Not one to leave out, NVIDIA is also using this week’s launches to deploy new graphics adapters for laptops, which partners will pair with these new Ryzen and Core processors. The company is also unveiling a fairly large set of additions to its laptop technology portfolio, introducing new features to better manage TDP allocations for laptops and, for the first time, the ability to have G-Sync in one Optimus compatible laptop. Overall, while this week is primarily focused on AMD and Intel, NVIDIA is focused on offering partners (and consumers) something new for this generation of laptops.
GeForce RTX 2080 Super and RTX 2070 Super
First, NVIDIA is launching two new mobile graphics adapters this morning. The GeForce RTX 2080 Super and RTX 2070 Super, both of which launched on the desktop last summer, are now arriving on laptops. Like their desktop counterparts, the new adapters are based on NVIDIA’s existing TU104 silicon, so there are no new GPUs per se today, but their launch offers OEMs additional options for dGPUs for their High-end gaming laptops.
As has been the case for NVIDIA throughout this generation, although the company does not have separate and labeled SKUs for mobiles, the new laptop parts have their own set of specifications. Specifically, although moving parts have the same number of CUDA cores and the same memory support as their desktop brothers, they have different clock and TDP profiles, due to the limitations of the form factor of the laptop. All in all, the new Super parts are designed for 80 W + laptops, with the flagship RTX 2080 Super model approved for 150 W (or more) designs, as suppliers have the ability to push the adapter roughly as strong as they think they can get away with desktop computers that we commonly see in the wider market for ultra-powerful laptops.
Otherwise, these are fairly typical GeForce RTX references. Boost clocks range from 1080 MHz to 1560 MHz, depending on what laptop manufacturers choose for power and performance. The RTX 2080 Super will have a TU104 GPU of 3072 CUDA core fully activated, while the RTX 2070 Super will have a 2560 core version of the same GPU.
Meanwhile, memory is the only other notable change here: while the two adapters come with 8 GB of GDDR6 memory, unlike the RTX 2080 Super desktop, the mobile version won’t come with GDDR6 15.5 Gbps. Instead, it comes with 14 Gbit / s memory like the rest of the RTX range. Overclocked VRAM is quite expensive in terms of power, so it’s not too surprising to see NVIDIA drop it here.
NVIDIA is also taking this opportunity to deploy small hardware updates to its line of laptops. In terms of memory, the company has confirmed for the first time that it is working with memory providers on low-voltage GDDR6 memory. Unfortunately, the details here are thin – it’s not clear if the low-voltage RAM used by NVIDIA is different from the GDDR6 1.25v already offered by memory providers – but even 1.25v would be a noticeable decrease from the normal 1.35v memory. NVIDIA sets VRAM memory consumption at around 20 to 25 watts for their laptop solutions, so being able to reduce even 10% of that is a couple of more watts that can be transferred to the GPU itself for more performance.
And according to the theme of energy efficiency, NVIDIA tells us that they also worked with partners to get better VRMs in laptops. This is another area where the details are pretty thin, but VRM is a priority area for the business. Voltage regulation is a game of efficiency – any power you lose is waste heat that consumes a laptop’s thermal budget – so the goal is always to maximize efficiency. Coupled with NVIDIA’s new Dynamic Boost technology (more on that in a moment), the need for more efficient VRMs (especially high power solutions) is at an all time high.
GeForce GTX 1650 Ti and GTX 1650 (GDDR6) also
In addition to their new high-end hardware, NVIDIA is also launching a pair of new low-end SKU references for mobile space. This is the GeForce GTX 1650 Ti and a GDDR6 version of the GTX 1650.
The GTX 1650 Ti is a particularly interesting question, as it does not have a desktop counterpart. So far, NVIDIA has launched office parts first, and then has laptop parts launched at the same time as the office parts, or later entirely. But for the GTX 1650 Ti, we have a purely mobile part, at least for the moment.
The material itself should not be too surprising. Here, NVIDIA is reusing its TU117 GPU, which is the same GPU that powered the original GTX 1650 mobile. The big change here is that the SKU Ti gets a much better definition: while the standard GTX 1650 has “up to” 1024 CUDA cores and comes with two different types of memory, the GTX 1650 Ti is guaranteed to have 1024 cores CUDA as well as GDDR6 memory. Coupled with a slightly higher maximum TDP of 55W, it should offer better performance. Although there is still a noticeable gap between this fully activated TU117 part and the next part of the battery, the mobile GTX 1660 Ti based on TU116.
Joining the GTX 1650 Ti will be another GTX 1650 reference, the GTX 1650 with GDDR6. As mentioned in the name, this is a mobile GTX 1650 with GDDR6 memory instead of GDDR5. NVIDIA does not describe any performance figures for the new part, so performance expectations should be left to the imagination of the reader, but to otherwise equivalent specifications, this would represent a 50% increase in memory bandwidth, from 8 Gbps GDDR5 at 12 Gbps GDD6.
However, it will be up to laptop vendors to decide which GTX 1650 configuration they use and how to disclose it. The GDDR6 version doesn’t get its own canonical reference name, so a laptop with it could have anything from an 896 model with GDDR5 to a 1024 model with GDDR6. In the end, the system requirements have not changed, but laptop manufacturers now have another option for a slightly more powerful configuration. Or we could go with the GTX 1650 Ti and ignore the uncertainty.
Rebalance the stack of GeForce Laptop products
With the addition of the new RTX 2080 Super, RTX 2070 Super, GTX 1650 Ti and GTX 1650 (GDDR6) adapters to its portfolio, NVIDIA is using this week’s launch to rebalance the entire stack of portable products. As a result, some products are discontinued, and others are lowered in prices to fill positions previously covered by other parts.
First, like the office domain, the normal RTX 2080 has now disappeared from laptops. With the RTX 2080 Super taking the place of flagship – and not being very different from the original RTX 2080 – NVIDIA has completely deleted the original. The RTX 2070 Super is instead the NVIDIA second-level laptop adapter.
The RTX 2070, meanwhile, still remains in place. Instead, it is pushed down the stack of products to the third level position. NVIDIA now expects the RTX 2070 to start appearing in laptops at a price as low as $ 1,199.
The RTX 2060 is also there. And this is a particularly notable change, as the RTX 2060 will now be NVIDIA’s anchor SKU for $ 999 notebooks. This location was previously owned by the GTX 1660 Ti, and although NVIDIA does not explicitly discuss the price of laptop parts, by reading between the lines, it is clear that the company has reduced the prices of laptop adapters for let this new stack of products happen. So, as NVIDIA likes to promote, RTX laptops now start at $ 999.
In fact, all new mobile SKUs are launched today, the RTX 2060, now cheaper, is certainly the most important of NVIDIA. The company’s OEM partners announce 5 new / updated laptops with the part and more promise to come. As in office space, NVIDIA is keen to dislodge its own legacy parts and entice gamers to switch to a laptop with a new GeForce reference, and although NVIDIA certainly delivers the goods there, their case n is not helped by the relative stagnation Intel. Fortunately, the new Zen 2-based APUs from AMD have just been launched, and although the market will not change overnight, this gives the Green Team new performance opportunities with the Black Team (or is this old green team?).
Finally, the new and updated GeForce GTX 1650 SKUs will flush out the low end of the NVIDIA stack of portable products. The Pascal-based GTX 1050, the last remaining GeForce GTX brand from the previous generation, is now on the verge of extinction. In its place, the GTX 1650 is demoted to take over. GTX 1650 laptops, meanwhile, will hit the market for as little as $ 699. Between that and the RTX 2060 will be the GTX 1660 Ti, as well as the new GTX 1650 Ti. And below $ 699 we will see the usual mashash of the latest generation laptops, as well as NVIDIA’s entry-level non-GTX laptop parts, the GeForce MX3xx series.
In conclusion, as with this week’s laptop CPU launches, laptops with the new updated GeForce references are expected to hit the market soon. While the ongoing coronavirus pandemic has thrown a key in exact release dates, AMD Ryzen Mobile 4000 laptops are already delivered. Meanwhile, Intel Comet Lake-S laptops are expected to be available soon. As a result, we are already seeing ASUS Ryzen laptops shipped with GeForce dGPUs, while Comet Lake-H laptops with the new parts are expected to hit the market in a few weeks.