New NVIDIA compiler lets developers offload math functions to GPU

D_o_S · Feb 21, 2007

NVIDIA has announced the release of beta versions of the SDK and C compiler for their Compute Unified Device Architecture (CUDA) technology. The C compiler includes a set of C language extensions that will enable developers to write C code that targets NVIDIA's GPUs directly. These extensions are supported by software libraries and a special CUDA driver that exposes the GPU to the OS and applications as a math coprocessor.

This approach differs to that taken by AMD/ATI and their "Close to Metal" (CTM) initiative. With CTM, AMD/ATI has opened up the low-level ISA so that their graphics products can be programmed directly in assembly language. CTM relies on developers creating libraries and higher-level tools for in-game use.

NVIDIA CUDA technology is a fundamentally new computing architecture that enables the GPU to solve complex computational problems in consumer, business, and technical applications. CUDA (Compute Unified Device Architecture) technology gives computationally intensive applications access to the tremendous processing power of NVIDIA graphics processing units (GPUs) through a revolutionary new programming interface. Providing orders of magnitude more performance and simplifying software development by using the standard C language, CUDA technology enables developers to create innovative solutions for data-intensive problems. For advanced research and language development, CUDA includes a low level assembly language layer and driver interface.

View at TechPowerUp Main Site

WarEagleAU · Feb 21, 2007

Cool deal. :rockout:

Alec§taar · Feb 21, 2007

WarEagleAU said:
Cool deal.

It is!

I saw ATI apply this type of thing to SETI@Home a couple of years back, & it made tearing thru unit processing way, WAY fast...

It would definitely seem that videocard GPU's are much faster @ that type of computation (largely "FPU/floating point unit" oriented on the mobo CPU).

APK

XooM · Feb 21, 2007

hate to bust your bubble, but that was more likely Folding@Home a few months ago.

Homeless · Feb 21, 2007

I though folding@home only worked for ati cards

Alec§taar · Feb 21, 2007

XooM said:
hate to bust your bubble, but that was more likely Folding@Home a few months ago.

No "bubble to burst"...

And, you're probably correct - It probably was most likely Folding@Home this was applied to, after all!

(I did both projects for a decent stretch (for this forums' team in fact for Folding@Home) - but, I did FAR more on SETI though, & since it began in 1999 (took a break 2001 - 2002, didn't have "enough machine" imo back then to do units fast))

* However: I am fairly certain where I saw mention of it was RIGHT before I joined here, around a year ago, SO YOU ALSO, may be "off" on the dates you mention (a few months ago, because I joined here way longer ago, than that, & I saw it on their forums quite a bit before I left them) on the SETI@Home forums!

Hey - they're both (as I am sure you know) 'distributed computing' concepts, & I was a part of them both...

Now, as to details on them? Heh, they're 'hazy' for me now, & what I saw on forums about them. Why hazy?? Simply because they're not 'crucial to my existence'... non-essential information, for me???

I let it fade... it 'takes up space' is why, & gets a "DB reorg" (compacted out blank records).

APK

P.S.=> Am I human? Do I forget things that aren't "110% crucial to my existence"?? Heck, absolutely - this 'factoid' isn't paying the bills for me, it's merely "trivia" @ this point...

Plus, I can stand correction @ times, like anybody else - so, thanks for that, on that note! apk

XooM · Feb 21, 2007

Homeless said:
I though folding@home only worked for ati cards

presently, yep, but i would hazard a guess that they're probably pursuing development for nVidia's latest line of cards.

@APK: The F@H GPGPU client was first beta launched at the beginning of last october (2006), but discussion was flying about it for well over a year before

ShadowFlare · Feb 21, 2007

It would be great if microsoft supports things like this in their .NET framework, considering that .NET apps can get machine-specific optimizations when they are compiled on the computer running them.

Alec§taar · Feb 21, 2007

XooM said:
@APK: The F@H GPGPU client was first beta launched at the beginning of last october (2006), but discussion was flying about it for well over a year before

Probably! All I remember about it was hearing about it @ the SETI forums, & saying "Now, THAT is a great idea!"

(Couldn't recall if it was beta or what was what... just that I knew it was going on OR going to be going on, rather...)

* Yep... getting old & senile here I think... has to be this in part: I never used to forget anything, even details... not the case anymore!

(LOL - OH WELL!)

APK

Scavar · Feb 22, 2007

This sounds like it should be good for a lot of people.....but will it actually work?

Processor	AMD Opteron 144
Motherboard	DFI Lanparty nF4 SLI-DR Expert
Cooling	Watercooled - Alphacool Nexxxos XP, BIX2, Eheim HPPS
Memory	2x 512MB OCZ PC 3200EL Platinum Rev.2 (TCCD)
Video Card(s)	2x Gainward GeForce 6800 Ultra (430/1200)
Storage	4x WD Raptor 740GD in RAID 0
Display(s)	Eizo FlexScan L768
Case	CM Stacker
Audio Device(s)	Audigy 2
Power Supply	Silverstone Zeus ST65ZF

System Name	Pandemic 2020
Processor	AMD Ryzen 5 "Gen 2" 2600X
Motherboard	AsRock X470 Killer Promontory
Cooling	CoolerMaster 240 RGB Master Cooler (Newegg Eggxpert)
Memory	32 GB Geil EVO Portenza DDR4 3200 MHz
Video Card(s)	ASUS Radeon RX 580 DirectX 12 DUAL-RX580-O8G 8GB 256-Bit GDDR5 HDCP Ready CrossFireX Support Video C
Storage	WD 250 M.2, Corsair P500 M.2, OCZ Trion 500, WD Black 1TB, Assorted others.
Display(s)	ASUS MG24UQ Gaming Monitor - 23.6" 4K UHD (3840x2160) , IPS, Adaptive Sync, DisplayWidget
Case	Fractal Define R6 C
Audio Device(s)	Realtek 5.1 Onboard
Power Supply	Corsair RMX 850 Platinum PSU (Newegg Eggxpert)
Mouse	Razer Death Adder
Keyboard	Corsair K95 Mechanical & Corsair K65 Wired, Wireless, Bluetooth)
Software	Windows 10 Pro x64

Processor	DualCore AMD Athlon 64x2 4800+ (o/c 2801mhz STABLE (Ketxxx, POGE, Tatty One, ME))
Motherboard	ASUS A8N-SLI Premium (PCIe x16, x4, x1)
Cooling	PhaseChange Coolermaster CM754/939 (fan/heatsink), Thermalright heatspreaders + fan built on (RAM)
Memory	512mb PC-3200 DDR400 (set DDR-33 for o/c) by Corsair (matched pair, 2x256mb) 200.1/200mhz
Video Card(s)	BFG GeForce 7900 GTX OC 512mb GDDR3 ram (o/c manually to 686 core/865 memory) - PhaseChange cooled
Storage	Dual "Raptor X" 16mb 10krpm/RAID 0 Promise EX8350 x4 PCIe 128mb & Intel IO chip/CENATEK RocketDrive
Display(s)	SONY 19" Trinitron MultiScan 400ps 1600x1200 75hz refresh 32-bit color
Case	Antec Super-LanBoy (aluminum baby-tower w/ lower front & upper rear cooling exhaust fans)
Audio Device(s)	RealTek AC97 onboard mobo stereo sound (Altec Lansing ACS-45 speakers - 10 yrs. still running!)
Power Supply	Antec 500w ATX 2.0 "SmartPower" powersupply
Software	Windows Server 2003 SP #1 fully patched, & massively tuned/tweaked to-the-max (plus latest drivers)

Processor	Athlon 64 3800 x2 Windosr @ 2.65 (and rising)
Motherboard	BIOSTAR TForce 550
Cooling	Custom Liquid (WMD20RLZT, Swiftech STORM, 2-302 w/ custom shroud, 2x sanyo denki)
Memory	Patriot PDC22G5300LLK
Video Card(s)	Sapphire x1900GT
Storage	1x maxtor 40gb, 2x hitachi T7K250 160gb drives RAID 0, 1x 160gb Spinpoint
Display(s)	2x 17" CRT (dells; one from 1998, one from 2001) at 1600x1200 each
Case	Aspire X-SuperAlien
Audio Device(s)	integrated
Power Supply	Seasonic S12 600watt
Software	WinXP SP2, Folding@Home, Battlefield2, etc

Processor	DualCore AMD Athlon 64x2 4800+ (o/c 2801mhz STABLE (Ketxxx, POGE, Tatty One, ME))
Motherboard	ASUS A8N-SLI Premium (PCIe x16, x4, x1)
Cooling	PhaseChange Coolermaster CM754/939 (fan/heatsink), Thermalright heatspreaders + fan built on (RAM)
Memory	512mb PC-3200 DDR400 (set DDR-33 for o/c) by Corsair (matched pair, 2x256mb) 200.1/200mhz
Video Card(s)	BFG GeForce 7900 GTX OC 512mb GDDR3 ram (o/c manually to 686 core/865 memory) - PhaseChange cooled
Storage	Dual "Raptor X" 16mb 10krpm/RAID 0 Promise EX8350 x4 PCIe 128mb & Intel IO chip/CENATEK RocketDrive
Display(s)	SONY 19" Trinitron MultiScan 400ps 1600x1200 75hz refresh 32-bit color
Case	Antec Super-LanBoy (aluminum baby-tower w/ lower front & upper rear cooling exhaust fans)
Audio Device(s)	RealTek AC97 onboard mobo stereo sound (Altec Lansing ACS-45 speakers - 10 yrs. still running!)
Power Supply	Antec 500w ATX 2.0 "SmartPower" powersupply
Software	Windows Server 2003 SP #1 fully patched, & massively tuned/tweaked to-the-max (plus latest drivers)

New NVIDIA compiler lets developers offload math functions to GPU

D_o_S

Moderator

WarEagleAU

Bird of Prey

Alec§taar

New Member

XooM

New Member

Homeless

Alec§taar

New Member

XooM

New Member

ShadowFlare

New Member

Alec§taar

New Member

Scavar

New Member

Processor	Athlon 64 Venice 3200+ 2.0 GHz, max 2.6 GHz with Zalman CNPS7000B-AlCu
Motherboard	EpoX 9NPA+Ultra nForce4 Ultra with Zalman ZM-NB47J
Cooling	All Zalman heatsinks (CNPS7000B-AlCu, ZM-NB47J, VF700-Cu)
Memory	1 GB (2x512 MB) DDR400 Corsair XMS C2 series, max 233 MHz @ 2-3-2-9 1T
Video Card(s)	Sapphire Radeon X800GTO2 256 MB PCIe max 540/600, modded to 16 pipes
Storage	Seagate 80GB SATA, Maxtor 160GB PATA, Maxtor 200GB PATA
Display(s)	Dell 17" Trinitron CRT
Case	Lian Li PC-60B Plus
Audio Device(s)	Built-in Realtek chip
Power Supply	Enermax Noisetaker EG495AX-VE, 485 watts, active PFC
Software	Windows XP Pro SP2, Windows XP Pro x64, Windows Vista RC1 32-bit

System Name	ScarredWolf(Desktop), MBlackWolf(Laptop)
Processor	E6600(Desktop), T7300(Laptop)
Motherboard	EVGA 680i(Desktop), IFL90(Laptop)
Cooling	Akasa EVO 120(Desktop), No idea(Laptop)
Memory	G Skill PI 8GB 4x2gb(Desktop), G Skill 3GB 1GB/2GB(Laptop)
Video Card(s)	8800GTS 640mb(Desktop), 8600m GT(Laptop)
Storage	3x250GB 1x500GB(Desktop), 1x320GB(Laptop)
Display(s)	Acer AL2216W 22"(Desktop), 15.4"(Laptop)
Case	Cosmos 1000(Desktop), PowerPro J 10:15(Laptop)
Audio Device(s)	CreativeX-Fi/Z-5500(Desktop), Realtek/No idea(Laptop)
Power Supply	PC Power and Cooling Silencer 610w(Desptop), shrug(Laptop)
Software	Windows Vista Ultimatex64 with tweaks(Both)
Benchmark Scores	I'm too lazy to benchmark anything.