NVIDIA Tesla P6 vs Intel Data Center GPU Max 1100
GPU · Specs Compare
Graphics Card
Release Date
Mar 2017
Jan 2023
Generation
Tesla
Data Center GPU
Type
Professional
Professional
Bus Interface
MXM-B (3.0)
PCIe 5.0 x16
Clock Speeds
Base Clock
1012 MHz
1000 MHz
Boost Clock
1506 MHz
1550 MHz
Memory Clock
1502 MHz
600 MHz
Memory
Memory Size
16GB
48GB
Memory Type
GDDR5
HBM2e
Memory Bus
256bit
8192bit
Bandwidth
192.3GB/s
1229GB/s
Render Config
SM Count
16
—
Shading Units
2048
7168
TMUs
128
448
ROPs
64
0
L1 Cache
48 KB (per SM)
64 KB (per EU)
L2 Cache
2 MB
204 MB
Tensor Cores
—
448
RT Cores
—
56
Theoretical Performance
Pixel Rate
96.38 GPixel/s
0 MPixel/s
Texture Rate
192.8 GTexel/s
694.4 GTexel/s
FP16 (half)
96.38 GFLOPS
22.22 TFLOPS
FP32 (float)
6.169 TFLOPS
22.22 TFLOPS
FP64 (double)
192.8 GFLOPS
22.22 TFLOPS
Graphics Processor
GPU Name
GP104
Ponte Vecchio
GPU Variant
GP104-995-A1
—
Architecture
Pascal
Generation 12.5
Foundry
TSMC
Intel
Process Size
16 nm
10 nm
Transistors
7.2 billion
100 billion
Die Size
314 mm²
1280 mm²
Board Design
TDP
90W
300W
Suggested PSU
250 W
700 W
Outputs
No outputs
No outputs
Power Connectors
None
1x 12-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
▲ Specs Compare
Data sourced from official specifications and benchmark tests.