Gadgetory

welcome back to hardware I'm boxed at this point we've all seen the announcement of a new videos new GeForce 20 series graphics cards from the desktop in the art x20 atti the ITX 2080 and our TX 2070 it won't be too long before we'll get performance numbers for these cards as well which is pretty exciting but before these cards hit the desktop I thought it would be an interesting thought experiment a prediction I don't know something along those lines to discuss what the mobile lineup of these GPUs might look like it's a certainty that in video we'll bring at least some of these GPUs to gaming laptops after the desktop launch and a few tidbits we've heard from industry sources suggest it'll be around November when we hear about geforce 20g ps4 laptop so that's about a month after the release of the RT X 2070 and that makes sense considering with the 10 series laptop parts were announced around 2 months after the launch of the 1070 anyway in this video I'll be breaking down the specs of the RT X cards that have been announced so far and giving my thoughts into how these GPUs might translate into laptop versions you know what sort of specs we can see and what features will be kept or omitted again we don't have any concrete information on these parts so this isn't a rumor or leaked video it's just a bit of fun speculation I guess and discussion into how invidious laptop GPUs typically differ from their desktop counterparts so let's start with the RT X xx atti at the top end because this one is pretty simple it's very unlikely we'll see the RT X xx attr in laptops simply because it's 250 watt TDP is too high for most laptop form factors when creating a laptop GPU the power draw and TDP is the most important aspects laptops have much more limited cooling systems compared to what is possible in desktops and this is especially true when you consider that most gaming laptops these days are either slim and portable systems or more mid tier devices rather than massively chunky beasts and the slimmer you go the less cooling power you have which restricts the sort of GPU TDP SiC and support with 10 series laptops even the most chunky beasts topped out at fully-fledged GT ten 80s as that was the highest-end laptop GPU Nvidia provided the GTX 1080 on the desktop had a TDP of a hundred and eighty watts and that pushed down to around 150 watts for laptops whereas the GTX 10 ATT I had a 250 watt TDP and there was no laptop equivalent so with the RT X 20 ATT I also packing a 250 watt TDP we're almost certainly not going to see it in laptops as the TPP is simply too high the ITX 2080 is an interesting one like with the GTX 1080 in previous generations I expect the RT X 2080 to be the top end GPU available in a mobile form factor and aside from max-q versions which I'll talk a little bit about later the fully fledged RT X 20 80 will be restricted to a larger laptop designs due to its higher TDP the ITX 2080s TDP is a bit of an unusual case NVIDIA has listed it as 215 watts for the desktop so that's up from 180 watts to the GTX 1080 but there has been some talk that part of this TDP is allocated for virtual link the new USBC connector spec designed for VR headsets supporting this connector adds around 30 watts to the graphics cards TDP requirement at least allegedly as virtual link provides power directly to the VR headset I'm not sure where the Nvidia will leave virtual link enabled for laptop GPUs but I'd imagine using a VR headset with the laptop is a bit more of a niche use case than VR with a desktop in any case I'd assume laptop vendors could choose not to support virtual link and therefore not have to worry about the added TDP cost of the connector so in that case laptops with that virtual link could integrate an RT X 28 e and theoretically I only have to design a cooler for a TDP of 185 watts or so that's pretty similar to the GTX 1080s TDP of 180 watts and then with further laptop optimizations we'll likely see that drop back down to around the 150 watt mark of the 10 eighties laptop bearing so even though the RT X 20 80 does pack a higher TDP than its predecessor I fully expected to make its way to laptops at around 150 watt TDP in the end now the question becomes what sort of specs and performance can we expect of the RT X 2080 and laptops well with the GT X 1080 the laptop and desktop variants were identical so the same core configuration same clock speeds same memory and provided the cooling performance was adequate the laptop 1080 performed on par with the desktop 1080 in the video it does seem very keen on offering laptop versions of their GPS that are equivalent to the desktop version so I expect that to continue with the RT X 2080 in other words I fully expect the laptop ITX 2080 to have 2944 CUDA cores with boost clocks in the 1710 megahertz range and it will still use 8gig of GDD are 6 memory as for real-world performance we're still not sure how the cars will perform in the desktop so it's hard to say for certain but we expect the Arctic's 2080 to perform around the level of the GT X 1080 Ti and NVIDIA x' own charts show a 30 to 40 percent performance improvement over the GTX 1080 in best-case scenarios so for top-end laptops getting a 35 percent performance bump also in the same form factor is certainly quite a tasty proposition how would Nvidia manage to get this performance boost from roughly the same TDP well chewing is built using TSM CS 12 nanometer process compared to 16 nanometers for Pascal that's not a huge change in Nvidia has chosen not to shrink the die on twelve nanometer but instead use I guess the wider pathways that 12 nanometers provides however the slight process improvement should bring a more favorable voltage to frequency curve so running cheering at the same frequencies as Pascal should consume less power at least in theory and we saw something like this in practice with second gen rise and moving from 40 nanometers to 12 nanometers it could run at lower voltages for the same frequencies so when you look at the r-tx 2080 compared to the GTX 1080 boost clocks are pretty similar 1710 megahertz for the 2080 and 17 33 megahertz for the 1080 with cheering on 12 nanometer it should require less voltage to run at that frequency compared to Pascal but then the r-tx 2080 bumps up the CUDA coil count from 2560 to 2944 so it's a wider GPU at the same clocks so it looks like nvidia has gained some power Headroom by not increasing the clock speed of the artex 2080 and put that towards making the GP whiner with the end result being similar power consumption for the 2080 and 1080 and that is good news for laptops where TDP is much more important than with desktops it's a pretty similar story with the RT X 2070 in video lists a desktop TV P of 175 watts factor in virtual link possibly increasing the TDP and the 2070 should pull back to around 150 watts the same TDP as the desktop 1070 and again the laptop version of the 1070 set around 115 Watts so I expect the laptop RT x 2070 to be rated for something similar the laptop version of the 1070 was a bit of an enigma in that it was different to the desktop 1070 in terms of specifications but performed around the same the laptop variant had 2048 CUDA cores and a boost clock of 1640 5 megahertz compared to 1920 CUDA cores in the desktop rate with a boost clock of 1683 megahertz Nvidia could do something similar with the laptop 2070 but I think the case of the 1070 was fairly unique and I don't really expect them to follow that exact path again at the same TDP the RT X 2070 should be able to provide more performance than the gtx 1070 so again whatever laptops that could support the 1070 TDP they'll be able to bump that up to an RT X 2070 and get more performance in the same form factor and that would be great news for more of our game users a lot of fairly compelling laptops were able to handle the 10 70s TDP and I think again this will be the sweet spot for high performance gaming laptops how they get this extra performance is basically the same as the RT X 2080 the 27 T is clocked around the same level as the GTX 1070 but it includes 2304 cuda cores compared to 2048 all thanks to the small chip from 16 nanometers to 12 nanometers on paper that's a 12 percent performance jump not sure what we'll be getting in practice just yet but it's looking unlikely the 27 t will reach the level of the GTX 1080 that said any performance increase in the same form factor is very welcome in constrained laptops it's trickier to predict what will happen to the tensor cause an RT course in laptop versions of the RT X 28 e and 27 t considering ray tracing is the flagship feature of these GPUs I fully expect the laptop various to support ray tracing bomb so that will mean these cause will need to be on the die and active weather in video will disable some tents or RT cause to save power I'm not sure though it would be the most obvious candidate for power savings at the end of the day though ray tracing is extremely computationally intensive so if your video really wants to promote this features being supported by their laptop GPUs they'll probably have to keep the RT cause fully enabled it will certainly be interesting to see how that pans out and what power implications it has I also expect Nvidia to continue the trend of offering max-q variants of the RT X 2070 and RT X 2080 I know there are plenty of people out there that dislike max-q is they think it's some form of artificially restricting their GPU from reaching its full potential blue reality it's actually quite a good idea for laptops and other cooling restricted systems the key thing max-q does is provide a wider range of GPUs that sit at different EVPs this allows a manufacturer to choose a GPU that's better suited to their cooling solution for example a laptop might have more than enough thermal Headroom for an RC X 2070 but not enough for an RT X 2080 instead of capping that system to RTX 2070 performance that system could integrate an RT X 2080 max-q at a TDP between the 27 and 28 offering better performance in the 2070 but not quite the same level as the 2080 but still being within the cooling solution that they have designed with the GeForce 10 serious max cube variants of the 1080 and 1071 clocked around 250 to 300 megahertz are lower than their fully fledged counterparts while using the exact same GPU with the same core configuration and memory the clock speeds were chosen such that the GPU is operating an optimal frequency on Pascal's voltage frequency curve giving the best efficiency I expect something very similar with the GeForce 20 series we'll get an art X 2070 max Q and that'll be clocked around 250 megahertz lower that will sit between the 20 70 and an as yet announced 2060 and then the art X 2018 max Q also be clocked around 250 megahertz lower to sit between the 2070 and 28 again just speculation but that's what I expect will happen usually the max cube variants are 10% faster than the GPU below them and 10 slower than the non max-q model but we'll wait to see how that one plays out as for pricing we know if the desktop cards that the GeForce 20 series is pretty expensive with prices above their 10 series counterparts and it's unlikely they will offer as good value considering what we know about their performance so far with the laptop versions it will probably be a very similar story better performance in the same form factor but also considerably higher prices an RT X 2070 laptop will likely cost at least $100 more than gtx 1070 laptops and that margin will be higher for RT x 2080 laptops compared to JT x 1080 laptops we are expecting better performance in the same sort of designs but for some buyers that may not justify the price increase that said laptops are sold as entire systems rather than a standalone GPUs so the value proposition when you compare entire system prices might end up being a bit more favorable than on the desktop side comparing standalone cards I'm definitely excited to see what Nvidia does with the GeForce 20 series and laptops and how much more performance we can get in the same form factors I think these GPUs could offer a bit more a laptop buys than desktop system builders considering laptops are constrained in way as desktops are not on any performance games without making laptops chunkier and less portable is always welcome that's it for this discussion though I'll be interested to see how the mobile versions of the ITX 2070 and 2080 actually end up but it sounds like left to wait until later in the year to find out for sure stay tuned for our coverage of the desktop card that's coming up in the next few weeks as we get closer to the launch subscribe to ensure you don't miss it and consider supporting us on patreon you can get access to our exclusive discord chat there and I guess I'll catch you in the next one