엔비디아, AWS 클라우드에서 GPU 가속 'G2 인스턴스' 제공 시작
무슨 발표인가
- Amazon EC2 G2 인스턴스로 클라우드 기반 그래픽 가속
- SaaS 기업이 디자인·시각화·미디어 제작용 클라우드 서비스 구축 가능
원문 (영어)
SANTA CLARA, CA - NVIDIA today announced NVIDIA GRID technology is now available from Amazon Web Services (AWS) through its newly announced Amazon Elastic Compute Cloud (Amazon EC2) G2 instance, delivering GPU acceleration to users running graphics-intensive applications and games in the cloud.
This expands the uses of cloud computing from storage, data processing and 2D applications to 3D, fully GPU-accelerated, interactive consumer and professional applications. With NVIDIA GRID GPUs, software-as-a-service (SaaS) companies can now build cloud-based offerings with extreme graphics performance for design, visualization, media creation, games and more.
AWS is offering an NVIDIA GRID GPU instance, known as the G2 instance, via its Amazon EC2 cloud, starting today. "AWS sees a growing benefit for adding GPUs to our cloud," said Matt Wood, general manager of Data Science at AWS. "The NVIDIA GRID GPUs in our new G2 instances enable graphical applications to be rendered in the AWS cloud and streamed to a world with increasing internet bandwidth and proliferation of device types."
Designed for cloud computing, NVIDIA GRID GPUs make possible a new generation of GPU-accelerated SaaS applications -- such as virtual workstations, accelerated virtual desktops and gaming-as-a-service. Based on the NVIDIA Kepler architecture, GRID GPUs include a powerful H.
264 encoding engine that lets high-resolution graphics be compressed in real time and streamed to any internet-connected display. As a result, internet-connected devices -- such as PCs, Macs, tablets, the NVIDIA SHIELD , smart TVs, micro-consoles or smartphones -- can tap the tremendous power of GPUs to meet the needs of scientists, researchers, designers, engineers, gamers and more.
원문: NVIDIA News — "Amazon Web Services Deploys NVIDIA GRID GPUs" (2024-04-05) 공식 원문: https://nvidianews.nvidia.com/news/amazon-web-services-deploys-nvidia-grid-gpus-2775398
A small team that reads too much internet so you don't have to.
