Main menu


NVIDIA GeForce RTX 4090 With Over 100 TFLOPS Of Power GPU Rumored

NVIDIA's next-gen flagship GPU is rumoured to deliver over 2.5 times more raw compute power over RTX 3090 Ti.

While the rumours about the AMD RDNA3 flagship processor indicate it will offer over 4 times more single-precision compute power over RDNA2, NVIDIA is supposedly doing a similar upgrade to its upcoming flagship. The AD102 GPU, based on Ada Lovelace architecture, is expected to deliver over 100 TFLOPS of power, which is 2.5 more than 40 TFLOPS offered by RTX 3090 Ti and 2.8 times more than RTX 3090. The FP32 (single-precision) power does not automatically guarantee better gaming performance, though.

Both Greymon55 and Kopite7kimi concur that the TFLOPS war maybe a piece of the fight for the quickest work area illustrations. There is more affecting everything, for example, raytracing speed increase, upheld super-goal tech and different elements that might steer the results for any design.

To accomplish 100 TFLOPS of force, the AD102 GPU with 18432 CUDA centres would need to be timed at 2.7 GHz, however, it's basically 100% sure that RTX 4090 will transport with a to some degree incapacitated GPU. In this manner, the clock speed will naturally be higher. As indicated by Greymon55, cutting edge lead cards could send with fundamentally the same clock speeds, which on account of AMD Navi 31 GPU implies 3.0 GHz and that is it is utilized to accept full GPU.

The facts really confirm that we know a ton about cutting edge GPUs as of now, a few bits of gossip have been around for quite a long time. However, this doesn't imply that we know it all yet. The FP32 CUDA/Stream Processor count can in any case change. What all leaders seem to concur with is that cutting edge GPUs will require a great deal of force.

Source: Videocardz@kopite7kimi@greymon55 via Wccftech