• Competitor rules

    Please remember that any mention of competitors, hinting at competitors or offering to provide details of competitors will result in an account suspension. The full rules can be found under the 'Terms and Rules' link in the bottom right corner of your screen. Just don't mention competitors in any way, shape or form and you'll be OK.

AMD Pirate Islands Radeon R9 300 Series

F5fJaln.jpg
 
Why would they kill off their current flagship cards inside a year with nothing on the market battering the 290's?
 
humbug said:
I think its about time AMD did what Nvidia do, is 5.6 TeraFlops necessary on a gaming card?

The R9 390X looks like it would have about 9 TeraFlops of DP Compute, that's insane. AMD could cut half the compute performance out, save on a lot of power consumption and still end up with huge compute performance.
Click to expand...

Yes high compute is exceptionally important on a gaming card, compute is a natural product of any fpu power, all shaders provide compute. The difference is single precision and double precision. Double precision literally means it can deal with numbers twice as long, 64bit vs 32bit numbers. 64bit numbers aren't currently used at all in gaming. But hardware to deal with 64bit increases die size/powerusage without any benefit to gaming.

You won't have a faster gaming card without increasing SP compute numbers, you can cut out all DP capable shading capability without effecting gaming performance in the slightest. The 680gtx is a SP compute beast but it sucks badly at DP compute, that is the difference between the 680gtx/7970.

The 680gtx also went smaller bus so trailed significantly at higher res. It's all trade offs, Nvidia hit the sweet spot, right number of shaders for a 256bit bus for 1080p with very little die space wasted on DP.
 
pgi947 said:
Why would they kill off their current flagship cards inside a year with nothing on the market battering the 290's?
Click to expand...

Why do Apple, Qualcomm, Intel all make faster chips all the time? because it's what silicon companies do.

If you wait till someone releases something good, then it will be 2 years before you can react to it, and in that time you'll lose most of your sales. That is why people update their products constantly. From start to finish it will take 2-3 years to get a gpu to market. You can't just react to what everyone else is doing, you have to attempt to make the best thing you can all the time. That means when a new process is available(the main thing effecting bottom line performance on gpu's) then you need to plan for a new product on that process close to when it's first available because your competition will.

If AMD released a 20nm chip this year and Nvidia wait for that to be released, they'd only get their 20nm chip out a couple years later, no one reacts to the other guy in silicon you do your own thing, make a good chip and hope it's better or relatively close to what someone else makes.
 
I understand that everything is in the pipeline years in advance, what I meant was they appear to be rushing it out (obviously everything is speculation at this point), from waiting near 2 years between the 7900 series and 290, seemingly in no rush to halt GK110's domination of the high end market, to reacting to nothing inside a year.

My money is on early 2015 before AMD make a move.
 
The colleagues over at WccfTech posted something about the next generation Radeon graphics cards. They dug up an old (what is claimed to be) roadmap which shows details about three GPUs, the R9 390X, R9 380X and R9 370X. There is no validation regarding the source material and their post is highly speculative. Then again .. rumors always start somewhere and props to them for retrieving that info.

Now in their news item posted they already claim themselves that all information is to be taken with a pinch of salt, which really is the proper way to address this information.

The source leak indicates future Pirate Islands GPU code names and some specs. Specs NEVER are final which makes me frown up-on the posted material, anyway here's what they are claiming:

--

According to these details all GPUs will be based on the TSMC 20nm Node and will be true Pirate Island cores, which is why nomenclature of the dies will be derivative in nature. Another thing mentioned is that all Pirate Island GPUs will have the DirectX 12 Hardware Feature Set. According to these details the R9 370X is slated for announcement/arrival sometime this July-August this year. The R9 370X will feature a ‘Treasure Island XTX’ core and supposedly has 1536 Stream-processors, 96 Texture Units and 48 ROPs on the uncut die. Of course this road-map precedes the report we got of TSMC having a little trouble with 20nm so I am not sure how valid the time frame is anymore.

Now according to the details, we will see the R9 390X before the R9 380X. The R9 390X will feature the ‘Bermuda XTX’ core and feature a staggeringly high number of SPs, ie. 4224. The Texture Unit count is 264 with 96 ROPs. It is slated to show up late 2014 around November or so. Once again keep in mind the TSMC comment above. Finally the R9 380X which will feature the ‘Fiji XTX’ core and the following die configuration: 3072 SPs, 192 Texture Units and 72 ROPs and should appear sometime early 2015. Now interestingly the R9 390X ‘Bermuda XTX’ GPU is slated to have 512 Bits of Memory Bandwidth while as the R9 380X is slated to have 384 Bits with the R9 370X coming last with 256 Bits. Now the road-map even hints at the clock speeds of AMD’s future GPUs but I think it is prudent to mention that all these tech specs at this point in time are about as solid as the wind. However let us continue, with the help of this table:

GPU Codename Core Stream Processors* Texture Units* ROPs* Core Clock* Memory Clock* Memory Bandwidth*
R9 370X Treasure Island Treasure Island XTX 1536 96 48 ~900Mhz ~5Ghz 256Bit
R9 380X Fiji Fiji XTX 3072 192 72 ~900Mhz ~6Ghz 384Bit
R9 390X Bermuda Bermuda XTX 4224 264 96 ~1000Mhz ~7Ghz 512Bit
* Values are not indicative of the final product.
Click to expand...
LINK
 
Isn't WCCF responsible for about 90% of these "leaks"?

AMD might want to look into that.

Oh, they're not? I wonder why.
 
Both manufacturers will have something new on the table for when Haswell-E lands and people look to refresh their kit. Who knows whether those new cards are 20nm flagship cards or some sort of stop-gap but there will be something new at the high-end, Haswell-E rig builders won't be interested in mid-range cards.
 
drunkenmaster said:
If AMD released a 20nm chip this year and Nvidia wait for that to be released, they'd only get their 20nm chip out a couple years later, no one reacts to the other guy in silicon you do your own thing, make a good chip and hope it's better or relatively close to what someone else makes.
Click to expand...

You make a good point. I wouldn't be the first to suggest though that Nvidia and AMD seem to always be on exactly the same page, often nearly-simultaneously releasing products at the same performance and price levels. I wonder how much they're really "doing their own thing".
 
joeyjojo said:
You make a good point. I wouldn't be the first to suggest though that Nvidia and AMD seem to always be on exactly the same page, often nearly-simultaneously releasing products at the same performance and price levels. I wonder how much they're really "doing their own thing".
Click to expand...

each side get on with making silicon, they might have a number of these ready for production so that they can react to a release from the other side depending on performance and price points

hence the Titan > 780 > 780ti releases... they are all based on GK110 just with minor tweaks to bring them in at the price/performance level they wanted at the time
 
You must log in or register to reply here.
Back
Top Bottom