AMD's upcoming Radeon Pro W7900 graphics card which will be powered by the RDNA 3 GPU architecture has been spotted in Puget Bench.
AMD's Next-Gen Radeon Pro Graphics Card Spotted: Radeon Pro W7900 With RDNA 3 GPU Architecture
AMD is already working on the successor to its Radeon Pro W6000 series graphics cards in the form of the flagship Radeon Pro W7900. As the name suggests, the graphics card will be aiming next-gen workstations with its brand new RDNA 3 GPU architecture and also house the Navi 31 GPU that has been used on the Radeon RX 7900 XTX & 7900 XT Gaming cards.
Now while the specifications remain unknown, we can definitely expect the Radeon W7900 Pro to offer huge amounts of VRAM. The Radeon Pro W6900X (Apple-Exclusive) & the Radeon Pro W6800 double the VRAM to 32 GB versus the 16 GB featured on consumer variants. If the same is the case with the Radeon Pro W7000 series, we can expect up to 48 GB of memory on the flagship Radeon W7900 Pro. That will be the same amount of memory as the NVIDIA RTX 6000 Ada graphics card & AMD has been able to offer as much memory as NVIDIA's top 24 GB RTX 4090 on its 7900 XTX card too.


2 of 9
As for the GPU configuration, we might be looking at the full-fledged Navi 31 GPU die for the AMD Radeon Pro W7900 graphics card though the final specifications can always change unless they are officially announced. The full Navi 31 GPU offers a total of 48 WGPs, 96 CUs, and 6144 cores. There are also 6 MCD's which will feature 16 MB Infinity Cache per die and 96 MB in total across a 384-bit wide bus interface.
Puget Bench Photoshop
GPU Score
0
40
80
120
160
200
240
0
40
80
120
160
200
240
NVIDIA RTX 4090 168
AMD RX 7900 XTX 160
NVIDIA RTX 6000 Ada 149
NVIDIA RTX 4080 148
AMD Pro W7900 135
Now if we compare the AMD Radeon Pro W7900 graphics card to the NVIDIA RTX 6000 Ada in the same benchmark, we see that the NVIDIA option is around 11% faster purely in the GPU score. The scores can change as mature drivers for the Radeon Pro W7000 series arrive but AMD has priced the Pro lineup very competitively so even if there's a 10% advantage to NVIDIA, the Radeon Pro might end up having the value advantage.
AMD Radeon Pro Workstation Graphics Lineup:
| Graphics Card Name | Radeon Pro W7900 | Radeon Pro W7800 | Radeon Pro W6900X | Radeon Pro W6800 | Radeon Pro VII | Radeon Pro W5700X | Radeon Pro W5700 | Radeon Pro WX 9100 | Radeon Pro WX 8200 | Radeon Pro WX 7100 |
|---|---|---|---|---|---|---|---|---|---|---|
| GPU | Navi 31 | Navi 31 | Navi 21 | Navi 21 | Vega 20 | Navi 10 | Navi 10 | Vega 10 | Vega 10 | Polaris 10 |
| Process Node | 5nm+6nm | 5nm+6nm | 7nm | 7nm | 7nm | 7nm | 7nm | 14nm | 14nm | 14nm |
| Compute Units | 96 CU | 70 CU | 80 | 60 | 60 | 40 | 36 | 64 | 56 | 36 |
| Stream Processors | 6144 | 4480 | 5120 | 3840 | 3840 | 2560 | 2304 | 4096 | 3584 | 2304 |
| Clock Speed (Peak) | ~2.5 GHz | ~2.5 GHz | 2171 MHz | 2320 MHz | 1700 MHz | 2040 MHz | 1930 MHz | 1500 MHz | 1500 MHz | 1243 MHz |
| VRAM | 48 GB GDDR6 | 32 GB GDDR6 | 32 GB GDDR6 | 32 GB GDDR6 | 16 GB HBM2 | 16 GB GDDR6 | 8 GB GDDR6 | 16 GB HBM2 | 8 GB HBM2 | 8 GB GDDR5 |
| Memory Bandwidth | 864 GB/s | 576 GB/s | 512 GB/s | 512 GB/s | 1024 GB/s | 448 GB/s | 448 GB/s | 512 GB/s | 484 GB/s | 224 GB/s |
| Memory Bus | 384-bit | 256-bit | 256-bit | 256-bit | 4096-bit | 256-bit | 256-bit | 2048-bit | 2048-bit | 256-bit |
| Compute Rate (FP32) | 61.3 TFLOPs | 45.2 TFLOPs | 22.23 TFLOPs | 17.82 TFLOPs | 13.1 TFLOPs | 9.5 TFLOPs | 8.89 TFLOPs | 12.3 TFLOPs | 10.8 TFLOPs | 5.7 TFLOPs |
| TDP | 295W | 260W | 300W | 250W | 250W | 240W | 205W | 250W | 230W | 150W |
| Price | $3999 US | $2499 US | $5999 US | $2249 US | $1899 US | $999 US | $799 US | $2199 US | $999 US | $799 US |
| Launch | 2023 | 2023 | 2021 | 2021 | 2020 | 2019 | 2019 | 2017 | 2018 | 2016 |
News Source: KOMACHI_ENSAKA









