[B! GPGPU] Glnã®ãƒ–ãƒƒã‚¯ãƒžãƒ¼ã‚¯

Gln id:Gln

GPGPUã«é–¢ã™ã‚‹Glnã®ãƒ–ãƒƒã‚¯ãƒžãƒ¼ã‚¯ (29)

${{author_name}}$

{{{comment_expanded}}}

{{label}}

{{#is_bookmark}}ãƒªã‚¹ãƒˆ{{/is_bookmark}}{{^is_bookmark}}ãƒªãƒ³ã‚¯{{/is_bookmark}}

${{author_name}}$
{{author_name}}{{created}}
{{ #comment }}{{ comment }}{{ /comment }}
- {{ label }}

${{author_name}}$

{{{comment_expanded}}}

{{label}}

{{#is_bookmark}}ãƒªã‚¹ãƒˆ{{/is_bookmark}}{{^is_bookmark}}ãƒªãƒ³ã‚¯{{/is_bookmark}}

ã‚¹ãƒ‘ã‚³ãƒ³ã€Œäº¬ã€ã«é–¢ã™ã‚‹ç´ æœ´ãªç–‘å•
æ˜¨æ™©æ”¾é€ã•ã‚ŒãŸNHKã®ã‚¯ãƒãƒ¼ã‚ºã‚¢ãƒƒãƒ—ç¾ä»£ã€Œè¶…é«˜é€Ÿè¨ˆç®—ãŒèµ·ã“ã™â€œæ–°ãƒ»ç”£æ¥é©å‘½â€ã€œã‚¹ãƒ‘ã‚³ãƒ³ã€Œäº¬ã€ã®ã²ã‚‰ãæœªæ¥ã€œã€ã‚’è¦‹ãŸã€‚æœ¬æ¥ãªã‚‰ã°ã€Œã‚¹ãƒ‘ã‚³ãƒ³ã‚’ä½¿ã£ãŸã‚·ãƒŸãƒ¥ãƒ¬ãƒ¼ã‚·ãƒ§ãƒ³ã‚’ä½¿ãˆã°...ã€ã¨ä¸€èˆ¬åè©žã‚’ä½¿ã†ã¹ãéƒ¨åˆ†ã‚’ã“ã¨ã”ã¨ãã€Œäº¬ã‚’ä½¿ãˆã°...ã€ã¨è¨€ã„æ›ãˆã¦ã„ã‚‹ãŸã‚ã€ã™ã£ã‹ã‚Šã€Œã¡ã‚‡ã†ã¡ã‚“ç•ªçµ„ã€ã«æˆã‚Šä¸‹ãŒã£ã¦ã„ã‚‹ã€‚ ã€Œãªãœäº¬ãªã®ã‹ï¼Ÿã€ã¨ã„ã†éƒ¨åˆ†ãŒç§ã«ã¯å…¨ãä¼ã‚ã£ã¦æ¥ãªã‹ã£ãŸã®ã ãŒã€ã“ã®ç•ªçµ„ã‚’è¦‹ãŸäººã®å¤§åŠã®äººã¯ã€ã€Œäº¬ã£ã¦ã™ã”ã„ã€‚äº‹æ¥ä»•åˆ†ã‘ãªã‚“ã‹ã—ãªãã¦è‰¯ã‹ã£ãŸã€ã¨æ„Ÿã˜ãŸã«é•ã„ãªã„ï¼ˆã¨ã„ã†ã‹ã€ãã†ãªã‚‹ã‚ˆã†ã«ä½œã‚‰ã‚Œã¦ã„ã‚‹ï¼‰ã€‚ ã“ã®ç•ªçµ„ã‚’è¦‹ã¦ã€ç§ã®é ã®ä¸ã«ã¯ä»¥ä¸‹ã®ã‚ˆã†ãªç–‘å•ãŒæ¬¡ã€…ã¨æµ®ã‹ã‚“ã ã®ã ãŒã€ã“ã®ç•ªçµ„ã¯ã“ã‚Œã‚‰ã®ç–‘å•ã«ç”ãˆã¦ã„ãªã„ã©ã“ã‚ã‹ã€ç–‘å•ã‚’æç¤ºã™ã‚‰ã—ã¦ã„ãªã„ã®ãŒä½•ã¨ã‚‚æ®‹å¿µã ã€‚ æœ¬å½“ã«å¤§é‡ã®ç¨Žé‡‘ã‚’ã¤ãŽè¾¼ã‚€ä¾¡å€¤ãŒã‚ã‚‹ã®ã‹ï¼Ÿç¨Žé‡‘ã‚’ä½¿ã†ã«ã—ã¦ã‚‚ã€ã‚‚ã£ã¨åˆ¥ã®æ–¹æ³•ãŒã‚ã‚‹ã®ã§ã¯ãªã„ã‹ï¼Ÿ ç„¡æ–™ã§äº¬ã‚’ä½¿ã‚ã›ã¦ã‚‚ã‚‰ãˆã‚‹ç ”ç©¶æ©Ÿ
Gln 2013/01/13
NHK

HPC

gpgpu
ãƒªãƒ³ã‚¯
Windowsã®ãƒ‘ã‚¹ãƒ¯ãƒ¼ãƒ‰ã¯GPUã‚’25å€‹ä½¿ãˆã°ç´„6åˆ†ã‹ã‚‰6æ™‚é–“ã§çªç ´ãŒå¯èƒ½ã€æ¯Žç§’3500å„„é€šã‚Šã‚‚ã®ç·å½“ãŸã‚ŠãŒå¯èƒ½ãªæ–¹æ³•ã¨ã¯ï¼Ÿ
ä¸€èˆ¬çš„ãªä¼æ¥ã§ä½¿ç”¨ã•ã‚Œã¦ã„ã‚‹Windowsã®ãƒ‘ã‚¹ã‚³ãƒ¼ãƒ‰ã‚’6æ™‚é–“ä»¥å†…ã«çªç ´ã§ãã‚‹GPUã‚¯ãƒ©ã‚¹ã‚¿ãƒ¼ã‚’ä½¿ç”¨ã—ãŸã‚¯ãƒ©ãƒƒã‚ãƒ³ã‚°ã®ã‚·ã‚¹ãƒ†ãƒ ãŒé–‹ç™ºã•ã‚ŒãŸã€ã¨Ars TechnicaãŒå ±ã˜ã¦ã„ã¾ã™ã€‚ 25-GPU cluster cracks every standard Windows password in 6 hours | Ars Technica http://arstechnica.com/security/2012/12/25-gpu-cluster-cracks-every-standard-windows-password-in-6-hours/" ã“ã®ã‚·ã‚¹ãƒ†ãƒ ã‚’é–‹ç™ºã—ãŸã®ã¯Stricture Consulting Groupç¤¾ã®CEOã§ã‚ã‚‹Jeremi M Gosneyæ°ã§ã€ãƒŽãƒ«ã‚¦ã‚§ãƒ¼ã®ã‚ªã‚¹ãƒã§é–‹å‚¬ã•ã‚ŒãŸPasswords^12 conferenceã«ã¦ãã®è©³ç´°ã‚’ç™ºè¡¨ã—ã¾ã—ãŸã€‚ Gos
Gln 2012/12/12
GPU

GPGPU

password

Security

opencl
ãƒªãƒ³ã‚¯
ç±³NVIDIAã®CEOãŒçµ¶è³›ã™ã‚‹â€œæ—¥æœ¬ã®CUDAâ€
ã€Œã‚°ãƒ©ãƒ•ã‚£ãƒƒã‚¯ã‚¹ã§ã¯ãªãæ±Žç”¨ã®GPUã‚³ãƒ³ãƒ”ãƒ¥ãƒ¼ãƒ†ã‚£ãƒ³ã‚°ã«æ³¨ç›®ã—ã¦ã„ãã€ã¨è¿°ã¹ãŸç±³NVIDIA CEOã®ã‚¸ã‚§ãƒ³ã‚¹ãƒ³ãƒ»ãƒ•ã‚¡ãƒ³æ°ã«ã‚ˆã‚‹åŸºèª¿è¬›æ¼”ã®å†…å®¹ã¯ã€2010å¹´9æœˆã«ç±³å›½ã§è¡Œã‚ã‚ŒãŸã€ŒGPU Techno logy Conferenceã€ã®åŒæ°ã«ã‚ˆã‚‹åŸºèª¿è¬›æ¼”ã¨ã»ã¼å…±é€šã—ãŸã€‚CUDAç’°å¢ƒã§é–‹ç™ºã•ã‚ŒãŸGPUã‚³ãƒ³ãƒ”ãƒ¥ãƒ¼ãƒ†ã‚£ãƒ³ã‚°ã¯ã€è‡ªå‹•è»Šç”£æ¥ã€å»ºç¯‰ã€ã‚¤ãƒ³ãƒ†ãƒªã‚¢ã§ã«ãŠã‘ã‚‹ãƒ‡ã‚¶ã‚¤ãƒ³ã‚·ãƒŸãƒ¥ãƒ¬ãƒ¼ã‚·ãƒ§ãƒ³ã‚„ã€æµä½“ã‚·ãƒŸãƒ¥ãƒ¬ãƒ¼ã‚·ãƒ§ãƒ³çµæžœã®ãƒªã‚¢ãƒ«ã‚¿ã‚¤ãƒ è¡¨ç¤ºã€åŒ»è–¬å“é–‹ç™ºã€å¤©ä½“é‹å‹•ã‚·ãƒŸãƒ¥ãƒ¬ãƒ¼ã‚·ãƒ§ãƒ³ã€ãã—ã¦å¤©æ°—äºˆå ±ã«ç”¨ã„ã‚‹å¤§æ°—ã‚·ãƒŸãƒ¥ãƒ¬ãƒ¼ã‚·ãƒ§ãƒ³ãªã©ã€é«˜åº¦ãªä¸¦åˆ—æ¼”ç®—å‡¦ç†ã‚’å¿…è¦ã¨ã™ã‚‹é ˜åŸŸã§åºƒãä½¿ã‚ã‚Œã¦ã„ã‚‹ã€‚ ã“ã®ã‚±ãƒ¼ã‚¹ã‚¹ã‚¿ãƒ‡ã‚£ã¨ã—ã¦ã€æ±äº¬å·¥æ¥å¤§å¦ å¦è¡“å›½éš›æƒ…å ±ã‚»ãƒ³ã‚¿ãƒ¼ã®é’æœ¨å°Šä¹‹æ°ãŒã€åŒå¤§å¦ã®TSUBAME 2.0ã§ãƒ•ãƒ«GPUæ¼”ç®—ã‚’å®Ÿè¡Œã™ã‚‹æ¬¡ä¸–ä»£æ°—è±¡ãƒ¢ãƒ‡ãƒ«ã‚’ç´¹ä»‹ã—ãŸã€‚æ°—è±¡ã®æ•°å€¤äºˆå ±ã§ã¯ã€é¢¨é€Ÿã‚„æ°—åœ§ã€æ°´è’¸æ°—ã®æŒ™å‹•ã‚’æ±‚ã‚ã‚‹â€œåŠ›å¦éŽç¨‹â€ã¨ã€é›²
Gln 2012/04/01
GPU

NVIDIA

gpgpu

cuda
ãƒªãƒ³ã‚¯
ã€å¤šå’Œç”°æ–°ä¹Ÿã®ãƒ‹ãƒ¥ãƒ¼ã‚¢ã‚¤ãƒ†ãƒ è¨ºæ–å®¤ã€‘ Fermiãƒ™ãƒ¼ã‚¹ã®æ–°ãƒ©ã‚¤ãƒ³ãƒŠãƒƒãƒ—ãŒç™»å ´ã€ŒQuadro 5000ã€
Gln 2012/03/30
GPU

nvidia

GPGPU
ãƒªãƒ³ã‚¯
CPUã®é™ç•Œã‚’è¶…ã™â€¦ã‚¹ãƒ‘ã‚³ãƒ³ã«å€£ã„ã€ã€ŒGPUã€æ´»ç”¨
ã‚°ãƒ¼ã‚°ãƒ«æ¤œç´¢ã‚„Twitterã€Facebookãªã©ã€Œãƒ“ãƒƒã‚°ãƒ‡ãƒ¼ã‚¿ã€ã‚’æ‰±ã†ã‚µãƒ¼ãƒ“ã‚¹ãŒæ™®åŠã—ã€ã“ã‚Œã¾ã§ä¸å¯èƒ½ã ã¨æ€ã£ã¦ã„ãŸã“ã¨ã‚’å®Ÿç¾ã§ãã‚‹æ–°åž‹ITï¼ˆæƒ…å ±æŠ€è¡“ï¼‰ãŒç¶šã€…ã¨ç™»å ´ã€ä¸€èˆ¬ä¼æ¥ã«ã‚‚èº«è¿‘ãªã‚‚ã®ã«ãªã‚Šã¤ã¤ã‚ã‚‹ã€‚ãƒ“ãƒƒã‚°ãƒ‡ãƒ¼ã‚¿ã¨ã¯ã€å¾“æ¥ã®ã‚³ãƒ³ãƒ”ãƒ¥ãƒ¼ãƒ†ã‚£ãƒ³ã‚°æŠ€è¡“ã§ã¯çŸæ™‚é–“ã§åŽé›†ãƒ»è§£æžã™ã‚‹ã®ãŒé›£ã—ã„ã€è†¨å¤§ãªé‡ã®ãƒ‡ãƒ¼ã‚¿ã®ã“ã¨ã€‚æƒ…å ±ã‚·ã‚¹ãƒ†ãƒ ã®æ¬¡ä»£ã‚’æ‹…ã†7å¤§ITãƒˆãƒ¬ãƒ³ãƒ‰ã‚’ç´¹ä»‹ã™ã‚‹æœ¬é€£è¼‰ã®ç¬¬4å›žã¯ã€æœ€æ–°ã‚¹ãƒ¼ãƒ‘ãƒ¼ã‚³ãƒ³ãƒ”ãƒ¥ãƒ¼ã‚¿ï¼ˆã‚¹ãƒ‘ã‚³ãƒ³ï¼‰ã§ã‚‚è„šå…‰ã‚’æµ´ã³ã‚‹ã€ŒGPGPUï¼ˆGeneral-Purpose computing on GPUï¼‰ã€æŠ€è¡“ã‚’æ‰±ã†ã€‚ æç”»å‡¦ç†ã«æœ€é©åŒ–ã•ã‚ŒãŸã€ŒGPUï¼ˆã‚°ãƒ©ãƒ•ã‚£ãƒƒã‚¯ã‚¹å‡¦ç†å°‚ç”¨ãƒ—ãƒã‚»ãƒƒã‚µï¼‰ã€ã®åŠ›ã‚’å€Ÿã‚Šã¦ã€ãƒ‘ã‚½ã‚³ãƒ³ã®å¿ƒè‡“éƒ¨ã¨ã—ã¦ã‚ˆãçŸ¥ã‚‰ã‚Œã‚‹ã€ŒCPUï¼ˆä¸å¤®æ¼”ç®—å‡¦ç†è£…ç½®ï¼‰ã€ã®é™ç•Œã‚’è¶…ãˆã‚‹â€•â€•ã€‚ãƒ‡ãƒ¼ã‚¿è§£æžå‡¦ç†ã‚’é«˜é€ŸåŒ–ã™ã‚‹ä¸€æ‰‹æ³•ã¨ã—ã¦ã€GPUã®ä½¿ã„ã“ãªã—ãŒå¤§ããªãƒ†ãƒ¼ãƒžã«ãªã£ã¦ããŸã€‚CPUã¨GPUã®ã©
Gln 2011/12/16
GPU

GPGPU
ãƒªãƒ³ã‚¯
JCSãŒGPGPUã‚µãƒ¼ãƒã®æ–°è£½å“ã‚’ç™ºå£²ã€æœ€é«˜æ€§èƒ½ã¯5TFLOPSä»¥ä¸Š ï¼ ï¼ IT
2011/10/19 æ—¥æœ¬ã‚³ãƒ³ãƒ”ãƒ¥ãƒ¼ãƒ†ã‚£ãƒ³ã‚°ã‚·ã‚¹ãƒ†ãƒ ï¼ˆJCSï¼‰ã¯2011å¹´10æœˆ18æ—¥ã€GPGPUï¼ˆGeneral Purpose computing on Graphics Processing Unitsï¼‰æè¼‰ã‚µãƒ¼ãƒã®æ–°è£½å“ã®è²©å£²ã‚’é–‹å§‹ã—ãŸã€‚GPGPUæè¼‰ã‚¹ãƒšãƒ¼ã‚¹ã‚’åºƒã’ã€ã‚ˆã‚Šé«˜æ€§èƒ½ãªGPGPUã‚’åˆ©ç”¨å¯èƒ½ã«ã—ã€å˜ç²¾åº¦æµ®å‹•å°æ•°ç‚¹æ¼”ç®—ã§5TFLOPSä»¥ä¸Šã®æ€§èƒ½ã‚’ç™ºæ®ã™ã‚‹ã‚ˆã†ã«ãªã£ãŸã“ã¨ãŒç‰¹é•·ã€‚å¤§å¦ãƒ»ç ”ç©¶å®¤ã«ãŠã‘ã‚‹ç§‘å¦æŠ€è¡“è¨ˆç®—ã‚„ã€è£½é€ æ¥ã«ãŠã‘ã‚‹ã‚·ãƒŸãƒ¥ãƒ¬ãƒ¼ã‚·ãƒ§ãƒ³ã¨ã„ã£ãŸç”¨é€”ã‚’ç‹™ã£ã¦å£²ã‚Šè¾¼ã‚€ã€‚
Gln 2011/10/19
GPGPU

NVIDIA

HPC
ãƒªãƒ³ã‚¯
ã‚¹ãƒ‘ã‚³ãƒ³ãƒ©ãƒ³ã‚ãƒ³ã‚°ã®TOP500ã§ä¸å›½è£½ã‚·ã‚¹ãƒ†ãƒ ãŒä¸–ç•Œä¸€ã« ï½žä¸Šä½5ä½ã®å†…ã€1ä½ã¨3ä½ã€4ä½ãŒNVIDIAã®GPUæŽ¡ç”¨
Gln 2010/11/16
NVIDIA

TSUBAME

HPC

GPGPU
ãƒªãƒ³ã‚¯
ã€ã‚¤ãƒ™ãƒ³ãƒˆãƒ¬ãƒãƒ¼ãƒˆã€‘ NVIDIAãŒã€ŒGPUã‚³ãƒ³ãƒ”ãƒ¥ãƒ¼ãƒ†ã‚£ãƒ³ã‚°2010ã€ã‚’é–‹å‚¬ ï½žGPUã‚³ãƒ³ãƒ”ãƒ¥ãƒ¼ãƒ†ã‚£ãƒ³ã‚°ãŒç”Ÿã‚€æ–°ã—ã„ã‚½ãƒªãƒ¥ãƒ¼ã‚·ãƒ§ãƒ³ã‚’ç´¹ä»‹
Gln 2010/07/21
HPC

GPU

GPGPU

NVIDIA
ãƒªãƒ³ã‚¯
ã€å¾Œè—¤å¼˜èŒ‚ã®Weeklyæµ·å¤–ãƒ‹ãƒ¥ãƒ¼ã‚¹ã€‘ Fermiãƒãƒ¼ã‚¸ãƒ§ãƒ³2ã¨è¨€ãˆã‚‹GF104ã®æ£ä½“
Gln 2010/07/16
GPU

Fermi

NVIDIA

gpgpu
ãƒªãƒ³ã‚¯
GPGPU ãŒã‚¢ãƒ„ã„ã€‚ä¸€ç•ªã§ã¯ãªãä¸€ç•ªä¹—ã‚Šã«ãªã‚ã†ã€‚ - æ¦è”µé‡Žæ—¥è¨˜
PFI ã‚»ãƒŸãƒŠãƒ¼ GPU ã‚³ãƒ³ãƒ”ãƒ¥ãƒ¼ãƒ†ã‚£ãƒ³ã‚°ã®ç¾çŠ¶ã¨ã‚¹ãƒ¼ãƒ‘ãƒ¼ã‚³ãƒ³ãƒ”ãƒ¥ãƒ¼ãƒ†ã‚£ãƒ³ã‚°ã®æœªæ¥ã‚’è¦‹ã‚‹ã€‚äºˆæƒ³ä»¥ä¸Šã«é¥ã‹ã«ãŠã‚‚ã—ã‚ã‹ã£ãŸã€‚èª¬æ˜Žã‚‚åˆ†ã‹ã‚Šã‚„ã™ã„ã—ãªã«ã‚ˆã‚Š @nushio ã•ã‚“ã®è©±ã—æ–¹ãŒå¿ƒåº•æ¥½ã—ãã†ãªã®ãŒã¨ã¦ã‚‚ã‚ˆã„ :-) ã‚¨ãƒ³ã‚¸ãƒ‹ã‚¢ã«ã›ã‚ˆç ”ç©¶è€…ã«ã›ã‚ˆã€ä¸€ç•ªå¤§äº‹ãªã®ã¯è‡ªåˆ†ã®ã‚„ã£ã¦ã„ã‚‹ã“ã¨ã«æƒ…ç†±ã‚’ã‹ã‘ã‚‰ã‚Œã‚‹ã‹ã€æ¥½ã—ã‚“ã§ã„ã‚‹ã‹ã€ã¨ã„ã†ã“ã¨ã«å°½ãã‚‹ã¨æ€ã†ã€‚ä¸Šè¨˜ã®ãƒªãƒ³ã‚¯ã¯æ”¾æ˜ ã•ã‚ŒãŸã‚‚ã®ã®éŒ²ç”»ãªã®ã ãŒã€ã‚¹ãƒ©ã‚¤ãƒ‰ã¯ã“ã¡ã‚‰ã€‚ãƒˆãƒ¼ã‚¯ã‚‚ã¡ã‚‡ã†ã©1æ™‚é–“ç¨‹åº¦ãªã®ã§ã€æ™‚é–“ãŒã‚ã‚Œã°ã‚¹ãƒ©ã‚¤ãƒ‰ã ã‘ã§ã¯ãªãã€ãƒˆãƒ¼ã‚¯ã®æœ€åˆã®æ•°åˆ†ã ã‘ã§ã‚‚è¦‹ã‚‹(ã¨ã„ã†ã‹èžã)ã“ã¨ã‚’ãŠå‹§ã‚ã™ã‚‹ã€‚å…ˆæ—¥ã®ã‚¦ã‚§ãƒ–å¦ä¼šã®ã¨ãã‚‚æ€ã£ãŸãŒã€æ±äº¬ã«ã„ãªãã¦ã‚‚ã“ã†ã„ã†ã®ãŒèžã‘ã‚‹æ™‚ä»£ã«ãªã£ã¦ã€ã™ã”ãä¾¿åˆ©ã ãªã‚ã€‚(ã‚ã¨ã‹ã‚‰è¦‹ã‚‹ã“ã¨ã‚‚ã§ãã‚‹ã—ã€æ–‡å—é€šã‚Šæ™‚ç©ºã‚’è¶…ãˆã¦ã„ã‚‹) GPGPU ã£ã¦ãªã‚“ãªã®ã‚ˆã€ã¨ã„ã†ã¨ã€ã“ã‚Œã¯ General Purpose computing
Gln 2010/03/12
gpgpu

ç ”ç©¶

è¨ˆç®—
ãƒªãƒ³ã‚¯
AMDã€GPGPUã‚½ãƒ•ãƒˆã‚¦ã‚§ã‚¢é–‹ç™ºç”¨ãƒ—ãƒ©ãƒƒãƒˆãƒ•ã‚©ãƒ¼ãƒ ã€ŒATI Stream SDK v2.0ã€
Gln 2009/12/24
OpenCL

GPGPU

ATI

amd
ãƒªãƒ³ã‚¯
2009/12/10 GPUã‚³ãƒ³ãƒ”ãƒ¥ãƒ¼ãƒ†ã‚£ãƒ³ã‚°ã®ç¾çŠ¶ã¨ã‚¹ãƒ¼ãƒ‘ãƒ¼ã‚³ãƒ³ãƒ”ãƒ¥ãƒ¼ãƒ†ã‚£ãƒ³ã‚°ã®æœªæ¥
PFIç¤¾å†…ã‚»ãƒŸãƒŠãƒ¼ 2009å¹´12æœˆ10æ—¥ 20:00-21:00(äºˆå®š) GPUã‚³ãƒ³ãƒ”ãƒ¥ãƒ¼ãƒ†ã‚£ãƒ³ã‚°ã®ç¾çŠ¶ã¨ã‚¹ãƒ¼ãƒ‘ãƒ¼ã‚³ãƒ³ãƒ”ãƒ¥ãƒ¼ãƒ†ã‚£ãƒ³ã‚°ã®æœªæ¥ ç™ºè¡¨è€…: æ‘ä¸» å´‡è¡Œï¼ˆãƒ—ãƒªãƒ•ã‚¡ãƒ¼ãƒ‰ã‚¤ãƒ³ãƒ•ãƒ©ã‚¹ãƒˆãƒ©ã‚¯ãƒãƒ£ãƒ¼ ç ”ç©¶é–‹ç™ºéƒ¨é–€ãƒ»äº¬éƒ½å¤§å¦å¤§å¦é™¢ã€€ç‰©ç†å¦ç¬¬äºŒæ•™å®¤ï¼‰ ã‚»ãƒŸãƒŠãƒ¼éŒ²ç”»URL: http://www.ustream.tv/recorded/2837689 ã“ã®ã‚¹ãƒ©ã‚¤ãƒ‰ã¯ã€ç™ºè¡¨å¾Œã«ã¿ãªã•ã¾ã‹ã‚‰ã„ãŸã ã„ãŸè²´é‡ãªæ„è¦‹ã‚’ã‚‚ã¨ã«æ”¹è¨‚ã—ãŸç‰ˆã§ã™ã€‚ç™ºè¡¨æ™‚ç‚¹ã§ã®ç‰ˆã¯ã“ã¡ã‚‰: http://www.slideshare.net/pfi/20091210-gpu-2735685Read less
Gln 2009/12/11
hpc

programming

gpgpu
ãƒªãƒ³ã‚¯
ã€å¾Œè—¤å¼˜èŒ‚ã®Weeklyæµ·å¤–ãƒ‹ãƒ¥ãƒ¼ã‚¹ã€‘ ä»•åˆ‡ã‚Šç›´ã—ã¨ãªã£ãŸLarrabeeã®ä½•ãŒå•é¡Œã ã£ãŸã®ã‹
Gln 2009/12/10
GPGPU

intel

CPU
ãƒªãƒ³ã‚¯
ã€Œå›½å†…æœ€é€Ÿã€ã‚¹ãƒ‘ã‚³ãƒ³3800ä¸‡ã€€é–‹ç™ºã®ã‚ã‚Šæ–¹ã‚ãã‚Šè°è«–ã¯å¿…è‡³
è¡Œæ”¿åˆ·æ–°ä¼šè°ã®äº‹æ¥ä»•åˆ†ã‘ã§ã€æ¬¡ä¸–ä»£ã‚¹ãƒ¼ãƒ‘ãƒ¼ã‚³ãƒ³ãƒ”ãƒ¥ãƒ¼ã‚¿ãƒ¼ï¼ˆã‚¹ãƒ‘ã‚³ãƒ³ï¼‰ã®é–‹ç™ºäºˆç®—ãŒã€Œå¤§å¹…å‰Šæ¸›ã€ã¨åˆ¤å®šã•ã‚ŒãŸã“ã¨ãŒæ³¢ç´‹ã‚’å‘¼ã¶ä¸ã€é•·å´Žå¤§å¦ãªã©ã®ç ”ç©¶ãƒãƒ¼ãƒ ãŒå›½å†…æœ€é€Ÿã®ã‚¹ãƒ‘ã‚³ãƒ³ã‚’é–‹ç™ºã—ã€Œã‚¹ãƒ‘ã‚³ãƒ³ã®ãƒŽãƒ¼ãƒ™ãƒ«è³žã€ã¨ã‚‚å‘¼ã°ã‚Œã‚‹è³žã‚’å—è³žã—ãŸã€‚é©šãã¹ãã¯ãã®é–‹ç™ºè²»ç”¨ã§ã€ã‚ãšã‹3800ä¸‡å††ã€‚é€šå¸¸ã¯é–‹ç™ºã«æ•°ç™¾å„„å˜ä½ã«è²»ç”¨ãŒå¿…è¦ã¨ã•ã‚Œã‚‹ã‚¹ãƒ‘ã‚³ãƒ³é–‹ç™ºã®ã‚ã‚Šæ–¹ã‚’ã‚ãã‚Šã€è°è«–ãŒèµ·ã“ã‚‹ã“ã¨ã«ãªã‚Šãã†ã ã€‚ ã€Œæ—¥æœ¬æœ€é€Ÿã€ã‚’è¨˜éŒ²ã—ãŸã‚¹ãƒ‘ã‚³ãƒ³ã¯ã€é•·å´Žå¤§å¦å·¥å¦éƒ¨ã®æµœç”°å‰›åŠ©æ•™ã‚’ä¸å¿ƒã¨ã™ã‚‹ã‚°ãƒ«ãƒ¼ãƒ—ãŒé–‹ç™ºã€‚158ãƒ†ãƒ©ãƒ•ãƒãƒƒãƒ—ã‚¹ï¼ˆ1ç§’ã«158å…†å›žè¨ˆç®—ï¼‰ã¨ã„ã†æ€§èƒ½ã‚’å®Ÿç¾ã—ãŸã€‚ã“ã‚Œã¾ã§ã®å›½å†…æœ€é€Ÿã¯ã€NECãŒæµ·æ´‹ç ”ç©¶æ©Ÿæ§‹ã«ç´å…¥ã—ãŸã€Œåœ°çƒã‚·ãƒŸãƒ¥ãƒ¬ãƒ¼ã‚¿ã‚·ã‚¹ãƒ†ãƒ ã€ã®122.4ãƒ†ãƒ©ãƒ•ãƒãƒƒãƒ—ã‚¹ã€‚ä»Šå›žã®è¨˜éŒ²ã¯ã“ã‚Œã‚’ä¸Šå›žã‚‹ã‚‚ã®ã ã€‚ ã€Œã‚¹ãƒ‘ã‚³ãƒ³ã®ãƒŽãƒ¼ãƒ™ãƒ«è³žã€ã‚’å—è³ž 11æœˆ20æ—¥ã¾ã§ç±³ã‚ªãƒ¬ã‚´ãƒ³å·žã§é–‹ã‹ã‚Œã¦ã„ãŸå›½éš›å¦ä¼šã€Œã‚¹ãƒ¼ãƒ‘ãƒ¼ã‚³ãƒ³ãƒ”ãƒ¥ãƒ¼ãƒ†ã‚£ãƒ³ã‚°2009ã€ã§ã¯ã€ã€Œ
Gln 2009/11/28
HPC

GPU

GPGPU
ãƒªãƒ³ã‚¯
ã€å¾Œè—¤å¼˜èŒ‚ã®Weeklyæµ·å¤–ãƒ‹ãƒ¥ãƒ¼ã‚¹ã€‘ NVIDIA Fermiã®ãƒžãƒ«ãƒã‚¹ãƒ¬ãƒƒãƒ‡ã‚£ãƒ³ã‚°ã‚¢ãƒ¼ã‚ãƒ†ã‚¯ãƒãƒ£
Gln 2009/11/06
GPGPU

NVIDIA

Fermi
ãƒªãƒ³ã‚¯
ã€å¾Œè—¤å¼˜èŒ‚ã®Weeklyæµ·å¤–ãƒ‹ãƒ¥ãƒ¼ã‚¹ã€‘ NVIDIAãŒç›®æŒ‡ã™ç©¶æ¥µã®ãƒ—ãƒã‚»ãƒƒã‚µã¸ã¨é€²ã‚€ã€ŒFermiã€ã‚¢ãƒ¼ã‚ãƒ†ã‚¯ãƒãƒ£
Gln 2009/10/24
NVIDIA

GPGPU

HPC
ãƒªãƒ³ã‚¯
NVIDIAã€ŒOptiXã€ã‚¨ãƒ³ã‚¸ãƒ³ç™ºè¡¨ã€GPUã§ãƒ¬ã‚¤ãƒˆãƒ¬ãƒ¼ã‚·ãƒ³ã‚°ã‚’é«˜é€Ÿå‡¦ç† | ãƒ‘ã‚½ã‚³ãƒ³ | ãƒžã‚¤ã‚³ãƒŸã‚¸ãƒ£ãƒ¼ãƒŠãƒ«
ç±³NVIDIAã¯8æœˆ4æ—¥ (ç¾åœ°æ™‚é–“)ã€Siggraph 2009ã«ãŠã„ã¦ã€ãƒ¬ã‚¤ãƒˆãƒ¬ãƒ¼ã‚·ãƒ³ã‚°ãƒ»ã‚¨ãƒ³ã‚¸ãƒ³ã€ŒOptiXã€ã‚’ç™ºè¡¨ã—ãŸã€‚ã‚½ãƒ•ãƒˆã‚¦ã‚¨ã‚¢é–‹ç™ºè€…å‘ã‘ã‚¢ãƒ—ãƒªã‚±ãƒ¼ã‚·ãƒ§ãƒ³ãƒ»ã‚¢ã‚¯ã‚»ãƒ©ãƒ¬ãƒ¼ã‚·ãƒ§ãƒ³ãƒ»ã‚¨ãƒ³ã‚¸ãƒ³ç¾¤ã®1ã¤ã§ã€åŒã‚¹ã‚¤ãƒ¼ãƒ„ã«ã¯ä»–ã«ã€ŒSceniXã€ã€ŒCompleXã€ã€ŒPhysX 64-bitã€ãªã©ã®ã‚¨ãƒ³ã‚¸ãƒ³ãŒå«ã¾ã‚Œã‚‹ã€‚ ãƒ¬ã‚¤ãƒˆãƒ¬ãƒ¼ã‚·ãƒ³ã‚°ã¯ã€3Dã‚°ãƒ©ãƒ•ã‚£ãƒƒã‚¯ã‚¹ã«ãŠã„ã¦ã€æ˜ åƒé¢ã®å…¨ã¦ã®ãƒ”ã‚¯ã‚»ãƒ«ã‚’é€šéŽã—ã¦è¦–ç‚¹ã«ã¨ã©ãå…‰ç·šã‚’ãƒˆãƒ¬ãƒ¼ã‚¹ã™ã‚‹ãƒ¬ãƒ³ãƒ€ãƒªãƒ³ã‚°æ‰‹æ³•ã ã€‚è¦–ç‚¹ã‚„å…‰æºã®ä½ç½®ã«åŸºã¥ãã€ã‚ªãƒ–ã‚¸ã‚§ã‚¯ãƒˆã®è¡¨é¢ã®åå°„ã‚„å±ˆæŠ˜ã€é™°å½±ã€é€æ˜Žåº¦ãªã©ã‚’ç´°ã‹ãåæ˜ ã•ã›ãŸé«˜å“è³ªãªæç”»ã‚’å®Ÿç¾ã™ã‚‹ã€‚ãŸã ã—ãƒ”ã‚¯ã‚»ãƒ«ã”ã¨ã«å…‰ç·šçµŒè·¯ã‚’ãŸã©ã‚‹ãŸã‚è¨ˆç®—é‡ãŒè†¨å¤§ã«ãªã‚Šã€å‡¦ç†ã«æ™‚é–“ãŒã‹ã‹ã‚‹ã®ãŒãƒ‡ãƒ¡ãƒªãƒƒãƒˆã ã£ãŸã€‚ OptiXã‚¨ãƒ³ã‚¸ãƒ³ã¯Cè¨€èªžã‚’ç”¨ã„ã¦ãƒ—ãƒã‚°ãƒ©ãƒŸãƒ³ã‚°ã§ãã‚‹ãƒ¬ã‚¤ãƒˆãƒ¬ãƒ¼ã‚·ãƒ³ã‚°ãƒ»ãƒ‘ã‚¤ãƒ—ãƒ©ã‚¤ãƒ³ã ã€‚NVIDIAã¯ã€Œä¸–ç•Œåˆã®ã‚¤ãƒ³ã‚¿ãƒ©ã‚¯ãƒ†ã‚£ãƒ–ãƒ»ãƒ¬ã‚¤ãƒˆ
Gln 2009/08/09
ãƒ¬ã‚¤ãƒˆãƒ¬ãƒ¼ã‚·ãƒ³ã‚°ãƒ»ã‚¨ãƒ³ã‚¸ãƒ³ã€ŒOptiXã€ã‚’ç™ºè¡¨ã—ãŸã€‚ã‚½ãƒ•ãƒˆã‚¦ã‚¨ã‚¢é–‹ç™ºè€…å‘ã‘ã‚¢ãƒ—ãƒªã‚±ãƒ¼ã‚·ãƒ§ãƒ³ãƒ»ã‚¢ã‚¯ã‚»ãƒ©ãƒ¬ãƒ¼ã‚·ãƒ§ãƒ³ãƒ»ã‚¨ãƒ³ã‚¸ãƒ³ç¾¤ã®1ã¤ã§ã€åŒã‚¹ã‚¤ãƒ¼ãƒ„ã«ã¯ä»–ã«ã€ŒSceniXã€ã€ŒCompleXã€ã€ŒPhysX 64-bitã€ãªã©ã®ã‚¨ãƒ³ã‚¸ãƒ³ãŒå«ã¾ã‚Œã‚‹ã€‚

3D

gpgpu

NVIDIA

GPU

graphics
ãƒªãƒ³ã‚¯
ã€è¥¿å·å’Œä¹…ã®ä¸å®šæœŸã‚³ãƒ©ãƒ ã€‘ GPGPU/CUDAã§å¿«é©å‹•ç”»ç·¨é›†å…¥é–€
Gln 2009/05/19
GPU

gpgpu

cuda

å‹•ç”»

å‹•ç”»ç·¨é›†
ãƒªãƒ³ã‚¯
å¾Œè—¤å¼˜èŒ‚ã®Weeklyæµ·å¤–ãƒ‹ãƒ¥ãƒ¼ã‚¹
â—äººæã‚’å¼•ãå…¥ã‚Œã¦å¤‰èº«ã‚’ç¹°ã‚Šè¿”ã™NVIDIA NVIDIAã®æŠ€è¡“çš„ãªæ–¹å‘æ€§ã¯ã€åŒç¤¾ã«ã©ã‚“ãªäººç‰©ãŒåŠ ã‚ã£ãŸã‹ã«ã‚ˆã£ã¦ã‚ã‹ã‚‹ã€‚NVIDIA GPUã®æœ€å¤§ã®è»¢æ©Ÿã¨ãªã£ãŸã€ŒGeForce 8800(G80)ã€ã®èƒŒå¾Œã«ã¯ã€ä¸¦åˆ—ã‚³ãƒ³ãƒ”ãƒ¥ãƒ¼ã‚¿ã®ã‚¢ãƒ¼ã‚ãƒ†ã‚¯ãƒˆã§ã‚ã‚‹John Nickolls(ã‚¸ãƒ§ãƒ³ãƒ»ãƒ‹ã‚³ãƒ«ã‚º)æ°(ç¾Director of Architecture, Nvidia)ãŒã„ãŸã€‚Nickollsæ°ã¯ã€è¶…ä¸¦åˆ—SIMD(Single Instruction, Multiple Data)ã‚¹ãƒ¼ãƒ‘ãƒ¼ã‚³ãƒ³ãƒ”ãƒ¥ãƒ¼ã‚¿ã€ŒMasPar Computerã€ã®ã‚¢ãƒ¼ã‚ãƒ†ã‚¯ãƒˆã ã£ãŸäººç‰©ã€‚MasParã®ã‚¢ãƒ¼ã‚ãƒ†ã‚¯ãƒãƒ£ã‚’ã€éƒ¨åˆ†çš„ã«GPUã«æŒã¡è¾¼ã‚“ã ã€‚ã€Œ(MasParã¨G80ã«ã¯)é•ã†éƒ¨åˆ†ã‚‚è‰²ã€…ã‚ã‚‹ãŒã€å…ƒã«ãªã£ã¦ã„ã‚‹ã‚¢ã‚¤ãƒ‡ã‚¢ã¯éžå¸¸ã«ä¼¼ã¦ã„ã‚‹ã€ã¨Nickollsè‡ªèº«ã‚‚èªžã£ã¦ã„ãŸã€‚ NVIDIAã®äººæé›†ã‚ã¯GPUãƒãƒ¼ãƒ‰çµ¡ã¿ã ã‘ã§ã¯ãª
Gln 2009/02/11
GPU

gpgpu

NVIDIA

parallel
ãƒªãƒ³ã‚¯
AMDã€ATI Streamã®å±•é–‹ã‚’è§£èª¬
12æœˆ16æ—¥ å®Ÿæ–½ æ—¥æœ¬AMDæ ªå¼ä¼šç¤¾ã¯16æ—¥ã€åŒç¤¾ã®GPUã‚³ãƒ³ãƒ”ãƒ¥ãƒ¼ãƒ†ã‚£ãƒ³ã‚°ãƒ—ãƒ©ãƒƒãƒˆãƒ•ã‚©ãƒ¼ãƒ ã€ŒATI Streamã€ã®ç¾çŠ¶ã¨ã€ä»Šå¾Œã®å±•é–‹ã«ã¤ã„ã¦è§£èª¬ã—ãŸã€‚ä»Šå›žã®å†…å®¹ã¯ã™ã§ã«ç±³å›½ã§ç™ºè¡¨æ¸ˆã¿ã ãŒã€å›½å†…ã§ã¯åˆã‚ã¦ã®èª¬æ˜Žã¨ãªã‚‹ã€‚ ATI Streamã¨ã¯ã€AMDè£½GPUã§GPUã‚³ãƒ³ãƒ”ãƒ¥ãƒ¼ãƒ†ã‚£ãƒ³ã‚°ã‚’è¡Œãªã†ãŸã‚ã®ãƒ—ãƒ©ãƒƒãƒˆãƒ•ã‚©ãƒ¼ãƒ ã§ã€NVIDIAãŒCUDAã§å®Ÿç¾ã—ã¦ã„ã‚‹ã®ã¨åŒã˜ã‚ˆã†ã«ã€Radeonã‚·ãƒªãƒ¼ã‚ºã§æ±Žç”¨ã®æ¼”ç®—ãŒã§ãã‚‹ã‚ˆã†ã«ãªã‚‹ã€‚ AMDã§ã¯ã€ãã®é–‹ç™ºãƒ—ãƒ©ãƒƒãƒˆãƒ•ã‚©ãƒ¼ãƒ ã¨ãªã‚‹ATI Stream SDKã‚’é–‹ç™ºè€…å‘ã‘ã«å…¬é–‹ã€‚ã¾ãŸã€12æœˆã«å…¬é–‹ã•ã‚ŒãŸGPUãƒ‰ãƒ©ã‚¤ãƒã€ŒCatalystã€ã«ã€ATI Streamã¸ã®å¯¾å¿œã‚’è¿½åŠ ã™ã‚‹ã¨ã¨ã‚‚ã«ã€ATI Streamä¸Šã§å‹•ä½œã™ã‚‹å‹•ç”»ã‚³ãƒ³ãƒãƒ¼ãƒˆãƒ„ãƒ¼ãƒ«ã€ŒAvivo Video Converterã€ã‚’ç„¡å„Ÿã§é…å¸ƒé–‹å§‹ã—ãŸã€‚ ç±³AMDã‚°ãƒ©ãƒ•ã‚£ãƒƒã‚¯ãƒ—ãƒãƒ€ã‚¯ãƒˆãƒ»ã‚°ãƒ«ãƒ¼ãƒ— ã‚½ãƒ•ãƒˆ
Gln 2008/12/18
AMD

CPU

GPU

gpgpu

OpenCL
ãƒªãƒ³ã‚¯
1 2 æ¬¡ã®ãƒšãƒ¼ã‚¸