Tag: rtx4070
AORUS GeForce RTX® 40 Series Apex of Cooling Official Trailer
NVIDIA introduces GeForce RTX 4090/4080 series, RTX 4090 launches October 12th for 1599 USD
NVIDIA debuts “Ada” GeForce RTX 40 series
NVIDIA formally introduces three new graphics cards.
The new RTX 40 series are here. NVIDIA CEO Jensen Huang has now officially introduced RTX 4090, RTX 4080 16GB and RTX 4080 12GB models, the first SKUs from the next-generation of graphics series codenamed “Ada”.
The flagship NVIDIA RTX 40 GPU features 76 billion transistors and TSMC 4N process technology. New architecture introduces 3rd Gen RT core and 4th Gen Tensor Core. NVIDIA confirms Ada Lovelace supports DLSS 3 upscaling technology. For game streaming, NVIDIA RTX 40 GPUs have dual AV1 encoders supporting up to 8K 60 FPS recordings.
NVIDIA RTX 4090
The new flagship features AD102-300 GPU with 16384 CUDA cores and boost clock up to 2520 MHz. This means a single-precision performance of 82.6 TFLOPS, 2.3x more than its predecessor RTX 3090. The flagship SKU based on Ada architecture will be equipped with 24GB of GDDR6X memory, with peak bandwidth at 1 TB/s. This new card will require even more power than 3090 Ti, by at least 100W, with default TDP of 450W.
NVIDIA confirms this model will launch on October 12 at 1599 USD. The Founders Edition pictured below is a triple-slot design powered by one 16-pin power connector.
The company announced multiple designs from its board partners, including ZOTAC, Inno3D, Colorful, Palit, Gainward, Gigabyte, MSI and ASUS. Unsurprisingly, there is no EVGA card.
NVIDIA RTX 4080 series
Jensen Huang also announced two graphics cards sharing the same model number but different memory and GPU specs. The RTX 4080 16GB is to feature an AD103 GPU with 9728 CUDA cores, a total of 16GB of GDDR6X memory clocked at 22.5 Gbps and TDP of 320W. This model is set to launch in November for at least 1199 USD.
What was supposed to be RTX 4070 is being introduced as RTX 4080 12GB. This SKU has AD104 GPU and 7680 CUDA cores. As the name suggests, there is 12GB GDDR6X memory on this model and TDP at 285W. NVIDIA has put a 899 USD price on this SKU.
None of the RTX 40 GPUs has NVLink and they are using PCIe Gen4 x16 interface.
| RUMORED NVIDIA GeForce RTX 40 Series Specs | |||
|---|---|---|---|
| VideoCardz.com | GeForce RTX 4090 24GB | GeForce RTX 4080 16GB | GeForce RTX 4080 12GB |
| Board-SKU | PG139-SKU330 | PG139-SKU360 | PG141-SKU331 |
| Architecture | Ada (TSMC 4N) | Ada (TSMC 4N) | Ada (TSMC 4N) |
| GPU | AD102-300 | AD103-300 | AD104-400 |
| SMs | 128 | 76 | 60 |
| CUDA Cores | 16384 | 9728 | 7680 |
| Boost Clock | 2520 MHz | 2505 MHz | 2610 MHz |
| Memory | 24 GB G6X | 16 GB G6X | 12 GB G6X |
| Memory Bus | 384-bit | 256-bit | 192-bit |
| Memory Speed | 21 Gbps | 23 Gbps | 21 Gbps |
| Bandwidth | 1008 GB/s | 736 GB/s | 504 GB/s |
| Default TGP | 450W | 320W | 285W |
| Max TGP | 660W | 516W | 366W |
| MSRP | 1599 USD | 1199 USD | 899 USD |
NVIDIA details AD102 GPU, up to 18432 CUDA cores, 76.3B transistors and 608 mm²
NVIDIA AD102 GPU has 76.3B transistors
The most transistor-packed consumer GPU yet.
Not everything was revealed by NVIDIA today, but luckily for us, some board partners were quick to share the missing details.
Today, NVIDIA introduced its Ada Lovelace architecture for next-gen gaming, workstation and server GPUs. This architecture is based on custom TSMC 4N process and brings higher raster, raytracing and AI-accelerated computing over Ampere.
The AD102 GPU has 76.3 billion transistors and 608.4 mm². This means that the transistor density of 125.5 million per mm² is 2.78x higher than GA102 “Ampere” GPU manufactured by Samsung using 8N node. Those details were confirmed by PNY for RTX 6000 Ada workstation graphics card.
NVIDIA RTX 6000 ADA Specs, Source: PNY
NVIDIA Ada features Shader Execution Reordering (SER) which supposedly makes raster operations faster, providing up to 25% better gaming performance. Furthermore, Ada features next-generation RT Core (Gen3) and Tensor cores (Gen4). The latter delivers up to 1400 TFLOPS, 4,375 times more than Ampere’s 3rd generation cores.
The AD102 GPU will not be used by RTX 4090 gaming card, RTX 6000 ADA workstation and L40 Server GPU. With 2048 CUDA core remaining budget, it is very likely that NVIDIA will introduce an even faster gaming card later.
| NVIDIA Flagship Gaming GPUs | |||||
|---|---|---|---|---|---|
| VideoCardz.com | AD102 | GA102 | TU102 | GV100 | GP102 |
| Launch Year | 2022 | 2020 | 2018 | 2017 | 2017 |
| Architecture | Ada Lovelace | Ampere | Turing | Volta | Pascal |
| Node | TSMC 4N | SAMSUNG 8N | TSMC 12nm | TSMC 12nm | TSMC 16nm |
| Die Size | 608 mm² | 628 mm² | 754 mm² | 815 mm² | 471 mm² |
| Transistors | 76.3B | 28.3B | 18.6B | 21.1B | 12.0B |
| Trans. Density | 125.5M TRAN/mm2 | 45.1M TRAN/mm2 | 24.7M TRAN/mm2 | 25.9M TRAN/mm2 | 25.5M TRAN/mm2 |
| CUDA Cores | 18432 | 10752 | 4608 | 5120 | 3840 |
| Tensor Cores | 576 Gen4 | 336 Gen3 | 576 Gen2 | 640 | – |
| RT Cores | 144 Gen3 | 84 Gen2 | 72 Gen1 | – | – |
| Memory Bus | GDDR6X 384-bit | GDDR6X 384-bit | GDDR6 384-bit | HBM2 3072-bit | GDDR6X 384-bit |
Source: PNY
Tech 365 