Earlier quoted context omitted.
From the article: more CUDA cores at a lower clock. Since clock scaling isn't linear on power consumption, doubling the cores and halving the clock (as an example, not the actual ratio they used), leaves you with a net efficiency gain.
Tom's Hardware nicely demonstrated the non-linearity of power consumption in their desktop GTX1060 review: http://www.tomshardware.com/reviews/nvidia-geforce-gtx-1060-... At factory settings the card draws 120W and pushes ~110fps in their 1440p test, but throttling the power limit down to just 60W only reduced it to ~90fps. (As an aside, the AMD RX480 comparison shows why people are disappointed with Apple supposedly…
Nvidia stuffs desktop GTX 1080, 1070, 1060 into laptops, drops the “M”
51–60 of 83 posts
Re: Nvidia stuffs desktop GTX 1080, 1070, 1060 into laptops, drops the “M”
#52I think this is a sign they're worried about AMD Polaris. Most people don't realize just how much AMD has turned around the past year. I saw an article recently about people shorting Nvidia. Full disclosure: I'm an AMD stock holder.
My full disclosure: I am very long Nvidia (and it has been very kind to me so far)
Re: Nvidia stuffs desktop GTX 1080, 1070, 1060 into laptops, drops the “M”
#53Besides gaming, anyone has used this beefy laptops to run GPU intensive machine learning algorithms? I am curious to see if it's practical to use a gaming laptop vs. a desktop to run tensorflow calculations.
Re: Nvidia stuffs desktop GTX 1080, 1070, 1060 into laptops, drops the “M”
#54THIS. I'm not going to buy a laptop that looks like a prop from a Michael Bay movie. The best current option for a laptop with a GPU and a design that wouldn't be embarrassing to leave the house with is the Microsoft Surface Book, which is expensive, has a mediocre GPU and is actually still kind of embarrassing to own. I'm pretty excited about the day that gaming laptop manufacturers realize that their target audience isn't entirely composed of guys whose main fashion inspiration is Reaper from Overwatch.
Re: Nvidia stuffs desktop GTX 1080, 1070, 1060 into laptops, drops the “M”
#55Earlier quoted context omitted.
Tom's Hardware nicely demonstrated the non-linearity of power consumption in their desktop GTX1060 review: http://www.tomshardware.com/reviews/nvidia-geforce-gtx-1060-... At factory settings the card draws 120W and pushes ~110fps in their 1440p test, but throttling the power limit down to just 60W only reduced it to ~90fps. (As an aside, the AMD RX480 comparison shows why people are disappointed with Apple supposedly…
I just don't understand why Apple seems to prefer AMD. Bad experience with Nvidia's drivers in the old Core Two Duo MBPs? Does AMD have a better track record?
Nvidia cards are capable of OpenCL but they've never performed as well with it as they do with CUDA. AMD has always been the better option for that.
Of course Apple could implement CUDA support in their software, but they've never been big on running with vendor specific standards that they had no part in the development of.
Re: Nvidia stuffs desktop GTX 1080, 1070, 1060 into laptops, drops the “M”
#56Earlier quoted context omitted.
I just don't understand why Apple seems to prefer AMD. Bad experience with Nvidia's drivers in the old Core Two Duo MBPs? Does AMD have a better track record?
Apple is a backer of and is invested in OpenCL. OS X itself leverages OpenCL throughout the OS (Quicklook for example uses it to make previews faster) and of course FCP/Motion/etc make heavy use of OpenCL as well. Nvidia cards are capable of OpenCL but they've never performed as well with it as they do with CUDA. AMD has always been the better option for that. Of course Apple could implement CUDA support in their sof…
Although Apple created OpenCL and gave it to Khronos, they have the most outdated support for OpenCL.
The future on Apple platforms is called Metal compute.
There were around 6 Metal talks at WWDC 2016 and zero about Khronos technologies.
Re: Nvidia stuffs desktop GTX 1080, 1070, 1060 into laptops, drops the “M”
#57NVIDIA laptop GPUs were always the "same chip". Each "chip" in NVIDIA can be floorswept differently, with parts lasered off and its operating clock range adjusted. This is why the 1080 and the 1070 is the "same chip"--GP104.
Previous mobile chips were actually the "same chip" as the desktop ones, except they lasered more off and reduced the clocks even more, sometimes reduced the clocks a lot and lasered less to make the performance better by cramming more hardware.
They just dropped the M thing to show that "oh look, we've come this far!" but in reality, none of their policy actually changed--just floorsweep differently to have less TDP and hopefully it's close enough to desktop tier perf.
edit: what they are, are different SKUs of the "same chip".
edit again: I'm not saying this isn't any small achievement, Pascal has brought a ton of improvements to the design. I'm just saying it's a marketing move that I expect the HN crowd to look through.
Re: Nvidia stuffs desktop GTX 1080, 1070, 1060 into laptops, drops the “M”
#58$500 is pretty steep for what's essentially just a tiny case + power supply, but if it works as advertised with no serious pitfalls, I might be tempted to make a splurge for the extra flexibility.
Though I wish someone could make a smaller, cheaper graphics dock that's built specifically to house less power hungry, single-slotted cards like the RX 460. Something like that would be more than enough to handle my modest gaming needs for the foreseeable future.
Re: Nvidia stuffs desktop GTX 1080, 1070, 1060 into laptops, drops the “M”
#59Anyone here have any experience with the new generation of TB3 External GPU docks like the Razer Core? $500 is pretty steep for what's essentially just a tiny case + power supply, but if it works as advertised with no serious pitfalls, I might be tempted to make a splurge for the extra flexibility. Though I wish someone could make a smaller, cheaper graphics dock that's built specifically to house less power hungry,…
Re: Nvidia stuffs desktop GTX 1080, 1070, 1060 into laptops, drops the “M”
#60Meh, this is bullshit. NVIDIA laptop GPUs were always the "same chip". Each "chip" in NVIDIA can be floorswept differently, with parts lasered off and its operating clock range adjusted. This is why the 1080 and the 1070 is the "same chip"--GP104. Previous mobile chips were actually the "same chip" as the desktop ones, except they lasered more off and reduced the clocks even more, sometimes reduced the clocks a lot a…
The 980m was substantially cut down compared to the desktop 980 and only had about 55% of the performance.