NVIDIA CMP 40HX vs AMD Radeon RX 470D
We compared two Desktop platform GPUs: 8GB VRAM CMP 40HX and 4GB VRAM Radeon RX 470D to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA CMP 40HX 's Advantages
Released 4 years and 4 months late
Boost Clock has increased by 37% (1650MHz vs 1206MHz)
More VRAM (8GB vs 4GB)
Larger VRAM bandwidth (448.0GB/s vs 211.2GB/s)
512 additional rendering cores
AMD Radeon RX 470D 's Advantages
Lower TDP (120W vs 185W)
Score
Benchmark
FP32 (float)
CMP 40HX
+75%
7.603 TFLOPS
Radeon RX 470D
4.322 TFLOPS
Graphics Card
Feb 2021
Release Date
Oct 2016
Mining GPUs
Generation
Arctic Islands
Desktop
Type
Desktop
PCIe 1.0 x4
Bus Interface
PCIe 3.0 x16
Clock Speeds
1470 MHz
Base Clock
926 MHz
1650 MHz
Boost Clock
1206 MHz
1750 MHz
Memory Clock
1650 MHz
Memory
8GB
Memory Size
4GB
GDDR6
Memory Type
GDDR5
256bit
Memory Bus
256bit
448.0GB/s
Bandwidth
211.2GB/s
Render Config
-
Compute Units
28
36
SM Count
-
2304
Shading Units
1792
144
TMUs
112
64
ROPs
32
288
Tensor Cores
-
36
RT Cores
-
64 KB (per SM)
L1 Cache
16 KB (per CU)
4 MB
L2 Cache
2 MB
-
-
-
Theoretical Performance
105.6 GPixel/s
Pixel Rate
38.59 GPixel/s
237.6 GTexel/s
Texture Rate
135.1 GTexel/s
15.21 TFLOPS
FP16 (half)
4.322 TFLOPS
7.603 TFLOPS
FP32 (float)
4.322 TFLOPS
237.6 GFLOPS
FP64 (double)
270.1 GFLOPS
Board Design
185W
TDP
120W
450 W
Suggested PSU
300 W
No outputs
Outputs
1x HDMI 2.0b
3x DisplayPort 1.4a
1x 8-pin
Power Connectors
1x 6-pin
Graphics Processor
TU106
GPU Name
Ellesmere
TU106-100-A1
GPU Variant
Polaris 10 PROD
Turing
Architecture
GCN 4.0
TSMC
Foundry
GlobalFoundries
12 nm
Process Size
14 nm
10.8 billion
Transistors
5.7 billion
445 mm²
Die Size
232 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 (12_0)
4.6
OpenGL
4.6
3.0
OpenCL
2.1
1.3
Vulkan
1.2
7.5
CUDA
-
6.8
Shader Model
6.4
