ºÅÛÀ» ´ë»óÀ¸·Î ÇÏ¿© ºí·Ï Á᫐ ±×·¡ÇÁ ó¸® ½Ã½ºÅÛ¿¡ Àû¿ëÀÌ ¾î·Æ´Ù. º» ³í¹®¿¡¼­´Â ºí·Ï Á᫐ ±×·¡ÇÁ ó¸® ½Ã½ºÅÛÀ» ´ë»óÀ¸·Î Àû¿ë °¡´ÉÇÑ ·Îµå ¹ë·±½Ì ±â¹ýÀ» Á¦¾ÈÇÑ´Ù. Á¦¾È ±â¹ýÀº µ¿ÀûÀ¸·Î ºí·ÏÀ» Àç¹èÄ¡ÇÏ¿© Á¡ÁøÀûÀ¸·Î ±×·¡ÇÁ ºÐÇÒ »óŸ¦ °³¼±½ÃÅ°¸ç, Çظ¦ ã¾Æ³ª°¡´Â °úÁ¤¿¡¼­ Áö¿ª ÃÖÀûÇظ¦ ¹þ¾î³ª±â À§ÇÑ ºí·Ï ºÐÇÒ Àü·«À» ÇÔ²² Á¦½ÃÇÑ´Ù.
¿µ¹®³»¿ë
(English Abstract)
The scale of graph data has been increased rapidly because of the growth of mobile Internet applications and the proliferation of social network services. This brings upon the imminent necessity of efficient distributed and parallel graph processing approach since the size of these large-scale graphs are easily over a capacity of a single machine. Currently, there are two popular parallel graph processing approaches, vertex-centric graph processing and block centric processing. While a vertex-centric graph processing approach can easily be applied to the parallel processing system, a block-centric graph processing approach is proposed to compensate the drawbacks of the vertex-centric approach. In these systems, the initial quality of graph partition affects to the overall performance significantly. However, it is a very difficult problem to divide the graph into optimal states at the initial phase. Thus, several dynamic load balancing techniques have been studied that suggest the progressive partitioning during the graph processing time. In this paper, we present a load balancing algorithms for the block-centric graph processing approach where most of dynamic load balancing techniques are focused on vertex-centric systems. Our proposed algorithm focus on an improvement of the graph partition quality by dynamically reassigning blocks in runtime, and suggests block split strategy for escaping local optimum solution.
Å°¿öµå(Keyword) ºí·Ï Áß½É Ã³¸®   ´ë±Ô¸ð ±×·¡ÇÁ µ¥ÀÌÅÍ   ·Îµå ¹ë·±½Ì   ºí·Ï Àç¹èÄ¡   Block-Centric Processing   Large-Scale Graphs   Load Balancing   Block Reassignment  
ÆÄÀÏ÷ºÎ PDF ´Ù¿î·Îµå