NVIDIA P102 100 vs NVIDIA A10 PCIe
GPU · Specs Compare
Graphics Card
Release Date
Feb 2018
Apr 2021
Generation
Mining GPUs
Tesla
Type
Desktop
Professional
Bus Interface
PCIe 3.0 x4
PCIe 4.0 x16
Clock Speeds
Base Clock
1582 MHz
885 MHz
Boost Clock
1683 MHz
1695 MHz
Memory Clock
1376 MHz
1563 MHz
Memory
Memory Size
5GB
24GB
Memory Type
GDDR5X
GDDR6
Memory Bus
320bit
384bit
Bandwidth
440.3GB/s
600.2GB/s
Render Config
SM Count
25
72
Shading Units
3200
9216
TMUs
200
288
ROPs
80
96
L1 Cache
48 KB (per SM)
128 KB (per SM)
L2 Cache
0 MB
6 MB
Tensor Cores
—
288
RT Cores
—
72
Theoretical Performance
Pixel Rate
134.6 GPixel/s
162.7 GPixel/s
Texture Rate
336.6 GTexel/s
488.2 GTexel/s
FP16 (half)
168.3 GFLOPS
31.24 TFLOPS
FP32 (float)
10.77 TFLOPS
31.24 TFLOPS
FP64 (double)
336.6 GFLOPS
976.3 GFLOPS
Graphics Processor
GPU Name
GP102
GA102
GPU Variant
GP102-100-A1
GA102-890-A1
Architecture
Pascal
Ampere
Foundry
TSMC
Samsung
Process Size
16 nm
8 nm
Transistors
11.8 billion
28.3 billion
Die Size
471 mm²
628 mm²
Board Design
TDP
250W
150W
Suggested PSU
600 W
450 W
Outputs
No outputs
No outputs
Power Connectors
2x 8-pin
1x 8-pin
Graphics Features
DirectX
12 (12_1)
12 Ultimate (12_2)
OpenGL
4.6
4.6
OpenCL
3.0
3.0
Vulkan
1.3
1.3
CUDA
6.1
8.6
Shader Model
6.4
6.6
Benchmark
3DMark Time Spy
7,042
—
3DMark Time Spy Extreme
3,817
—
▲ Specs Compare
Data sourced from official specifications and benchmark tests.