NVIDIA A2 vs NVIDIA CMP 40HX
We compared two Desktop platform GPUs: 16GB VRAM A2 and 8GB VRAM CMP 40HX to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA A2 's Advantages
Released 9 months late
Boost Clock has increased by 7% (1770MHz vs 1650MHz)
More VRAM (16GB vs 8GB)
Lower TDP (60W vs 185W)
NVIDIA CMP 40HX 's Advantages
Larger VRAM bandwidth (448.0GB/s vs 200.1GB/s)
1024 additional rendering cores
Score
Benchmark
FP32 (float)
A2
4.531 TFLOPS
CMP 40HX
+67%
7.603 TFLOPS
Blender
A2
902
CMP 40HX
+30%
1174
Graphics Card
Nov 2021
Release Date
Feb 2021
Quadro
Generation
Mining GPUs
Desktop
Type
Desktop
PCIe 4.0 x8
Bus Interface
PCIe 1.0 x4
Clock Speeds
1440 MHz
Base Clock
1470 MHz
1770 MHz
Boost Clock
1650 MHz
1563 MHz
Memory Clock
1750 MHz
Memory
16GB
Memory Size
8GB
GDDR6
Memory Type
GDDR6
128bit
Memory Bus
256bit
200.1GB/s
Bandwidth
448.0GB/s
Render Config
-
-
-
10
SM Count
36
1280
Shading Units
2304
40
TMUs
144
32
ROPs
64
40
Tensor Cores
288
10
RT Cores
36
128 KB (per SM)
L1 Cache
64 KB (per SM)
2 MB
L2 Cache
4 MB
-
-
-
Theoretical Performance
56.64 GPixel/s
Pixel Rate
105.6 GPixel/s
70.80 GTexel/s
Texture Rate
237.6 GTexel/s
4.531 TFLOPS
FP16 (half)
15.21 TFLOPS
4.531 TFLOPS
FP32 (float)
7.603 TFLOPS
70.80 GFLOPS
FP64 (double)
237.6 GFLOPS
Board Design
60W
TDP
185W
250 W
Suggested PSU
450 W
No outputs
Outputs
No outputs
None
Power Connectors
1x 8-pin
Graphics Processor
GA107
GPU Name
TU106
-
GPU Variant
TU106-100-A1
Ampere
Architecture
Turing
Samsung
Foundry
TSMC
8 nm
Process Size
12 nm
Unknown
Transistors
10.8 billion
Unknown
Die Size
445 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 Ultimate (12_2)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.3
Vulkan
1.3
8.6
CUDA
7.5
6.6
Shader Model
6.8
