NVIDIA CMP 50HX vs AMD Radeon Vega 8
GPU · Specs Compare
Graphics Card
Release Date
Jun 2021
Jan 2021
Generation
Mining GPUs
Cezanne
Type
Desktop
Integrated
Bus Interface
PCIe 1.0 x4
IGP
Clock Speeds
Base Clock
1350 MHz
300 MHz
Boost Clock
1545 MHz
2000 MHz
Memory Clock
1750 MHz
System Shared
Memory
Memory Size
10GB
System Shared
Memory Type
GDDR6
System Shared
Memory Bus
320bit
System Shared
Bandwidth
560.0GB/s
System Dependent
Render Config
SM Count
56
—
Shading Units
3584
512
TMUs
192
32
ROPs
80
8
Tensor Cores
448
—
RT Cores
56
—
L1 Cache
64 KB (per SM)
—
L2 Cache
5 MB
—
Compute Units
—
8
Theoretical Performance
Pixel Rate
123.6 GPixel/s
16.00 GPixel/s
Texture Rate
296.6 GTexel/s
64.00 GTexel/s
FP16 (half)
22.15 TFLOPS
4.096 TFLOPS
FP32 (float)
11.07 TFLOPS
2.048 TFLOPS
FP64 (double)
346.1 GFLOPS
128.0 GFLOPS
Graphics Processor
GPU Name
TU102
Cezanne
GPU Variant
TU102-100-A1
—
Architecture
Turing
GCN 5.1
Foundry
TSMC
TSMC
Process Size
12 nm
7 nm
Transistors
18.6 billion
9.8 billion
Die Size
754 mm²
156 mm²
Board Design
TDP
250W
45W
Suggested PSU
600 W
—
Outputs
No outputs
No outputs
Power Connectors
2x 8-pin
None
Graphics Features
DirectX
12 Ultimate (12_2)
12 (12_1)
OpenGL
4.6
4.6
OpenCL
3.0
2.1
Vulkan
1.3
1.2
CUDA
7.5
—
Shader Model
6.8
6.4
Benchmark
3DMark Time Spy
—
893
3DMark Time Spy Extreme
—
423
▲ Specs Compare
Data sourced from official specifications and benchmark tests.