• Welcome to TechPowerUp Forums, Guest! Please check out our forum guidelines for info related to our community.

AMD EPYC 7003 Processors to Power Singapore's Fastest Supercomputer

btarunr

Editor & Senior Moderator
Staff member
Joined
Oct 9, 2007
Messages
47,885 (7.38/day)
Location
Dublin, Ireland
System Name RBMK-1000
Processor AMD Ryzen 7 5700G
Motherboard Gigabyte B550 AORUS Elite V2
Cooling DeepCool Gammax L240 V2
Memory 2x 16GB DDR4-3200
Video Card(s) Galax RTX 4070 Ti EX
Storage Samsung 990 1TB
Display(s) BenQ 1440p 60 Hz 27-inch
Case Corsair Carbide 100R
Audio Device(s) ASUS SupremeFX S1220A
Power Supply Cooler Master MWE Gold 650W
Mouse ASUS ROG Strix Impact
Keyboard Gamdias Hermes E2
Software Windows 11 Pro
AMD announced that AMD EPYC 7003 Series processors will be used to power a new supercomputer for the National Supercomputing Centre (NSCC) Singapore, the national high-performance computing (HPC) resource center dedicated to supporting science and engineering computing needs.

The system will be based on the HPE Cray EX supercomputer and will use a combination of the EPYC 7763 and EPYC 75F3 processors. The supercomputer is planned to be fully operational by 2022 and is expected to have a peak theoretical performance of 10 petaFLOPS, 8x faster than NSCC's existing pool of HPC resources. Researchers will use the system to advance scientific research across biomedicine, genomics, diseases, climate, and more.



"AMD EPYC processors are the leading choice for the HPC research that makes an impact on the world, and that's why they have been chosen to power Singapore's most powerful supercomputer," said Ram Peddibhotla, corporate vice president, AMD EPYC product management. "We're excited to work with HPE and the National Supercomputing Centre Singapore to help unlock scientific discoveries across medicine, diseases, climate, engineering and more."

View at TechPowerUp Main Site
 
AMD forgot to mention that it also has NVIDIA A100 GPUs, in addition to the above-mentioned CPUs. I'd imagine a good chunk of the petaFLOPS are coming from these.
 
AMD forgot to mention that it also has NVIDIA A100 GPUs, in addition to the above-mentioned CPUs. I'd imagine a good chunk of the petaFLOPS are coming from these.

Linpack FLOPs come from GPUs, but HPCG-FLOPs come from CPUs and the interconnect (100Gbit fiber maybe??)

Basically: GPUs are good at some tasks, CPUs on others. Anyone building a supercomputer today tries to create a balance, so that your underlying customers benefit (be it weather-prediction, protein folding, virtual-weapons testing, or quantum computer emulation, etc. etc.). For some tasks, the GPU will be the core source of compute power. For others, the CPU is the source.

Linpack-FLOPs is the original FLOPs benchmark. But HPCG-FLOPs is arguably more realistic on a wider variety of workloads... and is a lesser known secondary benchmark. Still, its a good idea to keep the HPCG benchmark in mind... if only to remind ourselves about the huge differences different workloads have.
 
AMD forgot to mention that it also has NVIDIA A100 GPUs, in addition to the above-mentioned CPUs. I'd imagine a good chunk of the petaFLOPS are coming from these.
Does that make any sense to you? Why would they even care to mention NVIDIAS product. That's NVIDIAS job. They're only highlighting their own product which makes sense.
 
I said many times before (for years), and I'll say it again. Intel should have skipped 11th generation and went right to 12th. had they done so they might have gotten this contract. And yes I am well aware skipping a generation would have cost big bucks, but, "in life if you don't take chances..." the point, had they taken a big chance and got caught up, they might have secured this contract.
 
I said many times before (for years), and I'll say it again. Intel should have skipped 11th generation and went right to 12th. had they done so they might have gotten this contract. And yes I am well aware skipping a generation would have cost big bucks, but, "in life if you don't take chances..." the point, had they taken a big chance and got caught up, they might have secured this contract.
What does 11th gen a desktop cpu line have to do with servers. If they skipped 11th gen intel would have still loss this contract.
 
I said many times before (for years), and I'll say it again. Intel should have skipped 11th generation and went right to 12th. had they done so they might have gotten this contract. And yes I am well aware skipping a generation would have cost big bucks, but, "in life if you don't take chances..." the point, had they taken a big chance and got caught up, they might have secured this contract.
11th Gen of desktop processor? Intel recently released their 10nm Ice Lake based Xeon, and to be honest, this probably will not change anything since this decision should have been made months ago. Countries and companies don't make decision at a spur of the moment like we would just walk into a store and buy something out of the blue. In addition, it is not as easy as skipping one generation and gone for the next. Development of these processors started years ago, and killing off any product means losing out all the sunk cost.

Does that make any sense to you? Why would they even care to mention NVIDIAS product. That's NVIDIAS job. They're only highlighting their own product which makes sense.
I agree. Nvidia is after all, a competitor. So if AMD wins a massive contract, its obvious they will just highlight their products. If anyone wants to mention both AMD and Nvidia, it will be the company, i.e. HPE, in this case, who made this sale.
 
queue the Underdog theme song.
 
AMD forgot to mention that it also has NVIDIA A100 GPUs, in addition to the above-mentioned CPUs. I'd imagine a good chunk of the petaFLOPS are coming from these.
It's not like AMD gets to decide what GPUs their customers use. If someone wants AMD CPU nodes and Nvidia GPUs why the well would AMD be the ones to talk about that ?
 
Back
Top