Intel and AMD Path to Zettaflop Supercomputers

In 2021, Intel talked reaching Zettascale in three phases. AMD CEO talked about getting to a Zettaflop in 2030-2035. AMD CEO indicated that an earlier Zettaflop supercomputer would need about 500 Megawatts of power. Exascale systems today consume 21MW of power.

AMD and Intel have managed to roughly double the performance of their CPUs and GPUs every 2.4 years. HPE, Atos, and Lenovo have achieved similar gains roughly every 1.2 years at the system level, Su says power efficiency is lagging behind. Citing the performance and efficiency figures gleaned from the top supercomputers, AMD says gigaflops per watt is doubling roughly every 2.2 years, about half the pace the systems are growing.

AMD aims to resolve this efficiency issue by innovating and utilizing creative packaging technologies. As per AMD, a 3D stacked approach is around 50x more efficient than an off-package copper solution.

AMD was more specific about using 3D stacked approaches and chiplets to achieve the performance gains. AMD CEO Su says the package is the new motherboard. Chiplets will allow chipmakers to address three of the low hanging fruits when it comes to compute efficiency: compute energy, communications energy, and memory energy. Modular chiplet or tile architectures have numerous advantages. Chipmakers using chiplets can use optimal process tech for each component.

Assuming this trend continues unchanged, AMD estimates that we’ll achieve a zettaflop-class supercomputer in about 10-years give or take

Intel’s general path to a Zettaflop supercomputer that is 1000 times more powerful than the best supercomputer today.
1. Optimizing Exascale with Next-Gen Xeon and Next-Gen GPU in 2022/2023;
2. In 2024/2025 with the integration of Xeon plus Xe called Falcon as well as Silicon Photonics or ‘LightBringer’;
3. Zettascale around 2027.

Intel has gone on the record saying that Aurora, the upcoming supercomputer for Argonne, will be in excess of two ExaFLOPs of 64-bit double-precision compute.

In February, 2023, Intel recently announced that the test system (Borealis) for the exascale Aurora deployment at Argonne National Laboratory in Illinois is finally live.

Aurora will feature around 10,000 server blades, each featuring 2x 4th Generation Intel Xeon Scalable Processors (which we know as Sapphire Rapids) and 6x Intel Data Center GPU Max Series (which we know as Ponte Vecchio) chips. The Intel Borealis test system (also based out of Argonne) will feature just 128 server blades although in an identical configuration and scalable setting as its larger variant. Aurora will be the size of 2 basketball courts and 600 tons and a rated peak performance of 2 EXAFLOPs, this will likely be one of the first exascale supercomputers in the US and one of the fastest in the entire world.

Intel talks about getting an architecture jump of 16x, power and thermals are 2x, data movement is 3x, and process is 5x. That is about 500x, on top of the two ExaFLOP Aurora system, to get to a ZettaFLOP.

The 16X architecture jump, Intel says the foundational element is the IPC per watt improvement. Intel thinks we know how to do the 16x performance improvement pretty easily, or relatively. The power efficiency is the challenge there in terms of both the architecture and microarchitectural opportunities that are ahead of us.

8 thoughts on “Intel and AMD Path to Zettaflop Supercomputers”

  1. Too bad they can’t colocate these super hot chips within a nuclear reactor, since both are running at similar heat densities…

  2. Why are the different factors that Intel lists multiplicative? For instance, why does twice as efficient thermals make the computer twice as fast, if nothing else changes? Should you not have to double the size of the arithmetic unit also? And the same line reasoning goes for all the factors…

  3. In the past people have theorized Zetascale could do perfect weather prediction 2 weeks. I will be curious where weather prediction is in 10 years.

    • Yes… Not only that, but progress towards miniaturization of all the different components will continue. They can now pack transistors two atoms wide, far more densely than the synaptic connections in the human brain.

      Computing power has already surpassed human capability in many ways. I mean that’s kinda the point of building these types of machines. It’s how we leverage this type of computation power for the benefit of the people that is important.

      The computers discussed in the article aren’t even non-classical computers. Now when we start talking about quantum computers is when things get really interesting. Quantum computers need only reach 1000 qubits for them to perform calculations…in 5 minutes… what it would take a classical computer… like the one discussed in this article…the entire lifetime of the universe to calculate…

  4. Compare to Apple M chip , they are still very far from a good power per watt performance, may be they need to take some lesson here

Comments are closed.