Intel Data Center GPU Max Subsystem vs NVIDIA P104 100
GPU · Specs Compare
Graphics Card
Release Date
Jan 2023
Dec 2017
Generation
Data Center GPU
Mining GPUs
Type
Professional
Desktop
Bus Interface
PCIe 5.0 x16
PCIe 1.0 x4
Clock Speeds
Base Clock
900 MHz
1607 MHz
Boost Clock
1600 MHz
1733 MHz
Memory Clock
1565 MHz
1251 MHz
Memory
Memory Size
128GB
4GB
Memory Type
HBM2e
GDDR5X
Memory Bus
8192bit
256bit
Bandwidth
3205GB/s
320.3GB/s
Render Config
Shading Units
16384
1920
TMUs
1024
120
ROPs
0
64
Tensor Cores
1024
—
RT Cores
128
—
L1 Cache
64 KB (per EU)
48 KB (per SM)
L2 Cache
408 MB
2 MB
SM Count
—
15
Theoretical Performance
Pixel Rate
0 MPixel/s
110.9 GPixel/s
Texture Rate
1638 GTexel/s
208.0 GTexel/s
FP16 (half)
52.43 TFLOPS
104.0 GFLOPS
FP32 (float)
52.43 TFLOPS
6.655 TFLOPS
FP64 (double)
52.43 TFLOPS
208.0 GFLOPS
Graphics Processor
GPU Name
Ponte Vecchio
GP104
Architecture
Generation 12.5
Pascal
Foundry
Intel
TSMC
Process Size
10 nm
16 nm
Transistors
100 billion
7.2 billion
Die Size
1280 mm²
314 mm²
GPU Variant
—
GP104-100-A1
Board Design
TDP
2400W
Unknown
Suggested PSU
2800 W
200 W
Outputs
No outputs
No outputs
Power Connectors
1x 16-pin
1x 8-pin
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
6.8
CUDA
—
6.1
Benchmark
3DMark Time Spy
—
5,439
3DMark Time Spy Extreme
—
2,718
OctaneBench
—
124
Blender
—
701
▲ Specs Compare
Data sourced from official specifications and benchmark tests.