Thursday, November 14th 2013

AMD Announces First "Supercomputing" Server Graphics Card With 12 GB Memory

Press Release by
Cristian_25H
 Discuss (48 Comments)
AMD today announced the new AMD FirePro S10000 12 GB Edition graphics card, designed for big data high-performance computing (HPC) workloads for single precision and double precision performance. With full support for PCI Express 3.0 and optimized for use with the OpenCL compute programming language, the AMD FirePro S10000 12 GB Edition GPU features ECC memory plus DirectGMA support allowing developers working with large models and assemblies to take advantage of the massively parallel processing capabilities of AMD GPUs based on the latest AMD Graphics Core Next (GCN) architecture. AMD FirePro S10000 12 GB Edition GPU is slated for availability in Spring 2014.
The AMD FirePro S10000 12GB Edition graphics card is a compelling solution for a variety of scenarios:
  • Compute/Visualization Server: finance, oil exploration, aeronautics and automotive, design and engineering, geophysics, life sciences, medicine and defense
  • Double precision: genetic sequencing, computational fluid dynamics, structural mechanics, numeral analytics, reservoir simulation, automated reasoning and weather forecasting
  • Single precision: seismic processing, molecular dynamics, satellite imaging, explicit crash test simulation, video enhancement, signal processing, video transcoding, digital rendering and medical imaging
  • Ultra High-end Workstation (Requiring GPU compute and 3D graphics performance): Oil and gas, computer aided engineering
"Our compute application customers asked for a solution that offers increased memory to support larger data sets as they create new products and services," said David Cummings, senior director and general manager, Professional Graphics, AMD. "In response, we're announcing the AMD FirePro S10000 12 GB Edition graphics card to meet that additional memory demand with support for OpenCL and high-end compute and graphics technologies."

"AMD is proving again to be a key player in providing outstanding 3D graphics and GPGPU compute solutions based on the OpenCL Khronos Group standard for the industry with the announcement of the new AMD FirePro S10000 12 GB graphics card," said Nicolas Duny, VP R&D Technologies, Dassault Systèmes. "AMD is an industry innovator by responding to our customers' needs with cutting edge technology. The AMD FirePro S10000 12 GB card will be a welcome addition to the market and to our customers."

"Our customers are always eager for additional memory, so the introduction of the AMD FirePro S10000 12 GB Edition graphics card means key applications will finally be able to take advantage of the graphics compute capabilities," said Laurent Bertaux, CEO, CAPS. "As a leading provider of software and solutions for the HPC community, CAPS recognizes that this is a great opportunity for customers to reduce the potential for the bottleneck of data transfer, thus improving overall application performance. CAPS is a long-time AMD supporter so we're pleased that CAPS FORTAN and C compilers for OpenCL can immediately make full use of the 12GB memory offered in this new AMD FirePro solution."

The current AMD FirePro S10000 graphics solution with 6 GB of GDDR5 memory has received great acclaim. For example, the University of Frankfurt's Institution of Advanced Studies use of the card with the SANAM supercomputer ranks in the top five on the Green500 List as one of the most powerful and energy-efficient supercomputers powered by graphics processors.

The AMD FirePro S10000 with 6 GB of memory is currently available for purchase while the AMD FirePro S10000 12 GB Edition graphics card is slated for availability in Spring 2014.

Related News

Add your own comment

48 Comments on AMD Announces First "Supercomputing" Server Graphics Card With 12 GB Memory

#26
librin.so.1
Recus, dude, the absolute energy consumption level is irrelevant. The only important part is [performance / Watt], in other words - efficiency. And this supercomputer has the 4th best efficiency in the world. Your argument is invalid.

Also, You do show how You can't even do simple math - the Beacon is 110 TFLOPS and the BlueGene/Q is 189 TFLOPS. While the SANAM is 421 TFLOPS. In other words - it outperfroms those two supercomputers combined. Your argument is invalid x2.
Posted on Reply
#27
NeoXF
RecusLearn to to understand what Green500 stands for.

Fanboy detected.
Dude, seriously... stop embarrassing yourself, just stop posting.
Posted on Reply
#28
SIGSEGV
RecusLooks like someone doesn't understand what's going on.



While similar performance Beacon and BlueGene/Q using 45 kW and 82 kW, Sanan using 179 kW.

Who even thinking about W when parents paying bills? :laugh:
Posted on Reply
#29
Recus
VinskaRecus, dude, the absolute energy consumption level is irrelevant. The only important part is [performance / Watt], in other words - efficiency. And this supercomputer has the 4th best efficiency in the world. Your argument is invalid.

Also, You do show how You can't even do simple math - the Beacon is 110 TFLOPS and the BlueGene/Q is 189 TFLOPS. While the SANAM is 421 TFLOPS. In other words - it outperfroms those two supercomputers combined. Your argument is invalid x2.
As I said: "Who even thinking about W when parents paying bills?"

Btw, how did you got 421? Sanam - 532 TFlop/s Rmax, 1098 TFlop/s Rpeak.
NeoXFDude, seriously... stop embarrassing yourself, just stop posting.
Go to look at Mantle powerpoint...
Posted on Reply
#30
Brusfantomet
theoneandonlymrkAt any rate this card already has the tech for fully unified memory with either gpu able to see write and move data anywhere and across busses it's likely its just us consumers waiting to use thesr features , pro grade driver's are a different beast.
since SLI and CF is working on the same data sets (models, textures ++) there will never be a way to get more than one card of RAM without a massive performance impact. The only way would bee if there is invented a new bus with the same low latency AND high banwith as local RAM can give.

The ability to use system RAM does lessen the need for massive frame buffers, given that the prefetching algorithms work.
Posted on Reply
#31
Nihilus
Glad to see GPUs are doing amazing things in super computer efficiency (as recus showed us).
Posted on Reply
#32
TheoneandonlyMrK
Brusfantometsince SLI and CF is working on the same data sets (models, textures ++) there will never be a way to get more than one card of RAM without a massive performance impact. The only way would bee if there is invented a new bus with the same low latency AND high banwith as local RAM can give.

The ability to use system RAM does lessen the need for massive frame buffers, given that the prefetching algorithms work.
these are likely not attached or used in crossfire, why would they be whilst supercomputing and the whole point of that in supercomputing is so that they can work on different bits of the same data set(massive) and update each others memoryIf neccessary, ie the performance drop would be nill if the application efficiently packets the data into workable blocks., im no programmer though :D
Posted on Reply
#33
Brusfantomet
theoneandonlymrkthese are likely not attached or used in crossfire, why would they be whilst supercomputing and the whole point of that in supercomputing is so that they can work on different bits of the same data set(massive) and update each others memoryIf neccessary, ie the performance drop would be nill if the application efficiently packets the data into workable blocks., im no programmer though :D
the answer was directed at consumer cards in CF
Posted on Reply
#34
TheoneandonlyMrK
Brusfantometthe answer was directed at consumer cards in CF
This isn't one of those, check it's price and its made for a different purpose where cross fire is pointless and driver support and features are not variable they are validated to a spec an ieee spec. They pay lots.
Posted on Reply
#35
Solaris17
Super Dainty Moderator
this card......could play crysis
Posted on Reply
#36
Brusfantomet
theoneandonlymrkThis isn't one of those, check it's price and its made for a different purpose where cross fire is pointless and driver support and features are not variable they are validated to a spec an ieee spec. They pay lots.
i know, but it seamed theoneandonlymrk was waiting for the possibility to not have the same data in both the cards RAM in CF, like in compute. I merely pointed out that it probably never will happen.
Posted on Reply
#37
qubit
Overclocked quantum bit
Solaris17this card......could play crysis
Nah, it would be short on memory. :laugh:
Posted on Reply
#38
TheoneandonlyMrK
Brusfantometi know, but it seamed theoneandonlymrk was waiting for the possibility to not have the same data in both the cards RAM in CF, like in compute. I merely pointed out that it probably never will happen.
And I pointed out your wrong

THIS IS a server gfx card it won't be used like a consumer xfire on a stick and would as I said use its whole memory on.

Several different remote virtual servers eg

Or two points of the same or different large data sets stop bringing consumer points up in this thread as its pointless.

No server administrator is buying this without a specific use already planned(xfire wont be one used often) and that purpose is unlikely to be to play crisis sorry.
Posted on Reply
#39
cdawall
where the hell are my stars
I'm really confused what happened. The 4th most efficient setup on the list uses s1000000000000000000 cards it just so happens to have more hence the highest power consumption...
Posted on Reply
#40
Nihilus
cdawallI'm really confused what happened. The 4th most efficient setup on the list uses s1000000000000000000 cards it just so happens to have more hence the highest power consumption...
Most of us get it, one person still does not. :rolleyes:

Adding to that, most things lose a little efficiency as you scale up. ALL THINGS EQUAL, an 8 core cpu will never have as good of a performance/watt as a 4 core; an 5.0 liter v-8 will not have the hp/liter as 2.5 4cyl and so on. Being that this supercomputer has very high performance and still at the top of the list speaks volumes.
Posted on Reply
#41
HumanSmoke
cdawallI'm really confused what happened. The 4th most efficient setup on the list uses s1000000000000000000 cards it just so happens to have more hence the highest power consumption...
Pretty much, although efficiency largely stems from a high ratio of GPU to CPU. A large percentage of supers are either CPU only, or weighted heavily towards the CPU. SANAM has equal numbers of CPUs and GPUs. It's no coincidence that the list is topped by the most efficient CPUs allied with the most efficient GPUs -Eurora and Aurora Tigon are both 1:1, while NICS's Beacon has 2 Xeon Phi GPUs for every CPU.
It is actually a testament to IBM's Power architecture that their CPU-only BlueGene systems still feature highly in the (largely subjective) Linpack synthetic benchmark runs.
Posted on Reply
#42
Recus
NihilusMost of us get it, one person still does not. :rolleyes:

Adding to that, most things lose a little efficiency as you scale up. ALL THINGS EQUAL, an 8 core cpu will never have as good of a performance/watt as a 4 core; an 5.0 liter v-8 will not have the hp/liter as 2.5 4cyl and so on. Being that this supercomputer has very high performance and still at the top of the list speaks volumes.
So it can be most efficient with high power consumption but can't be fastest (780Ti) with high price?
Posted on Reply
#43
Nihilus
RecusSo it can be most efficient with high power consumption but can't be fastest (780Ti) with high price?
I can not make sense of this at all. :confused:

:wtf:
Posted on Reply
#44
NeoXF
Brusfantometsince SLI and CF is working on the same data sets (models, textures ++) there will never be a way to get more than one card of RAM without a massive performance impact. The only way would bee if there is invented a new bus with the same low latency AND high banwith as local RAM can give.

The ability to use system RAM does lessen the need for massive frame buffers, given that the prefetching algorithms work.
So a APU supercomputer (w/ heterogeneous memory) would have a huge upper-hand in that regard, compared with a CPU/GPU split one? (think 64GB RAM per socket/APU).
Posted on Reply
#48
FX-GMC
RecusLooks like someone doesn't understand what's going on.



While similar performance Beacon and BlueGene/Q using 45 kW and 82 kW, Sanan using 179 kW.

Who even thinking about W when parents paying bills? :laugh:
Not similar performance, similar efficiency. Take column 4 of your chart and convert it to watts. Then multiply that by column 2 and you have total FLOPS. Ya follow?
Posted on Reply
Add your own comment
May 12th, 2024 09:58 EDT change timezone

Latest GPU Drivers

New Forum Posts

Popular Reviews

Controversial News Posts