ATI 40nm GPUs arrive
SURPRISE SURPRISE DAAMIT has launched its first 40nm GPUs. Well, 40nm but not as we thought they'd be... these are the Mobility Radeon HD 4860 and Mobility Radeon HD 4830.
Yes, the red-and-green team has snuck in two mobile parts built on the 40nm process, before their desktop counterparts. The numbering on these parts also represents the relative product performance. According to the AMD benchmarketing, the Mobility 4860 will perform about 8% faster than the current crop of Mobility 4850. The 4830 will fall appropriately behind the latter, although we're guesstimating from the specs. Both parts share higher clock rates than their predecessors, but only 640 stream processors.
The duet is said to have a tamer power consumption than their predecessors, of course, which fits in with the process shrink and the specs. However we weren't able to get AMD to offer us their benchmarketing on this. We'll have to wait for a partner to ship us a notebook.
Memory-wise, the cheaper part, the 4830, will support a shared-memory architecture or dedicated VRAM, depending on the notebook model. The 4860 will have GDDR5 from Qimonda (yes, still churning out the memory).
Here's a spec sheet for 55nm and 40nm MXM modules.
You'll notice the GFlops on the 4830 don't add up @ 450MHz speed (450x640x2/1000 is 576GFlops). More like 400MHz, but it could be a typo.
On a parallel announcement, Asus has squealed with glee it'll be adopting the new graphics chippery in their upcoming K-series notebooks. µ
Share this:
ShareBusiness Intelligence Software
Customer Relationship Management (CRM)
Enterprise Accounting Software
Enterprise Resource Planning (ERP)
Enterprise Systems Management
This may be an interesting process, if the 8% claim and the chart provided are true, that 8% performance gain comes with 130 million LESS trannies.
You'll also notice that the number of shaders has decreased from 800 to 640. The speed increase is possible though due to the use of GDDR5 (4860) vs. GDDR3 (4850) memory.
Thingamajic, the 4860 is not able to do more calculations per second because of an increased RAM speed; that has nothing to do with it. The increased rate of calculation, despite the reduction in stream processors, is due to the higher clock speed, and whatever improvements may have been made to the GPU.
They chopped the bandwidth to 128bit and still got a speed bump? I guess we'll see how well they stand up once the benchmarkers get at them.
Not even a month ago INQ reported that the TSMC 40nm process was supposed to be very leaky. As a result no performance increase or power consumption reduction was to be expected.
Now we are seeing 40nm parts with the same speed as their 55nm counterparts, but with halved power consumption.
Does it mean that the TSMC 40nm process is all fixed and ready to go?
Does it also mean that we can expect a 100% increase of desktop parts performance?
With all this success at 40nm, I am very eager to see what they do with the next desktop product line. Hopefully no more stupid power requirements.
Hell, they could fit two of the HD 4870 X2 cards onto one desktop card!! today. the HD 4870x4 yah baby, give it to me now!
More likely, NVidia mocked up the design, while ATI designed theirs right - the result: lower power.
from 256bit to 128bit, why step back in time ATI?
I want 1024bit and 2048bit, now!!! ;-)
Its late and making us 40nm guineapigs. Winndows7 is around corner i.e. DX11. these DX10.1 40nm are for 4-6 months. Plus there is no mentioning of Mobility FireGL. it wasnt with 55nm and even not in 40nm. Is M-FireGL dead till DX11. I guess we should avoid it to force them for DX10.1 based FireGL at least.