NVIDIA CMP 70HX vs AMD Radeon RX 470D
We compared two Desktop platform GPUs: 8GB VRAM CMP 70HX 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 70HX 's Advantages
Released 4 years and 3 months late
Boost Clock has increased by 16% (1395MHz vs 1206MHz)
More VRAM (8GB vs 4GB)
Larger VRAM bandwidth (608.3GB/s vs 211.2GB/s)
2048 additional rendering cores
Score
Benchmark
FP32 (float)
CMP 70HX
+147%
10.71 TFLOPS
Radeon RX 470D
4.322 TFLOPS
Graphics Card
Jan 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
1365 MHz
Base Clock
926 MHz
1395 MHz
Boost Clock
1206 MHz
1188 MHz
Memory Clock
1650 MHz
Memory
8GB
Memory Size
4GB
GDDR6X
Memory Type
GDDR5
256bit
Memory Bus
256bit
608.3GB/s
Bandwidth
211.2GB/s
Render Config
-
Compute Units
28
30
SM Count
-
3840
Shading Units
1792
120
TMUs
112
64
ROPs
32
120
Tensor Cores
-
30
RT Cores
-
128 KB (per SM)
L1 Cache
16 KB (per CU)
4 MB
L2 Cache
2 MB
-
-
-
Theoretical Performance
89.28 GPixel/s
Pixel Rate
38.59 GPixel/s
167.4 GTexel/s
Texture Rate
135.1 GTexel/s
10.71 TFLOPS
FP16 (half)
4.322 TFLOPS
10.71 TFLOPS
FP32 (float)
4.322 TFLOPS
167.4 GFLOPS
FP64 (double)
270.1 GFLOPS
Board Design
Unknown
TDP
120W
200 W
Suggested PSU
300 W
No outputs
Outputs
1x HDMI 2.0b
3x DisplayPort 1.4a
1x 12-pin
Power Connectors
1x 6-pin
Graphics Processor
GA104
GPU Name
Ellesmere
GA104-100-A1
GPU Variant
Polaris 10 PROD
Ampere
Architecture
GCN 4.0
Samsung
Foundry
GlobalFoundries
8 nm
Process Size
14 nm
17.4 billion
Transistors
5.7 billion
392 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
8.6
CUDA
-
6.8
Shader Model
6.4
