NVIDIA A10G vs NVIDIA CMP 170HX
GPU · Specs Compare
Graphics Card
Release Date
Apr 2021
Sep 2021
Generation
Tesla
Mining GPUs
Type
Professional
Desktop
Bus Interface
PCIe 4.0 x16
PCIe 4.0 x4
Clock Speeds
Base Clock
1320 MHz
1140 MHz
Boost Clock
1710 MHz
1410 MHz
Memory Clock
1563 MHz
1458 MHz
Memory
Memory Size
12GB
16GB
Memory Type
GDDR6
HBM2e
Memory Bus
384bit
4096bit
Bandwidth
600.2GB/s
1493GB/s
Render Config
SM Count
72
70
Shading Units
9216
4480
TMUs
288
280
ROPs
96
128
Tensor Cores
288
280
RT Cores
72
—
L1 Cache
128 KB (per SM)
192 KB (per SM)
L2 Cache
6 MB
8 MB
Theoretical Performance
Pixel Rate
164.2 GPixel/s
180.5 GPixel/s
Texture Rate
492.5 GTexel/s
394.8 GTexel/s
FP16 (half)
31.52 TFLOPS
50.53 TFLOPS
FP32 (float)
31.52 TFLOPS
12.63 TFLOPS
FP64 (double)
985.0 GFLOPS
6.317 TFLOPS
Graphics Processor
GPU Name
GA102
GA100
GPU Variant
GA102-890-A1
GA100-105F-A1
Architecture
Ampere
Ampere
Foundry
Samsung
TSMC
Process Size
8 nm
7 nm
Transistors
28.3 billion
54.2 billion
Die Size
628 mm²
826 mm²
Board Design
TDP
150W
250W
Suggested PSU
450 W
600 W
Outputs
No outputs
No outputs
Power Connectors
8-pin EPS
2x 8-pin
Graphics Features
DirectX
12 Ultimate (12_2)
N/A
OpenGL
4.6
N/A
OpenCL
3.0
3.0
Vulkan
1.3
N/A
CUDA
8.6
8.0
Shader Model
6.6
N/A
▲ Specs Compare
Data sourced from official specifications and benchmark tests.