This makes me think, why couldn't Maxwell had come out instead of Kepler? Nothing has really changed since Kepler was released, except 28nm has gotten more mature. I realized these architectures take years to develop, but it seems like Maxwell is just so much better than Kepler on perf/watt considering they are both on the same node. They are both running DX11, VRAM hasn't changed much besides memory speed.
Guess I need to read up on why graphics architectures get more advanced over time.
Same reason we didn't have Haswell before Ivy Bridge. As chip designers discover more of the options available to them, we get better products.
Honestly, I think Maxwell is a huge step in the right direction for GPUs. Yes, smaller architecture allows manufacturers to pack in more brute force on a given wafer, but what Nvidia is doing here is innovating and advancing the state of tech. I like it.
Then nvidia would have been competing with GCN using Fermi.This makes me think, why couldn't Maxwell had come out instead of Kepler? Nothing has really changed since Kepler was released, except 28nm has gotten more mature. I realized these architectures take years to develop, but it seems like Maxwell is just so much better than Kepler on perf/watt considering they are both on the same node. They are both running DX11, VRAM hasn't changed much besides memory speed.
Guess I need to read up on why graphics architectures get more advanced over time.
There is one thing quite interesting about this product from a technical point of view. It shows just how little impact architectural changes really have on practical performance. We see it a lot with refresh cards but rather than tweaks this is a big change and yet the expected performance at the same die size is effectively the same. All the progress in the computing industry is based on the doubling of transistors based on density increases. Without that progressing we get basically nothing. This is the way of the industry, the cards worth buying are those based on new processes, those are the big upgrades, everything else is a tweak with minor improvements.
We're getting power efficiency. As far as I understand, power efficiency can almost always be converted to more performance because given the same power budget, it allows driving the chips harder, building larger chips, or using multiple chips per card. It's just that Nvidia isn't currently under enough competetive pressure to do so?There is one thing quite interesting about this product from a technical point of view. It shows just how little impact architectural changes really have on practical performance. We see it a lot with refresh cards but rather than tweaks this is a big change and yet the expected performance at the same die size is effectively the same. All the progress in the computing industry is based on the doubling of transistors based on density increases. Without that progressing we get basically nothing.
Combine the two and you have a technological marvel. Timing didn't work out this time, but we'll get there eventually, and then we'll look back on the 290/X and 780/Ti and joke about how inelegant they were.
There is one thing quite interesting about this product from a technical point of view. It shows just how little impact architectural changes really have on practical performance.
Absolutely none of those same people complain about the exhaust temps or power consumption of the r290x and r290.
I do. I will not put a card that requires more than one 6-pin connector in my systems. Sweating in an island of heat is not my idea of fun gaming.
I do. I will not put a card that requires more than one 6-pin connector in my systems. Sweating in an island of heat is not my idea of fun gaming.
I believe you are exaggerate.
I use a HD7950 OC to 1GHz at 35c ambient in summer and i dont feel the difference in temperature when i play and when not.
I do. I will not put a card that requires more than one 6-pin connector in my systems. Sweating in an island of heat is not my idea of fun gaming.
I do. I will not put a card that requires more than one 6-pin connector in my systems. Sweating in an island of heat is not my idea of fun gaming.
Absolutely none of those same people complain about the exhaust temps or power consumption of the r290x and r290. People will forever continue to spin and justify a particular brand or vendor no matter the situation.
I am hearing $699 CAN for 980. No idea about performance.
Extremely disappointing progress-wise. A 970 at almost 1400Mhz can't match a 1200Mhz 290. More interested in these chips making their way into laptops.
I am looking forward to seeing what the performance/watt is to try and extrapolate what a 3200 CUDA core GK110 could do
I think you dramatically misunderstand just how little 75 watts is.
Do you start sweating in an island of heat when you turn on a light bulb? Because one those puts out more heat than a second 6-pin would add.
There is one thing quite interesting about this product from a technical point of view. It shows just how little impact architectural changes really have on practical performance. We see it a lot with refresh cards but rather than tweaks this is a big change and yet the expected performance at the same die size is effectively the same. All the progress in the computing industry is based on the doubling of transistors based on density increases. Without that progressing we get basically nothing. This is the way of the industry, the cards worth buying are those based on new processes, those are the big upgrades, everything else is a tweak with minor improvements.
Gibbo over at OCUk already pretty much revealed that the 980 will be ~780ti, while the 970 will be ~780.
This is still a good result on the same node, with less power use, so they got both good perf/w as well as perf/mm2 gains. Definitely Maxwell is a GREAT architecture.
Because it's already hot as hell inside your house / room.
3x DP for Triple G-sync monitors (G-Sync Surround) and HDMI 2.0 and Titan-like reference cooler
I agree on the architecture part. $399 for 970 and $549 for 980 then?
Many people would consider a $400 NV card slightly slower than 290X but only uses 148W and has 20%+ overclocking headroom. If after-market 970s can provide 92-93% of the performance of 290X at such a dramatically lower power level, combined with NV's strong brand value and NV-specific features, it'll be enough to make 290Xs irrelevant for the majority of the market (1080p and below gamers) even if AMD were to drop 290X to $400. I think AMD will need to drop 290 to $319 and 290X to $359 if a 148W 970 is $399.
I's hypocritically funny that when Fermi 1.0 came out, it was blasted nonstop and continuously for it's inferior perf/w and temperatures. People lambasted how a gtx480 would heat an entire room after an hour or two of gaming. The complaints continued until gtx580 upped the performance, dropped the thermals, and slightly lowered power consumption.
Absolutely none of those same people complain about the exhaust temps or power consumption of the r290x and r290. People will forever continue to spin and justify a particular brand or vendor no matter the situation.
Why would AMD need to price the 290X under the 970 if the 970 is around 290/780 performance? If 970 comes in $399 at ~290/780 performance I'd expect the 290X to settle down to ~$449 with promotions/sales/rebates sporadically bringing it closer to $399. Also 290 would probably be MSRPed to $349.