NVIDIA CMP 30HX vs NVIDIA A2
We compared two Desktop platform GPUs: 6GB VRAM CMP 30HX and 16GB VRAM A2 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA CMP 30HX 's Advantages
Boost Clock has increased by 1% (1785MHz vs 1770MHz)
Larger VRAM bandwidth (336.0GB/s vs 200.1GB/s)
128 additional rendering cores
NVIDIA A2 's Advantages
Released 9 months late
More VRAM (16GB vs 6GB)
Lower TDP (60W vs 125W)
Score
Benchmark
FP32 (float)
CMP 30HX
+10%
5.027 TFLOPS
A2
4.531 TFLOPS
Blender
CMP 30HX
801
A2
+12%
902
Graphics Card
Feb 2021
Release Date
Nov 2021
Mining GPUs
Generation
Quadro
Desktop
Type
Desktop
PCIe 1.0 x4
Bus Interface
PCIe 4.0 x8
Clock Speeds
1530 MHz
Base Clock
1440 MHz
1785 MHz
Boost Clock
1770 MHz
1750 MHz
Memory Clock
1563 MHz
Memory
6GB
Memory Size
16GB
GDDR6
Memory Type
GDDR6
192bit
Memory Bus
128bit
336.0GB/s
Bandwidth
200.1GB/s
Render Config
-
-
-
22
SM Count
10
1408
Shading Units
1280
88
TMUs
40
48
ROPs
32
-
Tensor Cores
40
-
RT Cores
10
64 KB (per SM)
L1 Cache
128 KB (per SM)
1536 KB
L2 Cache
2 MB
-
-
-
Theoretical Performance
85.68 GPixel/s
Pixel Rate
56.64 GPixel/s
157.1 GTexel/s
Texture Rate
70.80 GTexel/s
10.05 TFLOPS
FP16 (half)
4.531 TFLOPS
5.027 TFLOPS
FP32 (float)
4.531 TFLOPS
157.1 GFLOPS
FP64 (double)
70.80 GFLOPS
Board Design
125W
TDP
60W
300 W
Suggested PSU
250 W
No outputs
Outputs
No outputs
1x 8-pin
Power Connectors
None
Graphics Processor
TU116
GPU Name
GA107
TU116-100-A1
GPU Variant
-
Turing
Architecture
Ampere
TSMC
Foundry
Samsung
12 nm
Process Size
8 nm
6.6 billion
Transistors
Unknown
284 mm²
Die Size
Unknown
Graphics Features
12 (12_1)
DirectX
12 Ultimate (12_2)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.3
Vulkan
1.3
7.5
CUDA
8.6
6.8
Shader Model
6.6
