Tuesday, July 16th 2019
NVIDIA GeForce RTX 2080 Super Features 10 Percent Faster Memory
NVIDIA's upcoming GeForce RTX 2080 Super graphics card doesn't just max out the 12 nm "TU104" silicon and add higher GPU clock-speeds, but also features the highest-clocked GDDR6 memory solution on the market, to make the most of the 256-bit wide memory bus of the silicon. NVIDIA deployed 15.5 Gbps GDDR6 memory, which is 10.7 percent faster than the 14 Gbps memory used on the original RTX 2080 and other RTX 20-series graphics cards. The memory real-clock is set at 1937 MHz compared to 1750 MHz on the original RTX 2080. At this memory frequency, the RTX 2080 Super enjoys a memory bandwidth just a touch short of 500 GB/s, at 496 GB/s.
Besides memory, the RTX 2080 Super maxes out the "TU104" silicon by enabling all 3,072 CUDA cores physically present, as opposed to just 2,944 of them being enabled on the original RTX 2080. The card is also endowed with 192 TMUs, 64 ROPs, 384 Tensor cores, and 48 RT cores. The GPU frequencies are set at 1650 MHz with 1815 MHz GPU Boost, compared to 1515/1710 MHz of the original RTX 2080. NVIDIA is launching the RTX 2080 Super at an MSRP of USD $699, with availability slated for July 23. The company's add-in card (AIC) partners are allowed to design custom-design cards that come with improved cooling solutions and higher clocks.
Besides memory, the RTX 2080 Super maxes out the "TU104" silicon by enabling all 3,072 CUDA cores physically present, as opposed to just 2,944 of them being enabled on the original RTX 2080. The card is also endowed with 192 TMUs, 64 ROPs, 384 Tensor cores, and 48 RT cores. The GPU frequencies are set at 1650 MHz with 1815 MHz GPU Boost, compared to 1515/1710 MHz of the original RTX 2080. NVIDIA is launching the RTX 2080 Super at an MSRP of USD $699, with availability slated for July 23. The company's add-in card (AIC) partners are allowed to design custom-design cards that come with improved cooling solutions and higher clocks.
63 Comments on NVIDIA GeForce RTX 2080 Super Features 10 Percent Faster Memory
You have RTX2080's out there, those wont sell now really, unless you drop the price decently enough.
And you fill up the shelves with new cards with only a 4% increase that you suddenly hope people will buy?
What person would not have bought an RTX2080 up untill now but will buy one that is 4% faster?
Not to mention relatively soon enough we will have all new cards which probably have some good improvements on the main selling points of these cards, the ray tracing capability.
Well sure it looses some value, but it still does not make it worthless. One thing is for sure though, there's no much point of upgrading from rtx 2080 to rtx 2080S. Unless you can do it by some kind of step up program like EVGAs.15.5 Gbps actually concerns me a bit: If it is OC 14Gbps memory that would be awful. But if it is underclocked 16Gbps memory that would be awesome, that OC headroom...
And then replace those, not sold till this day cards, with the same card that is 4% faster and expect people to suddenly now buy them.
I would find that very odd.
3,072 core count
500 GB/s memory bandwidth
RTX 2080 Ti
4,352 core count
616 GB/s memory bandwidth
The 2080 Super is in no way going to be as powerful as the 2080 Ti. There is a 1,280 core difference between them.
If you are a smart consumer, you know that one-generation-old doesn't mean useless, so you turn this to your advantage and get that tech at massive discounts.
This 4% minor progress. I know what you mean and it is still than nothing but the question is what triggered the progress? And of course if the progress you mentioned is everything you could achieve or is it so low on purpose? I bet it's the second one.
The progress is "triggered" by improved yields.
I do want developers to use Vulkan, but the games we have so far is using an abstraction layer to simulate Direct3D 11, which defeats the purpose of the new API, and we have no statistical basis to claim that AMD is inherently better in Vulkan, yet all over the forums people claim AMD do, and even a couple of reviewers.