NVIDIA Grace CPU Delivers Up To 30% Higher Performance At 70% Better Efficiency Versus Latest x86 Data Center Chips
NVIDIA has announced sampling of its Grace CPU Superchip which will be delivering some major performance efficiency gains versus x86 chips.
NVIDIA first announced its Grace CPU and the respective Superchip design at GTC 2022. The Grace CPU is NVIDIA's first processor based on a custom Arm architecture that will be aiming at the server / HPC segment. The CPU comes in two Superchip configurations, a Grace Superchip module with two Grace CPUs and a Grace+Hopper Superchip with one Grace CPU connected to a Hopper H100 GPU.
Today, at GTC 2023, NVIDIA unveiled the Grace CPU Superchip for the first time to the public. The whole unit measures 5 x 8 inches and can be both air-cooled and passive-cooled. NVIDIA showed both, a standard passive heatsink and a large 1U rack heatsink design. Two Grace CPU Superchip modules can fit within a single 1U air-cooled server.
The company also shared some new performance metrics in Microservices and Big Data workloads where the NVIDIA Grace CPU Superchip was able to beat the latest class of x86 CPUs from Intel and AMD by up to 30% while delivering 70% higher efficiency and 2x the data throughput. NVIDIA states that CSPs can outfit a power-limited data center with 1.7 times more Grace servers, each delivering 25% higher throughput. At ISO power, Grace CPU Superchip gives CSPs 2x the growth opportunity.
Some of the main highlights of Grace include:
Being NVIDIA's first server CPU, Grace features 72 Arm v9.0 cores that offer support for SVE2 and various virtualization extensions such as Nested Virtualization and S-EL2. The CPU is fabricated on TSMC's 4N process node, an optimized version of the 5nm process node which is made exclusively for NVIDIA. The new architecture can provide up to 7.1 TFLOPs of
Read more on wccftech.com
