NVIDIA A100 PCIe 80 GB vs NVIDIA CMP 170HX 10 GB
GPU · Specs Compare
Graphics Card
Release Date
Jun 2021
Sep 2021
Generation
Tesla Ampere(Axx)
Mining GPUs
Type
Professional
Desktop
Bus Interface
PCIe 4.0 x16
PCIe 1.0 x4
Clock Speeds
Base Clock
1065 MHz
1140 MHz
Boost Clock
1410 MHz
1410 MHz
Memory Clock
1512 MHz
1215 MHz
Memory
Memory Size
80GB
10GB
Memory Type
HBM2e
HBM2e
Memory Bus
5120bit
5120bit
Bandwidth
1.94TB/s
1.56TB/s
Render Config
SM Count
108
70
Shading Units
6912
4480
TMUs
432
280
ROPs
160
128
Tensor Cores
432
280
L1 Cache
192 KB (per SM)
192 KB (per SM)
L2 Cache
80 MB
10 MB
Theoretical Performance
Pixel Rate
225.6 GPixel/s
180.5 GPixel/s
Texture Rate
609.1 GTexel/s
394.8 GTexel/s
FP16 (half)
77.97 TFLOPS
50.53 TFLOPS
FP32 (float)
19.49 TFLOPS
12.63 TFLOPS
FP64 (double)
9.746 TFLOPS
6.317 TFLOPS
Graphics Processor
GPU Name
GA100
GA100
Architecture
Ampere
Ampere
Foundry
TSMC
TSMC
Process Size
7 nm
7 nm
Transistors
54.2 billion
54.2 billion
Die Size
826 mm²
826 mm²
GPU Variant
—
GA100-105A-A1
Board Design
TDP
300W
250W
Suggested PSU
700 W
600 W
Outputs
No outputs
No outputs
Power Connectors
8-pin EPS
2x 8-pin
Graphics Features
DirectX
N/A
N/A
OpenGL
N/A
N/A
OpenCL
3.0
3.0
Vulkan
N/A
N/A
CUDA
8.0
8.0
Shader Model
N/A
N/A
Benchmark
OctaneBench
310
—
Blender
3,722
—
▲ Specs Compare
Data sourced from official specifications and benchmark tests.