中文翻译
摘要: 微软在Computex宣布推出Surface Laptop Ultra，首发搭载英伟达RTX Spark超级芯片。该Arm架构芯片融合CPU与GPU，配备最高128GB统一内存，AI算力达1 Petaflop。新品定位轻薄与高性能之间，深度整合Copilot+，专为本地AI智能体与游戏打造。预计今年秋季上市，标志着AI PC进入新阶段。
正文
(Credit: Microsoft)
Table of Contents
Compare Specs: Our Picks Side by Side
Inside the Surface Laptop Ultra
Rewriting Windows for the Age of Agentic AI
Finally, a Thin-and-Light Built for Gaming
Maturing the Vision: 'The Most Powerful Thing We’ve Ever Made'
Release Timing and the Price of Ultimate Power
Alongside Nvidia's keynote at
Computex
, Microsoft announced a new Surface PC—the Surface Laptop Ultra—which will feature Nvidia's new
RTX Spark superchip
. This Microsoft and Nvidia team-up is the first of several major announcements we expect to see during
Computex
as the chip maker makes a play to power the next generation of premium laptops, with an emphasis on AI and gaming.
The Laptop Ultra expands Microsoft's consumer Surface line with more Windows on Arm technology, following years of Surface built on
Qualcomm's Snapdragon X Arm processors
. Unlike the Qualcomm chips, though, Nvidia's new RTX Spark superchip combines the processing might of
Nvidia's DGX Spark
and the graphics capability of an Nvidia RTX 5070 laptop GPU to power a new Windows-based agentic AI paradigm.
Slated to launch this fall, the Surface Laptop Ultra bridges the gap between thin-and-light ultraportables and beefy workstation laptops, offering the template for a new consumer category that can drive a full petaflop of AI-ready compute power. It's the next phase of evolution for AI PCs, combining
Copilot+
features with the raw muscle to power on-device AI models and agents.
Inside the Surface Laptop Ultra
The Microsoft Surface Laptop Ultra is built around Nvidia's new CPU, the
RTX Spark
. This Arm-based superchip features 20 Grace compute cores, paired with 6,144 Blackwell RTX cores. This fusion of CPU and GPU muscle is combined with up to 128GB of unified memory, blowing past the limitations of smaller VRAM caches seen on dedicated GPUs.
The system is engineered around the Nvidia silicon, leveraging the high-efficiency hardware to deliver unparalleled power in a sl
采集时间: 2026-06-01 20:37:12
AI微软AI人工智能技术