{"id":2113,"date":"2022-05-24T05:43:55","date_gmt":"2022-05-24T05:43:55","guid":{"rendered":"https:\/\/salarydistribution.com\/machine-learning\/2022\/05\/24\/nvidia-adds-liquid-cooled-gpus-for-sustainable-efficient-computing\/"},"modified":"2022-05-24T05:43:55","modified_gmt":"2022-05-24T05:43:55","slug":"nvidia-adds-liquid-cooled-gpus-for-sustainable-efficient-computing","status":"publish","type":"post","link":"https:\/\/salarydistribution.com\/machine-learning\/2022\/05\/24\/nvidia-adds-liquid-cooled-gpus-for-sustainable-efficient-computing\/","title":{"rendered":"NVIDIA Adds Liquid-Cooled GPUs for Sustainable, Efficient Computing"},"content":{"rendered":"
\n

In the worldwide effort to halt climate change, Zac Smith is part of a growing movement to build data centers that deliver both high performance and energy efficiency.<\/p>\n

He\u2019s head of edge infrastructure at Equinix, a global service provider that manages more than 240 data centers and is committed to becoming the first in its sector to be climate neutral.<\/p>\n

\u201cWe have 10,000 customers counting on us for help with this journey. They demand more data and more intelligence, often with AI, and they want it in a sustainable way,\u201d said Smith, a Julliard grad who got into tech in the early 2000\u2019s building websites for fellow musicians in New York City.<\/p>\n

Marking Progress in Efficiency<\/b><\/h2>\n

As of April, Equinix has issued $4.9 billion in green bonds. They\u2019re investment-grade instruments Equinix will apply to reducing environmental impact through optimizing power usage effectiveness (PUE), an industry metric of how much of the energy a data center uses goes directly to computing tasks.<\/p>\n

Data center operators are trying to shave that ratio ever closer to the ideal of 1.0 PUE.\u00a0 Equinix facilities have an average 1.48 PUE today with its best new data centers hitting less than 1.2.<\/p>\n

<\/p>\n

\"Equinix<\/p>\n

<\/a>

Equinix is making steady progress in the energy efficiency of its data centers as measured by PUE (inset).<\/figcaption><\/figure>\n

In another step forward, Equinix opened in January a dedicated facility to pursue advances in energy efficiency. One part of that work focuses on liquid cooling.<\/p>\n

Born in the mainframe era, liquid cooling is maturing in the age of AI. It\u2019s now widely used inside the world\u2019s fastest supercomputers in a modern form called direct-chip cooling.<\/p>\n

Liquid cooling is the next step in accelerated computing<\/a> for NVIDIA GPUs that already deliver up to 20x better energy efficiency on AI inference and high performance computing jobs than CPUs.<\/p>\n

Efficiency Through Acceleration\u00a0<\/b><\/h2>\n

If you switched all the CPU-only servers running AI and HPC worldwide to GPU-accelerated systems, you could save a whopping 11 trillion watt-hours of energy a year. That\u2019s like saving the energy more than 1.5 million homes consume in a year.<\/p>\n

Today, NVIDIA adds to its sustainability efforts with the release of our first data center PCIe GPU using direct-chip cooling.<\/p>\n

Equinix is qualifying the A100 80GB PCIe Liquid-Cooled GPU<\/a> for use in its data centers as part of a comprehensive approach to sustainable cooling and heat capture. The GPUs are sampling now and will be generally available this summer.<\/p>\n

Saving Water and Power<\/b><\/h2>\n

\u201cThis marks the first liquid-cooled GPU introduced to our lab, and that\u2019s exciting for us because our customers are hungry for sustainable ways to harness AI,\u201d said Smith.<\/p>\n

Data center operators aim to eliminate chillers that evaporate millions of gallons a water a year to cool the air inside data centers. Liquid cooling promises systems that recycle small amounts of fluids in closed systems focused on key hot spots.<\/p>\n

\u201cWe\u2019ll turn a waste into an asset,\u201d he said.<\/p>\n

Same Performance, Less Power<\/b><\/h2>\n

In separate tests, both Equinix and NVIDIA found a data center using liquid cooling could run the same workloads as an air-cooled facility while using about 30 percent less energy. NVIDIA estimates the liquid-cooled data center could hit 1.15 PUE, far below 1.6 for its air-cooled cousin.<\/p>\n

Liquid-cooled data centers can pack twice as much computing into the same space, too. That\u2019s because the A100 GPUs use just one PCIe slot; air-cooled A100 GPUs fill two.<\/p>\n

<\/p>\n

\"NVIDIA<\/p>\n

<\/a>

NVIDIA sees power savings, density gains with liquid cooling.<\/figcaption><\/figure>\n

At least a dozen system makers plan to incorporate these GPUs into their offerings later this year. They include ASUS, ASRock Rack, Foxconn Industrial Internet, GIGABYTE, H3C, Inspur, Inventec, Nettrix, QCT, Supermicro, Wiwynn and xFusion.<\/p>\n

A Global Trend<\/b><\/h2>\n

Regulations setting energy-efficiency standards are pending in Asia, Europe and the U.S. That\u2019s motivating banks and other large data center operators to evaluate liquid cooling, too.<\/p>\n

And the technology isn\u2019t limited to data centers. Cars and other systems need it to cool high-performance systems embedded inside confined spaces.<\/p>\n

The Road to Sustainability<\/b><\/h2>\n

\u201cThis is the start of a journey,\u201d said Smith of the debut of liquid-cooled mainstream accelerators.<\/p>\n

Indeed, we plan to follow up the A100 PCIe card with a version next year using the H100 Tensor Core GPU<\/a> based on the NVIDIA Hopper architecture<\/a>. We plan to support liquid cooling in our high-performance data center GPUs and our NVIDIA HGX platforms for the foreseeable future.<\/p>\n

For fast adoption, today\u2019s liquid-cooled GPUs deliver the same performance for less energy. In the future, we expect these cards will provide an option of getting more performance for the same energy, something users say they want.<\/p>\n

\u201cMeasuring wattage alone is not relevant, the performance you get for the carbon impact you have is what we need to drive toward,\u201d said Smith.<\/p>\n

Learn more about our new A100 PCIe liquid-cooled GPUs<\/a>.<\/p>\n<\/div>\n","protected":false},"excerpt":{"rendered":"

https:\/\/blogs.nvidia.com\/blog\/2022\/05\/23\/liquid-cooled-gpus-computex\/<\/p>\n","protected":false},"author":0,"featured_media":2114,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[3],"tags":[],"_links":{"self":[{"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/posts\/2113"}],"collection":[{"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/types\/post"}],"replies":[{"embeddable":true,"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/comments?post=2113"}],"version-history":[{"count":0,"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/posts\/2113\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/media\/2114"}],"wp:attachment":[{"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/media?parent=2113"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/categories?post=2113"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/salarydistribution.com\/machine-learning\/wp-json\/wp\/v2\/tags?post=2113"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}