NVIDIA launches first mainstream server liquid-cooled GPU to support sustainable development
According to NVIDIA's official website, NVIDIA has launched liquid-cooled GPUs to help achieve sustainable and efficient computing. The liquid-cooled NVIDIA A100 PCIe GPU can meet customers' needs for high-performance green data centers and is the first of its kind among mainstream server GPUs.
NVIDIA launches first mainstream server liquid-cooled GPU to support sustainable development
In order to curb climate change, global enterprises are accelerating the construction of high-performance, energy-efficient data centers, and Zac Smith, director of edge infrastructure at Equinix, is also involved. He works for Equinix, a global service provider that manages more than 240 data centers and is committed to being the first in the industry to achieve climate neutrality.
Energy efficiency steadily improves
As of April, Equinix has issued $4.9 billion in green bonds. Equinix will use these investment tools to optimize power usage effectiveness (PUE) in order to reduce its environmental impact. PUE is an industry metric that measures how much energy a data center uses is directed toward computing tasks. Data center operators are trying to reduce PUE to the ideal level of close to 1.0. Equinix facilities currently have an average PUE of 1.48, and its new data centers can have PUEs as low as 1.2. Equinix took a step further in this direction in January when it launched a new facility dedicated to improving energy efficiency. Part of this work focuses on liquid cooling technology. Liquid cooling technology was born in the mainframe era and has become increasingly mature in the AI era. Today, liquid cooling technology has been widely used in high-speed supercomputers around the world in the form of direct-to-chip cooling. NVIDIA GPUs are 20 times more energy efficient than CPUs in AI inference and high-performance computing, and liquid cooling technology will naturally be used for accelerated computing.
Increase efficiency through acceleration
If all CPU servers running AI and HPC in the world were switched to GPU acceleration systems, up to 11 trillion watt hours of energy could be saved every year. The amount of energy saved could power more than 1.5 million homes for a year. Today, NVIDIA released the first data center PCIe GPU to adopt direct-to-chip cooling technology, contributing to sustainable development. Equinix is validating the A100 80GB PCIe liquid-cooled GPU for use in its data centers as part of a comprehensive approach to sustainable cooling and heat capture. The GPU is now in beta and is expected to be officially released this summer.
Save water and electricity
"This is the first liquid-cooled GPU to be introduced in our labs, and we are excited because customers are eager to leverage AI in sustainable ways," said Smith. Data center operators aim to eliminate the chillers used to cool gases inside data centers, which evaporate millions of gallons of water each year. With liquid cooling technology, the system only needs to recycle a small amount of liquid in a closed system and can focus on the main heating points. "We're going to turn waste into treasure," Smith said.
Same performance but less power consumption
"Same performance, less power consumption. In separate tests, both Equinix and NVIDIA found that data center workloads using liquid cooling technology can match those of air-cooled facilities while using about 30% less energy. NVIDIA estimates that liquid cooling technology The PUE of a cold data center may reach 1.15, which is much lower than the PUE of 1.6 for air cooling. Under the same conditions of space, a liquid-cooled data center can achieve double the computing volume. This is because the A100 GPU only uses one PCIe slot, and The air-cooled A100 GPU requires the use of two PCIe slots.
At least a dozen system manufacturers plan to use liquid-cooled GPUs in their products later this year, including ASUS, ASRock Rack, Foxconn Industrial Internet, GIGABYTE ), H3C, Inspur, Inventec, Nettrix, QCT, Supermicro, Wiwynn and xFusion ).
global trends
In Asia, Europe and the United States, regulations setting energy efficiency standards have yet to be finalized. This has also prompted banks and other large data center operators to join the evaluation of liquid cooling technology. The use of liquid cooling technology is not limited to data centers. Automobiles and other systems also require the technology to cool high-performance systems in enclosed spaces.
The road to sustainable development
"We're about to start a new journey," Smith said of the debut of this mainstream accelerator using liquid cooling technology. In fact, NVIDIA plans to launch a version of the A100 PCIe card next year equipped with the H100 Tensor Core GPU based on the NVIDIA Hopper architecture. In the near future, NVIDIA plans to apply liquid cooling technology to its own high-performance data center GPUs and NVIDIA HGX platforms. To drive rapid adoption, today's announcement of liquid-cooled GPUs reduces power consumption while maintaining performance. In the future, we expect these cards to show better performance and meet user needs while using the same energy. Smith said, "Merely measuring power is meaningless. Reducing carbon emissions while improving performance is the direction we strive for."
As a leading radiator manufacturer, Sinda Thermal can offer wide range of heat sink types, such as aluminum extruded heat sink, skived fin heat sink, pin fin heat sink, zipper fin heatsink, liquid cooling cold plate, etc. Aslo we can provide great quality and outstanding customer service. Sinda Thermal consistently delivers custom heatsinks to meet the unique requirements of various industries.
Sinda Thermal was established in 2014 and has grown rapidly due to its commitment to excellence and innovation in the field of thermal management. The company has a great manufacturing facility equipped with advanced technology and machinery, this ensures that Sinda Thermal is able to produce various types of radiators and customize them to meet the different needs of customers.
FAQ
1. Q: Are you a trading company or manufacturer?
A: We are a leading heat sink manufacturer, our factory has been founded over 8 years, we are professional and experienced.
2. Q: Can you provide OEM/ODM service?
A: Yes, OEM/ODM are available.
3. Q: Do you have MOQ limit?
A: No, we don't set up MOQ, prototype samples are available.
4. Q: What's the lead time of the production?
A: For prototype samples, the lead time is 1-2 weeks, for mass production, the lead time is 4-6 weeks.
5. Q: Can I visit your factory?
A: Yes, Welcome to Sinda Thermal.
