![]() |
|
|
#1 |
|
My name is Dave
Join Date: Apr 2006
Location: The Great White North
Posts: 10,775 (4.14/day)
Thanks: 4,497
Thanked 5,236 Times in 3,211 Posts
|
Volta to bring 1 TB/s memory bandwidth to GPUs?
__________________
Gadgets, Phones, Tablets, Cameras, TVs, HiFi...NextPowerUp -Only real men play games THIS way. |
|
|
|
|
|
#2 |
![]() Join Date: Jan 2009
Location: Brisbane, Australia
Posts: 2,518 (1.58/day)
Thanks: 57
Thanked 528 Times in 470 Posts
|
That robot in the intro is scary awesome!
__________________
“it's still EA.. they will F*** it up. F***ing up games is the only thing they do consistently.” -TRIPTEX_MTL
|
|
|
|
|
|
#3 |
![]() Join Date: Dec 2010
Location: State College, PA, USA
Posts: 436 (0.49/day)
Thanks: 118
Thanked 107 Times in 78 Posts
|
1TB/sec sounds great, but that's ~4x the bandwidth of current high end GPUs. If bandwidth doubles each generation and Volta is two generations away, then it's normal progress.
|
|
|
|
| The Following 3 Users Say Thank You to The Von Matrices For This Useful Post: |
|
|
#4 |
|
Knowledgeable Posting Whore
Join Date: Aug 2010
Location: Seattle, WA
Posts: 5,792 (5.81/day)
Thanks: 1,285
Thanked 1,087 Times in 839 Posts
|
So Volta is their codename for the generation after Maxwell? Interesting...
__________________
Motocross is not just a sport, it's a lifestyle. ![]() File Server: Intel Pentium G630, 8GB PNY 1600, AsRock H77M Micro, Corsair CX430M, Vertex 2 90GB (OS), 2x WD Red 2TB in RAID1 “We will never know our full potential, unless we push ourselves to find it. -Travis Rice”
|
|
|
|
|
|
#5 | |
![]() Join Date: Mar 2008
Location: Minnesota
Posts: 1,925 (1.01/day)
Thanks: 803
Thanked 554 Times in 362 Posts
|
Quote:
|
|
|
|
|
|
|
#6 | |
![]() Join Date: Jan 2012
Location: Indonesia
Posts: 363 (0.71/day)
Thanks: 496
Thanked 271 Times in 151 Posts
|
Quote:
![]() Here : http://blogs.nvidia.com/2013/03/live...g-at-gtc-2013/ http://blogs.nvidia.com/2013/03/nvid...idias-roadmap/ |
|
|
|
|
| The Following User Says Thank You to okidna For This Useful Post: |
|
|
#7 |
![]() |
The keynote was 12hrs ago.
![]() Nothing too exciting just a bunch of graphs and the funniest part was when they were introducing the director for upcoming Fantastic Four and how GRID would help out. The crowd just didnt seam interested and JJ-H was try'n to get them interested. Even the director was like eh.. And not one mention of Project Shield just a reference to it when hes showing off Ira which had the responses scripted since you can tell it resets for each responce on the video. |
|
|
|
|
|
#8 |
|
My name is Dave
Join Date: Apr 2006
Location: The Great White North
Posts: 10,775 (4.14/day)
Thanks: 4,497
Thanked 5,236 Times in 3,211 Posts
|
Tegra roadmap:
I had school today, so missed this, some interesting stuff but at the same time seemed like too much pandering. Will be interesting to hear some of the other presentations that'll be given over the next few days, so yeah, GTC is still ongoing. Maybe more interesting stuff will come in the next few days.
__________________
Gadgets, Phones, Tablets, Cameras, TVs, HiFi...NextPowerUp -Only real men play games THIS way. |
|
|
|
|
|
#9 |
![]() Join Date: Jan 2009
Location: on top of that big mountain on mars(e Eu)
Posts: 1,420 (0.90/day)
Thanks: 39
Thanked 272 Times in 234 Posts
|
logan prototype
|
|
|
|
| The Following User Says Thank You to DarkOCean For This Useful Post: |
|
|
#10 |
![]() Join Date: Aug 2004
Location: California, U.S.A.
Posts: 2,003 (0.63/day)
Thanks: 552
Thanked 513 Times in 218 Posts
|
I know the technology is completely different, but I remember Nvidia embedding the VRAM to the RSX GPU substrate for PS3 back in 2006, I think it didn't offer much of a performance advantage back then due to the 128bit bus.
Embedding some sort of cache in the same substrate as the GPU die and giving it a 1024bit direct bus to the GPU could provide the necessary increase in bandwidth. Since all the traces between the GPU and this cache memory would be relatively short and not an actual part of the PCB design, this approach would be feasible from an economic point of view. I bet cards would still require more VRAM on the PCB with a more conventional bus in order to reduce design complexity and cost, and allow for more memory availability due to VRAM density not being limited by packaging constrains.
__________________
Main Rig: See System Specs HTPC Game room: Ci7 SB 2600K@4.5Ghz - Asus ROG Maximus IV Gene-Z - EVGA 2xGTX680s SLI - 4x4GBs GSkill Ripjaws - 2x120GBs Vertex 3MIOPS - OCZ 1.25 kW PSU HTPC Bedroom: C2Q Q9550@3.4Ghz - Asus ROG Striker II - EVGA 2xGTX680s SLI - 2x4GBs Kingston HyperX - 2x120GBs Agility 3 - SB Recon3D - Silverstone 1 kW PSU Lappy: Samsung Series 7 NP700G7C - Ci7 IVB 3610QM@2.3~3.3Ghz - 17.3" 1920x1080 120 Hz - GeForce GTX675M - 16GBs 1600Mhz RAM - 512GBs Crucial M4 - 6X BluRay Last edited by 15th Warlock; Mar 20, 2013 at 06:53 AM. |
|
|
|
|
|
#11 |
|
Knowledgeable Posting Whore
Join Date: Aug 2010
Location: Seattle, WA
Posts: 5,792 (5.81/day)
Thanks: 1,285
Thanked 1,087 Times in 839 Posts
|
Here is what I have to say to Nvidia now after watching a lot of the videos from today.
__________________
Motocross is not just a sport, it's a lifestyle. ![]() File Server: Intel Pentium G630, 8GB PNY 1600, AsRock H77M Micro, Corsair CX430M, Vertex 2 90GB (OS), 2x WD Red 2TB in RAID1 “We will never know our full potential, unless we push ourselves to find it. -Travis Rice”
|
|
|
|
|
|
#12 | |
![]() |
Quote:
Tegra roadmap needs to be push 2yrs forward to be competative. Logan should have been what Tegra 4 "Wayne" Tegra4i "Grey" is. Thats why Qualcomm S600 is stealing all the flagship this year. Not one new phone that has been anounced will be using Tegra4i on there flagship product. The only one commited to carring Tegra4i is ZTE. Parker is going to be a year or more late as thing stand. Dell has been testing AppliedMicro 64bit ARM since late last year and AMD will be producing a hybrid by 2014. By the time Parker rolls out 2nd gen 64bit ARM SoCs will be coming out. |
|
|
|
|
|
|
#13 |
![]() |
Bandwidth doesn't double with each generation. They've been slacking with bandwidth improvements for awhile now. It's been a pretty slow craw from 100 to 200 GB/s.
|
|
|
|
|
|
#14 |
![]() Join Date: Oct 2004
Location: Europe/Slovenia
Posts: 3,967 (1.26/day)
Thanks: 39
Thanked 753 Times in 541 Posts
|
The question here is, is memory bandwidth really that important? My answer is that GPU clock, throughput, shading perfomance and everything around it is far more important than high raw memory bandwidth.
__________________
RejZoR's Little Secrets @ rejzor dot tk |
|
|
|
|
|
#15 |
![]() Join Date: Jun 2011
Location: Idaho
Posts: 2,282 (3.27/day)
Thanks: 457
Thanked 429 Times in 320 Posts
|
That is what I was wondering. Its a terabyte a second of bandwidth... At the very least it will make memory not a bottleneck for a while.
|
|
|
|
|
|
#16 | |
![]() |
Quote:
![]() [Source: PCGH] |
|
|
|
|
|
|
#17 |
![]() |
Those have already shown up in recent drivers
NVIDIA_DEV.0FC4 = "NVIDIA D14P1-15" NVIDIA_DEV.0FC5 = "NVIDIA D15M2-03" NVIDIA_DEV.0FDA = "NVIDIA GK107-ES-A1" NVIDIA_DEV.0FE3 = "NVIDIA GeForce GT 745M" NVIDIA_DEV.0FE5 = "NVIDIA GeForce K340 USM" NVIDIA_DEV.0FE6 = "NVIDIA NVS K1 USM" NVIDIA_DEV.0FE7 = "NVIDIA Generic K1 USM" NVIDIA_DEV.0FEF = "NVIDIA GRID K340" NVIDIA_DEV.0FF0 = "NVIDIA NB1Q" NVIDIA_DEV.0FF1 = "NVIDIA NVS 1000" NVIDIA_DEV.0FF2 = "NVIDIA GRID K1" NVIDIA_DEV.0FF5 = "NVIDIA Tesla K1 USM" NVIDIA_DEV.0FF7 = "NVIDIA Quadro K1 USM" NVIDIA_DEV.1001 = "NVIDIA D15U-60" NVIDIA_DEV.1003 = "NVIDIA GK110 DT Bringup" NVIDIA_DEV.1004 = "NVIDIA D15U-50" NVIDIA_DEV.1182 = "NVIDIA GK104" NVIDIA_DEV.1184 = "NVIDIA GK104 " NVIDIA_DEV.118A = "NVIDIA GRID K520" NVIDIA_DEV.118B = "NVIDIA GeForce K2 USM" NVIDIA_DEV.118C = "NVIDIA NVS K2 USM" NVIDIA_DEV.118D = "NVIDIA Generic K2 USM" NVIDIA_DEV.1192 = "NVIDIA GeForce GK104" NVIDIA_DEV.119F = "NVIDIA GeForce GTX 780M" NVIDIA_DEV.11D1 = "NVIDIA GK106-INT343" NVIDIA_DEV.11D2 = "NVIDIA GK106-INT232" NVIDIA_DEV.11D3 = "NVIDIA GK106-ES" NVIDIA_DEV.11E2 = "NVIDIA GeForce GTX 765M" NVIDIA_DEV.11E3 = "NVIDIA GeForce GTX 760M" NVIDIA_DEV.11FF = "NVIDIA NB1Q " NVIDIA_DEV.11B0 = "NVIDIA Quadro K2 USM" NVIDIA_DEV.11B1 = "NVIDIA Tesla K2 USM" NVIDIA_DEV.11B6 = "NVIDIA N15E-Q1" NVIDIA_DEV.11B7 = "NVIDIA N15E-Q3" NVIDIA_DEV.11B8 = "NVIDIA N15E-Q5" NVIDIA_DEV.11BB = "NVIDIA Quadro 4100" NVIDIA_DEV.11C1 = "NVIDIA D14P2-30" NVIDIA_DEV.11C2 = "NVIDIA GK106" NVIDIA_DEV.1281 = "NVIDIA D15M2-05" NVIDIA_DEV.1282 = "NVIDIA D15M2-20" NVIDIA_DEV.1283 = "NVIDIA D15M2-10" NVIDIA_DEV.1285 = "NVIDIA GK208-100" NVIDIA_DEV.1290 = "NVIDIA GeForce GT 730M " NVIDIA_DEV.1291 = "NVIDIA GeForce GT 735M" NVIDIA_DEV.1293 = "NVIDIA GeForce GT 730M " NVIDIA_DEV.1294 = "NVIDIA GeForce GT 740M " NVIDIA_DEV.12A0 = "NVIDIA GK208" NVIDIA_DEV.12AD = "NVIDIA GK208-ES" NVIDIA_DEV.12AE = "NVIDIA GK208-CS1-C" NVIDIA_DEV.12AF = "NVIDIA GK208-INT" NVIDIA_DEV.12B0 = "NVIDIA GK208-CS-Q" NVIDIA_DEV.12B1 = "NVIDIA GK208 INT" Last edited by Xzibit; Mar 20, 2013 at 05:02 PM. Reason: bigger list |
|
|
|
| The Following User Says Thank You to Xzibit For This Useful Post: |
![]() |
| Currently Active Users Viewing This Thread: 1 (0 members and 1 guests) | |
| Thread Tools | |
|
|
Similar Threads
|
||||
| Thread | Thread Starter | Forum | Replies | Last Post |
| Muskin Enhanced Introduces Volta and Joule Series PSUs | btarunr | News | 13 | Jan 31, 2010 02:48 AM |
| PCI-E 2.0, what does it bring | _33 | Graphics Cards | 28 | Apr 30, 2009 05:02 PM |
| Bring on the Spider!!! | jbunch07 | Project Logs | 358 | Oct 3, 2008 04:11 PM |
| Sonnet's Volta increases iPod battery life by 50 hours | zekrahminator | News | 12 | Oct 28, 2006 02:41 AM |