NVIDIA P102 100 vs Intel Data Center GPU Max Subsystem

GPU Specs Compare

Graphics Card

Release Date
Feb 2018
Jan 2023
Generation
Mining GPUs
Data Center GPU
Type
Desktop
Professional
Bus Interface
PCIe 3.0 x4
PCIe 5.0 x16

Clock Speeds

Base Clock
1582 MHz
900 MHz
Boost Clock
1683 MHz
1600 MHz
Memory Clock
1376 MHz
1565 MHz

Memory

Memory Size
5GB
128GB
Memory Type
GDDR5X
HBM2e
Memory Bus
320bit
8192bit
Bandwidth
440.3GB/s
3205GB/s

Render Config

SM Count
25
-
Shading Units
3200
16384
TMUs
200
1024
ROPs
80
0
L1 Cache
48 KB (per SM)
64 KB (per EU)
L2 Cache
0 MB
408 MB
Tensor Cores
-
1024
RT Cores
-
128

Theoretical Performance

Pixel Rate
134.6 GPixel/s
0 MPixel/s
Texture Rate
336.6 GTexel/s
1638 GTexel/s
FP16 (half)
168.3 GFLOPS
52.43 TFLOPS
FP32 (float)
10.77 TFLOPS
52.43 TFLOPS
FP64 (double)
336.6 GFLOPS
52.43 TFLOPS

Graphics Processor

GPU Name
GP102
Ponte Vecchio
GPU Variant
GP102-100-A1
-
Architecture
Pascal
Generation 12.5
Foundry
TSMC
Intel
Process Size
16 nm
10 nm
Transistors
11.8 billion
100 billion
Die Size
471 mm²
1280 mm²

Board Design

TDP
250W
2400W
Suggested PSU
600 W
2800 W
Outputs
No outputs
No outputs
Power Connectors
2x 8-pin
1x 16-pin

Graphics Features

DirectX
12 (12_1)
12 (12_1)
OpenGL
4.6
4.6
OpenCL
3.0
3.0
Vulkan
1.3
N/A
CUDA
6.1
-
Shader Model
6.4
6.6

📊 Benchmark

3DMark Time Spy
7,042
-
3DMark Time Spy Extreme
3,817
-