Monday, February 9th 2015
Radeon R9 380X Based on "Grenada," a Refined "Hawaii"
AMD's upcoming Radeon R9 380X and R9 380 graphics cards, with which it wants to immediately address the GTX 980 and GTX 970, will be based on a "new" silicon codenamed "Grenada." Built on the 28 nm silicon fab process, Grenada will be a refined variant of "Hawaii," much in the same way as "Curacao" was of "Pitcairn," in the previous generation.
The Grenada silicon will have the same specs as Hawaii - 2,816 GCN stream processors, 176 TMUs, 64 ROPs, and a 512-bit wide GDDR5 memory interface, holding 4 GB memory. Refinements in the silicon over Hawaii could allow AMD to increase clock speeds, to outperform the GTX 980 and GTX 970. We don't expect the chip to be any more energy efficient at its final clocks, than Hawaii. AMD's design focus appears to be performance. AMD could save itself the embarrassment of a loud reference design cooler, by throwing the chip up for quiet custom-design cooling solutions from AIB (add-in board) partners from day-one.In other news, the "Tonga" silicon, which made its debut with the performance-segment Radeon R9 285, could form the foundation of Radeon R9 370 series, consisting of the R9 370X, and the R9 370. Tonga physically features 2,048 stream processors based on the more advanced GCN 1.3 architecture, 128 TMUs, 32 ROPs, and a 384-bit wide GDDR5 memory interface. Both the R9 370 and R9 370X could feature 3 GB of standard memory amount.
The only truly new silicon with the R9 300 series, is "Fiji." This chip will be designed to drive AMD's high-end single- and dual-GPU graphics cards, and will be built to compete with the GM200 silicon from NVIDIA, and the GeForce GTX TITAN-X it will debut with. This chip features 4,096 stream processors based on the GCN 1.3 architecture - double that of "Tonga," 256 TMUs, 128 ROPs, and a 1024-bit wide HBM memory interface, offering 640 GB/s of memory bandwidth. 4 GB could be the standard memory amount. The three cards AMD will carve out of this silicon, are the R9 390, the R9 390X, and the R9 390X2.
Source:
3DCenter.org
The Grenada silicon will have the same specs as Hawaii - 2,816 GCN stream processors, 176 TMUs, 64 ROPs, and a 512-bit wide GDDR5 memory interface, holding 4 GB memory. Refinements in the silicon over Hawaii could allow AMD to increase clock speeds, to outperform the GTX 980 and GTX 970. We don't expect the chip to be any more energy efficient at its final clocks, than Hawaii. AMD's design focus appears to be performance. AMD could save itself the embarrassment of a loud reference design cooler, by throwing the chip up for quiet custom-design cooling solutions from AIB (add-in board) partners from day-one.In other news, the "Tonga" silicon, which made its debut with the performance-segment Radeon R9 285, could form the foundation of Radeon R9 370 series, consisting of the R9 370X, and the R9 370. Tonga physically features 2,048 stream processors based on the more advanced GCN 1.3 architecture, 128 TMUs, 32 ROPs, and a 384-bit wide GDDR5 memory interface. Both the R9 370 and R9 370X could feature 3 GB of standard memory amount.
The only truly new silicon with the R9 300 series, is "Fiji." This chip will be designed to drive AMD's high-end single- and dual-GPU graphics cards, and will be built to compete with the GM200 silicon from NVIDIA, and the GeForce GTX TITAN-X it will debut with. This chip features 4,096 stream processors based on the GCN 1.3 architecture - double that of "Tonga," 256 TMUs, 128 ROPs, and a 1024-bit wide HBM memory interface, offering 640 GB/s of memory bandwidth. 4 GB could be the standard memory amount. The three cards AMD will carve out of this silicon, are the R9 390, the R9 390X, and the R9 390X2.
156 Comments on Radeon R9 380X Based on "Grenada," a Refined "Hawaii"
"Remember 2 wrongs don't make a right" GTA IV WKTT :p obviously :D
Don't forget that these cards will have a short lifespan and we are expecting soon the shrunk GPUs.
shrinking does also mean less space to work with and not any guaranteed performance gains. any gpu that is full dx12 will be some good stuff for a pretty long time.
And yes, those that bought cards with 4GB (or not as the 970 is) would have figured that into their choice. If 390X is to be AMD's next gen top tier card, you would hope it would have more as they have already seen fit (AIB's) to release a 8GB 290X with albeit small rewards at 4k.
IMO, I don't know if we need >4GB for gaming purpose except on poorly coded things (look at the recent CoD for bad memory hogging, or Titanfall IIRC). But if we do need >4GB in the next year or so, I'm pretty sure there will be developments to allow higher memory usage on the AMD chips.
So, to be plain - 4GB won't be an immediate worry and I'm sure it will be addressed when needed.
will wait the 390 tho ;)
I could see how it would be possible for shrinking gpu's to show many of the same problems. they are loving smaller lith for for mobile devices but perhaps there is bigger hurtles on the high end gpu side of things.
For Nvidia, GTX 760 is a GTX 680 rebrand. GTX 960 is a GTX 780 rebrand. Since the economy is the way it is, effectively selling off leftover stock is not what it use to be for both sides. So NVidia and AMD play the game of rebranding old chips into the next generation of graphic cards to get people to buy them instead of a high-end card due to budget constraints. A chip not sold, or a graphic card not sold, is money lost in the long run. I think it's been stigmatized into every high-end, gaming enthusiasts' mind, who knows a thing or two about AMD and NVidia Graphic Cards, that NVidia is king at 1080p, and anything above that, AMD dominate. Dominates barely... This could explain the expectations set by the consumers, and for their response: "The 390 only has a 4GB Framebuffer, isn't that a little lacking?" In addition, if you look at the past few generations of graphic cards, NVidia comes out with 2GBs, AMD comes out with 3GBs in the same generation. This has always been the trend. AMD will always have 1 GB more worth of memory than the same tier and generation card as NVidia's Card. On the Nvidia side, they try to make up for it by having a higher memory bandwidth. This is there way of making up for the lost in performance. Personally, I don't think 5GBs or more is needed, and if they really need the extra VRam, consumers could have just gotten a Sapphire R9-290x with the 8GB Framebuffer, or a Titan-black. Now, speaking of the future, there's no doubt in my mind that some variant of a R9-390x from one of the vendors, a non-reference card, will have 8 GBs or more in the not to distant future. In addition, there's really no need to go that high unless you are going surround or 4K. I bet the number of consumers who are at that level, or being in the position to own a 4K tv or surround setup is anywhere from 1 to 10%. The remaining consumers will probably still hover around the 1080p resolution for the next 2 to 5 years. Only games that in theory, can go above 4GBs VRam, would be Star Citizens, and Skyrim with a heavy set of mods on a 1080p setup. Crysis 3, at full blast settings, could peak around 3.6 GB Vram. Maybe that Lord of the Rings, Mordor game on high textures can go past it on 1080p resolution.
edit: it's late, I edited my stuff, I don't give a shet if you are a grammar Nazi...
As Breit rightly says, GM is not GK.
The cooler actually can do wonders... as clock really matters since turbo button was used on PC cases and the competition is so tight few 100Mhz can carve out the lead for sure, especially on minimum FPS.
What could be disappointing is the efficiency. With these chips you will only be getting 285 like efficiency, which is no where near Maxwell. Heat should be maintained pretty well IMO. AIB coolers with double fans are going to keep the temperatures down.
Also, higher efficiency would mean lower temps or more overhead for higher clocks which is never a bad thing.