Intel Data Center GPU Max Subsystem vs NVIDIA Tesla K20m
We compared two Professional market GPUs: 128GB VRAM Data Center GPU Max Subsystem and 5GB VRAM Tesla K20m to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
Intel Data Center GPU Max Subsystem 's Advantages
Released 10 years late
Boost Clock1600MHz
More VRAM (128GB vs 5GB)
Larger VRAM bandwidth (3205GB/s vs 208.0GB/s)
13888 additional rendering cores
NVIDIA Tesla K20m 's Advantages
Lower TDP (225W vs 2400W)
Score
Benchmark
FP32 (float)
Data Center GPU Max Subsystem
+1387%
52.43 TFLOPS
Tesla K20m
3.524 TFLOPS
Graphics Card
Jan 2023
Release Date
Jan 2013
Data Center GPU
Generation
Tesla
Professional
Type
Professional
PCIe 5.0 x16
Bus Interface
PCIe 2.0 x16
Clock Speeds
900 MHz
Base Clock
-
1600 MHz
Boost Clock
-
1565 MHz
Memory Clock
1300 MHz
Memory
128GB
Memory Size
5GB
HBM2e
Memory Type
GDDR5
8192bit
Memory Bus
320bit
3205GB/s
Bandwidth
208.0GB/s
Render Config
-
-
-
-
-
-
16384
Shading Units
2496
1024
TMUs
208
0
ROPs
40
1024
Tensor Cores
-
128
RT Cores
-
64 KB (per EU)
L1 Cache
16 KB (per SMX)
408 MB
L2 Cache
1280 KB
-
-
-
Theoretical Performance
0 MPixel/s
Pixel Rate
36.71 GPixel/s
1638 GTexel/s
Texture Rate
146.8 GTexel/s
52.43 TFLOPS
FP16 (half)
-
52.43 TFLOPS
FP32 (float)
3.524 TFLOPS
52.43 TFLOPS
FP64 (double)
1175 GFLOPS
Board Design
2400W
TDP
225W
2800 W
Suggested PSU
550 W
No outputs
Outputs
No outputs
1x 16-pin
Power Connectors
1x 6-pin + 1x 8-pin
Graphics Processor
Ponte Vecchio
GPU Name
GK110
-
-
-
Generation 12.5
Architecture
Kepler
Intel
Foundry
TSMC
10 nm
Process Size
28 nm
100 billion
Transistors
7.08 billion
1280 mm²
Die Size
561 mm²
Graphics Features
12 (12_1)
DirectX
12 (11_0)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
N/A
Vulkan
1.1
-
CUDA
3.5
6.6
Shader Model
5.1
