
A new rumor has surfaced about NVIDIA’s upcoming GeForce RTX 3080 Ti graphics card of reliable leakage, Kopite7kimi. According to the information, the GeForce RTX 3080 Ti will retain the same specifications as outlined last month, but will also receive the same GPU hash restriction treatment as the GeForce RTX 3060 to counter crypto-miners.
NVIDIA GeForce RTX 3080 Ti launches soon with 12GB of GDDR6X memory, 19Gbps kernel speed and hash restriction to counter Crypto miners
The NVIDIA GeForce RTX 3080 Ti has been circulating in the rumor mill for some time. It has disappeared several times and reappeared with different GPU configurations, but as we get closer to April, things become clear. The NVIDIA GeForce RTX 3080 Ti may well be launched and will retain the same core configuration as previously rumored, and will also come with a new feature first introduced on the GeForce RTX 3060.
NVIDIA has already said that the current GPUs will not be affected by the speed-limiting technology, but future SKUs will definitely receive amendments to counter miners against cryptocurrency. As such, the GeForce RTX 3080 Ti will also limit its hash rate in various cryptocurrency algorithms, making it quite useless and not a good investment for miners. For example, the GeForce RTX 3080 has a minehash rate of about 95-100 MH / s in Ethereum using the Daggerhashimoto algorithm.
If we use the same hash limit of 50% as the RTX 3060 and apply it to the RTX 3080 Ti, we get about 45-50 MH / s, which is the same mining as the RTX 3070, while paying much higher. sum for the Ti variant. This would mean that more cards could end up on gaming computers than mining platforms, but we can not say whether the availability of the card would be so great to begin with, as the RTX 3080 and RTX 3090 based on the GA102 GPU are still short . offer.
NVIDIA GeForce RTX 3080 Ti 12 GB ‘Rumored’ graphics card specifications
NVIDIA’s GeForce RTX 3080 Ti 12 GB FE (Founders Edition) graphics card is expected to feature the PG133-SKU15 PCB design and the GA102-250-KD-A1 graphics core. The GA102-250 GPU has also changed since we last saw it and will now contain 10240 CUDA cores within a total of 80 SM units. Since the main core configuration is brand new, the previously leaked watches and TMU / ROP scores must now be rejected.
NVIDIA_DEV.2208?
– 포시 포시 (@ harukaze5719) March 4, 2021
In terms of memory, the card contains 12 GB of GDDR6X memory. In contrast to the 19.5 Gbps speeds of the RTX 3090, the GeForce RTX 3080 Ti is said to maintain the same memory speeds as the RTX 3080 at 19 Gbps. Since we get 12 GB of memory, the NVIDIA GeForce RTX 3080 Ti will use a 384-bit bus interface equal to a total bandwidth of 912 GB / s. Although we see an 8 GB VRAM reduction over the previous specification, the larger bus interface should drive higher memory bandwidth.
The TGP for the card is the same as the RTX 3080 at 320 Watts. It is definitely necessary to feed the extra cores, so NVIDIA may need to optimize the clocks here.
NVIDIA GeForce RTX 30 Series ‘Ampere’ Graphics Card Specifications:
Graphic card name | NVIDIA GeForce RTX 3050 | NVIDIA GeForce RTX 3050 Ti | NVIDIA GeForce RTX 3060 | NVIDIA GeForce RTX 3060 Ti | NVIDIA GeForce RTX 3070 | NVIDIA GeForce RTX 3070 Ti? | NVIDIA GeForce RTX 3080 | NVIDIA GeForce RTX 3080 Ti? | NVIDIA GeForce RTX 3090 |
---|---|---|---|---|---|---|---|---|---|
GPU name | Ampere GA107 | Ampere GA106? | Ampere GA106-300 | Ampere GA104-200 | Ampere GA104-300 | Ampere GA102-150 | Ampere GA102-200 | Ampere GA102-250? | Ampere GA102-300 |
Process node | Samsung 8nm | Samsung 8nm | Samsung 8nm | Samsung 8nm | Samsung 8nm | Samsung 8nm | Samsung 8nm | Samsung 8nm | Samsung 8nm |
The Size | TBA | TBA | TBA | 395.2 mm2 | 395.2 mm2 | 628.4mm2 | 628.4mm2 | 628.4mm2 | 628.4mm2 |
Transistors | TBA | TBA | TBA | 17.4 Billion | 17.4 Billion | 28 Billion | 28 Billion | 28 Billion | 28 Billion |
CUDA core | 2304? | 3584? | 3584 | 4864 | 5888 | 7424? | 8704 | 10240? | 10496 |
TMUs / ROPs | TBA | TBA | 112/64 | 152/80 | 184/96 | 232/80 | 272/96 | 320/112? | 328/112 |
Tensor / RT core | TBA | TBA | 112/28 | 152/38 | 184/46 | 232/58 | 272/68 | 320/76? | 328/82 |
Base Clock | TBA | TBA | 1320 MHz | 1410 MHz | 1500 MHz | TBA | 1440 MHz | TBA | 1400 MHz |
Boost Clock | TBA | TBA | 1780 MHz | 1665 MHz | 1730 MHz | TBA | 1710 MHz | TBA | 1700 MHz |
FP32 Calculate | TBA | TBA | 12.7 TFLOPs | 16.2 TFLOPs | 20 TFLOP’s | TBA | 30 TFLOP’s | TBA | 36 TFLOP’s |
RT TFLOP’s | TBA | TBA | 25.4 TFLOPs | 32.4 TFLOPs | 40 TFLOP’s | TBA | 58 TFLOP’s | TBA | 69 TFLOP’s |
Tensor TOPs | TBA | TBA | 101 TOP’s | 129.6 TOP’s | 163 TOP’s | TBA | 238 TOP’s | TBA | 285 TOP’s |
Memory capacity | 4 GB GDDR6? | 6 GB GDDR6? | 12 GB GDDR6 | 8 GB GDDR6 | 8 GB GDDR6 | 10 GB GDDR6X? | 10 GB GDDR6X | 12 GB GDDR6X? | 24 GB GDDR6X |
Memory Bus | 128-bit | 192-bit? | 192-bis | 256-bis | 256-bis | 320-bit | 320-bit | 384-bis | 384-bis |
Memory speed | TBA | TBA | 15 Gbps | 14 Gbps | 14 Gbps | TBA | 19 Gbps | 19 Gbps | 19.5 Gbps |
Bandwidth | TBA | TBA | 360 Gbps | 448 Gbps | 448 Gbps | TBA | 760 Gbps | 912 Gbps | 936 Gbps |
TGP | 90W? | TBA | 170W | 200W | 220W | 320W? | 320W | 320W | 350W |
Price (MSRP / FE) | $ 149? | $ 199? | $ 329 | $ 399 US. | $ 499 US. | $ 599 US? | $ 699 US. | $ 999 US. | $ 1499 US. |
Start (availability) | 2021? | 2021? | February 2021 | December 2020 | October 29 | Q4 2020? | September 17 | April 2021? | September 24 |