AMD Radeon Instinct MI6 vs NVIDIA Tesla K20X
We compared two Professional market GPUs: 8GB VRAM Radeon Instinct MI6 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 MI6 's Advantages
Released 4 years and 1 months late
Boost Clock1233MHz
More VRAM (8GB vs 6GB)
Lower TDP (150W vs 235W)
NVIDIA Tesla K20X 's Advantages
Larger VRAM bandwidth (249.6GB/s vs 224.0GB/s)
384 additional rendering cores
Score
Benchmark
FP32 (float)
Radeon Instinct MI6
+44%
5.682 TFLOPS
Tesla K20X
3.935 TFLOPS
Graphics Card
Dec 2016
Release Date
Nov 2012
Radeon Instinct
Generation
Tesla
Professional
Type
Professional
PCIe 3.0 x16
Bus Interface
PCIe 3.0 x16
Clock Speeds
1120 MHz
Base Clock
-
1233 MHz
Boost Clock
-
1750 MHz
Memory Clock
1300 MHz
Memory
8GB
Memory Size
6GB
GDDR5
Memory Type
GDDR5
256bit
Memory Bus
384bit
224.0GB/s
Bandwidth
249.6GB/s
Render Config
36
Compute Units
-
-
-
-
2304
Shading Units
2688
144
TMUs
224
32
ROPs
48
-
-
-
-
-
-
16 KB (per CU)
L1 Cache
16 KB (per SMX)
2 MB
L2 Cache
1536 KB
-
-
-
Theoretical Performance
39.46 GPixel/s
Pixel Rate
40.99 GPixel/s
177.6 GTexel/s
Texture Rate
164.0 GTexel/s
5.682 TFLOPS
FP16 (half)
-
5.682 TFLOPS
FP32 (float)
3.935 TFLOPS
355.1 GFLOPS
FP64 (double)
1312 GFLOPS
Board Design
150W
TDP
235W
450 W
Suggested PSU
550 W
No outputs
Outputs
No outputs
1x 6-pin
Power Connectors
1x 6-pin + 1x 8-pin
Graphics Processor
Ellesmere
GPU Name
GK110
Ellesmere XT
GPU Variant
-
GCN 4.0
Architecture
Kepler
GlobalFoundries
Foundry
TSMC
14 nm
Process Size
28 nm
5.7 billion
Transistors
7.08 billion
232 mm²
Die Size
561 mm²
Graphics Features
12 (12_0)
DirectX
12 (11_0)
4.6
OpenGL
4.6
2.1
OpenCL
3.0
1.2
Vulkan
1.1
-
CUDA
3.5
6.4
Shader Model
5.1
