Use VRAM from only one card?

Smoblikat

Diamond Member
Nov 19, 2011
5,184
107
106
I understand memory isnt doubled when run in SLI due to latency issues with the bridge, but why do cards need to have the same amount of memory in order to work? Why cant they just make SLI edition cards with no memory and sell them for cheap just to use as extra GPU power? I thought the only memory being used was from the card that your monitor is plugged into.
 

Dark Shroud

Golden Member
Mar 26, 2010
1,576
1
0
Because the data stored in the memory of the primary card has to be mirrored across to the second card to properly render the content.
 

Smoblikat

Diamond Member
Nov 19, 2011
5,184
107
106
Because the data stored in the memory of the primary card has to be mirrored across to the second card to properly render the content.

I never knew that. Though now that you say it it makes sense. But what if you do alternate frame rendering? Then the data will be opposite, how does it do it then?
 

chimaxi83

Diamond Member
May 18, 2003
5,649
61
101
It is still the same data, with each GPU taking a turn rendering a frame.
 

ShintaiDK

Lifer
Apr 22, 2012
20,378
145
106
Yep, the cards or GPUs if you got 2 on a single card essentially got nothing to do with one another.

I guess you might trying to think on it as a PC with 2 CPUs in 2 sockets. Thats not how it is. Its more like 2 individual PCs you are trying to get to work together.

The only exchange is the finished renderframe, that they then try and sync it to appear properly.
 

PrincessFrosty

Platinum Member
Feb 13, 2008
2,301
68
91
www.frostyhacks.blogspot.com
Each GPU needs its own dedicated bank of memory to work from, the data in both banks of memory is the same which is why the effective memory in SLI or crossfire is not doubled with 2 cards.

Remember that GPUs and CPUs are basically just calculators, they take numbers from memory do a calculation and store the result back into memory, a GPU or CPU alone without any memory is basically useless.
 

Cerb

Elite Member
Aug 26, 2000
17,484
33
86
I understand memory isnt doubled when run in SLI due to latency issues with the bridge, but why do cards need to have the same amount of memory in order to work? Why cant they just make SLI edition cards with no memory and sell them for cheap just to use as extra GPU power? I thought the only memory being used was from the card that your monitor is plugged into.
Memory bandwidth is not infinite, and memory latency matters. To do what you purpose, memory bandwidth would need to be nearly doubled, so each GPU would have enough to feed it from one source.

PCI-e can't handle that kind of bandwidth, and that bandwidth, in terms of traces on the board, is a non-trivial part of the cost of a video card (mainly because it may necessitate boards with more layers and area as more traces are needed). Even using a custom interconnect, you'd still have the cost of the RAM bandwidth t be concerned with (more RAM chips, more traces, more solder pads).

So, the easiest way to handle it is to duplicate the contents of the RAM in each card, except for buffers, as that is tolerant of timing issues (well, in most games), and uses a very small portion of the available bandwidth.