For Energy-Efficient HPC, Less is More

By Ian Armas Foster

September 19, 2012

Near-Threshold Voltage, or NTV, has the potential to significantly cut energy requirements for high performance computing. This is becoming especially important for the largest supercomputers, which are already well into the multi-megawatt realm and are expected to hit tens of megawatts in the exascale era.

Intel recently demonstrated their NTV capabilities at ISSCC 2012, operating an x86 microprocessor on only 2 milliWatts of power. The company published three papers on their results, which were analyzed and discussed in an article at Real World Technologies by David Kanter.

The threshold voltage is the voltage required to generate a minimum of current across a transistor. Intel has discovered that the most efficient use of energy would be to operate a circuit near that of its threshold voltage, that is, the amount required to turn a transistor on.

There are a couple of intrinsically tricky things about operating at such a low voltage. The first is limiting dI/dt, the fancy mathematical way of expressing change in current over time. Rapid spikes or drops in current, especially those that would occur as a result of a particular transistor accidentally dropping beneath the threshold, can create computational errors.

Ideally, all transistors would be created equally. Statistically, however, since there sometimes lie billions of transistors on a given chip, some will perform worse that others.

Another challenge to overcome is the resulting power loss. The power available is proportional to the square of the voltage, such that a 10 percent reduction in voltage leads to a 19 percent reduction in power. While this reduced voltage would be a great way to increase efficiency, it would also be a great way to ensure your CPU does not have the juice required to run what it needs to.

Further, NTV significantly decreases frequency. “The 32nm Pentium core,” Kanter said about a core that ran using NTV “increased efficiency by about 5×, by running at slightly under 100MHz. The maximum frequency was 915MHz, so the absolute performance decreased by about an order of magnitude.”

As he notes, NTV would be impractical for general-purpose CPUs, as they are generally used for applications that expect reasonable single-threaded performance. Thus they require the higher voltages needed to drive faster clocks. On the other hand, HPC and its massively parallel computing environment could benefit greatly from NTV.

“Based on our analysis of these papers,” Kanter wrote, “Near-Threshold Voltage computing techniques are most applicable to highly parallel workloads. Generally, NTV is an ideal fit for HPC workloads and works very well for graphics, but not general purpose CPUs.”

Since HPC is highly parallelized and requires backups and fail-safe mechanisms throughout a computation, it can withstand the consequences of a single transistor giving out. HPC computations are also not expected to happen anywhere near real time, making the frequency decrease less of a problem. This is especially true of “throughput” accelerators like GPGPUs and Intel’s Xeon Phi, which are naturally frequency-constrained because of their high core counts.

There is a sense that this technology is being developed to specifically benefit HPC rather than it accidentally doing so. This is not only hinted at by the Intel papers themselves, but is also indirectly supported by the people funding the papers, specifically the US Government. “Perhaps most telling,” Kanter wrote, “US government grants typically focus on areas of national interest. Graphics simply is not vital to the country, whereas HPC is a critical tool for the Departments of Defense, Energy, and any number of intelligence agencies.”

Subscribe to HPCwire's Weekly Update!

Be the most informed person in the room! Stay ahead of the tech trends with industy updates delivered to you every week!

Quantum-circuit Cutting Fills a Gaping Quantum Computing Hole

December 5, 2022

A universal quantum computer with a million qubits will solve a wide range of problems, but even then, offloading entire problems to a quantum circuit may not be the best use of resources. With that in mind, companies and researchers are paying more attention to the concept of quantum-circuit cutting, which breaks down large quantum circuits into smaller fragments for execution across... Read more…

From Exasperation to Exascale: HPE’s Nic Dubé on Frontier’s Untold Story

December 2, 2022

The Frontier supercomputer – still fresh off its chart-topping 1.1 Linpack exaflops run and maintaining its number-one spot on the Top500 list – was still very much in the spotlight at SC22 in Dallas last month. Six Read more…

At SC22, Carbon Emissions and Energy Costs Eclipsed Hardware Efficiency

December 2, 2022

The race to ever-better flops-per-watt and power usage effectiveness (PUE) has, historically, dominated the conversation over sustainability in HPC – but at SC22, held last month in Dallas, something felt different. Ac Read more…

HPC Career Notes: December 2022 Edition

December 1, 2022

In this monthly feature, we’ll keep you up-to-date on the latest career developments for individuals in the high-performance computing community. Whether it’s a promotion, new company hire, or even an accolade, we’ Read more…

IBM Quantum Summit: Osprey Flies; Error Handling Progress; Quantum-centric Supercomputing

December 1, 2022

Part scorecard, part grand vision, IBM’s annual Quantum Summit held last month is a fascinating snapshot of IBM’s progress, evolving technology roadmap, and issues facing the quantum landscape broadly. Thankfully, IB Read more…

AWS Solution Channel

Shutterstock 1748437547

New – Amazon EC2 Hpc6id Instances Optimized for High Performance Computing

We have given you the flexibility and ability to run the largest and most complex high performance computing (HPC) workloads with Amazon Elastic Compute Cloud (Amazon EC2) instances that feature enhanced networking like C5nC6gnR5n, M5n, and our recently launched HPC instances Hpc6a. Read more…

 

shutterstock_1431394361

AI and the need for purpose-built cloud infrastructure

Modern AI solutions augment human understanding, preferences, intent, and even spoken language. AI improves our knowledge and understanding by delivering faster, more informed insights that fuel transformation beyond anything previously imagined. Read more…

AWS Introduces a Flurry of New EC2 Instances at re:Invent

November 30, 2022

AWS has announced three new Amazon Elastic Compute Cloud (Amazon EC2) instances powered by AWS-designed chips, as well as several new Intel-powered instances – including ones targeting HPC – at its AWS re:Invent 2022 Read more…

Shutterstock 1194728515

Quantum-circuit Cutting Fills a Gaping Quantum Computing Hole

December 5, 2022

A universal quantum computer with a million qubits will solve a wide range of problems, but even then, offloading entire problems to a quantum circuit may not be the best use of resources. With that in mind, companies and researchers are paying more attention to the concept of quantum-circuit cutting, which breaks down large quantum circuits into smaller fragments for execution across... Read more…

From Exasperation to Exascale: HPE’s Nic Dubé on Frontier’s Untold Story

December 2, 2022

The Frontier supercomputer – still fresh off its chart-topping 1.1 Linpack exaflops run and maintaining its number-one spot on the Top500 list – was still v Read more…

At SC22, Carbon Emissions and Energy Costs Eclipsed Hardware Efficiency

December 2, 2022

The race to ever-better flops-per-watt and power usage effectiveness (PUE) has, historically, dominated the conversation over sustainability in HPC – but at S Read more…

HPC Career Notes: December 2022 Edition

December 1, 2022

In this monthly feature, we’ll keep you up-to-date on the latest career developments for individuals in the high-performance computing community. Whether it Read more…

IBM Quantum Summit: Osprey Flies; Error Handling Progress; Quantum-centric Supercomputing

December 1, 2022

Part scorecard, part grand vision, IBM’s annual Quantum Summit held last month is a fascinating snapshot of IBM’s progress, evolving technology roadmap, and Read more…

AWS Introduces a Flurry of New EC2 Instances at re:Invent

November 30, 2022

AWS has announced three new Amazon Elastic Compute Cloud (Amazon EC2) instances powered by AWS-designed chips, as well as several new Intel-powered instances Read more…

Quantum Riches and Hardware Diversity Are Discouraging Collaboration

November 28, 2022

Quantum computing is viewed as a technology for generations, and the spoils for the winners are huge, but the diversity of technology is discouraging collaborat Read more…

2022 HPC Road Trip: Los Alamos

November 23, 2022

With SC22 in the rearview mirror, it’s time to get back to the 2022 Great American Supercomputing Road Trip. To refresh everyone’s memory, I jumped in the c Read more…

Nvidia Shuts Out RISC-V Software Support for GPUs 

September 23, 2022

Nvidia is not interested in bringing software support to its GPUs for the RISC-V architecture despite being an early adopter of the open-source technology in its GPU controllers. Nvidia has no plans to add RISC-V support for CUDA, which is the proprietary GPU software platform, a company representative... Read more…

RISC-V Is Far from Being an Alternative to x86 and Arm in HPC

November 18, 2022

One of the original RISC-V designers this week boldly predicted that the open architecture will surpass rival chip architectures in performance. "The prediction is two or three years we'll be surpassing your architectures and available performance with... Read more…

AWS Takes the Short and Long View of Quantum Computing

August 30, 2022

It is perhaps not surprising that the big cloud providers – a poor term really – have jumped into quantum computing. Amazon, Microsoft Azure, Google, and th Read more…

Chinese Startup Biren Details BR100 GPU

August 22, 2022

Amid the high-performance GPU turf tussle between AMD and Nvidia (and soon, Intel), a new, China-based player is emerging: Biren Technology, founded in 2019 and headquartered in Shanghai. At Hot Chips 34, Biren co-founder and president Lingjie Xu and Biren CTO Mike Hong took the (virtual) stage to detail the company’s inaugural product: the Biren BR100 general-purpose GPU (GPGPU). “It is my honor to present... Read more…

AMD Thrives in Servers amid Intel Restructuring, Layoffs

November 12, 2022

Chipmakers regularly indulge in a game of brinkmanship, with an example being Intel and AMD trying to upstage one another with server chip launches this week. But each of those companies are in different positions, with AMD playing its traditional role of a scrappy underdog trying to unseat the behemoth Intel... Read more…

Tesla Bulks Up Its GPU-Powered AI Super – Is Dojo Next?

August 16, 2022

Tesla has revealed that its biggest in-house AI supercomputer – which we wrote about last year – now has a total of 7,360 A100 GPUs, a nearly 28 percent uplift from its previous total of 5,760 GPUs. That’s enough GPU oomph for a top seven spot on the Top500, although the tech company best known for its electric vehicles has not publicly benchmarked the system. If it had, it would... Read more…

JPMorgan Chase Bets Big on Quantum Computing

October 12, 2022

Most talk about quantum computing today, at least in HPC circles, focuses on advancing technology and the hurdles that remain. There are plenty of the latter. F Read more…

New C++ Sender Library Enables Portable Asynchrony

December 5, 2022

NVIDIA is excited to announce the release of the stdexec library on GitHub and in the 22.11 release of the NVIDIA HPC Software Development Kit. The stdexec libr Read more…

Leading Solution Providers

Contributors

Using Exascale Supercomputers to Make Clean Fusion Energy Possible

September 2, 2022

Fusion, the nuclear reaction that powers the Sun and the stars, has incredible potential as a source of safe, carbon-free and essentially limitless energy. But Read more…

Nvidia, Qualcomm Shine in MLPerf Inference; Intel’s Sapphire Rapids Makes an Appearance.

September 8, 2022

The steady maturation of MLCommons/MLPerf as an AI benchmarking tool was apparent in today’s release of MLPerf v2.1 Inference results. Twenty-one organization Read more…

UCIe Consortium Incorporates, Nvidia and Alibaba Round Out Board

August 2, 2022

The Universal Chiplet Interconnect Express (UCIe) consortium is moving ahead with its effort to standardize a universal interconnect at the package level. The c Read more…

SC22 Unveils ACM Gordon Bell Prize Finalists

August 12, 2022

Courtesy of the schedule for the SC22 conference, we now have our first glimpse at the finalists for this year’s coveted Gordon Bell Prize. The Gordon Bell Pr Read more…

AMD’s Genoa CPUs Offer Up to 96 5nm Cores Across 12 Chiplets

November 10, 2022

AMD’s fourth-generation Epyc processor line has arrived, starting with the “general-purpose” architecture, called “Genoa,” the successor to third-gen Eypc Milan, which debuted in March of last year. At a launch event held today in San Francisco, AMD announced the general availability of the latest Epyc CPUs with up to 96 TSMC 5nm Zen 4 cores... Read more…

Intel Is Opening up Its Chip Factories to Academia

October 6, 2022

Intel is opening up its fabs for academic institutions so researchers can get their hands on physical versions of its chips, with the end goal of boosting semic Read more…

AMD Previews 400 Gig Adaptive SmartNIC SOC at Hot Chips

August 24, 2022

Fresh from finalizing its acquisitions of FPGA provider Xilinx (Feb. 2022) and DPU provider Pensando (May 2022) ), AMD previewed what it calls a 400 Gig Adaptive smartNIC SOC yesterday at Hot Chips. It is another contender in the increasingly crowded and blurry smartNIC/DPU space where distinguishing between the two isn’t always easy. The motivation for these device types... Read more…

Google Program to Free Chips Boosts University Semiconductor Design

August 11, 2022

A Google-led program to design and manufacture chips for free is becoming popular among researchers and computer enthusiasts. The search giant's open silicon program is providing the tools for anyone to design chips, which then get manufactured. Google foots the entire bill, from a chip's conception to delivery of the final product in a user's hand. Google's... Read more…

  • arrow
  • Click Here for More Headlines
  • arrow
HPCwire