The Frontier supercomputer at the Oak Ridge National Laboratory (ORNL) has exceeded 1.1 exaFLOPS (Rmax), leading the June 2022 TOP500 list as the world's fastest supercomputer and the first truly "exascale" system.
Frontier uses 9,408 64-core Epyc 7A53 CPUs and 37,632 AMD Instinct MI250X GPUs. It has 4.6 petabytes each of DDR4 and High Bandwidth Memory.
Frontier also reached #2 on the June 2022 Green500 list at 52.227 gigaFLOPS/Watt, behind the smaller Frontier Test & Development System:
Previously, Frontier had been characterized as a two peak exaflops system, but its first Top500 benchmark measures some 1.686 peak exaflops. (Oak Ridge said that there remains "much higher headroom on the GPUs and the CPUs" to achieve the two peak exaflops target.) Outside of Linpack and the Top500, the system benchmarks at 6.88 exaflops of mixed-precision performance on HPL-AI. The team ran out of time and was not able to submit an HPCG benchmark.
[...] Frontier also achieved another win out of the gate: second place on the spring 2022 Green500 list, which ranks supercomputers by their flops per watt. The Oak Ridge team accomplished this by delivering those 1.102 Linpack exaflops in a 21.1-megawatt power envelope, an efficiency of 52.23 gigaflops per watt (which works out to one exaflops at 19.15 megawatts). This puts the system well within the 20-megawatt exascale power envelope target set by DARPA in 2008—a target that had been viewed with much skepticism over the ensuing 14 years. Frontier was only outpaced in efficiency by its own test and development system (Frontier TDS, aka "Crusher"), which delivered 62.68 gigaflops per watt.
#10: 30.05 petaflops (Nov. 2021) → 46.10 petaflops (June 2022)
#100: 4.79 petaflops → 5.39 petaflops
#500: 1.65 petaflops → 1.65 petaflops (both are Lenovo C1040, Xeon E5-2673v4 20C 2.3GHz systems)
Previously: New TOP500 List Released -- Fugaku Holds Top Spot, Exascale Remains Elusive; Green500 Released Too!
Top500: No Exascale, Fugaku Still Reigns, Polaris Debuts at #12
Related Stories
Fugaku Holds Top Spot, Exascale Remains Elusive:
FRANKFURT, Germany; BERKELEY, Calif.; and KNOXVILLE, Tenn.— The 57 th edition of the TOP500 saw little change in the Top10. The only new entry in the Top10 is the Perlmutter system at NERSC at the DOE Lawrence Berkeley National Laboratory. The machine is based on the HPE Cray "Shasta" platform and a heterogeneous system with both GPU-accelerated and CPU-only nodes. Perlmutter achieved 64.6 Pflop/s, putting the supercomputer at No. 5 in the new list.
The Japanese supercomputer Fugaku held onto the top spot on the list. A system codeveloped by Riken and Fujitsu, Fugaku has an HPL benchmark score of 442 Pflop/s. This performance exceeds the No. 2 Summit by 3x. The machine is based on Fujitsu's custom ARM A64FX processor. What's more, in single or further reduced precision, which is often used in machine learning and AI, Fugaku's peak performance is actually above an exaflop. Such an achievement has caused some to introduce this machine as the first "Exascale" supercomputer. Fugaku already demonstrated this new level of performance on the new HPL-AI benchmark with 2 Eflop/s.
Outside of this, we saw quite a few instances of Microsoft Azure and Amazon EC2 Cloud instances fairly high on the list. Pioneer-EUS, the machine to snag the No. 24 spot and the No.27 Pioneer-WUS2, rely on Azure. The Amazon EC2 Instance Cluster at No. 41 utilizes Amazon EC2.
[...] Green500 results
AMD has announced its "Milan-X" Epyc CPUs, which reuse the same Zen 3 chiplets found in "Milan" Epyc CPUs with up to 64 cores, but with triple the L3 cache using stacked "3D V-Cache" technology designed in partnership with TSMC. This means that some Epyc CPUs will go from having 256 MiB of L3 cache to a whopping 768 MiB (804 MiB of cache when including L1 and L2 cache). 2-socket servers using Milan-X can have over 1.5 gigabytes of L3 cache. The huge amount of additional cache results in average performance gains in "targeted workloads" of around 50% according to AMD. Microsoft found an 80% improvement in some workloads (e.g. computational fluid dynamics) due to the increase in effective memory bandwidth.
AMD's next-generation of Instinct high-performance computing GPUs will use a multi-chip module (MCM) design, essentially chiplets for GPUs. The Instinct MI250X includes two "CDNA 2" dies for a total of 220 compute units, compared to 120 compute units for the previous MI100 monolithic GPU. Performance is roughly doubled (FP32 Vector/Matrix, FP16 Matrix, INT8 Matrix), quadrupled (FP64 Vector), or octupled (FP64 Matrix). VRAM has been quadrupled to 128 GB of High Bandwidth Memory. Power consumption of the world's first MCM GPU will be high, as it has a 560 Watt TDP.
The Frontier exascale supercomputer will use both Epyc CPUs and Instinct MI200 GPUs.
AMD officially confirmed that upcoming Zen 4 "Genoa" Epyc CPUs made on a TSMC "5nm" node will have up to 96 cores. AMD also announced "Bergamo", a 128-core "Zen 4c" Epyc variant, with the 'c' indicating "cloud-optimized". This is a denser, more power-efficient version of Zen 4 with a smaller cache. According to a recent leak, Zen 4c chiplets will have 16 cores instead of 8, will retain hyperthreading, and will be used in future Zen 5 Ryzen desktop CPUs as AMD's answer to Intel's Alder Lake heterogeneous ("big.LITTLE") x86 microarchitecture.
Also at Tom's Hardware (Milan-X).
Previously: AMD Reveals 'Instinct' for Machine Intelligence
AMD Launches "Milan" Epyc Server CPUs, with Zen 3 and up to 64 Cores
AMD at Computex 2021: 5000G APUs, 6000M Mobile GPUs, FidelityFX Super Resolution, and 3D Chiplets
AMD Unveils New Ryzen V-Cache Details at HotChips 33
AMD Aims to Increase Energy Efficiency of Epyc CPUs and Instinct AI Accelerators 30x by 2025
Top500: No Exascale, Fugaku Still Reigns, Polaris Debuts at #12
Submitted via IRC for Bytram
Source: https://www.hpcwire.com/2021/11/15/top500-no-exascale-fugaku-still-reigns-polaris-debuts-at-12/
No exascale for you -- at least, not within the High-Performance Linpack (HPL) territory of the latest Top500 list, issued today from the 33rd annual Supercomputing Conference (SC21), held in-person in St. Louis, Mo., and virtually, from Nov. 14–19. ""We were hoping to have the first exascale system on this list but that didn't happen," said Top500 co-author Jack Dongarra in a press briefing this morning.
In an alternate timeline, the United States might have stood up two exascale systems by now: Aurora at Argonne National Laboratory and Frontier at Oak Ridge National Laboratory. Installation continues on the latter, and when we talked to Intel last week, they said that Argonne was preparing for the arrival of Aurora, now slated to be a two exaflops peak machine, doubling its (most recent) previous performance target.
The 58th edition of the Top500 offers a familiar lineup at the top. Japan's Fugaku system is still in the number one spot providing 442 petaflops, with the U.S. systems Perlmutter – which improved its performance by nearly 10 percent to 70.9 petaflops – and Selene in fifth and sixth place, respectively. (DOE's Summit and Sierra and China's Sunway TaihuLight are still keeping their seats warm as well, holding second, third and fourth place respectively.)
| Rmax (PFLOPS) | #1 system | #10 system | #100 system | #500 system |
|---|---|---|---|---|
| Jun 2020 | 416 | 21.2 | 2.8 | 1.23 |
| Nov 2020 | 442 | 22.4 | 3.1 | 1.32 |
| Jun 2021 | 442 | 23.5 | 4.12 | 1.51 |
| Nov 2021 | 442 | 30 | 4.79 | 1.65 |
(Score: 2) by bmimatt on Tuesday May 31 2022, @07:59PM (10 children)
Are we reporting from the future? My calendar says: "May 31" :)
(Score: 2) by looorg on Tuesday May 31 2022, @08:26PM (5 children)
Super Computing in the WORLD of TOMORROW!
My super computer is so fast that it calculates tomorrow TODAY!
(Score: 2) by Gaaark on Tuesday May 31 2022, @08:38PM (2 children)
Well, they are running linux you know!
--- Please remind me if I haven't been civil to you: I'm channeling MDC. I have always been here. ---Gaaark 2.0 --
(Score: 0) by Anonymous Coward on Tuesday May 31 2022, @10:28PM
systemd?
(Score: 2) by bmimatt on Wednesday June 01 2022, @09:20AM
I am on the US west coast - do you mean they're using UTC for 'future' reporting?
(Score: 3, Funny) by liar on Tuesday May 31 2022, @09:47PM (1 child)
I seem to remember reading on The Onion years ago that an 'amd overclocker creates black hole in his basement and accidentally sucked himself into the future'... I believe it was right around the time AMD broke the 1 ghz barrier.
Noli nothis permittere te terere.
(Score: 0) by Anonymous Coward on Wednesday June 01 2022, @02:20AM
You liar!
(Score: 0) by Anonymous Coward on Tuesday May 31 2022, @08:29PM
It went nearly the speed of light, but we won't be sure until June when we catch up to it.
(Score: 2, Informative) by Anonymous Coward on Tuesday May 31 2022, @09:14PM
The list is published twice a year, in June and November. The top spots are usually set well in advance of those dates because the really big stuff makes the news with large gaps in between. However, it isn't uncommon for the bottom of the list to shift around before the list is formally set on the first.
(Score: 0) by Anonymous Coward on Wednesday June 01 2022, @01:37AM (1 child)
My C64 running Linux predicted this weeks ago. Come on people, try to keep up.
(Score: 1) by Chromium_One on Wednesday June 01 2022, @09:44AM
When you live in a sick society, everything you do is wrong.
(Score: 2) by inertnet on Tuesday May 31 2022, @09:13PM (1 child)
So, did the price for these go up or down because of this? Up because of chip shortage, or down because of more mass production?
(Score: 0) by Anonymous Coward on Tuesday May 31 2022, @09:19PM
Probably down. Prices for the super-computer goes down because they buy in bulk and usually have higher specifications than the general consumer. Because of this, more of the resulting chips and products are binned, which means more of the lower-performance chips are available.
(Score: 0) by Anonymous Coward on Tuesday May 31 2022, @11:43PM (5 children)
i wonder what the limit is for flops-per-watt-and-space until the secrit holo transmitters break down or start flickering :P
(Score: 2) by takyon on Wednesday June 01 2022, @12:01AM (4 children)
https://en.wikipedia.org/wiki/Limits_of_computation [wikipedia.org]
https://en.wikipedia.org/wiki/Margolus%E2%80%93Levitin_theorem [wikipedia.org]
[SIG] 10/28/2017: Soylent Upgrade v14 [soylentnews.org]
(Score: 0) by Anonymous Coward on Wednesday June 01 2022, @01:10AM (3 children)
As an old 60's engineer, I am a little confused here.
Are they doing useful things with the hardware?
Or, is it high speed masturbation?
As noted in damn near everything since the advent of DRM and bloatware?
(Score: 2) by sgleysti on Wednesday June 01 2022, @01:27AM
I could be wrong, but my understanding is that, since the ban on nuclear weapons testing, they've simulated nuclear weapons with large computers in the national labs such as this one.
(Score: 2) by takyon on Wednesday June 01 2022, @01:28AM
"Bloat" and increasingly higher level languages can make things more convenient for people.
If you want to squeeze everything out of the hardware, you need to hire dying engineers. And you will pay for it.
[SIG] 10/28/2017: Soylent Upgrade v14 [soylentnews.org]
(Score: 0) by Anonymous Coward on Wednesday June 01 2022, @10:31AM
Weather predictions
Climate modelling
These are just two things that come to mind. We also have plasma flows in fission reactor or designing a plane and testing it's flight surfaces.