Well, the wait is almost over. Nvidia’s Ampere keynote presentation released official specifications of the RTX 3080 and the buzz around it is unreal. The release date has been set for 17th September. The RTX 3080 looks like it will define a new level for gaming GPU performance and by a significant margin. Let’s look at those specifications and compare them to the previous high end option, the RTX 2080 Super.
- Related: RTX 3090 vs 3080: What are the key differences?
- Related: RTX 3070 vs 2070 Super: What are the key differences?
- Related: RTX 3080 Aftermarket Card Comparison List: 20+ Models Compared
RTX 3080 vs RTX 2080 Super: Specification Comparison
|RTX 3080||RTX 2080 Super|
|GPU Technology||Samsung 8N GA102-200||TSMC 12nm TU104-450|
|Boost Clock||1.71 GHz||1.815GHz|
|VRAM||10GB GDDR6X||8GB GDDR6|
|Memory Bandwidth||320Bit / 760 GB/s||256bit / 496 GB/s|
|PCIe Technology||PCIe 4.0||PCIe 3.0|
RTX 3080 vs RTX 2080 Super: Fabrication and architecture
The manufacturing process is Samsung’s ‘8N’ process, moving on from the 12nm GPU process at TSMC foundries used in the Turing GPUs. This allows Nvidia to claim over double the performance per watt showing that this is a significant advance. More efficiency means the chip stays cooler and be run at higher speeds. The TDP of the 3080 is 320W, matching that of the RTX 2080 Ti and substantially higher than then RTX 2080 Super. Nvidia recommend a 750W Power supply for this GPU. The quoted boost clock provides very little information as it can’t be compared between different architectures, so disregard that metric.
RTX 3080 vs RTX 2080 Super: Shader cores and rasterization performance
One of the most interesting features is that Nvidia quote 8704 shader cores for the RTX 3080 up from 3072 in the RTX 2080 Super: these individual cores parallelise the rendering of graphics and more is better. But the huge leap here isn’t all it seems. Traditionally one clock cycle allowed one compute operation but much like the ‘Double Data Rate’ access in RAM Ampere’s shaders complete two calculations in a single tick. This is due to the difference in the way Floating point 32 vs Floating point 16 calculations are processed and represents an ‘undoing’ of an earlier decision to halve FP16 calculation rates. It appears that Nvidia have doubled the shader units quoted to make this simple to understand, a quirk of terminology rather than a like for like comparison of the architecture. The Nvidia Keynote was a little guarded around actual specifications and focussed on compute performance metrics: these can be misleading when translated into actual gaming performance so we will have to wait to get our hands on these cards before we can talk about their actual performance with certainty. The simple statistics do significantly outpace the RTX 2080 Super so this GPU should be a fantastic performer. Quoted and tested performance in titles that can use the Ray Tracing and Tensor Cores with DLSS2.0 are certainly impressive so we’ll discuss that technology a little more later.
RTX 3080 vs RTX 2080 Super: Memory
The RTX 3080 has 10Gb of GDDR6X memory and much was made of their partnership with Micron to allow double the access rates. The RTX 3080 has a very high memory specification across the board and since memory access can be a limitation to GPU performance this will undoubtedly account for some ot the improvement. With a wider 320bit bus and 760GB/s bandwidth it’s clear Nvidia have made a big stride forwards in Memory performance for the RTX 3080. 10GB is ample VRAM for the most demanding games at the highest settings in 4K and the memory specification is worthy of a flagship GPU.
RTX 3080 vs RTX 2080 Super: AI Technologies
Nvidia’s Keynote heavily focussed on their AI implementations in relation to gaming. Turing brought hardware ray tracing into the mainstream but the performance impact made it a novelty in the few games that used it. For Ampere Nvidia have focussed their energies on using AI to combine the Ray Tracing and Machine learning cores of their GPU’s to give a huge performance uplift In games. The key technology is DLSS 2.0. This means ‘Deep Learning Super Sampling’. This Technology uses a supercomputer to train a neural network from incredibly high resolution 16K images. The neural network is game specific and included in Nvidia’s graphics drivers. When a game is running the GPU is able to generate a lower resolution frame and then use the GPUs Tensor cores and the neural network to upscale this to the native resolution. The effects are incredibly impressive, and the lowered computational load on the GPUs shader cores means frame rates can stay high. Importantly this technology overcomes the computational load of real time hardware Ray tracing the technology that hit frame rates on Turing GPU’s so hard. In flagship DLSS 2.0 titles such as ‘Control’ and ‘Death Stranding’ this technology appears to be a true next-gen leap in both visual fidelity and performance. A DLSS 2.0 up-scaled game looks better than native 4k, and runs 60-80% faster than 1440p native resolution. That’s a truly impressive feat. 4K AAA gaming has been the preserve of only the highest end GPU’s up until now and required advanced technologies like Ray Tracing to be disabled for acceptable performance. The RTX 3080 should be wholly capable of AAA gaming at 4K with hardware ray tracing enabled and effects cranked to Ultra: a truly remarkable feat.
RTX 3080 vs RTX 2080 Super: PCIe 4.0 and NVidia RTX I/O.
The RTX 3080 can utilise a PCIe 4.0 Bus – but let me put your mind at ease – you will NOT require a new motherboard to use this card! PCIe is both forwards and backwards compatible so this PCIe 4.0 card will fit and work well in an existing PCIe 3.0 Motherboard slot. In fact, not even the prodigious power of the Ampere GPU’s can saturate the PCIe 3.0 available bandwidth so there will be no negative impact of running this GPU in a system without PCIe 4.0. Indeed Nvidia’s own tech demos used an Intel i9-10900K CPU which is not PCIe 4.0 capable.
One of the interesting features highlighted during the keynote was Nvida’s RTX I/O. This PCIe Gen 4.0 technology addresses the storage access bottleneck that can hamper gaming performance. Because of storage limitations images and data are stored in a compressed format on a storage drive. Before use they need to be read, decompressed by the CPU then passed over the PCIe link to the GPU. When hard drives were slow this wasn’t an issue and CPUs could keep up without a problem. Now that PCIe 4.0 drives allow transfers of up to 7Gb/second the task of decompressing the data can actually overwhelm the CPU causing performance issues in-game. Nvidia has used the enhanced flexibility of PCIe 4.0 to cut out the middle man: The GPU will be allowed direct access to the data on the drive, freeing the CPU of that burden and lowering the overhead for data transfer. Whilst this is impressive technology, it’s not something that will be implemented right away. AMD X570 and B550 chipsets have PCIe 4.0 now, however Intel’s recent Comet Lake CPU’s are still not PCIe 4.0 equipped. Z490 series motherboards are capable of implementing it but this won’t become live without Intel’s next-generation CPU. Overall this technology looks like one that will mature over time as developers and systems adopt it rather than a killer feature on release day.
Conclusion: Price and Value
The RTX 3080 has a launch price of $699 and is released on 17th September 2020. If the performance promises made and demonstrated in the Nvidia Keynote are close to accurate this will represent a huge generational leap in Graphics card performance. This GPU’s little brother, the RTX 3070 is touted as out-performing the RTX 2080 Ti, a $1200 card. This makes the RTX 3080 a must-have product for 4K gamers, VR fanatics and anyone interested in experiencing the current cutting edge in PC graphics.
As news develops we’ll have more in-depth reviews of the RTX 3080’s performance, which models to buy, and full PC build recommendations that will support this GPU and allow it to perform to its full potential.
If you are looking to do a PC build now, and can’t wait for the RTX 3080 to be released, here are some of our graphics card guides you might find useful in narrowing your search.
- Best RTX 2080 Ti Aftermarket Cards
- Best RTX 2080 Super Aftermarket Cards
- Best RTX 2070 Super Aftermarket Cards
- Best RTX 2060 Super Aftermarket Cards
- Best Graphics Cards for Ryzen 9 3900X Builds
- Best Graphics Cards for Intel Core i9-9900K Builds
- Best Graphics Cards for Ryzen 5 3600