Nvidia’s RTX 3080 will reportedly be 20% faster than an RTX 2080 Ti

Over the past few weeks, specifications for Nvidia’s upcoming RTX 30 series have leaked onto the web, revealing what could be Nvidia’s next-generation GPU lineup and a new memory type called GDDR6X. 

At this time, we cannot confirm the validity of these specifications. Details of the Ampere series remain unknown to most Nvidia employees, making the best response from practically all Nvidia representatives be the industry standard “we don’t comment on rumours”. Take these specifications with a grain of salt, as while they have been independently reported by two sources, @KkatCorgi and @kolite7kimi, it is possible that these specifications originated from a single, possibly false, source. 

RTX 3080 

It has now been reported by @KkatCorgi that Nvidia’s upcoming RTX 3080 will offer (approximately) a 20% performance boost over Nvidia’s RTX 2080 Ti. At this time it is unknown what workload was used to measure this change, or if this performance boost is an average that was taken across multiple workloads using an RTX 3080 test sample. 

If the already leaked specifications of Nvidia’s RTX 3080 are correct, Nvidia will be offering its users the same number of CUDA cores as their RTX 2080 Ti. With faster memory, architectural advancements and (potentially) higher clock speeds, a 20% performance gain should be more than possible for Nvidia’s next-generation architecture. 

At this time, no memory producer has revealed GDDR6X memory, which is something which casts a lot of doubt onto these rumoured specifications. That said, GDDR6X could be a brand name for faster than normal GDDR6 memory, similar to how HBM2E memory is just a faster version of normal HBM2 memory.  

With Nvidia’s RTX 2080 Ti being both bandwidth and power-constrained in many of today’s games, it is easy to see how Ampere has the potential to deliver significant performance improvements over Turing. Smaller process tech and architectural enhancements will increase Ampere’s efficiency, performance per clock cycle, and raw clock speeds over Nvidia’s Turing-based RTX 2080 Ti. These factors should make Ampere a lot more powerful than Turing, at least on the high-end.

Below are a set of leaked specifications for Nvidia’s RTX 30 series of high-end GPUs. 
 

Â	RTX Titan (Ampere)	RTX 3090 /3080 Ti	RTX 3080	Titan RTX (Turing)	RTX 2080 Ti	RTX 2080 Super	RTX 2080
GPU	GA102-400	GA102-300	GA102-200	TU102-400	TU102-300	TU104-450	TU104-400
CUDA Cores	5376	5248	4352	4652	4352	3072	2944
Memory	24GB GDDR6X	12GB GDDR6X	10GB GDDR6X	24GB GDDR6	11GB GDDR6	8GB GDDR6	8GB GDDR6
Memory Speed	17Gbps	21Gbps	19Gbps	14Gbps	14Gbps	15.5 Gbps	14 Gbps
Memory Bus	384-bit	384-bit	320-bit	384-bit	352-bit	256-bit	256-bit
Memory Bandwidth	816GB/s	1008GB/s	760 GB/s	672 GB/s	616 GB/s	496 GB/s	448GB/s