NVIDIA Tesla P40 vs Intel Data Center GPU Max Subsystem
We compared two Professional market GPUs: 24GB VRAM Tesla P40 and 128GB VRAM Data Center GPU Max Subsystem to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA Tesla P40 's Advantages
Lower TDP (250W vs 2400W)
Intel Data Center GPU Max Subsystem 's Advantages
Released 6 years and 4 months late
Boost Clock has increased by 5% (1600MHz vs 1531MHz)
More VRAM (128GB vs 24GB)
Larger VRAM bandwidth (3205GB/s vs 347.1GB/s)
12544 additional rendering cores
Score
Benchmark
FP32 (float)
Tesla P40
11.76 TFLOPS
Data Center GPU Max Subsystem
+345%
52.43 TFLOPS
Graphics Card
Sep 2016
Release Date
Jan 2023
Tesla Pascal
Generation
Data Center GPU
Professional
Type
Professional
PCIe 3.0 x16
Bus Interface
PCIe 5.0 x16
Clock Speeds
1303 MHz
Base Clock
900 MHz
1531 MHz
Boost Clock
1600 MHz
1808 MHz
Memory Clock
1565 MHz
Memory
24GB
Memory Size
128GB
GDDR5
Memory Type
HBM2e
384bit
Memory Bus
8192bit
347.1GB/s
Bandwidth
3205GB/s
Render Config
-
-
-
30
SM Count
-
3840
Shading Units
16384
240
TMUs
1024
96
ROPs
0
-
Tensor Cores
1024
-
RT Cores
128
48 KB (per SM)
L1 Cache
64 KB (per EU)
3 MB
L2 Cache
408 MB
-
-
-
Theoretical Performance
147.0 GPixel/s
Pixel Rate
0 MPixel/s
367.4 GTexel/s
Texture Rate
1638 GTexel/s
183.7 GFLOPS
FP16 (half)
52.43 TFLOPS
11.76 TFLOPS
FP32 (float)
52.43 TFLOPS
367.4 GFLOPS
FP64 (double)
52.43 TFLOPS
Board Design
250W
TDP
2400W
600 W
Suggested PSU
2800 W
No outputs
Outputs
No outputs
8-pin EPS
Power Connectors
1x 16-pin
Graphics Processor
GP102
GPU Name
Ponte Vecchio
-
-
-
Pascal
Architecture
Generation 12.5
TSMC
Foundry
Intel
16 nm
Process Size
10 nm
11.8 billion
Transistors
100 billion
471 mm²
Die Size
1280 mm²
Graphics Features
12 (12_1)
DirectX
12 (12_1)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.3
Vulkan
N/A
6.1
CUDA
-
6.7
Shader Model
6.6
