Wednesday, February 12th 2014

GM107 Features 128 CUDA Cores Per Streaming Multiprocessor

NVIDIA's upcoming GM107 GPU, the first to be based on its next-generation "Maxwell" GPU architecture, reportedly features a different arrangement of CUDA cores and streaming multiprocessors to those typically associated with "Kepler," although the component hierarchy is similar. The chip reportedly features five streaming multiprocessors, highly integrated computation subunits of the GPU. NVIDIA is referring to these parts as "streaming multiprocessor (Maxwell)," or SMMs.

Further, each streaming multiprocessor features 128 CUDA cores, and not the 192 CUDA cores found in SMX units of "Kepler" GPUs. If true, GM107 features 640 CUDA cores, all of which will be enabled on the GeForce GTX 750 Ti. If NVIDIA is carving out the GTX 750 by disabling one of those streaming multiprocessors, its CUDA core count works out to be 512. NVIDIA will apparently build two GPUs on the existing 28 nm process, the GM107, and the smaller GM108; and three higher performing chips on the next-generation 20 nm process, the GM206, the GM204, and the GM200. The three, as you might have figured out, succeed the GK106, GK104, and GK110, respectively.


Source: VideoCardz
Add your own comment

42 Comments on GM107 Features 128 CUDA Cores Per Streaming Multiprocessor

#1
Arjai
So, basically the only thing going for these is DX11.2. Is that enough?
Posted on Reply
#2
HalfAHertz
Well...they are less but judging from the preliminary results, more powerful than the old SMs, so in the long run it should equal out? I guess that's how NV got those better power numbers - increased complexity but reduced the overall number of SMs.

Oh and GPUz was wrong :p
Posted on Reply
#3
Patriot
by: HalfAHertz
Well...they are less but judging from the preliminary results, more powerful than the old SMs, so in the long run it should equal out? I guess that's how NV got those better power numbers - increased complexity but reduced the overall number of SMs.
Probably more high level tuning than retooling the individual SP.
Balancing the components for efficiency gains, eliminating bottlenecks.
Posted on Reply
#5
Patriot
by: james888
So stream processors?
SP = cuda cores...
They are saying there are less SP/cudacores in each CU compute unit or SMM
Posted on Reply
#6
renz496
by: Arjai
So, basically the only thing going for these is DX11.2. Is that enough?
isn't that current kepler is DX11.2 capable as well?
Posted on Reply
#7
Patriot
by: Arjai
So, basically the only thing going for these is DX11.2. Is that enough?
by: renz496
isn't that current kepler is DX11.2 capable as well?
no... not even 11.1...
Software yes... but not hardware.

They support some of the features, but they are not DX 11.1 or 11.2 compliant.

Efficiency gains is where maxwell is supposed to be dominating on.
Posted on Reply
#8
Xzibit
by: renz496
isn't that current kepler is DX11.2 capable as well?
Nvidia site has all the 600 & 700 series listed as only 11

Even the latest GTX 780 Ti is only 11 compliant

by: PNY
Microsoft® DirectX® 11.2 (feature 11_0)
by: EVGA
DirectX 11.2 API (feature level 11_0)
Posted on Reply
#9
esrever
With this configuration, they can do 1/2 rate DP again which is how they are going to increase performance per watt they were promising.
Posted on Reply
#10
Arjai
So, somewhere, I read an article, linked in another 750 post, that said these 'new' cards were 11.2...basically, everything about these things is conjecture.

Perhaps, on the 18th, the conjecture will end? 6 more days. Have fun! I'm gonna wait and hopefully see some real tests, with real cards.

:D
Posted on Reply
#11
haswrong
but but but, will it support mantle?
Posted on Reply
#12
Fluffmeister
by: haswrong
but but but, will it support mantle?
Highly unlikey, nVidia users like to use decent CPU's so no need.
Posted on Reply
#13
Ghost
by: haswrong
but but but, will it support mantle?
Yes, it will. But only when Radeons start supporting CUDA along with PhysX.
Posted on Reply
#14
SIGSEGV
by: Fluffmeister
Highly unlikey, nVidia users like to use decent CPU's so no need.
lmfao..
dude.. i must admit it.. that you're very funny..
Posted on Reply
#15
semantics
by: Xzibit
Nvidia site has all the 600 & 700 series listed as only 11

Even the latest GTX 780 Ti is only 11 compliant
Somewhat sure they support DX11.1 features but only the ones that nvidia felt were perternant to games so they didn't get official compliance.
Posted on Reply
#16
Fluffmeister
by: semantics
Somewhat sure they support DX11.1 features but only the ones that nvidia felt were perternant to games so they didn't get official compliance.
Yeah It's basically a non issue, but peeps like to argue any advantage that they can.

We have been inundated with titles using DX11.2 after all.
Posted on Reply
#17
badtaylorx
i hate to say this,

but maxwell is looking pretty week....
Posted on Reply
#18
lemonadesoda
I guess with experience, they can now optimise the processor for the typical GPU and CUDA workload. If the device is cheaper, more efficient, cooler, I'm ok with it
Posted on Reply
#20
Fluffmeister
by: badtaylorx
i hate to say this,

but maxwell is looking pretty week....
I hate to say this, but it will be looking pretty next week.

But seriously, it's a GX107 part, of course it's not going to set the world alight on pure performance alone, but it's how it reaches that performance that will be interesting, especially how it compares to Kepler on the same process will be rather telling.
Posted on Reply
#21
xorbe
by: badtaylorx
maxwell is looking pretty week....
It's hanging in there with 640 cores / 128 bit bus, and it looks weak? It's a good sign for the beefier versions, I figured.
Posted on Reply
#22
BiggieShady
by: badtaylorx
i hate to say this,

but maxwell is looking pretty week....
I wouldn't judge their future big chip (GM200) based on small one (GM107).
Couple of things are interesting compared to Kepler : increased number of instructions per cycle, bigger cache and 15% larger transistor density on the same 28nm node.
Posted on Reply
#23
TheinsanegamerN
I cant wait to see what maxwell will be able to accomplish on a 20nm node with, say, the 180 watt TDP of a geforce 770. geforce 870 at 180 watt with performance of oced 780ti?
Posted on Reply
#24
Xzibit
by: BiggieShady
I wouldn't judge their future big chip (GM200) based on small one (GM107).
Couple of things are interesting compared to Kepler : increased number of instructions per cycle, bigger cache and 15% larger transistor density on the same 28nm node.
No kidding it has more L2 cache than the TITAN/780 Ti

GM107 = 2mb
GK107 = 256kb
GK110 = 1.5mb
Hawaii = 1mb

12mb of L2 cache on die soon... :respect:
Posted on Reply
#25
Recus
by: badtaylorx
i hate to say this,

but maxwell is looking pretty week....
GM107 will replace GK107 with a performance of GeForce GTX 480
You should find this particularly interesting. While GM107 utilizes 4 times less power than Fermi GF100, it will offer the same performance (actually even slightly better).
Nvidia is always achieve more with less Cuda cores since it was introduced:
8800 GTX/128 - HD 2900/320
GTX 285/240 - HD 4890/800
GTX 480/480 - HD 5870/1600
GTX 580/512 - HD 6970/1536
GTX 680/1536 - HD 7970/2048
GTX 780/2304-2880 - R9 290X/2816

Now both companies tied and Nvidia optimize their cores again. One day AMD will realize that something is not right with 10000 SP, 700 TDP, 199,9°C.
Posted on Reply
Add your own comment