本網站使用瀏覽器紀錄 (Cookies) 來提供您最好的使用體驗，我們使用的 Cookie 也包括了第三方 Cookie。相關資訊請訪問我們的隱私權與 Cookie 政策。如果您選擇繼續瀏覽或關閉這個提示，便表示您已接受我們的網站使用條款。 關閉
華碩今發表多款搭載AMD EPYC™ 9005系列處理器的伺服器，勢為AI資料中心的各項工作負載處理表現，奠下全新效能與密度標竿；其中包括支援AMD Instinct™ MI325X加速器的ESC A8A-E12U，還有具備8顆GPU訓練大規模AI模型的 ESC8000A-E13P，以及針對EDA與雲端運算所需的RS520QA-E13，再加上RS720A / 700A-E13和RS521A / 501A等多工作業處理的利器，將以極致效能勝任多元應用程式運算，滿足最嚴峻挑剔的使用需求。 採用Zen5架構的AMD EPYC 9005系列處理器，擁有高達192個核心／384個執行緒及高達5 GHz的頻率，是專為AI資料中心所量身打造的劃時代產品；同時，其憑藉領先業界的vCPU密度，並結合最完善的運算與AI功能，無時無刻皆可呈獻無與倫比的AI推論效能；此外，用戶還能輕鬆整合於既有的x86基礎架構，就算資料中心需轉換或遷移，亦確保系統持續運作不中斷，達最高效率。 AMD企業與HPC事業群全球副總裁John Morris 表示，「第五代AMD EPYC處理器和最新的AMD Instinct MI325X加速器足以因應AI資料中心所需的運算力，搭配先進且豐富的產品組合，是企業在快速變遷的時代洪流中，啟動數位轉型升級的完美夥伴。」 AI 伺服器：ESC A8A-E12U、ESC8000A-E13P 搭載8顆GPU的ASUS ESC A8A-E12U、ESC8000A-E13P，是針對平行運算與彈性網路功能而設計的伺服器，其中ESC A8A-E12U採用7U尺寸、雙AMD EPYC 9005 系列處理器，支援AMD Instinct™ MI325X加速器，並具備GPU至GPU雙向直接互連技術，可提供高達6 TB/s頻寬，有效擴充大型AI模型與HPC工作負載。而ESC8000A-E13P除同樣內建強大的AMD EPYC處理器，以及充裕的記憶體容量，亦配有NVIDIA 資料中心等級顯卡，完全相容NVIDIA® MGX架構，透過NVIDIA OVE與NIM服務，就能快速建立專用執行個體、促進模擬與訓練、實現即時協作，擴充基礎架構，將生成式人工智慧帶到更多應用場域！ 可擴充的多節點伺服器：RS520QA-E13 為電子設計自動化與雲端運算而生的ASUS RS520QA-E13，搭載AMD EPYC 9005 系列處理器，且兼具優異的記憶體擴充力，可支援每個節點12+8 DIMM配置，達到1DPC 6,000 MT/s、2DPC 4,400 MT/s的疾速傳輸；創新的前面板設計，使用規劃更加靈活，搭配符合人體工學的把手與無工具支架，維護保養事半功倍；此外，RS520QA-E13散熱表現卓越，效率絕佳的氣冷解決方案還支援高達400W的處理器，是迎戰嚴苛工作負載的不二首選。 通用伺服器：RS700A / 720A-E13、RS521A / 501A-E12 ASUS RS700A / 720A-E13配備AMD EPYC 9005系列處理器及192個核心，最多可支援24個DIMM，CPU TDP高達500W；其中RS720A-E13採用GPU最佳化設計，能容納24顆全閃存Gen5 NVMe固態硬碟和3個雙插槽GPU，非常適用於AI或HPC，其訓練有素的模型和精確預測力，可妥善處理即時產生的各式資料。而RS700A-E13至多能支援12顆全閃存NVMe固態硬碟，並擁有更高的頻寬，無論何種工作負載皆游刃有餘。 可實現最佳能源使用效率(PUE)與總體擁有成本(TCO)的ASUS RS521A / 501A-E12，內建AMD EPYC 9005系列處理器，且擴展性極高，不僅能充分滿足現代資料中心日益增長的需求，亦可為日常業務運營錦上添花；再加上出眾的內存功能和多樣化儲存選項，將能加速雲端、本地數據中心，以及混合雲環境中的作業優化。
全新Supermicro系統可幫助客戶實現資料中心升級，進而更順暢地運行AI工作負載 加州聖荷西2024年10月16日 /美通社/ -- Supermicro, Inc.（納斯達克股票代碼：SMCI）作為AI/ML、HPC、雲端、儲存和5G/邊緣領域的全方位IT解決方案提供企業，宣布推出搭載AMD EPYC™ 9005系列處理器和AMD Instinct™ MI325X GPU的全新伺服器、GPU加速系統與儲存伺服器系列。全新H14產品系列為業界內機種最廣泛的伺服器系列之一，此系列包含Supermicro的Hyper系統、Twin多節點伺服器和AI推論GPU系統，且這些機種皆可搭配氣冷或液冷散熱技術。新型「Zen5」處理器核心架構使用了具有完整資料路徑的AVX-512向量指令，支援基於CPU的AI推論，且每週期指令數（IPC）比先前第四代EPYC處理器提升17%，使每核心的效能更為優異。 100124-AMD Supermicro的H14系列採用最新第五代AMD EPYC處理器，每個CPU最多搭載192個核心，且散熱設計功率（TDP）最高可達500W。新型H14系列包含Hyper和FlexTwin™系統，可因應更高的散熱需求。該系列也包含三個適用於AI訓練於推論工作負載的系統，最多可支援10個GPU，並以AMD EPYC 9005系列CPU作為主要處理器。此外，H14系列也具有兩個支援AMD Instinct MI325X GPU的系統。 Supermicro總裁暨執行長梁見後表示：「相較於採用第二代EPYC 7002系列CPU的Supermicro H11系統，搭載EPYC 9005 64核心CPU的Supermicro H14伺服器在SPECrate®2017_fp_base的效能表現註1上提升了2.44倍。此大幅度的效能改善使客戶可將資料中心總佔用空間縮減至少三分之二註2，同時增加新的AI運算性能，進一步提升資料中心能源效率。憑藉Supermicro的液冷和氣冷技術、多元系統設計，以及經驗證的建構組件解決方案，H14伺服器系列能夠提供最高的效能、密度和能源效率。」 如需 Supermicro H14 產品系列的詳細資訊，請瀏覽：www.supermicro.com/aplus AMD執行副總裁暨資料中心解決方案事業群總經理Forrest Norrod表示：「Supermicro的『Building Block解決方案』使其能夠持續使基於AMD架構的解決方案快速上市，並涵蓋多種極具吸引力的系統設計。我們與Supermicro合作，運用其全球內部工程設計和製造能力，再結合他們的氣冷和液冷系統機架級整合技術，可在任何規模上使客戶透過AMD EPYC CPU和Instinct GPU快速實現價值。」 Supermicro的 H14伺服器陣容包含以下產品系列： Hyper - Supermicro的旗艦級企業伺服器，可支援兩個EPYC 9005 CPU，每個CPU最多包含192 個核心，並具有500W的功率，同時可透過24個DIMM插槽支援最高9TB記憶體，提供最高的效能。Hyper包括配備最高12個2.5吋NVMe/SATA磁碟機槽的1U機箱，或配備最高24個2.5吋NVMe/SATA磁碟機槽的2U機箱，採用先進的散熱設計，可容納最高效能的CPU，適用於需求嚴苛的AI推論、企業或雲端工作負載。 CloudDC - 此多功能系統經過最佳化設計，適用於雲端資料中心，並在1U規格的機殼內搭載單一EPYC 9005 CPU，具有最高12個2.5吋NVMe/SATA硬碟機槽。此系統採用OCP（開放運算平台）DC-MHS 規格（資料中心模組化硬體系統）技術，確保與OCP標準相容。 GrandTwin™ - GrandTwin為4節點運算平台，將單一EPYC 9005 CPU容納到高密度2U外形規格內。此系統經常用於物件儲存、虛擬化、高效能運算應用等多伺服器叢集應用。 FlexTwin™ - FlexTwin是一款2U 4節點高效能、高密度運算系統，其中每個節點具有雙EPYC 9005 CPU。此系統採用先進液冷技術，可實現高能源效率，且能使最高效能的 EPYC 9005 CPU順暢運行，適用於高效能運算、EDA和其他需求嚴苛的工作負載。 5U GPU 系統 - Supermicro搭載 EPYC CPU的5U PCIe GPU系統最多支援10個雙寬加速器，適合設計與視覺化應用。 4U GPU 系統（液冷） - 搭載EPYC CPU的高密度8路加速器平台，使用先進的液冷技術，在最緊湊的4U外形規格內支援OAM加速器，專為高效能AI和高效能運算應用所設計。 8U GPU 系統 - 此8路加速器系統使用AMD Instinct MI325X GPU及EPYC 9005 CPU，適用於大規模的LLM AI訓練。其8U機箱可被部署在任何氣冷資料中心內。 搭載AMD EPYC CPU的Supermicro H14產品現已可供客戶透過Supermicro JumpStart計畫進行測試。 Supermicro已於2024年10月10日在舊金山 Moscone中心舉行的AMD Advancing AI Day上展示了全新H14解決方案。 註1 Supermicro A+ Server 2023US-TR4搭配兩個AMD EPYC 7702 64核心CPU，在 SPECrate®2017_fp_base測試中得分為485（https://www.spec.org/cpu2017/results/res2020q1/cpu2017-20200204-20866.html，資料擷取日期為2024年10月2日），對照搭配兩個AMD EPYC 9555 64核心CPU的Supermicro AS-2126HS-TN，於SPECrate®2017_fp_base測試中得分為1670。搭載9555 CPU的AS-2126HS-TN結果已於2024年10月10日在www.spec.org/cpu2017/results上發布。 註2根據註（1）所述的SPECrate®2017_fp_base測試比較，使用搭載9555 CPU的AS-2126HS-TN與搭載7702 CPU的2023US-TR4相比，系統數量減少了70.9%。 關於Super Micro Computer, Inc. Supermicro（納斯達克股票代碼：SMCI）為應用最佳化全方位IT解決方案的全球領導者。Supermicro的成立據點及營運中心位於美國加州聖荷西，致力為企業、雲端、AI和5G電信/邊緣IT基礎架構提供領先市場的創新技術。我們是全方位IT解決方案製造商，提供伺服器、AI、儲存、物聯網、交換器系統、軟體及支援服務。Supermicro的主機板、電源和機箱設計專業進一步推動了我們的發展與產品生產，為全球客戶實現了從雲端到邊緣的下一代創新。我們的產品皆由企業內部團隊設計及製造（在美國、亞洲及荷蘭），透過全球化營運實現極佳的規模與效率，並藉營運最佳化降低總體擁有成本（TCO），以及經由綠色運算技術減少環境衝擊。屢獲殊榮的Server Building Block Solutions®產品組合，讓客戶可以自由選擇這些具高度彈性、可重複使用且極為多元的建構式組合系統，我們支援各種外形尺寸、處理器、記憶體、GPU、儲存、網路、電源和散熱解決方案（空調、自然氣冷或液冷），因此能為客戶的工作負載與應用提供最佳的效能。 Supermicro、Server Building Block Solutions和We Keep IT Green皆為Super Micro Computer, Inc.的商標和/或註冊商標。 所有其他品牌、名稱和商標皆為其各自所有者之財產。 AS-812GS AS-1116CS AS 2116GT AS-212 AS-5126GS AS-4125GS AS-2126FT
Supermicro, Inc.（納斯達克股票代碼：SMCI）作為AI/ML、HPC、雲端、儲存和5G/邊緣領域的全方位IT解決方案提供企業，宣布推出搭載AMD EPYC™ 9005系列處理器和AMD Instinct™ MI325X GPU的全新伺服器、GPU加速系統與儲存伺服器系列。全新H14產品系列為業界內機種最廣泛的伺服器系列之一，此系列包含Supermicro的Hyper系統、Twin多節點伺服器和AI推論GPU系統，且這些機種皆可搭配氣冷或液冷散熱技術。新型「Zen5」處理器核心架構使用了具有完整資料路徑的AVX-512向量指令，支援基於CPU的AI推論，且每週期指令數（IPC）比先前第四代EPYC處理器提升17%，使每核心的效能更為優異。 Supermicro的H14系列採用最新第五代AMD EPYC處理器，每個CPU最多搭載192個核心，且散熱設計功率（TDP）最高可達500W。新型H14系列包含Hyper和FlexTwin™系統，可因應更高的散熱需求。該系列也包含三個適用於AI訓練於推論工作負載的系統，最多可支援10個GPU，並以AMD EPYC 9005系列CPU作為主要處理器。此外，H14系列也具有兩個支援AMD Instinct MI325X GPU的系統。 Supermicro總裁暨執行長梁見後表示：「相較於採用第二代EPYC 7002系列CPU的Supermicro H11系統，搭載EPYC 9005 64核心CPU的Supermicro H14伺服器在SPECrate®2017_fp_base的效能表現註1上提升了2.44倍。此大幅度的效能改善使客戶可將資料中心總佔用空間縮減至少三分之二註2，同時增加新的AI運算性能，進一步提升資料中心能源效率。憑藉Supermicro的液冷和氣冷技術、多元系統設計，以及經驗證的建構組件解決方案，H14伺服器系列能夠提供最高的效能、密度和能源效率。」 如需 Supermicro H14 產品系列的詳細資訊，請瀏覽：www.supermicro.com/aplus AMD執行副總裁暨資料中心解決方案事業群總經理Forrest Norrod表示：「Supermicro的『Building Block解決方案』使其能夠持續使基於AMD架構的解決方案快速上市，並涵蓋多種極具吸引力的系統設計。我們與Supermicro合作，運用其全球內部工程設計和製造能力，再結合他們的氣冷和液冷系統機架級整合技術，可在任何規模上使客戶透過AMD EPYC CPU和Instinct GPU快速實現價值。」 Supermicro的 H14伺服器陣容包含以下產品系列： Hyper - Supermicro的旗艦級企業伺服器，可支援兩個EPYC 9005 CPU，每個CPU最多包含192 個核心，並具有500W的功率，同時可透過24個DIMM插槽支援最高9TB記憶體，提供最高的效能。Hyper包括配備最高12個2.5吋NVMe/SATA磁碟機槽的1U機箱，或配備最高24個2.5吋NVMe/SATA磁碟機槽的2U機箱，採用先進的散熱設計，可容納最高效能的CPU，適用於需求嚴苛的AI推論、企業或雲端工作負載。 CloudDC - 此多功能系統經過最佳化設計，適用於雲端資料中心，並在1U規格的機殼內搭載單一EPYC 9005 CPU，具有最高12個2.5吋NVMe/SATA硬碟機槽。此系統採用OCP（開放運算平台）DC-MHS 規格（資料中心模組化硬體系統）技術，確保與OCP標準相容。 GrandTwin™ - GrandTwin為4節點運算平台，將單一EPYC 9005 CPU容納到高密度2U外形規格內。此系統經常用於物件儲存、虛擬化、高效能運算應用等多伺服器叢集應用。 FlexTwin™ - FlexTwin是一款2U 4節點高效能、高密度運算系統，其中每個節點具有雙EPYC 9005 CPU。此系統採用先進液冷技術，可實現高能源效率，且能使最高效能的 EPYC 9005 CPU順暢運行，適用於高效能運算、EDA和其他需求嚴苛的工作負載。 5U GPU 系統 - Supermicro搭載 EPYC CPU的5U PCIe GPU系統最多支援10個雙寬加速器，適合設計與視覺化應用。 4U GPU 系統（液冷） - 搭載EPYC CPU的高密度8路加速器平台，使用先進的液冷技術，在最緊湊的4U外形規格內支援OAM加速器，專為高效能AI和高效能運算應用所設計。 8U GPU 系統 - 此8路加速器系統使用AMD Instinct MI325X GPU及EPYC 9005 CPU，適用於大規模的LLM AI訓練。其8U機箱可被部署在任何氣冷資料中心內。 搭載AMD EPYC CPU的Supermicro H14產品現已可供客戶透過Supermicro JumpStart計畫進行測試。 Supermicro已於2024年10月10日在舊金山 Moscone中心舉行的AMD Advancing AI Day上展示了全新H14解決方案。 註1 Supermicro A+ Server 2023US-TR4搭配兩個AMD EPYC 7702 64核心CPU，在 SPECrate®2017_fp_base測試中得分為485（https://www.spec.org/cpu2017/results/res2020q1/cpu2017-20200204-20866.html，資料擷取日期為2024年10月2日），對照搭配兩個AMD EPYC 9555 64核心CPU的Supermicro AS-2126HS-TN，於SPECrate®2017_fp_base測試中得分為1670。搭載9555 CPU的AS-2126HS-TN結果已於2024年10月10日在www.spec.org/cpu2017/results上發布。 註2根據註（1）所述的SPECrate®2017_fp_base測試比較，使用搭載9555 CPU的AS-2126HS-TN與搭載7702 CPU的2023US-TR4相比，系統數量減少了70.9%。
AMD宣布推出第4代AMD EPYC嵌入式8004系列處理器，擴展EPYC™嵌入式處理器持續樹立業界標準的領先地位，為網路、儲存和工業應用提供卓越的效能、效率、連接性與創新。 AMD EPYC嵌入式8004系列處理器專為運算密集型嵌入式系統所設計，可為高需求工作負載提供卓越效能，同時以緊湊的尺寸規格為空間和功率受限型應用最大程度地提升能源效率，並整合一套全面的嵌入式功能，以進一步增強系統效能與可靠性。AMD EPYC嵌入式8004系列專為在最嚴苛的嵌入式環境中提供出色效能而打造，非常適合網路系統、路由器、安全設備、企業和雲端暖／冷儲存以及工業邊緣應用，確保無縫處理動態工作負載。 突破性效能與能效 AMD EPYC嵌入式8004系列處理器憑藉AMD “Zen 4c”核心的優勢，實現全新水平的核心密度和每瓦效能。EPYC嵌入式8004是AMD嵌入式產品組合中首款整合這些核心的處理器系列，為平台效率和創新樹立了全新標杆，讓硬體供應商能夠設計差異化的節能平台，較上一代（“Zen 3”）帶來高達30%的每瓦效能提升註1。 AMD EPYC嵌入式8004系列處理器提供1P配置，從12到64核心（24至128執行緒），支援最高1.152TB DDR5記憶體容量（每通道2個DIMM，DIMM為96GB），熱設計功耗（TDP）範圍從70瓦至225瓦，旨在滿足多樣化應用需求。 豐富的I/O和功能整合於緊湊的空間 AMD EPYC嵌入式8004系列處理器經過精心設計，藉由高速I/O連接性（96通道PCIe® Gen 5）和擴展的記憶體頻寬（6通道DDR5-4800），可輕鬆處理資料密集型工作負載。這些功能使系統設計人員能夠輕鬆連接SSD、網卡和更多元件，以組建靈活且可擴展的系統組態。 AMD EPYC嵌入式8004系列處理器採用緊湊型SP6插槽尺寸規格，比AMD EPYC嵌入式9004系列處理器小了19%註2，佔用空間更少同時節能。這些裝置享有長達7年的生命週期支援，可助力系統設計人員維持平台使用壽命。 增強的嵌入式功能 AMD EPYC嵌入式8004系列處理器在資料傳輸能力、系統可靠性和資料保存方面表現出色，主要整合的功能包括： 直接記憶體存取（第4代AMD EPYC DMA）：旨在通過卸載CPU的資料傳輸提升系統效率和效能，使核心能夠專注於關鍵應用任務。 非透明橋接（NTB）：通過PCI Express（PCIe®）在雙主動式（active-active）配置中實現兩個CPU之間的資料交換，從而增強系統可靠性，確保在發生故障時仍能繼續運行。 DRAM更新至NVMe：斷電時將關鍵資料從DRAM更新至NVMe，協助確保關鍵資料得以保存。 雙SPI支援：支援使用兩個SPI ROM，一個用於BIOS，另一個用於安全引導載入程式，提供額外的安全保障。 裝置身份證明：通過允許對處理器進行加密認證，助力防範未經授權的CPU升級。 Yocto Project™框架支援：賦能客戶為嵌入式系統創建輕量級、最佳化的Linux®作業系統。 AMD EPYC嵌入式8004系列處理器非常適合尋求強大效能、同時對能源效率、熱靈活性和平台密度有著高要求的市場領域。AMD EPYC嵌入式8004系列處理器對在惡劣環境下承擔嚴苛工作負載的網路、儲存和工業邊緣系統進行了最佳化，可提供客戶所需的突破性每瓦效能優勢和先進功能。 註1：所述的每瓦效能結果基於AMD於2024年8月進行的測試，使用SPECrate® 2017 Integer吞吐量和SPECrate® 2017 Floating Point吞吐量基準來測量在AMD參考平台上配置的第4代AMD EPYC嵌入式8534P處理器（64C/128T/200W TDP）、雙列DDR5 4800MT/s記憶體、16x64GB、Ubuntu 22.043作業系統的每瓦效能，對比在AMD參考平台上配置的第3代EPYC嵌入式7713P處理器（64C/128T/225W TDP）、雙列3200MT/s記憶體、16x32GB、Ubuntu 20.04作業系統。對於兩個測試系統：BIOS設置ACPI SRAT、L3緩存、域設置為啟用、記憶體交叉和DRAM清理時間設置為禁用。結果將根據系統組態、設置、使用情況和其他因素而有所不同。SPECrate® 2017是SPEC的註冊商標（EMB-211）。 註2：SP5封裝尺寸72 mm x 75.4 mm，SP6封裝尺寸58.5 mm x 75.4 mm。 進一步瞭解AMD EPYC嵌入式8004系列處理器，敬請參閱 www.amd.com/epyc-embedded-8004。
New Supermicro Systems Enable Customers to Upgrade and Consolidate Data Centers for AI Workloads SAN JOSE, Calif., Oct. 11, 2024 /PRNewswire/ -- Supermicro, Inc. (NASDAQ: SMCI), a Total IT Solution Provider for AI, Cloud, Storage, and 5G/Edge, announces the launch of a new series of servers, GPU-accelerated systems, and storage servers featuring the AMD EPYC™ 9005 Series processors and AMD Instinct™ MI325X GPUs. The new H14 product line represents one of the most extensive server families in the industry, including Supermicro's Hyper systems, the Twin multi-node servers, and AI inferencing GPU systems, all available with air or liquid cooling options. The new "Zen5" processor core architecture implements full data path AVX-512 vector instructions for CPU-based AI inference and provides 17% better instructions per cycle (IPC) than the previous 4th generation EPYC processor, enabling more performance per core. 100124-AMD Supermicro's new H14 family uses the latest 5th Gen AMD EPYC processors which enable up to 192 cores per CPU with up to 500W TDP (thermal design power). Supermicro has designed new H14 systems including the Hyper and FlexTwin™ systems which can accommodate the higher thermal requirements. The H14 family also includes three systems for AI training and inference workloads supporting up to 10 GPUs which feature the AMD EPYC 9005 Series CPU as the host processor and two which support the AMD Instinct MI325X GPU. "Supermicro's H14 servers have 2.44X faster SPECrate®2017_fp_base performance1 using the EPYC 9005 64 core CPU as compared with Supermicro's H11 systems using the second generation EPYC 7002 Series CPUs," said Charles Liang, president and CEO, Supermicro. "This significant performance improvement allows customers to make their data centers more power efficient by reducing the total data center footprint by at least two-thirds2 while also adding new AI processing capabilities. The H14 server family provides the highest performance, density, and power efficiency available through Supermicro's liquid and air-cooling options, wide selection of system designs, and proven Building Block Solutions." For more information about the Supermicro H14 family of products, please visit: www.supermicro.com/aplus "Supermicro's 'Building Block Solutions' has enabled it to consistently deliver time-to-market solutions powered by AMD across a variety of compelling system designs," said Forrest Norrod, executive vice president and general manager, Data Center Solutions Group, AMD. "Our collaboration with Supermicro, along with their in-house engineering design and manufacturing capabilities worldwide combined with their rack-scale integration capability for both air and liquid-cooled systems enables customers of any scale to generate time-to-value from AMD EPYC CPUs and Instinct GPUs." Supermicro's H14 server lineup consists of the following product families: Hyper - Supermicro's flagship enterprise server supports maximum performance from two EPYC 9005 CPUs with up to the maximum 192 cores per CPU at 500W and up to 9TB memory in 24 DIMM slots. With either a 1U chassis with up to 12 2.5" NVMe/SATA bays or a 2U chassis with up to 24 2.5" NVMe/SATA bays, the Hyper's advanced cooling design accommodates the highest performance CPUs for use in demanding AI inference, enterprise or cloud workloads. CloudDC - This versatile system is optimized for use in Cloud Data Centers and features a single EPYC 9005 CPU with up to 12 2.5" NVMe/SATA drive bays in a 1U chassis. It's designed using the OCP (Open Compute Platform) DC-MHS specification (Data Center Modular Hardware System) which ensures compatibility with OCP standards. GrandTwin™ - The GrandTwin is a 4-node compute platform using single EPYC 9005 CPU in a very dense 2U form-factor. This system is often used in multi-server cluster applications such as object storage, virtualization, and HPC applications. FlexTwin™ - The FlexTwin is a 2U 4-node high-performance high-density compute system with dual EPYC 9005 CPUs per node. The advanced liquid-cooling provides high power efficiency and allows the operation of the highest performance EPYC 9005 CPUs for use in HPC, EDA and other demanding workloads. 5U GPU System – Supermicro's EPYC CPU-based 5U PCIe GPU system supports up to 10 double-width accelerators for design and visualization applications. 4U GPU System (Liquid Cooled) - This highly dense EPYC CPU-based 8-way accelerators platform supports OAM accelerators in the most compact 4U form-factor using advanced liquid-cooling. It is designed for high-performance AI and HPC applications. 8U GPU System - This 8-way accelerator system uses the AMD Instinct MI325X GPU along with the EPYC 9005 CPU for large-scale LLM AI training. The 8U chassis allows deployment in any air-cooled data center. Supermicro H14 products with AMD EPYC CPUs are available for customer testing today through Supermicro's JumpStart program. Supermicro will present the new H14 solutions at the AMD Advancing AI Day on October 10, 2024, at the San Francisco Moscone Center. 1SPECrate®2017_fp_base of 485 using the Supermicro A+ Server 2023US-TR4 and two AMD EPYC 7702 64 core CPUs (https://www.spec.org/cpu2017/results/res2020q1/cpu2017-20200204-20866.html retrieved October 2, 2024) compared with SPECrate®2017_fp_base of 1670 using the Supermicro AS-2126HS-TN and two AMD EPYC 9555 64 core CPUs. Results of the AS-2126HS-TN with the 9555 CPU to be published on www.spec.org/cpu2017/results on October 10, 2024. 2Based on the SPECrate®2017_fp_base comparison in footnote (1), reduction in number of systems using the AS-2126HS-TN with the 9555 CPU vs. 2023US-TR4 with the 7702 CPU is 70.9%. About Super Micro Computer, Inc. Supermicro (NASDAQ: SMCI) is a global leader in Application-Optimized Total IT Solutions. Founded and operating in San Jose, California, Supermicro is committed to delivering first-to-market innovation for Enterprise, Cloud, AI, and 5G Telco/Edge IT Infrastructure. We are a Total IT Solutions provider with server, AI, storage, IoT, switch systems, software, and support services. Supermicro's motherboard, power, and chassis design expertise further enables our development and production, enabling next-generation innovation from cloud to edge for our global customers. Our products are designed and manufactured in-house (in the US, Asia, and the Netherlands), leveraging global operations for scale and efficiency and optimized to improve TCO and reduce environmental impact (Green Computing). The award-winning portfolio of Server Building Block Solutions® allows customers to optimize for their exact workload and application by selecting from a broad family of systems built from our flexible and reusable building blocks that support a comprehensive set of form factors, processors, memory, GPUs, storage, networking, power, and cooling solutions (air-conditioned, free air cooling or liquid cooling). Supermicro, Server Building Block Solutions, and We Keep IT Green are trademarks and/or registered trademarks of Super Micro Computer, Inc. All other brands, names, and trademarks are the property of their respective owners. AMD, the AMD Arrow logo, AMD Instinct, EPYC, and combinations thereof are trademarks of Advanced Micro Devices, Inc. Other names are for informational purposes only and may be trademarks of their respective owners. AS-812GS AS-1116CS AS 2116GT AS-212 AS-5126GS AS-4125GS AS-2126FT
TAIPEI, Oct. 11, 2024 /PRNewswire/ -- MSI, a leading global provider of high-performance server solutions, today introduced its latest AMD EPYC™ 9005 Series CPU-based server boards and platforms, engineered to tackle the most demanding data center workloads with leadership performance and efficiency. MSI DC-MHS Server Solutions Powered by AMD EPYC 9005 Series Processors Meet the Evolving Demands of Modern Data Center Featuring AMD EPYC 9005 Series processors with up to 192 cores and 384 threads, MSI's new server platforms deliver breakthrough compute power, unparalleled density, and exceptional energy efficiency, making them ideal for handling AI-enabled, cloud-native, and business-critical workloads in modern data centers. According to Danny Hsu, General Manager of MSI's Enterprise Platform Solutions, "Our new AMD EPYC 9005 Series CPU-based platforms are not just about raw performance; they represent a strategic leap forward for data centers looking to maximize operational efficiency while minimizing their environmental footprint. These systems ensure that enterprises can stay ahead of evolving industry demands and adapt quickly to new opportunities." "5th Gen AMD EPYC Processors deliver the compute capabilities our customers require for their most demanding AI-enabled data center workloads," said Ravi Kuppuswamy, senior vice president, Server Business Unit, AMD. "Our highly efficient 'Zen 5' cores and innovative chiplet-based architecture allowed us to build an advanced, diversified server CPU portfolio that addresses the rapidly evolving needs of our customers and the modern data center." DC-MHS Server Solutions Redefining Flexibility and Scalability for Modern Data Centers MSI's DC-MHS server solutions address the evolving needs of today's data centers. Powered by AMD EPYC 9005 Series processors, the DC-MHS series supports the DC-SCM2 server management module, featuring the Aspeed AST2600 BMC, to significantly enhance server maintainability and operational efficiency, enabling enterprises to deploy high-performance systems with the agility needed to stay competitive in today's rapidly changing market. DC-MHS Multi-Node Servers MSI's DC-MHS multi-node server platforms house multiple nodes within a single chassis, maximizing space and resource utilization while reducing operational costs, enabling modern data centers to future-proof their infrastructure and enhance operational efficiency. Each platform is powered by a single AMD EPYC 9005 Series processor with up to 500W TDP, supports 12 DDR5 DIMM slots for high memory bandwidth, and an OCP NIC for enhanced connectivity. CD370-S4051-X2 3U 2-Node Core Compute Server: Supports 12 PCIe 5.0 x4 U.2 NVMe bays per node, delivering high-speed I/O and fast data transfer, and is ideal for AI-enabled and data-intensive workloads. CD270-S4051-X2 2U 2-Node Core Compute Server: Equipped with 6 PCIe 5.0 x4 U.2 NVMe bays per node, delivering fast, scalable compute performance, ideal for virtualization and data analytics. CD270-S4051-X4 2U 4-Node Core Compute Server: Features 3 PCIe 5.0 x4 U.2 NVMe bays per node and liquid-cooled options, excelling in throughput-heavy applications such as cloud environments. DC-MHS Enterprise Server CX271-S4056 2U Enterprise Server: Features a single AMD EPYC 9005 Series processor, 24 DDR5 DIMM slots with speeds up to 5200MT/s, 8 or 24 2.5 inch PCIe 5.0 x4 U.2 NVMe bays, and PCIe 5.0 x16 OCP NIC slots, it delivers fast, scalable performance. Its flexible design, including GPU acceleration options, makes it ideal for data-intensive workloads such as AI, virtualization, and cloud-native applications in modern data centers. DC-MHS Server Boards D4056 DC-MHS M-DNO Type-4 HPM: Supports a single AMD EPYC 9005 processor, 24 DDR5 DIMM slots, 2 NVMe M.2 ports, PCIe 5.0 expansion slots, and OCP 3.0 NIC support, this platform is built for memory-intensive and data-driven applications, offering fast data access. D4051 DC-MHS M-DNO Type-2 HPM: Designed for power efficiency with a single AMD EPYC 9005 processor, 12 DDR5 DIMM slots, 2 NVMe M.2 ports, and PCIe 5.0 x16 OCP NIC slot, this board delivers scalable performance for latency-sensitive workloads in a half-width form factor. CXL Memory Expansion Server with 8TB Memory for Data-Intensive Workloads S2301 2U CXL Memory Expansion Server: Powered by dual AMD EPYC 9005 Series processors and 24 DDR5 DIMM slots, the server is engineered to meet the demands of data centers requiring unparalleled memory capacity and scalability. Leveraging advanced CXL 2.0 technology, the S2301 integrates 8 E3.S 2T drive bays for CXL memory and 8 E3.S 1T NVMe storage, expanding total memory capacity to a remarkable 8TB, making it the ideal solution for data-intensive applications, such as In-Memory Database, Electronic Design Automation (EDA), and High-Performance Computing (HPC). GPU Servers with 4GPU for AI and High-Performance Computing The G4101-01 and G4101-03 GPU Servers offer exceptional performance for AI, machine learning, and HPC. Powered by a single AMD EPYC 9005 Series processor with 500W TDP and liquid cooling, these servers feature 12 DDR5 DIMM slots and 4 PCIe 5.0 triple-wide slots supporting GPGPUs up to 450W. With 12 PCIe 4.0 U.2 NVMe drives and Platinum or Titanium redundant 3000W power supplies, they deliver the reliability and power required for the most demanding workloads. Enterprise Servers for Performance-Critical Workloads and Storage Servers for Smaller Data Centers MSI's Enterprise and Storage Server lineup now features support for AMD EPYC 9005 Series processors, offering up to 24 DDR5 DIMM slots and delivering exceptional scalability, performance, and memory bandwidth of up to 6000MT/s. Enterprise Servers S2206-05-10G, S2206-06-10G, and S1206-02-10G are optimized for high-speed data transfer. These models feature 10G SFP+ Ethernet and are tailored for performance-critical workloads such as AI and machine learning. The S2206-06-10G stands out as the highest-performance model in this lineup, designed for data-heavy tasks requiring maximum I/O throughput. It features 3 PCIe 5.0 x16 FHHL slots and 16 PCIe 4.0 U.2 NVMe drives, combined with 8 SATA/SAS bays to deliver exceptional storage capacity and speed. For environments where 1 Gbps network speed is sufficient, Storage Servers such as the S2206-04 offer cost-effective solutions with strong compute and storage performance at a cost-effective price point, making them ideal for smaller data centers. Supporting Resources: Watch this video to discover how MSI's 5th Gen AMD EPYC processor-based servers are redefining data centers for next-generation computing.
A12 藝術空間
EPYC
請先登入後才能發佈新聞。
還不是會員嗎？立即 加入台灣產經新聞網會員 ，使用免費新聞發佈服務。 （服務項目） （投稿規範）
