Tesla K20s vs Radeon Instinct MI100
We compared two Professional market GPUs: 5GB VRAM Tesla K20s and 32GB VRAM Radeon Instinct MI100 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
Tesla K20s 's Advantages
Lower TDP (225W vs 300W)
Radeon Instinct MI100 's Advantages
Released 7 years and 9 months late
Boost Clock1502MHz
More VRAM (32GB vs 5GB)
Larger VRAM bandwidth (1229GB/s vs 208.0GB/s)
5184 additional rendering cores
Score
Benchmark
FP32 (float)
Tesla K20s
2870
Radeon Instinct MI100
+703%
23070
Graphics Card
Feb 2013
Release Date
Nov 2020
Tesla
Generation
Radeon Instinct
Professional
Type
Professional
PCIe 2.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
-
Base Clock
1000 MHz
-
Boost Clock
1502 MHz
1300 MHz
Memory Clock
1200 MHz
Memory
5GB
Memory Size
32GB
GDDR5
Memory Type
HBM2
320bit
Memory Bus
4096bit
208.0GB/s
Bandwidth
1229GB/s
Render Config
-
Compute Units
120
2496
Shading Units
7680
208
TMUs
480
40
ROPs
64
16 KB (per SMX)
L1 Cache
16 KB (per CU)
1280 KB
L2 Cache
8 MB
Theoretical Performance
29.90 GPixel/s
Pixel Rate
96.13 GPixel/s
119.6 GTexel/s
Texture Rate
721.0 GTexel/s
-
FP16 (half)
184.6 TFLOPS
2.870 TFLOPS
FP32 (float)
23.07 TFLOPS
956.8 GFLOPS
FP64 (double)
11.54 TFLOPS
Board Design
225W
TDP
300W
550 W
Suggested PSU
700 W
No outputs
Outputs
No outputs
-
Power Connectors
2x 8-pin
Graphics Processor
GK110
GPU Name
Arcturus
-
GPU Variant
Arcturus XL
Kepler
Architecture
CDNA 1.0
TSMC
Foundry
TSMC
28 nm
Process Size
7 nm
7.08 billion
Transistors
25.6 billion
561 mm²
Die Size
750 mm²
Graphics Features
12 (11_0)
DirectX
N/A
4.6
OpenGL
N/A
3.0
OpenCL
2.1
1.1
Vulkan
N/A
3.5
CUDA
-
5.1
Shader Model
N/A
