[Gamers Nexus]Titan V benchmarked : An Async Future for nVidia - Page 3 - Overclock.net

Forum Jump: 
Reply
 
Thread Tools
post #21 of 50 Old 12-12-2017, 11:43 PM
New to Overclock.net
 
Shiftstealth's Avatar
 
Join Date: Mar 2011
Location: Pittsburgh, PA
Posts: 4,346
Mentioned: 0 Post(s)
Tagged: 0 Thread(s)
Quoted: 4 Post(s)
Liked: 213
The best news out of the Titan V is that NVIDIA knows how to properly lay the HBM at the same height as the die.

Image here:
https://videocardz.com/74427/nvidia-titan-v-features-gv100-400-gpu

Shiftstealth is online now  
Sponsored Links
Advertisement
 
post #22 of 50 Old 12-13-2017, 12:07 AM
 
Pyrotagonist's Avatar
 
Join Date: Jan 2016
Posts: 568
Mentioned: 0 Post(s)
Tagged: 0 Thread(s)
Quoted: 0 Post(s)
Liked: 66
I compiled some of the results into an excel sheet if anyone's interested

BYOIYlt.png
https://www.gamersnexus.net/guides/3170-titan-v-gaming-benchmarks-async-future-is-bright-for-volta

The N/As are there because the cards that are tested are inconsistent from game to game; some of them don't include the Titan Xp overclocked and For Honor does not include the Titan V overclocked.

The Titan V is 17% faster on average than the Xp and 28% faster when comparing both cards overclocked. Though remember that the overclock results for some of the games where the Titan V does badly aren't all available.
Hydroplane and xTesla1856 like this.
Pyrotagonist is offline  
post #23 of 50 Old 12-13-2017, 12:30 AM
New to Overclock.net
 
tajoh111's Avatar
 
Join Date: Aug 2013
Posts: 1,234
Mentioned: 0 Post(s)
Tagged: 0 Thread(s)
Quoted: 1 Post(s)
Liked: 213
Quote:
Originally Posted by Charcharo View Post

The 780 Ti lost to the Titan Black

The 1080 Ti loses to the updated, full Titan Xp.


The problem is, the Kepler Titans were prosumer cards. Sure they were awesome for games, but that was not their forte. Their real value was as HPC, CUDA, scientific and prosumer cards. Which was great, they made sense and were actually CHEAP for the target audience.

But Maxwell and Pascal titans are just gaming cards. Nothing more.

This Titan V though seems like a return to form - an actual prosumer product. Not just some gaming thingy.

Thanks to AMD providing competition a bit giving semi pro drivers to Vega Frontier, Nvidia did the same thing and Titans are actually work horses for cad programs and good values now.

https://www.youtube.com/watch?v=oVxVIkw0xd8&feature=youtu.be&t=6m12s

These are the newest results with the newest drivers vs the frontier edition, and the titan XP are actually good cad rendering cards now among other pro applications. If your gaming and doing the same productivity applications the frontier edition is good at(aside from fp16 stuff), a titan XP will actually serve you well and make that 1200 dollars if your using it for certain professional applications a good value, atleast better than the Vega frontier because of the big leads(50% in gaming and 1-60% faster performance in professional applications) for 200 dollars more.

Until GV or GA102 comes out, titan XP will likely hold their value pretty well because of this.
tajoh111 is offline  
Sponsored Links
Advertisement
 
post #24 of 50 Old 12-13-2017, 01:04 AM
 
prjindigo's Avatar
 
Join Date: Mar 2011
Posts: 1,485
Mentioned: 0 Post(s)
Tagged: 0 Thread(s)
Quoted: 0 Post(s)
Liked: 152
Quote:
Originally Posted by Usario View Post

This is not a fully enabled part, it has 5120 SPs and a 3072-bit memory bus. GV100 has 5376 SPs and 4096-bit.

You can count on yields being crap with an 815mm^2 die, interposer and HBM2.

No, you're wrong in several ways.

The first of which is that this is a damaged bin part not an under-enabled part. nV can charge 2x as much for fully functional parts. These cards have a bad HBM2 stack on them or they'd be 16gb.

The second is that each HBM2 stack is only 128 bits wide and cannot be addressed with larger than 64bit data, it has two 64bit channels into it not 1024.
The parallelism of the ram in the HBM2 stack is immaterial.

These cards are 384bit, are missing an HBM2 stack, may have damaged nVlink parts and are useless in arrays because of it.

I've described elsewhere how HBM and HBM2 stacks work but basically the "ram controller" for the stack is in the bottom and has access channels to the PCIe and the GPU, the GPU communicates with 2x64bit bi-directional channels per stack at very high speed.

Claiming that the HBM is 3072 or 4096 wide is like claiming that 4-channel boards with 8 slots populated with 8gb sticks of ram are 1024bit wide memory buses. There may be 1024 bits of memory port address in there but it's still only 4x64 bit channels to the CPU for 256.

Don't propagate marketing twaddle like "4096" and "x86"... they're lies.
prjindigo is offline  
post #25 of 50 Old 12-13-2017, 02:59 AM
Paid AMD Shill
 
Usario's Avatar
 
Join Date: May 2011
Location: New York, NY
Posts: 4,720
Mentioned: 0 Post(s)
Tagged: 0 Thread(s)
Quoted: 0 Post(s)
Liked: 261
Quote:
Originally Posted by prjindigo View Post


No, you're wrong in several ways.

The first of which is that this is a damaged bin part not an under-enabled part. nV can charge 2x as much for fully functional parts. These cards have a bad HBM2 stack on them or they'd be 16gb.

The second is that each HBM2 stack is only 128 bits wide and cannot be addressed with larger than 64bit data, it has two 64bit channels into it not 1024.
The parallelism of the ram in the HBM2 stack is immaterial.

These cards are 384bit, are missing an HBM2 stack, may have damaged nVlink parts and are useless in arrays because of it.

I've described elsewhere how HBM and HBM2 stacks work but basically the "ram controller" for the stack is in the bottom and has access channels to the PCIe and the GPU, the GPU communicates with 2x64bit bi-directional channels per stack at very high speed.

Claiming that the HBM is 3072 or 4096 wide is like claiming that 4-channel boards with 8 slots populated with 8gb sticks of ram are 1024bit wide memory buses. There may be 1024 bits of memory port address in there but it's still only 4x64 bit channels to the CPU for 256.

Don't propagate marketing twaddle like "4096" and "x86"... they're lies.

None of what you said is relevant at all to my post or the question I was answering. For the record, I didn't even say why it wasn't fully enabled, and I could not care less about your being flustered with how HBM is marketed.
Usario is offline  
post #26 of 50 Old 12-13-2017, 04:13 AM
 
guttheslayer's Avatar
 
Join Date: Apr 2015
Posts: 2,886
Mentioned: 0 Post(s)
Tagged: 0 Thread(s)
Quoted: 0 Post(s)
Liked: 108
Quote:
Originally Posted by Charcharo View Post



This Titan V though seems like a return to form - an actual prosumer product. Not just some gaming thingy.


Its the first card with the "TITAN" imprint on the side of the shroud instead of Geforce, isnt that clear enough?


From this point onward, Nvidia is clear that TV no longer belong to Geforce or even any part of it.

guttheslayer is offline  
post #27 of 50 Old 12-13-2017, 04:19 AM - Thread Starter
PC Gamer
 
Charcharo's Avatar
 
Join Date: Nov 2015
Location: Sofia, Bulgaria
Posts: 1,157
Mentioned: 0 Post(s)
Tagged: 0 Thread(s)
Quoted: 0 Post(s)
Liked: 107
Quote:
Originally Posted by guttheslayer View Post

Its the first card with the "TITAN" imprint on the side of the shroud instead of Geforce, isnt that clear enough?


From this point onward, Nvidia is clear that TV no longer belong to Geforce or even any part of it.

Irrelevant. Words are cheap, useless even in this industry.

However the Tensor cores alone indicate things clearly enough. Hence why I am actually supportive of this product. Unlike the Pascal and Maxwell Titans, this one isnt a joke.

Defender of Gaming as an Art Form
Slayer of anti-gaming Consoles and the people who oppose eternal glory to our art form
Charcharo is offline  
post #28 of 50 Old 12-13-2017, 07:08 AM
 
prjindigo's Avatar
 
Join Date: Mar 2011
Posts: 1,485
Mentioned: 0 Post(s)
Tagged: 0 Thread(s)
Quoted: 0 Post(s)
Liked: 152
Quote:
Originally Posted by Usario View Post

None of what you said is relevant at all to my post or the question I was answering. For the record, I didn't even say why it wasn't fully enabled, and I could not care less about your being flustered with how HBM is marketed.


You were implying that these cards aren't broken and they are. They're all floor-sweepings at the screw factory.
prjindigo is offline  
post #29 of 50 Old 12-13-2017, 07:09 AM
 
prjindigo's Avatar
 
Join Date: Mar 2011
Posts: 1,485
Mentioned: 0 Post(s)
Tagged: 0 Thread(s)
Quoted: 0 Post(s)
Liked: 152
Quote:
Originally Posted by Charcharo View Post

Irrelevant. Words are cheap, useless even in this industry.

However the Tensor cores alone indicate things clearly enough. Hence why I am actually supportive of this product. Unlike the Pascal and Maxwell Titans, this one isnt a joke.

I'm uncertain how you've added to the discussion here since the tensor cores aren't visible on the packaging or the device.
prjindigo is offline  
post #30 of 50 Old 12-13-2017, 07:14 AM - Thread Starter
PC Gamer
 
Charcharo's Avatar
 
Join Date: Nov 2015
Location: Sofia, Bulgaria
Posts: 1,157
Mentioned: 0 Post(s)
Tagged: 0 Thread(s)
Quoted: 0 Post(s)
Liked: 107
Quote:
Originally Posted by prjindigo View Post

I'm uncertain how you've added to the discussion here since the tensor cores aren't visible on the packaging or the device.

They were part of the announcement tongue.gif !

I actually didnt expect Nvidia to do it. Mad props they left them in.

Defender of Gaming as an Art Form
Slayer of anti-gaming Consoles and the people who oppose eternal glory to our art form
Charcharo is offline  
Reply

Quick Reply

Thread Tools
Show Printable Version Show Printable Version
Email this Page Email this Page


Forum Jump: 

Posting Rules  
You may post new threads
You may post replies
You may not post attachments
You may not edit your posts

BB code is On
Smilies are On
[IMG] code is On
HTML code is Off
Trackbacks are Off
Pingbacks are Off
Refbacks are Off