NVIDIA CMP 40HX vs AMD Radeon RX Vega 11 Embedded
GPU · Specs Compare
Graphics Card
Release Date
Feb 2021
Apr 2018
Generation
Mining GPUs
Raven Ridge
Type
Desktop
Integrated
Bus Interface
PCIe 1.0 x4
IGP
Clock Speeds
Base Clock
1470 MHz
300 MHz
Boost Clock
1650 MHz
1251 MHz
Memory Clock
1750 MHz
System Shared
Memory
Memory Size
8GB
System Shared
Memory Type
GDDR6
System Shared
Memory Bus
256bit
System Shared
Bandwidth
448.0GB/s
System Dependent
Render Config
SM Count
36
—
Shading Units
2304
704
TMUs
144
44
ROPs
64
8
Tensor Cores
288
—
RT Cores
36
—
L1 Cache
64 KB (per SM)
—
L2 Cache
4 MB
—
Compute Units
—
11
Theoretical Performance
Pixel Rate
105.6 GPixel/s
10.01 GPixel/s
Texture Rate
237.6 GTexel/s
55.04 GTexel/s
FP16 (half)
15.21 TFLOPS
3.523 TFLOPS
FP32 (float)
7.603 TFLOPS
1.761 TFLOPS
FP64 (double)
237.6 GFLOPS
110.1 GFLOPS
Graphics Processor
GPU Name
TU106
Raven
GPU Variant
TU106-100-A1
—
Architecture
Turing
GCN 5.0
Foundry
TSMC
GlobalFoundries
Process Size
12 nm
14 nm
Transistors
10.8 billion
4.94 billion
Die Size
445 mm²
210 mm²
Board Design
TDP
185W
35W
Suggested PSU
450 W
—
Outputs
No outputs
No outputs
Power Connectors
1x 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
Blender
1,174
—
3DMark Time Spy
—
1,149
3DMark Time Spy Extreme
—
572
▲ Specs Compare
Data sourced from official specifications and benchmark tests.