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