Personal computing discussed

Moderators: renee, Flying Fox, morphine

 
JustAnEngineer
Gerbil God
Posts: 19661
Joined: Sat Jan 26, 2002 7:00 pm
Location: The Heart of Dixie

Re: AMD wins big for DOE -

Sat Oct 12, 2019 4:03 pm

Meanwhile, Intel has killed off its Omni-Path Xeons:
https://www.anandtech.com/show/14965/in ... -opa2-axed
· R5-3600X, Liquid Freezer II 280, RoG Strix X570-E, 64GiB PC4-28800, RTX3080, 2TB SX8200Pro +2TB MX500 +NAS, Define 7 Compact, Focus PX-850, S3220DGF +32UD99, FC900R OE, DeathAdder Chroma
 
Waco
Maximum Gerbil
Topic Author
Posts: 4178
Joined: Tue Jan 20, 2009 4:14 pm
Location: Los Alamos, NM

Re: AMD wins big for DOE -

Sun Oct 13, 2019 3:44 pm

Yep. Those were effectively dead when OPA2 was cancelled. :(
Victory requires no explanation. Defeat allows none.
 
JustAnEngineer
Gerbil God
Posts: 19661
Joined: Sat Jan 26, 2002 7:00 pm
Location: The Heart of Dixie

Re: AMD wins big for DOE -

Mon Oct 14, 2019 3:35 pm

LGA4677 Sapphire Rapids:
https://www.techpowerup.com/260119/inte ... is-lga4677
Bound for a 2021 market release; Intel will have transitioned to its advanced 7 nm EUV silicon fabrication node on the CPU front, and has adopted an "enterprise-first" strategy for the node. LGA4677 will be designed to handle the extremely high bandwidth of PCI-Express Gen 5
· R5-3600X, Liquid Freezer II 280, RoG Strix X570-E, 64GiB PC4-28800, RTX3080, 2TB SX8200Pro +2TB MX500 +NAS, Define 7 Compact, Focus PX-850, S3220DGF +32UD99, FC900R OE, DeathAdder Chroma
 
Waco
Maximum Gerbil
Topic Author
Posts: 4178
Joined: Tue Jan 20, 2009 4:14 pm
Location: Los Alamos, NM

Re: AMD wins big for DOE -

Tue Oct 15, 2019 7:49 pm

I'll be shocked if pcie 5 is shipping in 21 in anything Intel except Aurora...if even there.
Victory requires no explanation. Defeat allows none.
 
Captain Ned
Global Moderator
Posts: 28542
Joined: Wed Jan 16, 2002 7:00 pm
Location: Vermont, USA

Re: AMD wins big for DOE -

Tue Oct 15, 2019 7:57 pm

Waco wrote:
I'll be shocked if pcie 5 is shipping in 21 in anything Intel except Aurora...if even there.

Why do I think you'll be the first to know?
What we have today is way too much pluribus and not enough unum.
 
Waco
Maximum Gerbil
Topic Author
Posts: 4178
Joined: Tue Jan 20, 2009 4:14 pm
Location: Los Alamos, NM

Re: AMD wins big for DOE -

Tue Oct 15, 2019 8:26 pm

Captain Ned wrote:
Why do I think you'll be the first to know?

The day I can buy anything PCIe not under NDA you can be sure I'll say something. :)
Victory requires no explanation. Defeat allows none.
 
JustAnEngineer
Gerbil God
Posts: 19661
Joined: Sat Jan 26, 2002 7:00 pm
Location: The Heart of Dixie

Re: AMD wins big for DOE -

Wed Oct 16, 2019 5:36 am

...but PCIe 6 is "just around the corner"!
https://www.techpowerup.com/260177/pci- ... ze-by-2021
:lol:
· R5-3600X, Liquid Freezer II 280, RoG Strix X570-E, 64GiB PC4-28800, RTX3080, 2TB SX8200Pro +2TB MX500 +NAS, Define 7 Compact, Focus PX-850, S3220DGF +32UD99, FC900R OE, DeathAdder Chroma
 
Krogoth
Gerbil Elder
Posts: 5966
Joined: Tue Apr 15, 2003 3:20 pm
Location: somewhere on Core Prime
Contact:

Re: AMD wins big for DOE -

Wed Oct 16, 2019 11:29 am

JustAnEngineer wrote:
LGA4677 Sapphire Rapids:
https://www.techpowerup.com/260119/inte ... is-lga4677
Bound for a 2021 market release; Intel will have transitioned to its advanced 7 nm EUV silicon fabrication node on the CPU front, and has adopted an "enterprise-first" strategy for the node. LGA4677 will be designed to handle the extremely high bandwidth of PCI-Express Gen 5


You're a big socket!
Gigabyte Z390 AORUS-PRO Coffee Lake R 9700K, 2x16GiB of G.Skill RIPSAW DDR4-3600, Sapphire RX 6900XT, Seasonic GX-850 and Fractal Define 7 (W)
Ivy Bridge 3570K, 2x4GiB of G.Skill RIPSAW DDR3-1600, Gigabyte Z77X-UD3H, Corsair CX-750M V2, and PC-7B
 
JustAnEngineer
Gerbil God
Posts: 19661
Joined: Sat Jan 26, 2002 7:00 pm
Location: The Heart of Dixie

Re: AMD wins big for DOE -

Wed Oct 16, 2019 7:01 pm

Europe's AMD-powered Big Iron has been announced. It's just EPYC for 1/6th the price, though, not GPUs:
https://hothardware.com/news/amd-epyc-2 ... ercomputer
· R5-3600X, Liquid Freezer II 280, RoG Strix X570-E, 64GiB PC4-28800, RTX3080, 2TB SX8200Pro +2TB MX500 +NAS, Define 7 Compact, Focus PX-850, S3220DGF +32UD99, FC900R OE, DeathAdder Chroma
 
Waco
Maximum Gerbil
Topic Author
Posts: 4178
Joined: Tue Jan 20, 2009 4:14 pm
Location: Los Alamos, NM

Re: AMD wins big for DOE -

Wed Oct 16, 2019 9:41 pm

No GPUs means it'll probably be more useful. :P That's a beast of a machine with 1.5 PB of DRAM and that many cores/memory channels.

Hopefully Shasta / Slingshot pay off for Cray, they're certainly winning a lot of bids.
Victory requires no explanation. Defeat allows none.
 
JustAnEngineer
Gerbil God
Posts: 19661
Joined: Sat Jan 26, 2002 7:00 pm
Location: The Heart of Dixie

Re: AMD wins big for DOE -

Wed Feb 19, 2020 6:07 am

https://www.techpowerup.com/263990/amd- ... epyc-cores
https://hothardware.com/news/us-navy-cr ... idia-volta
The Cray Shasta will be deployed in the US Navy's Department of Defense Supercomputing Resource Center (DSRC) at Stennis Space Center in Mississippi. The peak theoretical computing capability of 12.8 PetaFLOPS will be built with 290,304 AMD EPYC (Rome) processor cores and 112 NVIDIA Volta V100 General-Purpose Graphics Processing Units (GPGPUs). The system will also feature 590 total terabytes (TB) of memory and 14 petabytes (PB) of usable storage, including 1 PB of NVMe-based solid state storage. Cray's Slingshot network will make sure all those components talk to each other at a rate of 200 Gigabits per second



https://www.techpowerup.com/263976/uk-p ... ercomputer
The UK government has set aside a budget of 1.56 billion US Dollars to install the world's most powerful supercomputer used for weather forecasting in the year 2022. Previously, the UK government used three Cray XC40 supercomputers that are capable of achieving a maximum of 14 PetaFLOPs at its peak performance. The future system plans to take that number and make it look tiny. With plans to make it 20 times more powerful than the current machine, we can estimate that the future supercomputer will have above 200 PetaFLOPs of computing performance.
· R5-3600X, Liquid Freezer II 280, RoG Strix X570-E, 64GiB PC4-28800, RTX3080, 2TB SX8200Pro +2TB MX500 +NAS, Define 7 Compact, Focus PX-850, S3220DGF +32UD99, FC900R OE, DeathAdder Chroma
 
blastdoor
Gerbil Elite
Posts: 808
Joined: Fri Apr 08, 2005 4:12 pm
Location: Real America

Re: AMD wins big for DOE -

Fri Feb 21, 2020 11:03 am

JustAnEngineer wrote:
Europe's AMD-powered Big Iron has been announced. It's just EPYC for 1/6th the price, though, not GPUs:
https://hothardware.com/news/amd-epyc-2 ... ercomputer


A CPU-only machine is definitely closer to being something I could actually use, but I think I'd be hard-pressed to actually use 748,544 cores .

10k cores, sure. But 748,544? That's a lot of cores.
1. iMac 27" (2020) i7 10700k; AMD Radeon Pro 5500 XT 8 GB; 64 GB RAM; 500 GB internal SSD + external box of SSDs
2. ThreadRipper 2990wx; Ubuntu; Headless; 64GB RAM
3. MacBook Pro (2017); Core i7-7820HQ; 16 GB RAM
 
Igor_Kavinski
Minister of Gerbil Affairs
Posts: 2077
Joined: Fri Dec 22, 2006 2:34 am

Re: AMD wins big for DOE -

Fri Feb 21, 2020 11:30 am

blastdoor wrote:
A CPU-only machine is definitely closer to being something I could actually use, but I think I'd be hard-pressed to actually use 748,544 cores .

10k cores, sure. But 748,544? That's a lot of cores.


You could simulate SkyNet and find out exactly which future is the most probable. Or ask the AI to write a better script and reboot the Terminator franchise. It can't be any worse than what we have got after T2.
 
JustAnEngineer
Gerbil God
Posts: 19661
Joined: Sat Jan 26, 2002 7:00 pm
Location: The Heart of Dixie

Re: AMD wins big for DOE -

Fri Feb 21, 2020 12:43 pm

Igor_Kavinski wrote:
You could simulate SkyNet...
Answer by Fredric Brown, 1954
· R5-3600X, Liquid Freezer II 280, RoG Strix X570-E, 64GiB PC4-28800, RTX3080, 2TB SX8200Pro +2TB MX500 +NAS, Define 7 Compact, Focus PX-850, S3220DGF +32UD99, FC900R OE, DeathAdder Chroma
 
Igor_Kavinski
Minister of Gerbil Affairs
Posts: 2077
Joined: Fri Dec 22, 2006 2:34 am

Re: AMD wins big for DOE -

Fri Feb 21, 2020 1:23 pm

JustAnEngineer wrote:
Igor_Kavinski wrote:
You could simulate SkyNet...
Answer by Fredric Brown, 1954


Awesome! This should be turned into an animated short or something. Loved it!
 
Captain Ned
Global Moderator
Posts: 28542
Joined: Wed Jan 16, 2002 7:00 pm
Location: Vermont, USA

Re: AMD wins big for DOE -

Fri Feb 21, 2020 1:52 pm

Same concept, different outcome. Isaac Asimov - "The Last Question".

http://www.physics.princeton.edu/ph115/LQ.pdf
What we have today is way too much pluribus and not enough unum.
 
Glorious
Gerbilus Supremus
Posts: 12343
Joined: Tue Aug 27, 2002 6:35 pm

Re: AMD wins big for DOE -

Fri Feb 21, 2020 1:54 pm

Frederic Brown's Arena is also really good, and if you know your Star Trek: TOS, you'll recognize it.

If you know your memes, you know that music where Kirk fights a weird dino-man? Yeah, thank Frederic Brown. :)
 
just brew it!
Administrator
Posts: 54499
Joined: Tue Aug 20, 2002 10:51 pm
Location: Somewhere, having a beer

Re: AMD wins big for DOE -

Fri Feb 21, 2020 9:51 pm

I've always wondered why Asimov assumed we would be using electromechanical relays to implement computer circuits in the year 2061, when vacuum tubes were already in widespread use when that story was written.
Nostalgia isn't what it used to be.
 
Captain Ned
Global Moderator
Posts: 28542
Joined: Wed Jan 16, 2002 7:00 pm
Location: Vermont, USA

Re: AMD wins big for DOE -

Fri Feb 21, 2020 10:17 pm

just brew it! wrote:
I've always wondered why Asimov assumed we would be using electromechanical relays to implement computer circuits in the year 2061, when vacuum tubes were already in widespread use when that story was written.

It explained why Multivac was so big??
What we have today is way too much pluribus and not enough unum.
 
just brew it!
Administrator
Posts: 54499
Joined: Tue Aug 20, 2002 10:51 pm
Location: Somewhere, having a beer

Re: AMD wins big for DOE -

Fri Feb 21, 2020 11:00 pm

Captain Ned wrote:
just brew it! wrote:
I've always wondered why Asimov assumed we would be using electromechanical relays to implement computer circuits in the year 2061, when vacuum tubes were already in widespread use when that story was written.

It explained why Multivac was so big??

Relays and vacuum tubes are roughly the same order of magnitude size-wise. And transistors even get a passing mention later in the story so he clearly was familiar with them.

Maybe WWIII happened and set us back 100 years technologically.
Nostalgia isn't what it used to be.
 
Captain Ned
Global Moderator
Posts: 28542
Joined: Wed Jan 16, 2002 7:00 pm
Location: Vermont, USA

Re: AMD wins big for DOE -

Fri Feb 21, 2020 11:11 pm

My guess is that his readers would grok relays and ponder about tubes.
What we have today is way too much pluribus and not enough unum.
 
just brew it!
Administrator
Posts: 54499
Joined: Tue Aug 20, 2002 10:51 pm
Location: Somewhere, having a beer

Re: AMD wins big for DOE -

Fri Feb 21, 2020 11:16 pm

This was a decade(ish) after ENIAC. I think the concept of a tube-based computer would've been fine.
Nostalgia isn't what it used to be.
 
Captain Ned
Global Moderator
Posts: 28542
Joined: Wed Jan 16, 2002 7:00 pm
Location: Vermont, USA

Re: AMD wins big for DOE -

Fri Feb 21, 2020 11:24 pm

No one ever accused Asimov of pushing a technological future.
What we have today is way too much pluribus and not enough unum.
 
JustAnEngineer
Gerbil God
Posts: 19661
Joined: Sat Jan 26, 2002 7:00 pm
Location: The Heart of Dixie

Re: AMD wins big for DOE -

Wed Mar 04, 2020 2:13 pm

https://videocardz.com/press-release/am ... ercomputer
U.S. Department of Energy now expects El Capitan to reach 2 exaflops once it’s fully installed, which would cement its place at the top of the US’s supercomputer inventory. El Capitan comes with a $600 million price tag and is intended to ensure the US’s leadership in supercomputers in the exascale era. Lawrence Livermore National Laboratory will be using the system to replace Sierra, their current IBM Power 9 + NVIDIA Volta supercomputer. All told, El Capitan will be 16 times more powerful than the system it replaces. LLNL will be using it primarily for nuclear weapons modeling – substituting for actual weapon testing – while the system will also see secondary use as a research system in other fields, particularly those where machine learning can be applied.

On the CPU side of matters, AMD will be supplying a standard version of their Zen 4-based “Genoa” EPYC processor. As it’s still two generations out from AMD’s current wares, the amount of information on Zen 4/Genoa is limited, but AMD is promising support for next-generation memory, Infinity Fabric 3, as well as broad promises of both single and multi-threaded performance leadership.

Meanwhile on the GPU side of matters, AMD and Cray are continuing to hold their cards rather close. While the companies are confirming that this will use a next-generation AMD GPU using a new architecture, they aren’t naming the architecture or offering too much in the way of details about it. For now, what they are saying is that these GPUs will be using next-generation HBM for their memory, and that they’ll bring support for mixed precision compute for improved deep learning performance.

For the first time AMD is naming their Infinity Fabric 3.0, which will be used to connect the processors within each blade. Like Frontier, El Capitan will be running in a 4:1 configuration, with four GPUs hooked up to each CPU. For Infinity Fabric 3.0, AMD is promising further improvements to inter-chip bandwidth and latency. However the most interesting claim is that these IF 3.0 device nodes will support unified memory across the CPU and GPU, which is something AMD doesn’t offer today. Indeed even Frontier is only slated to offer coherency between the processors which is a step below a true unified memory model. The devil is in the details of course – a unified memory system does not necessarily mean fast access to other devices’ memory – but this stands to be a major leap for AMD as a unified memory system can improve both the ease in programming such a system, and improving its performance when running heterogeneous workloads.

Finally, as previously mentioned, tying together the nodes will be Cray’s own Slingshot interconnect. Among other things, Slingshot supports adaptive routing, congestion management, and quality-of-service features. The interconnect is capable of 200Gb/sec per port, with individual blades incorporating a port for each GPU in the blade so that other nodes can directly read and write data to a GPU’s memory.

El Capitan is slated to use less than 40MW of power – and we’re told it’ll be "fairly substantially under that" – however at this time the DOE isn’t disclosing the total number of cabinets. But to put things in comparison, Frontier is slated to use 100 Shasta cabinets, with a total power budget lower than El Capitan. So we wouldn’t be too surprised to ultimately find out that part of the reason that El Capitan is 33% faster than Frontier is due to the DOE throwing more hardware at it and ordering more cabinets. But whatever the number, it’s going to be enough that El Capitan will be using direct liquid cooling.

Overall, El Capitan marks an important second exascale supercomputer win for AMD, while Cray will now be involved in all three US exascale systems. So it’s a big win for both vendors, and a continuation of momentum for AMD, who only just scored its first big supercomputer win in a long while with Frontier last year. The fact that El Capitan is a derivative of Frontier also means that with all three exascale systems now locked in, it will be NVIDIA who finds themselves on the outside looking in for this generation. As we noted with the Frontier announcement, the Intel Aurora and the AMD Frontier/El Capitan systems are coming from full-service processor vendors that supply both CPUs and GPUs. Current-generation systems like Summit use mixed vendors – e.g. IBM + NVIDIA – so the move to integrated vendors is a big shift for these CPU + accelerator systems. And while it makes a lot of sense for LLNL to order a copy of one of the other exascale systems in the name of efficiency, it should be noted that US DOE supercomputer contracts are as much political as they are technical. The US has a vested interest in supporting a domestic supercomputer industry and ensuring there are viable competitors to help keep costs down (there used to be several), so with three major processor alliances/vendors in the US, someone was bound to end up the odd man out.

At any rate, El Capitan is scheduled for delivery in early 2023.
· R5-3600X, Liquid Freezer II 280, RoG Strix X570-E, 64GiB PC4-28800, RTX3080, 2TB SX8200Pro +2TB MX500 +NAS, Define 7 Compact, Focus PX-850, S3220DGF +32UD99, FC900R OE, DeathAdder Chroma
 
Captain Ned
Global Moderator
Posts: 28542
Joined: Wed Jan 16, 2002 7:00 pm
Location: Vermont, USA

Re: AMD wins big for DOE -

Wed Mar 04, 2020 2:24 pm

Waco's new toy.
What we have today is way too much pluribus and not enough unum.
 
Waco
Maximum Gerbil
Topic Author
Posts: 4178
Joined: Tue Jan 20, 2009 4:14 pm
Location: Los Alamos, NM

Re: AMD wins big for DOE -

Wed Mar 04, 2020 2:28 pm

Captain Ned wrote:
Waco's new toy.

LLNL's goals and mine are pretty opposite, actually. I'm happy to see AMD winning bids but GPU based "FLOP stunts" aren't on my list of interesting machines.

LANL's next machine will be nothing like this. Hopefully announcing soon.
Victory requires no explanation. Defeat allows none.
 
Captain Ned
Global Moderator
Posts: 28542
Joined: Wed Jan 16, 2002 7:00 pm
Location: Vermont, USA

Re: AMD wins big for DOE -

Wed Mar 04, 2020 2:31 pm

Oops, didn't see LLNL.
What we have today is way too much pluribus and not enough unum.
 
Waco
Maximum Gerbil
Topic Author
Posts: 4178
Joined: Tue Jan 20, 2009 4:14 pm
Location: Los Alamos, NM

Re: AMD wins big for DOE -

Wed Mar 04, 2020 3:24 pm

It's easy to mix up the labs - I did until I worked at them. :)
Victory requires no explanation. Defeat allows none.
 
JustAnEngineer
Gerbil God
Posts: 19661
Joined: Sat Jan 26, 2002 7:00 pm
Location: The Heart of Dixie

Re: AMD wins big for DOE -

Tue May 05, 2020 5:01 am

https://www.techpowerup.com/266640/ners ... -successor
The National Energy Research Scientific Computing Center (NERSC), the mission high-performance computing facility for the U.S. Department of Energy's Office of Science at Lawrence Berkeley National Laboratory, has moved another step closer to making Perlmutter - its next-generation GPU-accelerated supercomputer - available to the science community in 2020.

A Cray Shasta supercomputer will feature 24 cabinets and provide 3-4 times the capability of NERSC's current supercomputer, Cori. Perlmutter will be deployed at NERSC in two phases: the first set of 12 cabinets, featuring GPU-accelerated nodes, will arrive in late 2020; the second set, featuring CPU-only nodes, will arrive in mid-2021. A 35-petabyte all-flash Lustre-based file system using HPE's ClusterStor E1000 hardware will also be deployed in late 2020. More than 6,000 next-generation NVIDIA GPU processors will power Perlmutter alongside the heterogeneous system's AMD CPUs. Nearly half of the workload currently running at NERSC is poised to take advantage of GPU acceleration.
· R5-3600X, Liquid Freezer II 280, RoG Strix X570-E, 64GiB PC4-28800, RTX3080, 2TB SX8200Pro +2TB MX500 +NAS, Define 7 Compact, Focus PX-850, S3220DGF +32UD99, FC900R OE, DeathAdder Chroma
 
Waco
Maximum Gerbil
Topic Author
Posts: 4178
Joined: Tue Jan 20, 2009 4:14 pm
Location: Los Alamos, NM

Re: AMD wins big for DOE -

Tue May 05, 2020 10:24 am

It still amazes me that they found a way to afford 30+ PiB of NVMe.
Victory requires no explanation. Defeat allows none.

Who is online

Users browsing this forum: No registered users and 5 guests
GZIP: On