NVIDIA CMP 50HX vs AMD Radeon E9390 PCIe
GPU · Specs Compare
Graphics Card
Release Date
Jun 2021
Oct 2019
Generation
Mining GPUs
Embedded
Type
Desktop
Mobile
Bus Interface
PCIe 1.0 x4
PCIe 3.0 x16
Clock Speeds
Base Clock
1350 MHz
713 MHz
Boost Clock
1545 MHz
1089 MHz
Memory Clock
1750 MHz
1250 MHz
Memory
Memory Size
10GB
8GB
Memory Type
GDDR6
GDDR5
Memory Bus
320bit
256bit
Bandwidth
560.0GB/s
160.0GB/s
Render Config
SM Count
56
—
Shading Units
3584
1792
TMUs
192
112
ROPs
80
32
Tensor Cores
448
—
RT Cores
56
—
L1 Cache
64 KB (per SM)
16 KB (per CU)
L2 Cache
5 MB
2 MB
Compute Units
—
28
Theoretical Performance
Pixel Rate
123.6 GPixel/s
34.85 GPixel/s
Texture Rate
296.6 GTexel/s
122.0 GTexel/s
FP16 (half)
22.15 TFLOPS
3.903 TFLOPS
FP32 (float)
11.07 TFLOPS
3.903 TFLOPS
FP64 (double)
346.1 GFLOPS
243.9 GFLOPS
Graphics Processor
GPU Name
TU102
Ellesmere
GPU Variant
TU102-100-A1
—
Architecture
Turing
GCN 4.0
Foundry
TSMC
GlobalFoundries
Process Size
12 nm
14 nm
Transistors
18.6 billion
5.7 billion
Die Size
754 mm²
232 mm²
Board Design
TDP
250W
75W
Suggested PSU
600 W
—
Outputs
No outputs
4x DisplayPort 1.4a
Power Connectors
2x 8-pin
None
Graphics Features
DirectX
12 Ultimate (12_2)
12 (12_0)
OpenGL
4.6
4.6
OpenCL
3.0
2.1
Vulkan
1.3
1.2
CUDA
7.5
—
Shader Model
6.8
6.4
▲ Specs Compare
Data sourced from official specifications and benchmark tests.