GDDR3 vs. GDDR5

[Firestrider]

I've heard that GDDR5 is less efficient at similar frequencies of GDDR3, is this true?

Which is better in terms of performance/watt at different frequencies? Is there any other features to GDDR5 that make it better than GDDR3?

[Cuiiey]

Well, im not 100% sure but i heard that GDDR5 has 3x times the performace gain over GDDR3.

[Rinne]

GDDR5 should be about 2x as fast per clock as GDDR3. It also consumes much less power at the same speed than GDDR3.

In fact, GDDR5 is so fast that it is bottlenecked by the GPU's that use it right now.

[henzo]

GDDR5 should be about 2x as fast per clock as GDDR3. It also consumes much less power at the same speed than GDDR3.

In fact, GDDR5 is so fast that it is bottlenecked by the GPU's that use it right now.

It may be faster than GDDr3, but mine does not like to be ramped up too high. So far my max stable oc is 975 for the mem. Anything higher and I get ramdom program crashes (like benches and some games).

[Zurvan]

GDDR5 can do 7Ghz(still going) while GDDR3 can do max 2.6 Ghz. <-- I think the efficiency isnt big enough to kill out this gap ;)
And thats effecive freq, 5 is QDR while 3 is DDR. I think 5 may take more power because of the same, but at smaller process it might not make much difference.

[ghost_recon88]

GDDR5 should be about 2x as fast per clock as GDDR3. It also consumes much less power at the same speed than GDDR3.

In fact, GDDR5 is so fast that it is bottlenecked by the GPU's that use it right now.

Exactly what he said. GDDR5 bandwidth is indeed 2x that of GDDR3. When you go to newegg and click on the HD 4870, you'll see the RAM speed rated @ 3600MHz when the the GDDR5 is really clocked @ 900MHz. 900x2=1800, then since it has 2x the bandwidth of GDDR3, 1800x2=3600MHz.

[Firestrider]

Found this on EETimes:


Inside the interface
GDDR5 will initially appear on 512-Mbit and 1-Gbit chips supporting data transfers at up to 4 Gbits/s per pin at gigahertz frequencies using a quad-rate clock. It can stretch to data rates as fast as 7 Gbits/s per pin, to deliver throughput of 12 to 28 Gbytes/s per chip.


The interface retains the single-ended structure of the previous generation but uses a new clocking technique and new low-power modes to consume an average of 2.5 watts at 5 Gbits/s running at 1.5 volts. Macri estimates the interface reduces power by about 30 percent compared with mainstream GDDR3.


The interface is backward-compatible with previous graphics and systems memory interconnects from Jedec. "It's possible to build a controller that handles everything from DDR2 up to GDDR5 running from 400 MHz to 5 Gbits/s, which is pretty amazing," Macri said.


Pin reductions and other streamlining steps aim to keep die size, and therefore cost, as low as possible. "Our GDDR5 physical-layer block is not a whole lot bigger than our competitor's GDDR3 PHY," said Macri.


GDDR5 extracts clock information from the data stream in a way that allows it to be flexible across different operating conditions--a fact that will help optimize performance when PC gamers overclock the chips. "This is much more flexible than any DRAM we have ever worked with in terms of going up and down in frequency and power," said Macri.


The spec supports read/write error detection directions and can do real-time error detection and repair. The clocking scheme simplifies board routing. The spec itself is in a final stage at Jedec. "There's [still] a lot of cleanup, but after a September ballot, it should be ready for publication," said Macri.


So it looks like it does consume less power: 30% compared to GDDR3. The snippet says up to 7 Gbps/s per pin data rate; at what frequency is this and have many "pins" do GPUs have (is it analogous to bus width in bits)?

[deathman20]

GDDR5 is better due to the fact the manufacture of said video card doesn't have to spend an expensive amount of money on chips and PCB layouts to get the same throughput from memory.

Its a trade off that the company has to be willing to take. In this case ATI got in early, and went GDDR5 w/ 256bit bus, while nVidia went in with GDDR3 say 512bit bus. While GDDR3 is more known out there and can get some good clock rates out of it, GDDR5 is where it will be at.

Currently though GDDR3 at least on some of the newer nVidia cards can push upwards of 2,800Mhz on a 512Bit Bus, where as ATI's can push 4,000Mhz on a 256bit bus. So in the end nVidia is winning with the GDDR3 because it can still push more information though there ram while being slower it has more highway lanes to process information. If to be equal in this case now totally depending on latencies on the ram chips (we'll take that out of this example) the GDDR3 w/ 512bit bus would have to run 2,000Mhz (easy by GDDR3 standards). Or ATI would have to run GDDR5 w/ 256bit bus at 5,600Mhz (no used on GPU's currently) to match performance.

In the end GDDR5 is better, cheaper for the manufacture to use, and in the end of the day better for you with less power being used to power the chips to get said speed and at a cheaper cost (GDDR5 is supposedly cheaper to manufacture).