Intel Data Center GPU Max Subsystem vs NVIDIA Tesla P40
GPU Specs Compare
Graphics Card
Release Date
Jan 2023
Sep 2016
Generation
Data Center GPU
Tesla Pascal
Type
Professional
Professional
Bus Interface
PCIe 5.0 x16
PCIe 3.0 x16
Clock Speeds
Base Clock
900 MHz
1303 MHz
Boost Clock
1600 MHz
1531 MHz
Memory Clock
1565 MHz
1808 MHz
Memory
Memory Size
128GB
24GB
Memory Type
HBM2e
GDDR5
Memory Bus
8192bit
384bit
Bandwidth
3205GB/s
347.1GB/s
Render Config
Shading Units
16384
3840
TMUs
1024
240
ROPs
0
96
Tensor Cores
1024
-
RT Cores
128
-
L1 Cache
64 KB (per EU)
48 KB (per SM)
L2 Cache
408 MB
3 MB
SM Count
-
30
Theoretical Performance
Pixel Rate
0 MPixel/s
147.0 GPixel/s
Texture Rate
1638 GTexel/s
367.4 GTexel/s
FP16 (half)
52.43 TFLOPS
183.7 GFLOPS
FP32 (float)
52.43 TFLOPS
11.76 TFLOPS
FP64 (double)
52.43 TFLOPS
367.4 GFLOPS
Graphics Processor
GPU Name
Ponte Vecchio
GP102
Architecture
Generation 12.5
Pascal
Foundry
Intel
TSMC
Process Size
10 nm
16 nm
Transistors
100 billion
11.8 billion
Die Size
1280 mm²
471 mm²
Board Design
TDP
2400W
250W
Suggested PSU
2800 W
600 W
Outputs
No outputs
No outputs
Power Connectors
1x 16-pin
8-pin EPS
Graphics Features
DirectX
12 (12_1)
12 (12_1)
OpenGL
4.6
4.6
OpenCL
3.0
3.0
Vulkan
N/A
1.3
Shader Model
6.6
6.7
CUDA
-
6.1