NVIDIA CMP 40HX vs AMD Radeon Pro VII
We compared two Desktop platform GPUs: 8GB VRAM CMP 40HX and 16GB VRAM Radeon Pro VII to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA CMP 40HX 's Advantages
Released 9 months late
Lower TDP (185W vs 250W)
AMD Radeon Pro VII 's Advantages
Boost Clock has increased by 3% (1700MHz vs 1650MHz)
More VRAM (16GB vs 8GB)
Larger VRAM bandwidth (1020GB/s vs 448.0GB/s)
1536 additional rendering cores
Score
Benchmark
FP32 (float)
CMP 40HX
7.603 TFLOPS
Radeon Pro VII
+71%
13.06 TFLOPS
Blender
CMP 40HX
1174
Radeon Pro VII
+184%
3343
Graphics Card
Feb 2021
Release Date
May 2020
Mining GPUs
Generation
Radeon Pro Vega
Desktop
Type
Desktop
PCIe 1.0 x4
Bus Interface
PCIe 4.0 x16
Clock Speeds
1470 MHz
Base Clock
1400 MHz
1650 MHz
Boost Clock
1700 MHz
1750 MHz
Memory Clock
1000 MHz
Memory
8GB
Memory Size
16GB
GDDR6
Memory Type
HBM2
256bit
Memory Bus
4096bit
448.0GB/s
Bandwidth
1020GB/s
Render Config
-
Compute Units
60
36
SM Count
-
2304
Shading Units
3840
144
TMUs
240
64
ROPs
64
288
Tensor Cores
-
36
RT Cores
-
64 KB (per SM)
L1 Cache
16 KB (per CU)
4 MB
L2 Cache
4 MB
-
-
-
Theoretical Performance
105.6 GPixel/s
Pixel Rate
108.8 GPixel/s
237.6 GTexel/s
Texture Rate
408.0 GTexel/s
15.21 TFLOPS
FP16 (half)
26.11 TFLOPS
7.603 TFLOPS
FP32 (float)
13.06 TFLOPS
237.6 GFLOPS
FP64 (double)
6.528 TFLOPS
Board Design
185W
TDP
250W
450 W
Suggested PSU
600 W
No outputs
Outputs
6x mini-DisplayPort 1.4a
1x 8-pin
Power Connectors
1x 6-pin + 1x 8-pin
Graphics Processor
TU106
GPU Name
Vega 20
TU106-100-A1
GPU Variant
Vega 20 GLXT WS
(215-0914026)
Turing
Architecture
GCN 5.1
TSMC
Foundry
TSMC
12 nm
Process Size
7 nm
10.8 billion
Transistors
13.23 billion
445 mm²
Die Size
331 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 (12_1)
4.6
OpenGL
4.6
3.0
OpenCL
2.1
1.3
Vulkan
1.3
7.5
CUDA
-
6.8
Shader Model
6.7
