BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:The 2nd NSTCCore Computing Service User Training Workshop in 2026:
  AI Applications with AMD
DTSTART;VALUE=DATE-TIME:20260527T010000Z
DTEND;VALUE=DATE-TIME:20260527T070000Z
DTSTAMP;VALUE=DATE-TIME:20260718T143500Z
UID:indico-event-73@indico4.twgrid.org
CONTACT:dicos-support@twgrid.org
DESCRIPTION:2026年 NSTCCore 高效能核心科學計算服務第二場教
 育訓練工作坊：AI應用（邀請AMD技術分享） \n\n2026年度第
 二場 「NSTCCore 高效能核心科學計算服務教育訓練工作坊
 」 將在 2026年 5 月 27 日（三） 於 中央研究院物理研
 究所（台北）舉行。本工作坊由  國科會高效能核心科學
 計算服務計畫 支持，並由 中央研究院物理研究所網格
 計算中心（ASGC）執行， 特別感謝 超微半導體 參與技術
 分享。\n\n本次特別邀請 超微半導體（AMD）講者，分享 AI
  與高效能運算（HPC）之發展趨勢，協助研究團隊掌握最
 新技術與應用方向。\n\n誠摯邀請各大專院校與研究機構
 ，具科學計算與大數據分析需求的團隊踴躍參加。\n\n活
 動重點\n\n\n	協助研究團隊便利使用 NSTCCore 核心計算服務
 \n	AI／HPC 發展趨勢與產業觀點\n	跨 CPU／GPU／NPU 平台之 LL
 M 應用與部署\n	促進產學交流與跨領域合作機會\n\n\n活動
 資訊\n\n\n	時間：2026 年 5 月 27 日（三）上午 9:00 ~ 下午 1
 :30\n	地點：台北中央研究院物理研究所 1F 演講廳\n	報名
 （5月24日截止）：https://indico4.twgrid.org/event/73/registrations/
 36/\n	問卷（5月27日開放）：https://indico4.twgrid.org/event/73/su
 rveys/13\n\n\n課程內容\n\n\n	高效能計算服務內容介紹\n	。
 資源現況與合作模式\n	。計算與儲存服務內容\n	。使用
 者應用案例展示\n	 \n	基礎實作訓練\n	。SLURM 與 DiCOSApp 
 計算服務操作（Batch 模式與 SaaS 模式）\n	。資料儲存服
 務與操作示範\n	 \n	AI 主題技術分享（AMD 講者）\n	。AI 
 與高效能運算（HPC）趨勢及從資料中心到邊緣端的技術
 演進\n	。基於 GPU 之 AI 訓練與加速技術（ROCm 最佳化）及
 異質運算實務應用\n	。跨 CPU／GPU／NPU 平台之 LLM 部署方
 法與產業實務案例分享\n\n\n注意事項\n\n\n	本次活動以中
 文為主，簡報資料提供中／英文版。\n	活動開放線上參
 與，報名時請選擇「線上參與」選項，連結將於會前寄
 送至報名者信箱。\n	受限於當天場地的網路環境，現場
 實作演練將以講者示範操作為主。本次仍將提供測試帳
 號，會前將統一寄送至報名者所填寫之電子郵件信箱；
 另亦可於現場提供，供與會者於會後使用。測試帳號之
 有效期限為 7 天。\n	為教學、推廣及成果報告用途，活
 動將進行錄音、錄影及拍照，若不希望入鏡或被錄音，
 請關閉攝影機與麥克風。\n	為響應一次用產品減量，鼓
 勵所有實體與會者自備環保杯與環保餐具。\n\n\n如有任
 何疑問，請來信 dicos-support@twgrid.org，期待與您在工作坊
 相見！\n\n\nThe 2nd NSTCCore Computing Service User Training Workshop i
 n 2026: AI Applications (AMD Technical Session)\n\nThe second NSTCCore Hig
 h-Performance Computing (HPC) User Training Workshop of 2026 will be held
  on Wednesday\, May 27\, 2026\, at Institute of Physics\, Academia Sinica\
 , Taipei. This workshop is supported by the NSTCCore HPC Service Project 
 and organized by the Academia Sinica Grid Computing Centre (ASGC)\,  with
  the technical contribution of Advanced Micro Devices\, Inc. (AMD). \n\nT
 his workshop will feature an invited talk by AMD on AI and HPC trends\, of
 fering insights into emerging technologies and real-world applications.\n\
 nWe sincerely invite research teams from universities and research institu
 tes with needs in scientific computing and big data analysis to actively p
 articipate in this event.\n\nWorkshop Highlights\n\n\n	Overview of the NST
 CCore program\, services\, resources\, and collaboration models.\n	Industr
 y insights on AI and HPC trends.\n	Efficient LLM deployment and inference 
 across CPU\, GPU\, and NPU platforms.\n	Foster collaboration and knowledge
  exchange between academia and industry.\n\n\nEvent Information\n\n\n	Date
  & Time: 9:00AM ~ 1:30PM\, Wednesday\, May 27\, 2026\n	Venue: 1F Auditor
 ium\, Institute of Physics\, Academia Sinica\, Taipei\n	Registration (Dead
 line: May 24): https://indico4.twgrid.org/event/73/registrations/36/\n	Que
 stionnaire (Open on May 27): https://indico4.twgrid.org/event/73/surveys
 /13\n\n\nProgram\n\n\n	Introduction to HPC Services\n	。Overview of resou
 rces and collaboration models\n	。Computing and storage service features\
 n	。User case demonstrations\n	 \n	Hands-on Training\n	。Practical intr
 oduction to SLURM & DiCOSApp (Batch and SaaS modes)\n	。Data storage serv
 ices and transfer demonstrations\n	 \n	AI Technical Session (Invited Spea
 ker from AMD) \n	。AI & HPC trends and datacenter-to-edge evolution\n	。
 GPU-based AI training and acceleration (ROCm optimization)\n	。LLM deploy
 ment across CPU/GPU/NPU with industry use cases\n\n\nNotes\n\n\n	The works
 hop will be conducted primarily in Chinese\, with presentation materials p
 rovided in Chinese or English.\n	Online participation is available. Please
  select the “Online Participation” option when registering. The access
  link will be sent to each participant’s registered email address prior 
 to the event.\n	Due to network limitations at the venue\, the hands-on ses
 sion will be conducted primarily as a live demonstration by the speaker. T
 est accounts will still be provided and sent to each participant’s regi
 stered email address before the event\, or distributed on-site for post-e
 vent use. Each test account will be valid for 7 days.\n	This event will be
  recorded (audio and video) and photographed for training\, outreach and r
 eporting purposes. If you prefer not to be recorded\, please turn off your
  camera and microphone.\n	To support our efforts in reducing the use of di
 sposable products\, all in-person attendees are encouraged to bring their 
 own reusable cups and cutlery.\n\n\nFor inquiries\, please contact us at d
 icos-support@twgrid.org. We sincerely look forward to your participation!\
 n\n \n\n \nhttps://indico4.twgrid.org/event/73/
LOCATION:1F Auditorium  (Institute of Physics\, Academia Sinica)
URL:https://indico4.twgrid.org/event/73/
END:VEVENT
END:VCALENDAR
