科技英語：英特爾Aurora成最快的 AI 系統(tǒng)

Intel, in collaboration with Argonne National Laboratory and Hewlett Packard Enterprise (HPE), has revealed that its Aurora supercomputer has exceeded the exascale computing threshold reaching speeds of 1.012 exaflops to become the fastest AI-focused system.
英特爾與阿貢國家實驗室和惠普企業(yè) (HPE) 合作，透露其 Aurora 超級計算機已突破百億億次計算閾值，速度達到 1.012 exaflops，成為最快的人工智能系統(tǒng)。

“The Aurora supercomputer surpassing exascale will allow it to pave the road to tomorrow’s discoveries,” said Ogi Brkic, Intel’s VP and GM of Data Centre AI Solutions. “From understanding climate patterns to unravelling the mysteries of the universe, supercomputers serve as a compass guiding us toward solving truly difficult scientific challenges that may improve humanity.”
英特爾副總裁兼數(shù)據(jù)中心人工智能解決方案總經(jīng)理 Ogi Brkic 表示：“超越百億億次計算的 Aurora 超級計算機將為其未來的發(fā)現(xiàn)鋪平道路。” “從了解氣候模式到揭開宇宙之謎，超級計算機就像指南針一樣，引導我們解決真正困難的科學挑戰(zhàn)，從而改善人類生活。”

Aurora has not only excelled in speed but also in innovation and utility. Designed from the outset as an AI-centric supercomputer, Aurora enables researchers to leverage generative AI models, significantly accelerating scientific discovery.
Aurora 不僅在速度方面表現(xiàn)出色，而且在創(chuàng)新和實用性方面也表現(xiàn)出色。 Aurora 從一開始就被設計為以人工智能為中心的超級計算機，使研究人員能夠利用生成式人工智能模型，顯著加速科學發(fā)現(xiàn)。

Groundbreaking work has already been achieved using Aurora, including mapping the 80 billion neurons of the human brain, enhancing high-energy particle physics with deep learning, and accelerating drug design and discovery through machine learning.
使用 Aurora 已經(jīng)取得了突破性的工作，包括繪制人腦 800 億個神經(jīng)元的圖譜、通過深度學習增強高能粒子物理學，以及通過機器學習加速藥物設計和發(fā)現(xiàn)。

At the core of Aurora lies the Intel Data Center GPU Max Series, built on the innovative Intel Xe GPU architecture, optimised for both AI and HPC tasks. This technological foundation enables parallel processing capabilities, crucial for handling complex neural network AI computations.
Aurora 的核心是英特爾數(shù)據(jù)中心 GPU Max 系列，該系列基于創(chuàng)新的英特爾 Xe GPU 架構構建，針對 AI 和 HPC 任務進行了優(yōu)化。 這一技術基礎實現(xiàn)了并行處理能力，這對于處理復雜的神經(jīng)網(wǎng)絡人工智能計算至關重要。

Details shared about the supercomputer highlight its grand scale, consisting of 166 racks, 10,624 compute blades, 21,248 Intel Xeon CPU Max Series processors, and 63,744 Intel Data Center GPU Max Series units, making it the largest GPU cluster worldwide.
分享的有關這臺超級計算機的詳細信息凸顯了其規(guī)模之大，由 166 個機架、10,624 個計算刀片、21,248 個英特爾至強 CPU Max 系列處理器和 63,744 個英特爾數(shù)據(jù)中心 GPU Max 系列單元組成，使其成為全球最大的 GPU 集群。

Alongside the hardware, Intel’s suite of software tools – including the Intel® oneAPI DPC++/C++ Compiler and an array of performance libraries – boost developer flexibility and system scalability.
除了硬件之外，英特爾的軟件工具套件（包括英特爾® oneAPI DPC++/C++ 編譯器和一系列性能庫）也提高了開發(fā)人員的靈活性和系統(tǒng)可擴展性。

Intel is also expanding its Tiber Developer Cloud, incorporating new state-of-the-art hardware and enhanced service capabilities to support the evaluation, innovation, and optimisation of AI models and workloads on a large scale.
英特爾還在擴展其 Tiber 開發(fā)者云，整合最先進的新硬件和增強的服務功能，以支持大規(guī)模人工智能模型和工作負載的評估、創(chuàng)新和優(yōu)化。

Looking forward, the deployment of new supercomputers integrated with Intel technologies is expected to transform various scientific fields. Systems like CMCC’s Cassandra will advance climate change modelling, while ENEA’s CRESCO 8 supports breakthroughs in fusion energy, among others, underscoring Intel’s dedication to advancing HPC and AI into new realms of discovery and innovation.
展望未來，集成英特爾技術的新型超級計算機的部署預計將改變各個科學領域。 CMCC 的 Cassandra 等系統(tǒng)將推進氣候變化建模，而 ENEA 的 CRESCO 8 支持聚變能源等方面的突破，突顯了英特爾致力于將 HPC 和 AI 推向發(fā)現(xiàn)和創(chuàng)新的新領域。