Quantum Bits: Rigetti Opens Access to Aspen-M; JPMorgan’s New QKD; Classiq Nets $33M, More

By John Russell

February 17, 2022

It’s been a busy week in quantum computing. Rigetti began providing much wider access to its 80-qubit system (Aspen-M), announced a collaboration with Nasdaq to develop FS apps, and struck a deal with Arm-based chip supplier Ampere to develop hybrid classical-quantum platforms.

Elsewhere, JPMorgan Chase, Toshiba, and Ciena reported successfully demonstrating a “first-of-its-kind” Quantum Key Distribution network for metropolitan areas that resists quantum computing attacks and supports 800Gbps data rates; UColorado’s CUbit Quantum Initiative added commercial members; Classiq took in $33M more in funding; and Israel’s Defense Ministry announced plans to develop a quantum computer.

Let’s start with Rigetti’s announcements.

Last June, the Berkeley-based company introduced its multi-chip design for quantum processors (QPUs); in December, it introduced Aspen-M, the first of those designs, an 80-qubit multi-chip quantum processor. Scaling up QPU size is an ongoing challenge throughout the quantum community, with several companies exploring multi-chip approaches. Rigetti is perhaps furthest along in those efforts, and has said the multi-chip approach is critical to building quantum computers large enough (by number of qubits) to tackle practical problems.

After initially allowing only limited access to Aspen-M, Rigetti has now expanded access to the new chip.

Rigetti’s 80-qubit Aspen-M: a commercial multi-chip quantum processor.

The company reported that “Aspen-M is now available on Rigetti Quantum Cloud Services and will support a number of Rigetti collaborations taking place with both enterprise and public sector customers including Nasdaq, Deloitte, DARPA and the U.S. Department of Energy. Beginning today, Aspen-M will also be available to end users on Amazon Braket, marking the latest in a series of increasingly powerful Rigetti systems offered through the service since Amazon Braket’s launch in 2019. In addition, Rigetti expects the 80-qubit system to be available through Azure Quantum, Strangeworks QC and Zapata’s Orquestra platform in the coming months.”

Of note, Rigetti chose to use an IBM-developed metric – CLOPS, or circuit layer operations per second – to characterize both its recent single-chip Aspen-11 (40 qubits) and its multi-chip Aspen-M (80 qubits) processors. Here’s an excerpt from the announcement:

“Conducting tests based on 100 shots, as set forth in the original published definition, the 40-qubit Aspen-11 system demonstrated a CLOPS of 844, while the 80-qubit Aspen-M system demonstrated a CLOPS of 892. These results suggest that current Rigetti systems perform as well or better on this CLOPS speed test as the number of qubits in the system increases. By comparison, IBM’s published CLOPS scores for systems with 5, 27, and 65 qubits were 1419, 951, and 753, respectively, as of the October 2021 publishing date.

“To reflect what users can potentially expect in typical use cases, Rigetti also evaluated CLOPS using 1000 shots. In this case, Aspen-11 performed at 7512 CLOPS and Aspen-M performed at 8333 CLOPS, demonstrating that comparable or better system speed persists at both higher shot counts and higher qubit counts. These speed tests were conducted using the production Rigetti QCS environment.[i]”

As IBM’s Katie Pizzolato (director, quantum theory & applications systems) noted at IBM’s Quantum Summit late last year: “There’s no getting away from it. Useful quantum computing requires running lots of circuits. Most applications require running at least a billion. If it takes my system more than five milliseconds to run a circuit, it’s simple math, a billion circuits will take you 58 days; that’s not useful quantum computing.”

Speed – CLOPS – matters.

Chad Rigetti, CEO

Rigetti founder and CEO Chad Rigetti said in the announcement: “Last year we introduced the world to our proprietary multi-chip technology. We believe our approach to building quantum computers has tremendous advantages, including allowing us to meet the challenges of scaling to systems capable of solving real-world problems. Aspen-M is our first commercial system based on this multi-chip technology. Today, we are excited to make Aspen-M generally available to our customers and to release the initial results of system speed tests run on Aspen-M through our production platform.”

Rigetti’s deal with Nasdaq is also significant. Financial services applications are expected to be among the low-hanging fruit for quantum computing. Secure communication, anchored by quantum key distribution technology is one likely use, but so are optimization functions and risk assessment applications. Nasdaq is home to many tech stocks and has a reputation for being an early adopter of technology.

The collaboration will leverage use of Rigetti’s new Aspen-M multi-chip processor and focus on “machine learning, optimization and simulation problems with Nasdaq’s market perspective, domain expertise and data,” say the companies. The collaboration will evaluate financial applications that “may benefit from the ability of quantum computing to solve computational problems with improved accuracy, speed, or cost.”

Fraud detection, order matching and risk management are cited as key targets. The two companies “are expected to pursue the development of algorithms and software with the goal of demonstrating the advantages of hybrid quantum-classical computers for solving the identified problems,” according to the announcement.

Lastly, Rigetti and Ampere today announced a strategic partnership to create hybrid quantum-classical computers designed to unlock a new generation of machine learning applications over the cloud.

According to the announcement, “The two companies will integrate Rigetti Quantum Processing Units (QPUs) with Ampere Altra Max cloud-native processors to create a hybrid computing environment intended to meet the rigorous demands of machine learning applications. This tight coupling of processing power has the goal of enabling the discovery and deployment of high performance machine learning algorithms, with Ampere Altra Max powered cloud servers expected to process vast amounts of data in concert with quantum calculations performed on Rigetti QPUs.”

This is an interesting deal; it gets Arm into the quantum game. Intel (x86 architecture) has long had a quantum effort that is developing both quantum processor technology based on silicon dots (spin-based qubits) and specialized cryo-controller chips. Intel has said it plans to leverage its CMOS manufacturing technology to scale its efforts. IBM likewise has both quantum and silicon chip expertise.

Renee James, Ampere’s founder and CEO, said, “Our collaboration with Rigetti is a natural extension of our strategy to create cloud native processors optimized for a wide range of workloads and customer needs. Quantum machine learning is emerging as a significant opportunity for scientific computing users and their providers of public and private clouds. We believe that Ampere and Rigetti will enable quantum computations of increased complexity, with the potential for higher performance at lower costs.”

The two companies “anticipate working together to optimize quantum computer simulation software to run on Ampere Altra Max processors. Quantum computer simulators enable developers to study and benchmark algorithms and applications by executing quantum circuits on classical computers before running the programs on actual quantum computers. With a simulator optimized for Altra Max, it is expected that Rigetti customers will have the ability to build and test quantum computations of increased complexity, with higher performance, at lower costs.”

Impressive triumvirate tackles QKD

Today, financial services giant JPMorgan Chase, chip and systems giant Toshiba, and networking power Ciena reported demonstrating “full viability of a first-of-its-kind Quantum Key Distribution (QKD) network for metropolitan areas, resistant to quantum computing attacks and capable of supporting 800 Gbps data rates.”

Quantum key distribution (QKD), of course, isn’t new, but it is increasingly important as modern classical computers get better at decryption and as we approach practical quantum computers that should be able to crack any existing codes. The critical prevention step is being able to detect any attempt to intercept and read encryption keys quickly and easily. QKD does this by using quantum-encoded photons, which are encoded such that an attempt to “listen in” (measure them) changes the photons and is instantly detected.

As described by a JPMorgan spokesman: “The measurement of photons transmitted in a fiber optic channel are used to generate keys, that are then exchanged and synchronized by a pair of QKD servers and used by cryptographic algorithms to encrypt and decrypt the information. The main security benefit behind QKD is the ability of the two communicating parties to detect disturbances in the fiber (e.g. eavesdropping attempts) enabling them to take appropriate action.” (Here’s a brief description of QKD.)

The collaborators published a paper today describing their work. Here’s portion of the abstract:

“To the best of our knowledge, this is the first time that an 800 Gbps quantum-secured optical channel—along with several other Dense Wavelength Division Multiplexed (DWDM) channels on the C-band and multiplexed with the QKD channel on the O- band—was established at distances up to 100 km, with secure-key rates relevant for practical industry use cases. In addition, during the course of these trials, transporting a blockchain application over this established channel was utilized as a demonstration of securing a financial transaction in transit over a quantum-secured optical channel.

“In a real-world operational environment, deployment of such high-capacity quantum-secured optical channels multiplexed with the quantum channel will inevitably introduce challenges due to their strict requirements, such as high launch powers and polarization fluctuations. Therefore, in the course of this re- search, experimental studies were conducted on the impact on the system performance—and specifically on the quantum channel—of several degradation factors present in real-world operational environments, including inter-channel interference (due to Raman scattering and nonlinear effects), attenuation, polarization fluctuations and distance dependency. The findings of this research pave the way towards the deployment of QKD- secured optical channels in high-capacity, metro-scale, mission- critical operational environments, such as Inter-Data Center Interconnects.”

Figures from the paper showing the experiment setup are below. Click to enlarge.

The work used a QKD-secured optical channel to deploy and secure Liink by J.P. Morgan, which JPMorgan describes as a production-grade, peer-to-peer blockchain network. Snapshot of the results:

  • A QKD channel was multiplexed on the same fiber as ultra-high bandwidth 800 Gbps optical channels for the first time and used to provide keys for encryption of the data stream.
  • Co-existence of the quantum channel with two 800 Gbps and eight 100 Gbps channels was demonstrated for a 70km fiber line, with a key rate sufficient to support up to 258 AES-256 encrypted channels at a key refresh rate of one key/sec.
  • Operation of QKD and the ten high-bandwidth channels was demonstrated for distances up to 100km.
  • The proof of concept network infrastructure relied on Toshiba’s Multiplexed QKD System, manufactured by Toshiba Europe at their Cambridge UK base, and Ciena’s Waveserver 5 platform, equipped with 800 Gbps optical-layer encryption and open APIs running over Ciena’s 6500 photonic solution. The tests were conducted in JPMorgan Chase’s fiber optic production simulation lab.

Marco Pistoia, distinguished engineer and head of the JPMorgan Chase’s FLARE (Future Lab for Applied Research and Engineering) is quoted in the release: “This work comes at an important time as we continue to prepare for the introduction of production-quality quantum computers, which will change the security landscape of technologies like blockchain and cryptocurrency in the foreseeable future.”

CU Boulder adds four industry partners to CUbit

Three companies – Atom Computing, ColdQuanta and Meadowlark Optics – and SPIE (the international society for optics and photonics) joined University of Colorado’s (CU Boulder) CUbit Quantum Initiative as members of its partners’ program. Regional efforts such CQI have been sprouting up around the country, seeking to leverage academic and commercial resources to develop quantum computing and quantum information sciences.

The partners program, according to CQI, is intended to cultivate “mutually beneficial collaborations with quantum-intensive enterprises.” No specific projects were cited, but the broad idea is to “accelerate CU Boulder’s quantum efforts, including through providing unique insights related to research and training, collaborating on workforce development programs, and providing real-world opportunities for CU Boulder students, postdocs and researchers.”

“We’re tremendously excited to welcome the first CUbit Innovation Partners as we launch our corporate partnership program,” said Philip Makotyn, executive director of the CUbit Quantum Initiative. “Building on existing close relationships, the program is an important step bringing together academics, national labs and industry to build a strong quantum ecosystem. The new members represent an important step supporting the national priority of quantum technologies.”

“Atom Computing has joined forces with the CUbit Quantum Initiative to drive critical R&D and talent development in Quantum Information Science,” said Rob Hays, CEO, Atom Computing. “As a member of the CUbit Advisory board, we will leverage our deep ties across CU Boulder and collaboration with other ecosystem players as a springboard to accelerate large-scale quantum computing, helping researchers and scientists reach their next big breakthrough.” Hays also has posted a blog about the partnership.

Classiq raises $33M in Series B round

Founded in May 2020, Tel Aviv-based Classiq is one of many young quantum software companies working to develop tools to ease and speed development of algorithms for use on quantum hardware. Today, it reported raising $33 million in a Series B round, which the company touts as “another sign that the world is moving from quantum exploration to quantum production – and that quantum software development is a key ingredient in gaining quantum advantage.” Indeed, Classiq is part of the rapid expansion of the quantum computing ecosystem.

Investors, according to Classiq, include: “Hewlett Packard Pathfinder, the venture capital program of Hewlett Packard Enterprise (HPE); Phoenix, a $60-billion insurance company; Spike Ventures, a Stanford alumni investor group; and Samsung NEXT, the investment arm of Samsung are new investors in the company. This round also included personal investments from Lip-Bu Tan and  Harvey Jones, joining existing investors Wing VC, Team8, Entrée Capital, Sumitomo Corp. (through IN Venture) and OurCrowd. This new round brings Classiq’s total funding to $48 million in 20 months of existence.”

“We welcome our new investors and are grateful for the continued support of our existing ones. Together, we are paving the fastest way towards quantum advantage and the only way beyond it,” said Nir Minerbi, co-founder and CEO at Classiq. “This new funding comes at a pivotal time. The quantum industry is now moving from consulting services to quantum products and from prototyping to production. With this funding, we will expand upon our work to become the platform on which forward-thinking organizations develop game-changing quantum software that makes the impossible possible.”

Classiq says it will use the new funds to quadruple the size of the company by expanding its team of world-class engineers and researchers, opening new offices around the globe, and continuing to develop and file revolutionary quantum algorithm design patents.

Paul Glaser, vice president and head of Hewlett Packard Pathfinder, is quoted as saying, “We were impressed by Classiq’s novel synthesis engine that automates the creation of quantum circuits and leads to significantly lower barriers of entry for quantum computing.”

Boaz Morris, investment manager at Phoenix, said, “While quantum hardware has made impressive progress, the software used to operate these advanced computers remains woefully inadequate. Classiq’s hardware-agnostic platform enables enterprises to develop sophisticated quantum software faster and better than any other method. We are thrilled to partner with the world-class team at Classiq as they continue to execute on their vision and become the leader in the quantum software stack.”

Israel Defense Ministry plans quantum computing investment

Government funding spigots throughout the world are being opened to advance quantum computing and avoid losing ground to rivals. Now, a report yesterday in The Times of Israel has said that the “Israeli Innovation Authority and the Defense Ministry will spend approximately NIS 200 million ($62 million) to develop Israel’s first quantum computer and lay the foundation for Israeli computational ability, which they said would lead to future developments in economics, technology, security, engineering, and science.”

According to the article, “[T]he budget will fund two parallel avenues. The Israel Innovation Authority will focus on developing the infrastructure for quantum computational ability which, it said, may include the use of technology from abroad. The Defense Ministry’s Directorate of Defense Research and Development (DDR&D), meanwhile, will establish a national center with quantum capabilities that will work with academia, industry, and government partners to develop a quantum processor and then a complete quantum computer.”

Bonus (qu)bits…

IonQ and Pacific Northwest National Laboratory today reported generating a “sustainable and robust source of barium qubits” for IonQ’s next-generation quantum computers. IonQ believes that this collaboration will supply barium qubits for its quantum computers in perpetuity, a key step as the company begins to scale its manufacturing operations. Rigetti today reported it achieved “entangling gate fidelities as high as 99.5% on its next-generation chip architecture,” crossing what is believed to be a key threshold for commercial quantum computing.

Note:

[i] CLOPS is calculated as M × K × S × D / time taken where: M = number of templates = 100; K = number of parameter updates = 10; S = number of shots = 100 (or 1000); and D = number of QV layers = log2 QV.  To Rigetti’s knowledge, CLOPS as a speed test has not been investigated or verified by any independent third party.  In addition, while Rigetti applied the above formula in testing the speed of Aspen-M and Aspen-11, there is no guarantee that Rigetti applied the test in the same way as IBM and, as a result, any variability in the application of the test as between Rigetti, IBM or others in the industry that may apply CLOPS in the future could render CLOPS scores incomparable and actual relative performance may materially differ from reported results.

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!

Is Time Running Out for Compromise on America COMPETES/USICA Act?

June 22, 2022

You may recall that efforts proposed in 2020 to remake the National Science Foundation (Endless Frontier Act) have since expanded and morphed into two gigantic bills, the America COMPETES Act in the U.S. House of Representatives and the U.S. Innovation and Competition Act in the U.S. Senate. So far, efforts to reconcile the two pieces of legislation have snagged and recent reports... Read more…

Cerebras Systems Thinks Forward on AI Chips as it Claims Performance Win

June 22, 2022

Cerebras Systems makes the largest chip in the world, but is already thinking about its upcoming AI chips as learning models continue to grow at breakneck speed. The company’s latest Wafer Scale Engine chip is indeed the size of a wafer, and is made using TSMC’s 7nm process. The next chip will pack in more cores to handle the fast-growing compute needs of AI, said Andrew Feldman, CEO of Cerebras Systems. Read more…

AMD’s MI300 APUs to Power Exascale El Capitan Supercomputer

June 21, 2022

Additional details of the architecture of the exascale El Capitan supercomputer were disclosed today by Lawrence Livermore National Laboratory’s (LLNL) Terri Quinn in a presentation delivered to the 79th HPC User Forum Read more…

IDC Perspective on Integration of Quantum Computing and HPC

June 20, 2022

The insatiable need to compress time to insights from massive and complex datasets is fueling the demand for quantum computing integration into high performance computing (HPC) environments. Such an integration would allow enterprises to accelerate and optimize current HPC applications and processes by simulating and emulating them on today’s noisy... Read more…

Q&A with Intel’s Jeff McVeigh, an HPCwire Person to Watch in 2022

June 17, 2022

HPCwire presents our interview with Jeff McVeigh, vice president and general manager, Super Compute Group, Intel Corporation, and an HPCwire 2022 Person to Watch. McVeigh shares Intel's plans for the year ahead, his pers Read more…

AWS Solution Channel

Shutterstock 152995403

Bayesian ML Models at Scale with AWS Batch

This post was contributed by Ampersand’s Jeffrey Enos, Senior Machine Learning Engineer, Daniel Gerlanc, Senior Director for Data Science, and Brandon Willard, Data Science Lead. Read more…

Microsoft/NVIDIA Solution Channel

Shutterstock 261863138

Using Cloud-Based, GPU-Accelerated AI for Financial Risk Management

There are strict rules governing financial institutions with a number of global regulatory groups publishing financial compliance requirements. Financial institutions face many challenges and legal responsibilities for risk management, compliance violations, and failure to catch financial fraud. Read more…

Nvidia, Intel to Power Atos-Built MareNostrum 5 Supercomputer

June 16, 2022

The long-troubled, hotly anticipated MareNostrum 5 supercomputer finally has a vendor: Atos, which will be supplying a system that includes both Nvidia and Intel CPUs and GPUs across multiple partitions. The newly reimag Read more…

Is Time Running Out for Compromise on America COMPETES/USICA Act?

June 22, 2022

You may recall that efforts proposed in 2020 to remake the National Science Foundation (Endless Frontier Act) have since expanded and morphed into two gigantic bills, the America COMPETES Act in the U.S. House of Representatives and the U.S. Innovation and Competition Act in the U.S. Senate. So far, efforts to reconcile the two pieces of legislation have snagged and recent reports... Read more…

Cerebras Systems Thinks Forward on AI Chips as it Claims Performance Win

June 22, 2022

Cerebras Systems makes the largest chip in the world, but is already thinking about its upcoming AI chips as learning models continue to grow at breakneck speed. The company’s latest Wafer Scale Engine chip is indeed the size of a wafer, and is made using TSMC’s 7nm process. The next chip will pack in more cores to handle the fast-growing compute needs of AI, said Andrew Feldman, CEO of Cerebras Systems. Read more…

AMD’s MI300 APUs to Power Exascale El Capitan Supercomputer

June 21, 2022

Additional details of the architecture of the exascale El Capitan supercomputer were disclosed today by Lawrence Livermore National Laboratory’s (LLNL) Terri Read more…

IDC Perspective on Integration of Quantum Computing and HPC

June 20, 2022

The insatiable need to compress time to insights from massive and complex datasets is fueling the demand for quantum computing integration into high performance computing (HPC) environments. Such an integration would allow enterprises to accelerate and optimize current HPC applications and processes by simulating and emulating them on today’s noisy... Read more…

Q&A with Intel’s Jeff McVeigh, an HPCwire Person to Watch in 2022

June 17, 2022

HPCwire presents our interview with Jeff McVeigh, vice president and general manager, Super Compute Group, Intel Corporation, and an HPCwire 2022 Person to Watc Read more…

Nvidia, Intel to Power Atos-Built MareNostrum 5 Supercomputer

June 16, 2022

The long-troubled, hotly anticipated MareNostrum 5 supercomputer finally has a vendor: Atos, which will be supplying a system that includes both Nvidia and Inte Read more…

D-Wave Debuts Advantage2 Prototype; Seeks User Exploration and Feedback

June 16, 2022

Starting today, D-Wave Systems is providing access to a 500-plus-qubit prototype of its forthcoming 7000-qubit Advantage2 quantum annealing computer, which is d Read more…

AMD Opens Up Chip Design to the Outside for Custom Future

June 15, 2022

AMD is getting personal with chips as it sets sail to make products more to the liking of its customers. The chipmaker detailed a modular chip future in which customers can mix and match non-AMD processors in a custom chip package. "We are focused on making it easier to implement chips with more flexibility," said Mark Papermaster, chief technology officer at AMD during the analyst day meeting late last week. Read more…

Nvidia R&D Chief on How AI is Improving Chip Design

April 18, 2022

Getting a glimpse into Nvidia’s R&D has become a regular feature of the spring GTC conference with Bill Dally, chief scientist and senior vice president of research, providing an overview of Nvidia’s R&D organization and a few details on current priorities. This year, Dally focused mostly on AI tools that Nvidia is both developing and using in-house to improve... Read more…

Royalty-free stock illustration ID: 1919750255

Intel Says UCIe to Outpace PCIe in Speed Race

May 11, 2022

Intel has shared more details on a new interconnect that is the foundation of the company’s long-term plan for x86, Arm and RISC-V architectures to co-exist in a single chip package. The semiconductor company is taking a modular approach to chip design with the option for customers to cram computing blocks such as CPUs, GPUs and AI accelerators inside a single chip package. Read more…

The Final Frontier: US Has Its First Exascale Supercomputer

May 30, 2022

In April 2018, the U.S. Department of Energy announced plans to procure a trio of exascale supercomputers at a total cost of up to $1.8 billion dollars. Over the ensuing four years, many announcements were made, many deadlines were missed, and a pandemic threw the world into disarray. Now, at long last, HPE and Oak Ridge National Laboratory (ORNL) have announced that the first of those... Read more…

AMD/Xilinx Takes Aim at Nvidia with Improved VCK5000 Inferencing Card

March 8, 2022

AMD/Xilinx has released an improved version of its VCK5000 AI inferencing card along with a series of competitive benchmarks aimed directly at Nvidia’s GPU line. AMD says the new VCK5000 has 3x better performance than earlier versions and delivers 2x TCO over Nvidia T4. AMD also showed favorable benchmarks against several Nvidia GPUs, claiming its VCK5000 achieved... Read more…

Top500: Exascale Is Officially Here with Debut of Frontier

May 30, 2022

The 59th installment of the Top500 list, issued today from ISC 2022 in Hamburg, Germany, officially marks a new era in supercomputing with the debut of the first-ever exascale system on the list. Frontier, deployed at the Department of Energy’s Oak Ridge National Laboratory, achieved 1.102 exaflops in its fastest High Performance Linpack run, which was completed... Read more…

Newly-Observed Higgs Mode Holds Promise in Quantum Computing

June 8, 2022

The first-ever appearance of a previously undetectable quantum excitation known as the axial Higgs mode – exciting in its own right – also holds promise for developing and manipulating higher temperature quantum materials... Read more…

Nvidia Launches Hopper H100 GPU, New DGXs and Grace Superchips

March 22, 2022

The battle for datacenter dominance keeps getting hotter. Today, Nvidia kicked off its spring GTC event with new silicon, new software and a new supercomputer. Speaking from a virtual environment in the Nvidia Omniverse 3D collaboration and simulation platform, CEO Jensen Huang introduced the new Hopper GPU architecture and the H100 GPU... Read more…

PsiQuantum’s Path to 1 Million Qubits

April 21, 2022

PsiQuantum, founded in 2016 by four researchers with roots at Bristol University, Stanford University, and York University, is one of a few quantum computing startups that’s kept a moderately low PR profile. (That’s if you disregard the roughly $700 million in funding it has attracted.) The main reason is PsiQuantum has eschewed the clamorous public chase for... Read more…

Leading Solution Providers

Contributors

ISC 2022 Booth Video Tours

AMD
AWS
DDN
Dell
Intel
Lenovo
Microsoft
PENGUIN SOLUTIONS

Intel Reiterates Plans to Merge CPU, GPU High-performance Chip Roadmaps

May 31, 2022

Intel reiterated it is well on its way to merging its roadmap of high-performance CPUs and GPUs as it shifts over to newer manufacturing processes and packaging technologies in the coming years. The company is merging the CPU and GPU lineups into a chip (codenamed Falcon Shores) which Intel has dubbed an XPU. Falcon Shores... Read more…

AMD Opens Up Chip Design to the Outside for Custom Future

June 15, 2022

AMD is getting personal with chips as it sets sail to make products more to the liking of its customers. The chipmaker detailed a modular chip future in which customers can mix and match non-AMD processors in a custom chip package. "We are focused on making it easier to implement chips with more flexibility," said Mark Papermaster, chief technology officer at AMD during the analyst day meeting late last week. Read more…

India Launches Petascale ‘PARAM Ganga’ Supercomputer

March 8, 2022

Just a couple of weeks ago, the Indian government promised that it had five HPC systems in the final stages of installation and would launch nine new supercomputers this year. Now, it appears to be making good on that promise: the country’s National Supercomputing Mission (NSM) has announced the deployment of “PARAM Ganga” petascale supercomputer at Indian Institute of Technology (IIT)... Read more…

Nvidia Dominates MLPerf Inference, Qualcomm also Shines, Where’s Everybody Else?

April 6, 2022

MLCommons today released its latest MLPerf inferencing results, with another strong showing by Nvidia accelerators inside a diverse array of systems. Roughly fo Read more…

AMD’s MI300 APUs to Power Exascale El Capitan Supercomputer

June 21, 2022

Additional details of the architecture of the exascale El Capitan supercomputer were disclosed today by Lawrence Livermore National Laboratory’s (LLNL) Terri Read more…

Nvidia, Intel to Power Atos-Built MareNostrum 5 Supercomputer

June 16, 2022

The long-troubled, hotly anticipated MareNostrum 5 supercomputer finally has a vendor: Atos, which will be supplying a system that includes both Nvidia and Inte Read more…

Industry Consortium Forms to Drive UCIe Chiplet Interconnect Standard

March 2, 2022

A new industry consortium aims to establish a die-to-die interconnect standard – Universal Chiplet Interconnect Express (UCIe) – in support of an open chipl Read more…

Covid Policies at HPC Conferences Should Reflect HPC Research

June 6, 2022

Supercomputing has been indispensable throughout the Covid-19 pandemic, from modeling the virus and its spread to designing vaccines and therapeutics. But, desp Read more…

  • arrow
  • Click Here for More Headlines
  • arrow
HPCwire