Well a titan with HBM necessarily wont run faster as such , core limit is still limit and more bandwidth is only going to help If it needs it.
-
Competitor rules
Please remember that any mention of competitors, hinting at competitors or offering to provide details of competitors will result in an account suspension. The full rules can be found under the 'Terms and Rules' link in the bottom right corner of your screen. Just don't mention competitors in any way, shape or form and you'll be OK.
AMD VEGA confirmed for 2017 H1
- Thread starter Doom112
- Start date
- Status
Well a titan with HBM necessarily wont run faster as such , core limit is still limit and more bandwidth is only going to help If it needs it.
NVidia have professional cards using HBM2 with exactly the same core count as the Pascal Titan, the pro cards run slower.
HBM2 won't give a magic boost to performance if it is not there already. It also won't make the slightest bit of difference if the card has enough bandwidth using GDDR5X.
Soldato
- Joined
- 19 Oct 2008
- Posts
- 6,034
Some don't get the especially some of those who supposedly are more educated about tech. NVidia will use it when it makes a good difference not to help market their cards.
Last edited:
Deleted member 651465
Deleted member 651465
Linus has a good video about this. He benchmarks the latest Quadro GPU against a Titan XP and finds HBM all a bit of nothingness, really.
That said, I hope AMD pull something out of the bag or they're doomed to become number 2 for another hardware generation.
Will there be any differences in overclocking headroom with HBM2?. I disappeared off the forums (work) after the release of the Fury/Nano in where people couldn't overclock much of anything to be honest. Now I know that changed from seeing a few results reading threads but I don't have the faintest of clues as to what the average overclock of HBM1 memory is.
Quite insulting and not needed here really. If you are referring to someone (seems that way), then why not address that person in a more respectful way?. If one person is misinformed, that doesn't mean the rest are.
Thing is, there's enthusiastic fans of most things in life. People can take it too far but that passion can also be used as a good thing. What you're on about Darren is a personality flaw in some people which has absolutely nothing to do with any product. What is important is that we stop the "we/them" mentality. Both AMD and Nvidia create amazing cards but without either of the two, it's a progressional and financial nightmare. Look at Intel.
Quite insulting and not needed here really. If you are referring to someone (seems that way), then why not address that person in a more respectful way?. If one person is misinformed, that doesn't mean the rest are.
Thing is, there's enthusiastic fans of most things in life. People can take it too far but that passion can also be used as a good thing. What you're on about Darren is a personality flaw in some people which has absolutely nothing to do with any product. What is important is that we stop the "we/them" mentality. Both AMD and Nvidia create amazing cards but without either of the two, it's a progressional and financial nightmare. Look at Intel.
Working on a base clock of 500mhz for HBM1 on the Fury cards most can overclock to 545mhz and if you are lucking you can get 600mhz.
HBM1 overclocks in steps, 545mhz 600mhz and I think the next one is 660mhz. If you try and run it at any other speed like 550mhz for example it will just default down to 545mhz.
This ^
I found on mine that performance seems to drop off at lower resolutions compared to GDDR5(X) equipped cards.
Even if no benefit over gddr5x in terms of performance at lower resolutions, hbm2 still will be better due to lowering power use alone, there are other benefits also. HBM memory from what I can see is the way forward
Associate
- Joined
- 10 Nov 2009
- Posts
- 1,099
- Location
- London
The thing that makes me sceptical of using current implementations to discuss HBM is that we have yet to see a chip fully engineered around using it. Vega will be the first so it will be interesting to see if it makes better use of it.
Both AMD and Nvidia wouldn't be moving towards HBM if the engineering and performance benefits weren't real, but possibly it's more of a forward thinking move looking to VR and 4k+.
Both AMD and Nvidia wouldn't be moving towards HBM if the engineering and performance benefits weren't real, but possibly it's more of a forward thinking move looking to VR and 4k+.
The slow speed of HBM is probably why the FuryX was weaker than the 980ti in sub 4K resoultions. When there is not enough data to use all the bandwidth, then the actual speed of data transfer is what determines performance.
I dare say things could have been different if AMD had opted for fast GDDR5X for the Fiji cards.
Can you link that please, both the P6000 and P5000 both use GDDR5x.
Neither use HBM.
The P6000 also runs faster than the Titan Xp in games, albeit with just under 300 more CUDA cores. Then again an increase of 10fps is huge, and it has better frame times.
http://hothardware.com/reviews/nvidia-quadro-p6000-and-p5000-workstation-gpu-reviews?page=1
Last edited:
That stepping is quite strange but something is better than nothing I suppose
. Thank you.HBM2 will react the same I'd guess then?. I hope there is headroom for the core in Vega if that's the case as it might be needed. If at stock the Vega is either neck and neck with an overclocked 1080 or lagging behind it in DX11 titles, that headroom might make a big difference. Speculation of course.
Soldato
- Joined
- 18 May 2010
- Posts
- 23,140
- Location
- London
Interested in RyZen platform. If I did an upgrade I'd want to replace my 970. If I was to get a new GPU I'd need a higher resolution monitor. All in all, new Nvidia GPU and new monitor would be very expensive. (Plus RyZen platform)
Vega could provide me with a solution as freesync panels are cheaper than Gsync.
Vega could provide me with a solution as freesync panels are cheaper than Gsync.
Caporegime
- Joined
- 8 Jul 2003
- Posts
- 30,063
- Location
- In a house
so Vegas only for the 4K brigade, bit of a small market that
Anyone on lower than 4K, only has the 480 to get from AMD, or has to go Nvidia for more performance, looks like its a 1080 for me then
So what do those with 1440p monitors do?so Vegas only for the 4K brigade, bit of a small market that
Anyone on lower than 4K, only has the 480 to get from AMD, or has to go Nvidia for more performance, looks like its a 1080 for me then
Correct, but it's going to take a long time to get there as the vast majority of graphics assets target 1080p.
It is not just a matter of having a card that can render 4K@60, it's also a matter of games shipping with high-quality textures suitable for 4K.
Associate
- Joined
- 27 Dec 2014
- Posts
- 1,686
- Location
- Southampton
so Vegas only for the 4K brigade, bit of a small market that
Anyone on lower than 4K, only has the 480 to get from AMD, or has to go Nvidia for more performance, looks like its a 1080 for me then
this isn't the only concern though. The other is how well will Vega perform in non Vulkan titles.
- Status