AMD Radeon Instinct MI300X vs NVIDIA Tesla K20X
We compared two Professional market GPUs: 192GB VRAM Radeon Instinct MI300X and 6GB VRAM Tesla K20X to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
AMD Radeon Instinct MI300X 's Advantages
Released 11 years and 1 months late
Boost Clock2100MHz
More VRAM (192GB vs 6GB)
Larger VRAM bandwidth (5171GB/s vs 249.6GB/s)
16768 additional rendering cores
NVIDIA Tesla K20X 's Advantages
Lower TDP (235W vs 750W)
Score
Benchmark
FP32 (float)
Radeon Instinct MI300X
+1976%
81.72 TFLOPS
Tesla K20X
3.935 TFLOPS
Graphics Card
Dec 2023
Release Date
Nov 2012
Radeon Instinct
Generation
Tesla
Professional
Type
Professional
PCIe 5.0 x16
Bus Interface
PCIe 3.0 x16
Clock Speeds
1000 MHz
Base Clock
-
2100 MHz
Boost Clock
-
2525 MHz
Memory Clock
1300 MHz
Memory
192GB
Memory Size
6GB
HBM3
Memory Type
GDDR5
8192bit
Memory Bus
384bit
5171GB/s
Bandwidth
249.6GB/s
Render Config
304
Compute Units
-
-
-
-
19456
Shading Units
2688
1216
TMUs
224
0
ROPs
48
1216
Tensor Cores
-
-
-
-
16 KB (per CU)
L1 Cache
16 KB (per SMX)
16 MB
L2 Cache
1536 KB
256 MB
L3 Cache
-
Theoretical Performance
0 MPixel/s
Pixel Rate
40.99 GPixel/s
2554 GTexel/s
Texture Rate
164.0 GTexel/s
653.7 TFLOPS
FP16 (half)
-
81.72 TFLOPS
FP32 (float)
3.935 TFLOPS
81.72 TFLOPS
FP64 (double)
1312 GFLOPS
Board Design
750W
TDP
235W
1150 W
Suggested PSU
550 W
No outputs
Outputs
No outputs
None
Power Connectors
1x 6-pin + 1x 8-pin
Graphics Processor
Aqua Vanjaram
GPU Name
GK110
-
-
-
CDNA 3.0
Architecture
Kepler
TSMC
Foundry
TSMC
5 nm
Process Size
28 nm
153 billion
Transistors
7.08 billion
1017 mm²
Die Size
561 mm²
Graphics Features
N/A
DirectX
12 (11_0)
N/A
OpenGL
4.6
3.0
OpenCL
3.0
N/A
Vulkan
1.1
-
CUDA
3.5
N/A
Shader Model
5.1
