NVIDIA CMP 40HX vs NVIDIA P106 090
We compared two Desktop platform GPUs: 8GB VRAM CMP 40HX and 3GB VRAM P106 090 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA CMP 40HX 's Advantages
Released 3 years and 7 months late
Boost Clock has increased by 8% (1650MHz vs 1531MHz)
More VRAM (8GB vs 3GB)
Larger VRAM bandwidth (448.0GB/s vs 192.2GB/s)
1536 additional rendering cores
NVIDIA P106 090 's Advantages
Lower TDP (75W vs 185W)
Score
Benchmark
FP32 (float)
CMP 40HX
+223%
7.603 TFLOPS
P106 090
2.352 TFLOPS
Blender
CMP 40HX
+383%
1174
P106 090
243
Graphics Card
Feb 2021
Release Date
Jul 2017
Mining GPUs
Generation
Mining GPUs
Desktop
Type
Desktop
PCIe 1.0 x4
Bus Interface
PCIe 1.0 x1
Clock Speeds
1470 MHz
Base Clock
1354 MHz
1650 MHz
Boost Clock
1531 MHz
1750 MHz
Memory Clock
2002 MHz
Memory
8GB
Memory Size
3GB
GDDR6
Memory Type
GDDR5
256bit
Memory Bus
192bit
448.0GB/s
Bandwidth
192.2GB/s
Render Config
-
-
-
36
SM Count
6
2304
Shading Units
768
144
TMUs
48
64
ROPs
48
288
Tensor Cores
-
36
RT Cores
-
64 KB (per SM)
L1 Cache
48 KB (per SM)
4 MB
L2 Cache
1536 KB
-
-
-
Theoretical Performance
105.6 GPixel/s
Pixel Rate
73.49 GPixel/s
237.6 GTexel/s
Texture Rate
73.49 GTexel/s
15.21 TFLOPS
FP16 (half)
36.74 GFLOPS
7.603 TFLOPS
FP32 (float)
2.352 TFLOPS
237.6 GFLOPS
FP64 (double)
73.49 GFLOPS
Board Design
185W
TDP
75W
450 W
Suggested PSU
250 W
No outputs
Outputs
No outputs
1x 8-pin
Power Connectors
1x 6-pin
Graphics Processor
TU106
GPU Name
GP106
TU106-100-A1
GPU Variant
GP106-090-A1
Turing
Architecture
Pascal
TSMC
Foundry
TSMC
12 nm
Process Size
16 nm
10.8 billion
Transistors
4.4 billion
445 mm²
Die Size
200 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 (12_1)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.3
Vulkan
1.3
7.5
CUDA
6.1
6.8
Shader Model
6.8
