ADVERTISEMENT

ADVERTISEMENT

Technology

NVIDIA GeForce RTX 4090 Graphics Card Nearly Twice as Fast as RTX 3090 in 3DMark Time Spy Extreme Test, Rumors Claim

ADVERTISEMENT

NVIDIA's GeForce RTX 4090 Graphics Card With Flagship AD102 GPU Headed For An October Launch, 24 GB GDDR6X Memory Onboard
Written by admin

ADVERTISEMENT

ADVERTISEMENT

The NVIDIA GeForce RTX 4090 graphics card is reported to be almost twice the performance of the RTX 3090 in the 3DMark Time Spy Extreme test.

NVIDIA GeForce RTX 4090 Almost Twice as Fast as RTX 3090 in 3DMark Time Spy Extreme Test Reportedly Hits 3GHz with Ease

The NVIDIA GeForce RTX 4090 graphics card will be the green team’s flagship offering in 2022. Various leaks and rumors have swirled around the map throughout the year, but as far as we can tell, the launch is more or less expected around the fourth quarter of 2022. With 3-4 months left before its launch, the rumors are now shifting the focus from specs to performance numbers.

Save7kimi was the first to announce that NVIDIA’s AD102 GPUs would be the first graphics chips to reach 100 teraflops of processing power. Now the same insider has shared performance data on 3DMark Time Spy Extreme. According to the source, the NVIDIA GeForce RTX 4090 will score over 19,000 points for graphics in the Time Spy Extreme test.

0

4000

8000

12000

16000

20000

24000

If we compare it to existing cards, this result would make the NVIDIA GeForce RTX 4090 at least 90% faster than the RTX 3090 and 70% faster than the RTX 3090 Ti. This is indeed a huge leap, but we must remember that we are talking about a purely synthetic workload here. GPU gaming might be a completely different story, and we don’t know if this score is based on final clocks/optimizations or not. The leader also states that it will be very easy for NVIDIA to achieve over 3 GHz clock speeds, which is in line with previous reports of TSMC 4N process node giving a huge boost in clock speed on Ada Lovelace’s GPUs.

NVIDIA GeForce RTX 4090 Specs Rumored

The NVIDIA GeForce RTX RTX 4090 graphics card is expected to feature the top-end AD102-300 GPU, but only the “Ti” variant will feature the full chip. The GeForce RTX 4090 will use a slightly stripped-down configuration.

The NVIDIA GeForce RTX 4090 will use 128 SMs out of 144 SMs for a total of 16,384 CUDA cores. The GPU will ship with 96MB of L2 cache and a total of 384 ROPs, which is just insane. Clock speeds are yet to be confirmed, but given that the TSMC 4N process is used, we expect clock speeds to reach or even exceed the 3.0 GHz range. The number of cores is 56% more than the RTX 3090, so many things like the clock, cache, architecture, and various other technologies greatly improve performance.

In terms of memory specs, the GeForce RTX 4090 is expected to come with a 24GB GDDR6X capacity that will run at 21Gb/s over a 384-bit bus interface. This will provide throughput up to 1 TB / s. This is the same bandwidth as the existing RTX 3090 Ti graphics card, and in terms of power consumption, TBP is said to be rated at 450W, which means TGP could be lower than that. The card will be powered by a single 16-pin connector providing up to 600W of power. It’s likely that we could get 500W+ custom designs, as we saw with the RTX 3090 Ti.

The graphics card is expected to be released in October 2022, followed by the rest of the Ada Lovelace line of graphics cards with GPU.

NVIDIA GeForce RTX 4090 Ti and RTX 4090 preliminary specs:

Video card name NVIDIA GeForce RTX 4090 Ti NVIDIA GeForce RTX 4090 NVIDIA GeForce RTX 3090 Ti NVIDIA GeForce RTX 3090
GPU name Ada Lovelace AD102-350? Ada Lovelace AD102-300? Amp GA102-350 Amp GA102-300
Process node TSMS 4N TSMS 4N Samsung 8nm Samsung 8nm
Die size ~600mm2 ~600mm2 628.4 mm2 628.4 mm2
transistors TBD TBD 28 billion 28 billion
CUDA cores 18432 16128 10752 10496
TMU/ROP To be confirmed / 384 To be confirmed / 384 336/112 328/112
Tensor / RT cores to be specified / to be specified to be specified / to be specified 336/84 328/82
Base clock TBD TBD 1560 MHz 1400 MHz
Clock boost ~ 2800 MHz ~2600 MHz 1860 MHz 1700 MHz
FP32 calculation ~103 teraflops ~90 teraflops 40 teraflops 36 teraflops
RT TFLOP TBD TBD 74 teraflops 69 teraflops
Tensor-TOPS TBD TBD 320 TOPs 285 TOPs
Memory size 24GB GDDR6X 24GB GDDR6X 24GB GDDR6X 24GB GDDR6X
Memory bus 384-bit 384-bit 384-bit 384-bit
Memory speed 24.0 Gbps 21.0 Gbps 21.0 Gbps 19.5 Gbps
Bandwidth 1152 GB/s 1008 GB/s 1008 GB/s 936 Gbps
THP 600 W 450 W 450 W 350 W
Price (MSRP / FE) 1999 USD? $1499? 1999 USD $1499
Launch (availability) 2023? October 2022? March 29, 2022 September 24, 2020

Products mentioned in this post


#NVIDIA #GeForce #RTX #Graphics #Card #Fast #RTX #3DMark #Time #Spy #Extreme #Test #Rumors #Claim

ADVERTISEMENT

ADVERTISEMENT

About the author

admin

Leave a Comment