AMD Radeon Pro Duo vs NVIDIA GeForce RTX 2080 Max-Q Full Specs
8,192 Shaders 1GHz | 2,944 Shaders 1.09GHz |
8GB HBM1.02TB/s | 8GB GDDR6384GB/s |
·· 16.38 TFLOPS | ·· 6.45 TFLOPS |
Form Factor PCIe Card | Form Factor Soldered |
TDP 350W | TDP 80W |
Power Connectors 3x 8-Pin | Power Connectors - |
Radeon Pro Duo16.38 TFLOPSFP32 (2x 8.19 TFLOPS)
GeForce RTX 2080 Max-Q206.3 TOPSINT4 TensorClock Speed ·· | Clock Speed ··· |
Peak OPS 16.38 TFLOPSFP32 | Peak OPS 206.3 TOPSINT4 Tensor |
- | Tensor FP16-16 51.58 TFLOPSTensor FP16-32 25.79 TFLOPS |
- | Tensor BF16 25.79 TFLOPS |
Tensor TF32 - | Tensor TF32 25.79 TFLOPS |
FP32 16.38 TFLOPS | FP32 6.45 TFLOPS |
FP64 1.02 TFLOPS | FP64 201.5 GFLOPS |
Tensor INT4 - | Tensor INT4 206.3 TOPS |
- | Tensor INT8 103.2 TOPS |
Ray - | Ray 19.45 TOPS |
Pixel Rate 64 GPixel/s | Pixel Rate 70.1 GPixel/s |
Texture Rate 256 GTexel/s | Texture Rate 201.5 GTexel/s |
Shaders 8,192 Shaders | Shaders 2,944 Shaders |
TMUs 512 TMUs | TMUs 184 TMUs |
ROPs 128 ROPs | ROPs 64 ROPs |
Tensor Cores - | Tensor Cores 368 T-Cores |
RT Cores - | RT Cores 46 RT-Cores |
CUs 128 CUs | SMs 46 SMs |
Base Clock - | Base Clock 735MHz |
Boost Clock 1GHz | Boost Clock 1.09GHz |
L2 Cache 2MB shared | L2 Cache 4.1MB shared |
8GB HBM | 8GB GDDR6 |
Memory Bus 4096-bit | Memory Bus 256-bit |
Memory Speed 1GT/s | Memory Speed 12GT/s |
Memory Bandwidth 1.02TB/s | Memory Bandwidth 384GB/s |
ECC No | ECC No |
TDP 350W | TDP 80W |
Multi-Monitor 4 | Multi-Monitor 3 |
HDCP HDCP 1.4 | HDCP HDCP 2.2 |
3x DisplayPort 1.2 | - |
1x HDMI 1.4 | - |
Encoder Model VCE 3.0 | Encoder Model NVENC 7 |
Decoder Model UVD 6.0 | Decoder Model NVDEC 4 |
Form Factor PCIe Card | Form Factor Soldered |
PCIe 2-Slots | PCIe - |
Height 111 mm (4.37")Width 277 mm (10.91")Depth 40 mm (1.57") | - |
Cooling Liquid 120mm Radiator 1x Fan | Cooling Open-Air - |
Power Connectors 3x 8-Pin | Power Connectors - |
Manufacturer | Manufacturer |
Chip Designer | Chip Designer |
Architecture | Architecture |
Family | Family |
Branding  | Branding  |
Codename Fiji | Codename NV164 |
Chip Variant Fiji Pro | Chip Variant TU104-150-KC-A1 |
Market Segment Desktop | Market Segment Laptop |
Release Date Apr 26, 2016 | Release Date Jan 29, 2019 |
Foundry TSMC | Foundry TSMC |
Fabrication Node 28nm | Fabrication Node 12FFN |
Die Size 596mm² | Die Size 545mm² |
Transistor Count 8.9 Billion | Transistor Count 13.6 Billion |
Transistor Density 14.93 MTr/mm² | Transistor Density 24.95 MTr/mm² |
No images available
No images available