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

NVIDIA Makes a Tesla Personal Supercomputer

malware

New Member
Joined
Nov 7, 2004
Messages
5,422 (1.13/day)
Likes
954
Location
Bulgaria
Processor Intel Core 2 Quad Q6600 G0 VID: 1.2125
Motherboard GIGABYTE GA-P35-DS3P rev.2.0
Cooling Thermalright Ultra-120 eXtreme + Noctua NF-S12 Fan
Memory 4x1 GB PQI DDR2 PC2-6400
Video Card(s) Colorful iGame Radeon HD 4890 1 GB GDDR5
Storage 2x 500 GB Seagate Barracuda 7200.11 32 MB RAID0
Display(s) BenQ G2400W 24-inch WideScreen LCD
Case Cooler Master COSMOS RC-1000 (sold), Cooler Master HAF-932 (delivered)
Audio Device(s) Creative X-Fi XtremeMusic + Logitech Z-5500 Digital THX
Power Supply Chieftec CFT-1000G-DF 1kW
Software Laptop: Lenovo 3000 N200 C2DT2310/3GB/120GB/GF7300/15.4"/Razer
#1
Today, scientific research is carried out on supercomputing clusters, a shared resource that consumes hundreds of kilowatts of power and costs millions of dollars to build and maintain. As a result, researchers must fight for time on these resources, slowing their work and delaying results. NVIDIA and its worldwide partners today announced the availability of the GPU-based Tesla Personal Supercomputer, which delivers the equivalent computing power of a cluster, at 1/100th of the price and in a form factor of a standard desktop workstation.




“We’ve all heard ‘desktop supercomputer’ claims in the past, but this time it’s for real,” said Burton Smith, Microsoft Technical Fellow. “NVIDIA and its partners will be delivering outstanding performance and broad applicability to the mainstream marketplace. Heterogeneous computing, where GPUs work in tandem with CPUs, is what makes such a breakthrough possible.”

Priced like a conventional PC workstation, yet delivering 250 times the processing power, researchers now have the horsepower to perform complex, data-intensive computations right at their desk, processing more data faster and cutting time to discovery.

“GPUs have evolved to the point where many real world applications are easily implemented on them and run significantly faster than on multi-core systems,” said Prof. Jack Dongarra, director of the Innovative Computing Laboratory at the University of Tennessee and author of LINPACK. “Future computing architectures will be hybrid systems with parallel-core GPUs working in tandem with multi-core CPUs."

Leading institutions including MIT, the Max Planck Institute, University of Illinois at Urbana-Champaign, Cambridge University, and others are already advancing their research using GPU-based personal supercomputers.

“GPU based systems enable us to run life science codes in minutes rather than the hours it took earlier. This exceptional speedup has the ability to accelerate the discovery of potentially life-saving anti-cancer drugs,” said Jack Collins, manager of scientific computing and program development at the Advanced Biomedical Computing Center in Frederick Md., operated by SAIC-Frederick, Inc.

At the core of the GPU-based Tesla Personal Supercomputer is the Tesla C1060 GPU Computing Processor which is based on the NVIDIA CUDA parallel computing architecture. CUDA enables developers and researchers to harness the massively parallel computational power of Tesla through industry standard C.

“Dell has led the workstation category for almost a decade and GPU computing represents a massive leap forward in performance that will bring supercomputer power to the masses,” said Antonio Julio, director, Dell Product Group. “The Dell Precision R5400 and T7400 will allow the scientific community to harness the capabilities of the NVIDIA Tesla C1060 GPU with up to two teraflops of computational power.”

As well as Dell, GPU-based Tesla Personal Supercomputers are available today from the following leading HPC OEMs, Systems Builders and Resellers: AMAX (US), Armari (UK), Asus (WW), Azken Muga (ES), Boxx (US), CAD2 (UK), CADnetwork (DE), Carri (FR), Colfax (US), Comptronic (DE), Concordia (IT), Connoisseur (IN), Dell (WW), Dospara (JP), E-Quattro (IT), JRTI (US), Lenovo (WW), Littlebit (CH), Meijin (RU), Microway (US), Sprinx (CZ), Sysgen (DE), Transtec (DE),Tycrid (US), Unitcom (JP), Ustar (UKR),Viglen (UK), Western Scientific (US)

To learn more about the industry-changing applications benefitting from NVIDIA GPU Computing technology, visit http://www.nvidia.com/cuda and for more information on the GPU-based NVIDIA Tesla Personal Supercomputer, please visit http://www.nvidia.com/personal_supercomputing.

Source: NVIDIA
 

newtekie1

Semi-Retired Folder
Joined
Nov 22, 2005
Messages
24,413 (5.50/day)
Likes
10,547
Location
Indiana, USA
Processor Intel Core i7 8700K@4.8GHz(Quick and dirty)
Motherboard AsRock Z370 Taichi
Cooling Corsair H110i GTX
Memory 32GB Corsair DDR4-3000
Video Card(s) PNY XLR8 GTX1060 6GB
Storage 480GB Crucial MX200 + 2TB Seagate Solid State Hybrid Drive with 128GB OCZ Synapse SSD Cache
Display(s) QNIX QX2710 1440p@120Hz
Case Fractal Design Define S
Audio Device(s) Onboard is good enough for me
Power Supply Corsair HX850
Software Windows 10 Pro x64
#2
So it is a computer with a rebadged GTX280 in it that they are charging out the nose for because it comes with a few pieces of specialized software to make use of CUDA.

And I'm almost positive that I read somewhere that the 9800GX2 outperformed the GTX280 in applications like this, though I think the 9800GX2 consumed more power. So in terms of performance per watt, the GTX280 was better, and power consumption actually is a concern for many in this market.
 
Joined
Dec 5, 2006
Messages
7,698 (1.90/day)
Likes
747
Processor i7-5820K
Motherboard Gigabyte X99-UD4
Cooling Corsair H100i
Memory 16GB Crucial DDR4-2400
Video Card(s) Asus Strix GTX 1070
Storage 240GB HyperX 3k, 500GB Samsung 850EVO, 2x WD Black 640gb, WD Black 1TB, Seagate 10TB
Display(s) 2x BenQ 24" 1920x1080
Case BitFenix Ghost
Audio Device(s) Focusrite Saffire PRO 14 -> DBX DriveRack PA+ -> Mackie MR8 and MR10 / Corsair Vengeance 2100
Power Supply Corsair RM1000i
Mouse Logitech G500s
Keyboard Logitech G110
Software Windows 10 x64 Pro
#3
So it is a computer with a rebadged GTX280 in it that they are charging out the nose for because it comes with a few pieces of specialized software to make use of CUDA.

And I'm almost positive that I read somewhere that the 9800GX2 outperformed the GTX280 in applications like this, though I think the 9800GX2 consumed more power. So in terms of performance per watt, the GTX280 was better, and power consumption actually is a concern for many in this market.
Power consumption means jack to most people in this market, but if you can claim 20% less, they may jump for it.

I really wish ATI would get on the wagon and get something alike going here..

I have personally been yelling for years for software like Cuda to come out.
 
Joined
May 9, 2006
Messages
2,106 (0.49/day)
Likes
275
System Name Not named
Processor Intel 8700k @ 5Ghz
Motherboard Asus ROG STRIX Z370-E Gaming
Cooling DeepCool Assassin II
Memory 16GB DDR4 Corsair LPX 3000mhz CL15
Video Card(s) Zotac 1080 Ti AMP EXTREME
Storage Samsung 960 PRO 512GB
Display(s) 24" Dell IPS 1920x1200
Case Fractal Design R5
Power Supply Corsair AX760 Watt Fully Modular
#4
ATI has come out with their own acceleration software now. It'll be some time before we see it practically used though I'd think.
 

WarEagleAU

Bird of Prey
Joined
Jul 9, 2006
Messages
10,809 (2.57/day)
Likes
529
Location
Gurley, AL
System Name Boddha Getta Boddha Getta Bah!
Processor AMD FX 6100 @ 4.432Ghz @1.382
Motherboard ASUS M5A99X EVO AMD 990X AMD SB950
Cooling Custom Water. EK 240MM Kit, Supreme HSF - Runs 35C
Memory 2 x 4GB Corsair Vengeance White LP @ 1.35V
Video Card(s) XFX Radeon HD 6870 980/1100
Storage WD Caviar Black 1.0TB, WD Caviar Green 1.0TB, WD 160GB
Display(s) Asus VH222/S 22: (21.5" Viewable) 1920x1080p HDMI LCD Monitor
Case NZXT White Switch 810
Audio Device(s) Onboard Realtek 5.1
Power Supply NZXT Hale 90 Gold Cert 750W Modular PSU
Software Windows 8.1 Profession 64 Bit
#5
Whats the price of the personal super computer here, I didnt see one stated. I dont know if AMD is gonna do what Nvidia is doing though. They have GPGPU with their software so Im not sure how that pans out.
 
Joined
May 5, 2008
Messages
3,318 (0.94/day)
Likes
301
Processor Intel i5-3570K @ 3.4Ghz
Motherboard Asrock LGA1155 Z77 Extreme 4
Cooling Cooler Master Evo 212
Memory 16GB (4X4) G.Skill Ripjaw 2 DDR3-1600
Video Card(s) Nvidia gForce GTX 660ti
Storage 1x Samsung 840 EVO 256GB 6Gb/s, 1x WD 500GB 6Gb/s, 1x WD 80GB 3Gb/s
Display(s) ASUS VH242H Black + 2 HP 2311x 23" LED
Case Fractal Design R4
Audio Device(s) Realtek OnBoard Both
Power Supply Cooler Master 850w
Software Windows 7 Ultimate 64-bit SP1
#6
Well I think that this is just ok, but I am thinking about getting a Tesla myself...Just as a extra processing unit inside my pc. Supposedly if you get about 3 Tesla's inside your PC it be quite as fast some of the top 10 servers in the world, except the Jaguar.
 

FordGT90Concept

"I go fast!1!11!1!"
Joined
Oct 13, 2008
Messages
21,039 (6.22/day)
Likes
10,143
Location
IA, USA
System Name BY-2015
Processor Intel Core i7-6700K (4 x 4.00 GHz) w/ HT and Turbo on
Motherboard MSI Z170A GAMING M7
Cooling Scythe Kotetsu
Memory 2 x Kingston HyperX DDR4-2133 8 GiB
Video Card(s) PowerColor PCS+ 390 8 GiB DVI + HDMI
Storage Crucial MX300 275 GB, Seagate 6 TB 7200 RPM
Display(s) Samsung SyncMaster T240 24" LCD (1920x1200 HDMI) + Samsung SyncMaster 906BW 19" LCD (1440x900 DVI)
Case Coolermaster HAF 932 w/ USB 3.0 5.25" bay
Audio Device(s) Realtek Onboard, Micca OriGen+
Power Supply Enermax Platimax 850w
Mouse SteelSeries Sensei RAW
Keyboard Tesoro Excalibur
Software Windows 10 Pro 64-bit
Benchmark Scores Faster than the tortoise; slower than the hare.
#7
So it is a computer with a rebadged GTX280 in it that they are charging out the nose for because it comes with a few pieces of specialized software to make use of CUDA.

And I'm almost positive that I read somewhere that the 9800GX2 outperformed the GTX280 in applications like this, though I think the 9800GX2 consumed more power. So in terms of performance per watt, the GTX280 was better, and power consumption actually is a concern for many in this market.
I think I have to agree on this one. It sounds like a whole lot of marketing BS.

Tesla C1060: 936 GFlOps
Peak of #10 on the top 500 list (11/2008): 233472 GFlOps

You'd need 250 GTX280-based Tesla processors to match match #10. I think it would be hard to fit 250 cards in a computer and still call it "personal." Hmm, they must have a pretty broad definition of "personal!" :roll:
 
Last edited:
Joined
Oct 23, 2008
Messages
491 (0.15/day)
Likes
9
Location
ireland
Processor amd phenom 2 x4 955 @3.8
Motherboard asus m4n68t v2
Cooling tx2 cooler
Memory kingston hyperx blu 1600mhz
Video Card(s) gtx460
Storage 300gb+320gb+500gb
Display(s) targa 19"
Case black
Audio Device(s) audigy 2
Power Supply 700 watt generic brand
Software win 7 64bit
#8
Well I think that this is just ok, but I am thinking about getting a Tesla myself...Just as a extra processing unit inside my pc. Supposedly if you get about 3 Tesla's inside your PC it be quite as fast some of the top 10 servers in the world, except the Jaguar.
screw the tesla get a 280 gtx for a quater the price and download cuda, done. happy days, sure even my recenly deceased 8800 gts g80 could do cuda.