NVIDIA CMP 40HX vs NVIDIA A10G
GPU · Specs Compare
Graphics Card
Release Date
Feb 2021
Apr 2021
Generation
Mining GPUs
Tesla
Type
Desktop
Professional
Bus Interface
PCIe 1.0 x4
PCIe 4.0 x16
Clock Speeds
Base Clock
1470 MHz
1320 MHz
Boost Clock
1650 MHz
1710 MHz
Memory Clock
1750 MHz
1563 MHz
Memory
Memory Size
8GB
12GB
Memory Type
GDDR6
GDDR6
Memory Bus
256bit
384bit
Bandwidth
448.0GB/s
600.2GB/s
Render Config
SM Count
36
72
Shading Units
2304
9216
TMUs
144
288
ROPs
64
96
Tensor Cores
288
288
RT Cores
36
72
L1 Cache
64 KB (per SM)
128 KB (per SM)
L2 Cache
4 MB
6 MB
Theoretical Performance
Pixel Rate
105.6 GPixel/s
164.2 GPixel/s
Texture Rate
237.6 GTexel/s
492.5 GTexel/s
FP16 (half)
15.21 TFLOPS
31.52 TFLOPS
FP32 (float)
7.603 TFLOPS
31.52 TFLOPS
FP64 (double)
237.6 GFLOPS
985.0 GFLOPS
Graphics Processor
GPU Name
TU106
GA102
GPU Variant
TU106-100-A1
GA102-890-A1
Architecture
Turing
Ampere
Foundry
TSMC
Samsung
Process Size
12 nm
8 nm
Transistors
10.8 billion
28.3 billion
Die Size
445 mm²
628 mm²
Board Design
TDP
185W
150W
Suggested PSU
450 W
450 W
Outputs
No outputs
No outputs
Power Connectors
1x 8-pin
8-pin EPS
Graphics Features
DirectX
12 Ultimate (12_2)
12 Ultimate (12_2)
OpenGL
4.6
4.6
OpenCL
3.0
3.0
Vulkan
1.3
1.3
CUDA
7.5
8.6
Shader Model
6.8
6.6
Benchmark
Blender
1,174
—
▲ Specs Compare
Data sourced from official specifications and benchmark tests.