I'm not sure what that's supposed to prove exactly. The lesser tests should be expected to result in lower bandwidth figures because you're moving such a small amount of data and your last test is 67MB -- not 67MB in addition to what you tested earlier but 67MB in total.
GeForce GTX 970s seem to have an issue using all 4GB of VRAM, Nvidia looking into it
- Thread starter Naked Snake
- Start date
- Status
I'm not sure what that's supposed to prove exactly. The lesser tests should be expected to result in lower bandwidth figures because you're moving such a small amount of data and your last test is 67MB -- not 67MB in addition to what you tested earlier but 67MB in total.
mugurumakensei
Member
There I allocated and transfered an entire 4GB chunk in less than .003s
Code:
bandwidthTest.exe --dtod --start=400000000 --end=400000000 --increment=3000000 --mode=
range --csv
[CUDA Bandwidth Test] - Starting...
Running on...
Device 0: GeForce GTX 970
Range Mode
bandwidthTest-D2D, Bandwidth = 143003.8 MB/s, Time = 0.00267 s, Size = 400000000
bytes, NumDevsUsed = 1
Result = PASSYou missed a 0. That's 400MB.
iN1njaCPFC
Member
I would assume that if they've advertised it as 2Gb, then it would be different hardware. Would just be inerested to know...Especially since I ordered a 970 SLI setup no earlier than 9 days ago.
mugurumakensei
Member
Interesting. I can't allocate past 2.1 GB in the official cuda test. I wonder how the "benchmark" gets around that limit.
Ah, strange.
mugurumakensei
Member
Actually make that 2 GB as the hard limit for Cuda memory allocations in the official bandwidth test.
I got it from here http://developer.download.nvidia.com/compute/DevZone/C/Projects/x64/bandwidthTest.zip
I'm also curious how he can guarantee the memory is L2 cache vs DRAM considering I'm not familiar with any functions that can tell you that information that's not deep in the drivers.
The schematics of the number of gpc's at anandtech indicate they've got exactly half of the gcc's vs the 980 which means it should work well with half the memory. (4gigs vs 2 gigs).
http://www.anandtech.com/show/8923/nvidia-launches-geforce-gtx-960
Z
ZombieFred
Unconfirmed Member
I have Samsung Memory and showing at 4096 MB. Am I safe?
cheezcake
Member
So far there's nothing conclusive. I guess we really do have to wait for a statement from NVIDIA.
Naked Snake
Member
That's just showing how much memory the card has, it's the same for all 970s, doesn't tell you anything about performance.
mugurumakensei
Member
Actually not strange if it's doing a bandwidth test internally to copy 2 GB, it has to have 2GB destination and and 2 GB source. After multiple runthroughs, I've noticed there's nothing consistent. It ranges from 40 GB/s to 89 GB/s for the same 2GB copy.
zerokoolpsx
Member
GIGABYTE GeForce GTX 970
Just bought this a few weeks ago too. Hope Nvidia can fix this.
Just bought this a few weeks ago too. Hope Nvidia can fix this.
Dog Problems
Banned
cripterion
Member
Can anyone explain to me why I have 29 chunks and 3712MiByte allocated while all the rest of you seem to have 30 chunks with 3840MB?
cheezcake
Member
Since the test only went up to 3.8 I'm assuming the problem is present?
I'm getting more curious about those of us whose drivers crash towards the end and those whose don't, I'm guessing from the 1.#J yours did as well?
Dog Problems
Banned
Yep, screen went black and I got the little pop up saying the driver stopped working.
cripterion
Member
Running SLI setup or a multi monitor?
Dog Problems
Banned
Single card and a single monitor.
Post your RAM capacity. Possibly it runs out of system ram and crashes?
Dog Problems
Banned
8 gigs. I ran it again and watched the process and it showed as using only 55 mb the entire time.
cripterion
Member
Hmmm ok thought it would be related to that but I guess not.
I don't get the flashing screen buy my driver crashes too. Running the 347.25 drivers for the record.
This whole thing leaves a bad taste in my mouth. I'm still waiting for MFAA support for SLI and the tesselation on AC:Unity by the way. And installing the new drivers I thought it would fix the god awful flashing water textures in that damn game but nope!
One thing's for sure though, last time I go SLI.
Ah ok, weird stuff.
Also people running the bench should be running off the IGP to keep 0mb VRAM allocated on the GTX 970.
cyberheater
PS4 PS4 PS4 PS4 PS4 PS4 PS4 PS4 PS4 PS4 PS4 PS4 PS4 PS4 PS4 PS4 PS4 Xbone PS4 PS4
Has there been any test on any 4Gb nVidia cards (any model) that passed this test?
I'm starting to think the benchmark tool or they way it talks to the driver is the issue.
I'm starting to think the benchmark tool or they way it talks to the driver is the issue.
You can fix that problem disabling startup videos.
I ran it on my 2GB 670 and only the last two chunks reported a drop in memory bandwidth, which could very easily be attributed to OS overhead.
Vigilant Walrus
Member
I have a MSI 970, have had no problems, but I upgraded from a 470, so it's no wonder that it would feel like a massive performance boost regardless if its 3,5 or 4 gigs.
Objectively Bad Opinion
Member
There's a picture of a 980 in the OP. The benches in the OP were run with Windows running on the IGP, not the graphics card. The 980 clears it with full performance for all chunks.
Naked Snake
Member
I used the IGP on my i5-2500 for years before I got the 970. Can I set Windows to run on IGP and still take full advantage of the 970 in games? And would there be any benefit to do doing so?
cripterion
Member
Damn that actually works! Puzzled as to why that made the game go disco on the textures but thanks!
cyberheater
PS4 PS4 PS4 PS4 PS4 PS4 PS4 PS4 PS4 PS4 PS4 PS4 PS4 PS4 PS4 PS4 PS4 Xbone PS4 PS4
Thanks. It's all quite odd.
YianGaruga
Banned
Just skimmed the thread so sorry if I missed it:
Are there any reports of people experiencing issues in games (meaning issues that start at ~3GB VRAM usage) that are possibly related to this? The benchmark looks strange but so far it seems like the only indicator that something is wrong.
EDIT: Just saw the case of games using different amount of memory depending on wether a 970 or 980 is used in the exact same scene.
Are there any reports of people experiencing issues in games (meaning issues that start at ~3GB VRAM usage) that are possibly related to this? The benchmark looks strange but so far it seems like the only indicator that something is wrong.
EDIT: Just saw the case of games using different amount of memory depending on wether a 970 or 980 is used in the exact same scene.
Objectively Bad Opinion
Member
Not really. IGP is mostly useful as an extra monitor port or if you need the features (like Quicksync, but AMD/Nvidia GPUs all have their own version of that now). Generally games will use the GPU Monitor 1 is connected to, I think.
If you need 100% of the performance your GPU is capable of, run games in exclusive fullscreen. Running both integrated and dedicated graphics at the same time is just asking for bugs and drama.
Sparrowhawk
Member
It's crazy how this is being discovered now. Glad I waited. Hopefully they'll fix the issue because I'm not really willing to put up $200+ more dollars for a 980.
Smushroomed
Banned
Waiting for the dust settle...
Not like I'm seeing any real-world issues now, but its the principle of the thing
Not like I'm seeing any real-world issues now, but its the principle of the thing
mugurumakensei
Member
Looking at the source code this is not purely testing bandwidth. Due to the computations inside of benchmarkdramkernel, it's also a measure of Compute performance.
If you wanted to test just plain bandwidth, you would waste some time populating another area of memory(not measuring this) then use cudaMemcpy to copy over the given chunk a number of times. Currently, the ALU will have to waste cycles for the arithmetic inside of the benchmark functions.
I've (probably) seen this problem in practice couple of times with my 970 G1 Rev 1.0. Recently last week when playing the Evolve beta. Even at 1080p the game uses over 3.5-3.6GB of VRAM and sometimes when I join/load a game, I have 5-10fps for a while before it goes back to solid 60fps which is what I have all the time besides these slowdowns to single digits. Most VRAM heavy games seem to mystically hover at around 3.5GB, never going above that. Meanwhile 980 users are reporting memory usage of well over 3.5GB with similar settings in those games.
- Status