NVIDIA Tesla K20X vs AMD Radeon Instinct MI100
We compared two Professional market GPUs: 6GB VRAM Tesla K20X and 32GB VRAM Radeon Instinct MI100 to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA Tesla K20X 's Advantages
Lower TDP (235W vs 300W)
AMD Radeon Instinct MI100 's Advantages
Released 8 years late
Boost Clock1502MHz
More VRAM (32GB vs 6GB)
Larger VRAM bandwidth (1229GB/s vs 249.6GB/s)
4992 additional rendering cores
Score
Benchmark
FP32 (float)
Tesla K20X
3.935 TFLOPS
Radeon Instinct MI100
+486%
23.07 TFLOPS
Graphics Card
Nov 2012
Release Date
Nov 2020
Tesla
Generation
Radeon Instinct
Professional
Type
Professional
PCIe 3.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
-
Base Clock
1000 MHz
-
Boost Clock
1502 MHz
1300 MHz
Memory Clock
1200 MHz
Memory
6GB
Memory Size
32GB
GDDR5
Memory Type
HBM2
384bit
Memory Bus
4096bit
249.6GB/s
Bandwidth
1229GB/s
Render Config
-
Compute Units
120
-
-
-
2688
Shading Units
7680
224
TMUs
480
48
ROPs
64
-
-
-
-
-
-
16 KB (per SMX)
L1 Cache
16 KB (per CU)
1536 KB
L2 Cache
8 MB
-
-
-
Theoretical Performance
40.99 GPixel/s
Pixel Rate
96.13 GPixel/s
164.0 GTexel/s
Texture Rate
721.0 GTexel/s
-
FP16 (half)
184.6 TFLOPS
3.935 TFLOPS
FP32 (float)
23.07 TFLOPS
1312 GFLOPS
FP64 (double)
11.54 TFLOPS
Board Design
235W
TDP
300W
550 W
Suggested PSU
700 W
No outputs
Outputs
No outputs
1x 6-pin + 1x 8-pin
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
