Next Euro HPC Chip Coming Next Year Will Be in 2026 EU Exascale System

By Agam Shah

March 7, 2024

The next supercomputing chip for Europe’s homegrown exascale supercomputer will come next year, according to an updated product roadmap.

The 2025-bound Rhea-2 chip will succeed the Rhea-1 chip, the Arm-based CPU powering Jupiter, Europe’s first exascale supercomputer, which is under construction and will go online next year.

The Rhea-2 chip will come from French company SiPearl and is part of a European initiative to develop homegrown CPUs, AI, embedded and automotive chips. The EU-funded effort, called the European Processor Initiative (EPI), was the driving force behind Rhea-1.

Rhea-2 will appear in an exascale supercomputer in Europe in 2026, most likely the Jules Vernes system hosted in France.

The release date of Rhea-2 and its implementation in a supercomputer was published in an EPI poster ahead of the EuroHPC Summit, which will be held between March 18-20 in Antwerp, Belgium.

EPI Roadmap (Click for larger Image) Source EPI.

The summit will bring together the who’s who in Europe’s HPC sector. It is being organized by the EuroHPC Joint Undertaking, which funds the development and management of systems including Lumi and Leonardo, which rank at five and six on the Top500 list of supercomputers, respectively.

Rhea2 will have a dual-chipset implementation and likely include HBM and DDR5 memory. SiPearl has largely kept quiet on Rhea2, but the company CEO shared more details on what the new chip would offer in an interview last year with HPCwire.

The new chip will be an overall upgrade from Rhea-1. It will be made using an advanced process compared to the Rhea-1, which was made using TSMC’s 6-nanometer N6 process.

CEO Philippe Notton said the Rhea-2 chip is a candidate for the future French Exascale supercomputer planned for the 2025-2026 timeframe. Based on Notton’s comments and the roadmap details, Rhea-2 could power the Jules Vernes Exascale system, which is funded by the EU, France, and the Netherlands and will be managed by GENCI (Grand Equipement National de Calcul Intensif), which is owned 49% by the French government.

EU-funded EPI has pushed aggressively to adopt the RISC-V architecture. However, SiPearl is sticking with Arm for server chips as the architecture is well-established and competitive in terms of performance and capabilities in HPC.

Developing the second-generation Rhea chip was faster as SiPearl learned a lot from the development of the original Rhea chip, Notton said.

With Rhea-2, SiPearl didn’t repeat mistakes in the development of Rhea-1, Notton said. “Of course, you’re going to make mistakes; you need to fix the mistakes. It takes time,” he said.

Technologies like HBM make Rhea-2 much better and faster, Notton told HPCwire.

Jupiter Coming Next Year

The EPI roadmap also revealed that Jupiter would go online next year. Jupiter is hosted by the Jülich Supercomputing Centre in Germany.

The system has a modular design, and Nvidia GPUs are attachments to the central system powered by Rhea chips. Researchers at Jülich are already using Nvidia GPUs in existing systems to run quantum simulations and will plug neuromorphic and quantum computers into Jupiter.

Jupiter was announced ahead of the Supercomputing 2023 (SC 23) show in Denver, and both Nvidia and SiPearl claimed to power the exascale system. Nvidia didn’t fully explain how the modular system would be used or whether it was using its homegrown CPUs to facilitate processing by its GPU.

Notton said SiPearl is working with many partners, including Nvidia, AMD, and Intel, to ensure Jupiter supports many different technologies. Supporting a wide range of software stacks is important for Jupiter to facilitate scientific computing, Notton said.

A second Exascale supercomputer will help the EU catch up with the US, which will likely have three supercomputers up and running by the end of this year.

European Sovereignty on Chips

The European Processor Initiative started in 2019, and was an early champion of SiPearl’s Rhea chip. SiPearl received seed funding from EPI, and the Rhea chip is counted a major success in Europe’s effort to build homegrown chips.

The initiative of homegrown chips took on more urgency after the chip shortage. The EU relied heavily on Taiwan and China for chip manufacturing and the US for intellectual property, and the EU Chips Act, which passed last year, incentivized localized chip manufacturing and supply chains.

Intel has announced its intent to establish a chip manufacturing factory in Germany and research and packaging facilities across Europe. It hopes the EU will fund its €33 billion outlay.

SiPearl has established a strong presence in the European supercomputing market and has commanded the attention of major GPU and AI chip makers in the US.

SiPearl partnered with AMD, Nvidia and Intel on hardware and software to provide flexibility for its clients — mostly the European institutions looking to build supercomputers — on technologies they can adopt in their supercomputers.

EPI Backing RISC-V

The European Processor Initiative started as a public-private partnership of European organizations, and SiPearl took advantage of that network to build its operations.

EPI partners have backed the open RISC-V instruction set architecture, which is still part of multiple academic experiments in the EU to test performance and software compatibility. SiPearl, taking on more risk to develop and move a chip to production, opted for the proven Arm architecture.

SiPearl operated on a shoestring with most of its funding from EPI, but late last year, it secured Series A funding to the tune of €90 million, with investors including Arm and Atos-owned Eviden.

Nonetheless, EPI partners developed the RISC-V-based EPAC (European Processor Accelerators) chips for vector processing, which is finding traction. The chip is designed for AI and ML processing and is open, meaning anyone can adopt and modify the design to their specific needs.

The EU has funded the EPI in phases, with the first phase wrapping up at the end of 2021. The second phase, called EPI2, wraps up by the end of the year with the commercialization of the Rhea-1 chip. EPI2 received funding of €70 million, with 50% of the sum coming from EuroHPC.

It is unclear if EPI will be funded for phase 3, though the plans from 2025 onwards would revolve around Rhea-3. The roadmap indicates EPI is planning a path to execute the phase 3 roadmap if it receives funding, though no official announcement has been made.

The EU Chips Act led to the creation of the Chips Joint Undertaking, which is focused on distributing funds and putting the legislation to work. It is equivalent to the EuroHPC JU, which is focused on supercomputing.

Subscribe to HPCwire's Weekly Update!

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

ISC 2024 Takeaways: Love for Top500, Extending HPC Systems, and Media Bashing

May 23, 2024

The ISC High Performance show is typically about time-to-science, but breakout sessions also focused on Europe's tech sovereignty, server infrastructure, storage, throughput, and new computing technologies. This round Read more…

HPC Pioneer Gordon Bell Passed Away

May 22, 2024

Legendary computer scientist Gordon Bell passed away last Friday at his home in Coronado, CA. He was 89. The New York Times has a nice tribute piece. A long-time pioneer with Digital Equipment Corp, he pushed hard for de Read more…

ISC 2024 — A Few Quantum Gems and Slides from a Packed QC Agenda

May 22, 2024

If you were looking for quantum computing content, ISC 2024 was a good place to be last week — there were around 20 quantum computing related sessions. QC even earned a slide in Kathy Yelick’s opening keynote — Bey Read more…

Atos Outlines Plans to Get Acquired, and a Path Forward

May 21, 2024

Atos – via its subsidiary Eviden – is the second major supercomputer maker outside of HPE, while others have largely dropped out. The lack of integrators and Atos' financial turmoil have the HPC market worried. If Atos goes under, HPE will be the only major option for building large-scale systems. Read more…

Core42 Is Building Its 172 Million-core AI Supercomputer in Texas

May 20, 2024

UAE-based Core42 is building an AI supercomputer with 172 million cores which will become operational later this year. The system, Condor Galaxy 3, was announced earlier this year and will have 192 nodes with Cerebras Read more…

Google Announces Sixth-generation AI Chip, a TPU Called Trillium

May 17, 2024

On Tuesday May 14th, Google announced its sixth-generation TPU (tensor processing unit) called Trillium.  The chip, essentially a TPU v6, is the company's latest weapon in the AI battle with GPU maker Nvidia and clou Read more…

ISC 2024 Takeaways: Love for Top500, Extending HPC Systems, and Media Bashing

May 23, 2024

The ISC High Performance show is typically about time-to-science, but breakout sessions also focused on Europe's tech sovereignty, server infrastructure, storag Read more…

ISC 2024 — A Few Quantum Gems and Slides from a Packed QC Agenda

May 22, 2024

If you were looking for quantum computing content, ISC 2024 was a good place to be last week — there were around 20 quantum computing related sessions. QC eve Read more…

Atos Outlines Plans to Get Acquired, and a Path Forward

May 21, 2024

Atos – via its subsidiary Eviden – is the second major supercomputer maker outside of HPE, while others have largely dropped out. The lack of integrators and Atos' financial turmoil have the HPC market worried. If Atos goes under, HPE will be the only major option for building large-scale systems. Read more…

Google Announces Sixth-generation AI Chip, a TPU Called Trillium

May 17, 2024

On Tuesday May 14th, Google announced its sixth-generation TPU (tensor processing unit) called Trillium.  The chip, essentially a TPU v6, is the company's l Read more…

Europe’s Race towards Quantum-HPC Integration and Quantum Advantage

May 16, 2024

What an interesting panel, Quantum Advantage — Where are We and What is Needed? While the panelists looked slightly weary — their’s was, after all, one of Read more…

The Future of AI in Science

May 15, 2024

AI is one of the most transformative and valuable scientific tools ever developed. By harnessing vast amounts of data and computational power, AI systems can un Read more…

Some Reasons Why Aurora Didn’t Take First Place in the Top500 List

May 15, 2024

The makers of the Aurora supercomputer, which is housed at the Argonne National Laboratory, gave some reasons why the system didn't make the top spot on the Top Read more…

ISC 2024 Keynote: High-precision Computing Will Be a Foundation for AI Models

May 15, 2024

Some scientific computing applications cannot sacrifice accuracy and will always require high-precision computing. Therefore, conventional high-performance c Read more…

Synopsys Eats Ansys: Does HPC Get Indigestion?

February 8, 2024

Recently, it was announced that Synopsys is buying HPC tool developer Ansys. Started in Pittsburgh, Pa., in 1970 as Swanson Analysis Systems, Inc. (SASI) by John Swanson (and eventually renamed), Ansys serves the CAE (Computer Aided Engineering)/multiphysics engineering simulation market. Read more…

Nvidia H100: Are 550,000 GPUs Enough for This Year?

August 17, 2023

The GPU Squeeze continues to place a premium on Nvidia H100 GPUs. In a recent Financial Times article, Nvidia reports that it expects to ship 550,000 of its lat Read more…

Comparing NVIDIA A100 and NVIDIA L40S: Which GPU is Ideal for AI and Graphics-Intensive Workloads?

October 30, 2023

With long lead times for the NVIDIA H100 and A100 GPUs, many organizations are looking at the new NVIDIA L40S GPU, which it’s a new GPU optimized for AI and g Read more…

Atos Outlines Plans to Get Acquired, and a Path Forward

May 21, 2024

Atos – via its subsidiary Eviden – is the second major supercomputer maker outside of HPE, while others have largely dropped out. The lack of integrators and Atos' financial turmoil have the HPC market worried. If Atos goes under, HPE will be the only major option for building large-scale systems. Read more…

Choosing the Right GPU for LLM Inference and Training

December 11, 2023

Accelerating the training and inference processes of deep learning models is crucial for unleashing their true potential and NVIDIA GPUs have emerged as a game- Read more…

Nvidia’s New Blackwell GPU Can Train AI Models with Trillions of Parameters

March 18, 2024

Nvidia's latest and fastest GPU, codenamed Blackwell, is here and will underpin the company's AI plans this year. The chip offers performance improvements from Read more…

AMD MI3000A

How AMD May Get Across the CUDA Moat

October 5, 2023

When discussing GenAI, the term "GPU" almost always enters the conversation and the topic often moves toward performance and access. Interestingly, the word "GPU" is assumed to mean "Nvidia" products. (As an aside, the popular Nvidia hardware used in GenAI are not technically... Read more…

Some Reasons Why Aurora Didn’t Take First Place in the Top500 List

May 15, 2024

The makers of the Aurora supercomputer, which is housed at the Argonne National Laboratory, gave some reasons why the system didn't make the top spot on the Top Read more…

Leading Solution Providers

Contributors

Eyes on the Quantum Prize – D-Wave Says its Time is Now

January 30, 2024

Early quantum computing pioneer D-Wave again asserted – that at least for D-Wave – the commercial quantum era has begun. Speaking at its first in-person Ana Read more…

The GenAI Datacenter Squeeze Is Here

February 1, 2024

The immediate effect of the GenAI GPU Squeeze was to reduce availability, either direct purchase or cloud access, increase cost, and push demand through the roof. A secondary issue has been developing over the last several years. Even though your organization secured several racks... Read more…

The NASA Black Hole Plunge

May 7, 2024

We have all thought about it. No one has done it, but now, thanks to HPC, we see what it looks like. Hold on to your feet because NASA has released videos of wh Read more…

Shutterstock 1285747942

AMD’s Horsepower-packed MI300X GPU Beats Nvidia’s Upcoming H200

December 7, 2023

AMD and Nvidia are locked in an AI performance battle – much like the gaming GPU performance clash the companies have waged for decades. AMD has claimed it Read more…

Intel Plans Falcon Shores 2 GPU Supercomputing Chip for 2026  

August 8, 2023

Intel is planning to onboard a new version of the Falcon Shores chip in 2026, which is code-named Falcon Shores 2. The new product was announced by CEO Pat Gel Read more…

GenAI Having Major Impact on Data Culture, Survey Says

February 21, 2024

While 2023 was the year of GenAI, the adoption rates for GenAI did not match expectations. Most organizations are continuing to invest in GenAI but are yet to Read more…

How the Chip Industry is Helping a Battery Company

May 8, 2024

Chip companies, once seen as engineering pure plays, are now at the center of geopolitical intrigue. Chip manufacturing firms, especially TSMC and Intel, have b Read more…

Q&A with Nvidia’s Chief of DGX Systems on the DGX-GB200 Rack-scale System

March 27, 2024

Pictures of Nvidia's new flagship mega-server, the DGX GB200, on the GTC show floor got favorable reactions on social media for the sheer amount of computing po Read more…

  • arrow
  • Click Here for More Headlines
  • arrow
HPCwire