Tuesday, November 17th 2015
Three AIB Branded Radeon R9 380X Graphics Cards Pictured
Here are the first pictures of three AIB-branded Radeon R9 380X graphics cards, including one each from ASUS, XFX, and GIGABYTE. The ASUS branded Radeon R9 380X graphics card, the R9 380X STRIX, features the company's dual-slot, dual-fan DirectCU II cooling solution. ASUS is also giving it a slick back-plate, and offering it in two variants based on factory-overclock (or lack of it).
The XFX branded R9 380X features a similar product size to the ASUS card, featuring a moderately long PCB, and a dual-slot, dual-fan "Double Dissipation" cooler. XFX will sell variants of this card in reference and factory-overclocked speeds. Lastly, there's GIGABYTE. Like the others, this card features a medium-size PCB, with the company's dual-slot WindForce 2X cooling solution. Based on the 28 nm "Tonga" aka "Antigua" silicon, the R9 380X reportedly features 2,048 GCN 1.2 stream processors, 128 TMUs, 32 ROPs, and a 256-bit wide GDDR5 memory interface, holding 4 GB of memory. It's expected to launch later this week.
Souces: VideoCardz, HardwareInfo, WCCFTech
The XFX branded R9 380X features a similar product size to the ASUS card, featuring a moderately long PCB, and a dual-slot, dual-fan "Double Dissipation" cooler. XFX will sell variants of this card in reference and factory-overclocked speeds. Lastly, there's GIGABYTE. Like the others, this card features a medium-size PCB, with the company's dual-slot WindForce 2X cooling solution. Based on the 28 nm "Tonga" aka "Antigua" silicon, the R9 380X reportedly features 2,048 GCN 1.2 stream processors, 128 TMUs, 32 ROPs, and a 256-bit wide GDDR5 memory interface, holding 4 GB of memory. It's expected to launch later this week.
41 Comments on Three AIB Branded Radeon R9 380X Graphics Cards Pictured
forums.geforce.com/default/topic/880779/geforce-900-series/gtx-960-ti-petition/
The same GPU layout is found in the GTX 970Mmobile card
GTX 960...................................GM206.....32 ROP, 64 TMU, 1024 shaders, 8 SMM, 128 bit bus
GTX 960 OEM/970M..........GM204.....48 ROP, 80 TMU, 1280 shaders, 10SMM, 192 bit bus
Relax the TDP pf the 960 OEM/970M and up the clocks and you would get a part that sits between the GTX 960 and GTX 970 in performance. Whether Nvidia would feel the need to do it is another thing. I guess it depends on how many salvage parts they have since the 970M seems to be a big seller in the mobile space.
I honestly don't think nVidia cared much about what happened with the 900 series. It was stopgap till Pascal either way. The flawed memory on the 970, a 128bit 960, and lack of Ti offerings till the 980 just reeks of laziness. In part of course due to AMD. Had the 300s been something new, I wonder if Ti variants would have shipped all around.
Figure there has to be a lot of corporate spying or information sharing going on. They both seem to know what each other is doing. Fury was the only thing threatening and nVidia dropped the 980Ti bombshell weeks before it launched.
Had nVidia given half a care about the 900s, we'd have had Ti versions on most of the tiers like we had with the 600s. I'd imagine there being a 970Ti without the memory trouble and a 192bit 960 Ti. Or even better, 256bit 960s.
Had there been a 970Ti without the memory trouble I'd probably have stayed with nVidia. But their answer to that being the overpriced 980...ehh.
Ti variants are not necessary if the competition isn't putting forth something that needs it. With the 380X coming out now, I propose Nvidia finally has a reason to.
The 980 may seem overpriced, but in performance it whips the 970's tail. Nevertheless, there is not enough room in between the 970 and the 980 to put a card in Ti variant in between the two cards without robbing from one or the other. The 980 makes money, so why steal from there, and the 3.5GB of Fast VRAM on the 970 had not hurt those sales either in the last 10 months.
I maintain that Nvidia has cared about Maxwell. There was alot of work put in the design, and performance coupled with energy efficiency shows this. Sales have been among their highest ever.
The thing is that AMD and nVidia cards are two very different animals even though they're doing the same thing. On one hand you have Maxwell in the green camp that packs a whopping 128 stream processors per SMM (11 SSMs for the 970,) versus AMD in the red camp with GCN 1.1 like on the 390 and 390X which have 64 stream processors per CU and 40 CUs like on the 390. Without getting too discouraged however, we've seen that AMD cards seem to have some muscle when it comes to GPGPU and parallel compute, probably a result of the large number of CUs and the really wide memory bus but, doesn't this sound a little too familiar? This is similar to the problem AMD had with their CPUs compared to Intel. AMD decided to give up some single threaded performance to get relatively large gains on parallel throughput. For a GPU this makes more sense than a CPU but when push comes to shove, you can only do so much in parallel, even more so with libraries only starting to become more parallel in nature. This is where nVidia wins because the beefier SMM cores in Maxwell and higher clocks simply produces more performance in most gaming situations, there is no denying that in my opinion and nVidia should be commended on a job well done. The more serial (not parallel,) the workload becomes, the better nVidia does. On the same token, applications that execute more GPU instructions in parallel where the rendering can actually utilize more of those 40 GCN 1.1 CUs like in the 290/390 and you have a formidable product. Problem is that not all games are coded well in order to use parallel resources and as a result, nVidia, like Intel, wins because their cores are faster and can do more with a focus on what's needed most with current games however, that gap evaporates when you start utilizing the extra resources that GCN 1.1 has despite the lower clock frequency at the cost of dev hours and more complex code.
So this really comes down to how games are developed, what kind of calls are being made to draw and render scenes, etc. So it's not just a matter of ROPs, or TMUs, or plain numbers. It's a matter of AMD going above and beyond the parallel compute thing but losing sight of where the market really was at. Unlike their CPUs though, I think that all of that work to add more parallel throughput to their GPUs is going to pay off as games start demanding more GPU power and we start seeing APIs like Vulkan and DX12 take advantage of it which is starting to better utilize these untapped resources.
I hope my rant wasn't too off topic. :)
www.geforce.com/hardware/desktop-gpus/geforce-gtx-960-oem
Do we know any product that have this "integrated" onto a motherboard? Would it still need/use dedicated memory, or is there a way to share that from system ram? You'd still need a phase power section for it. Cooling is another need but I suppose any CPU type cooler could be used.
All of GCN is kinda old, you have GCN 1.0 / 1.1 / 1.2, but generally its the same architecture with some (small) changes, it shouldn't be compared to Maxwell, which is a entirely new architecture, and thus way more effective. GCN can be better compared to Kepler. Fury is a "blown up" GCN 1.2 thats basically not a balanced product, which you can easily see on the fact that it has the same 64 ROPS compared to GCN 1.1 2816 shader cards like the 290X. Fury should have 96 ROPs or something inbetween, but the space wasn't available for it -- the GPU was already too big anyway, even without the restriction of the Interposer. And that's why Fury X loses to 980 Ti.
Also, 290X/390X with 2816 shaders have a hard time keeping up with the GTX 980 and only 2048 shaders -- that's just because Maxwell is a new and more efficient architecture and therefore the big gap in energy usage too.
That said, AMD still manages it - just not as efficient as NV does. And the 980 Ti has no real opponent, as it's far better than the ROP-bottlenecked Fury X.