NVIDIA Quadro RTX 8000 vs NVIDIA Tesla K20s
We compared two Professional market GPUs: 48GB VRAM Quadro RTX 8000 and 5GB VRAM Tesla K20s to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA Quadro RTX 8000 's Advantages
Released 5 years and 6 months late
Boost Clock1770MHz
More VRAM (48GB vs 5GB)
Larger VRAM bandwidth (672.0GB/s vs 208.0GB/s)
2112 additional rendering cores
NVIDIA Tesla K20s 's Advantages
Lower TDP (225W vs 260W)
Score
Benchmark
FP32 (float)
Quadro RTX 8000
+468%
16.31 TFLOPS
Tesla K20s
2.87 TFLOPS
Graphics Card
Aug 2018
Release Date
Feb 2013
Quadro
Generation
Tesla
Professional
Type
Professional
PCIe 3.0 x16
Bus Interface
PCIe 2.0 x16
Clock Speeds
1395 MHz
Base Clock
-
1770 MHz
Boost Clock
-
1750 MHz
Memory Clock
1300 MHz
Memory
48GB
Memory Size
5GB
GDDR6
Memory Type
GDDR5
384bit
Memory Bus
320bit
672.0GB/s
Bandwidth
208.0GB/s
Render Config
-
-
-
72
SM Count
-
4608
Shading Units
2496
288
TMUs
208
96
ROPs
40
576
Tensor Cores
-
72
RT Cores
-
64 KB (per SM)
L1 Cache
16 KB (per SMX)
6 MB
L2 Cache
1280 KB
-
-
-
Theoretical Performance
169.9 GPixel/s
Pixel Rate
29.90 GPixel/s
509.8 GTexel/s
Texture Rate
119.6 GTexel/s
32.62 TFLOPS
FP16 (half)
-
16.31 TFLOPS
FP32 (float)
2.870 TFLOPS
509.8 GFLOPS
FP64 (double)
956.8 GFLOPS
Board Design
260W
TDP
225W
600 W
Suggested PSU
550 W
4x DisplayPort 1.4a
1x USB Type-C
Outputs
No outputs
1x 6-pin + 1x 8-pin
Power Connectors
-
Graphics Processor
TU102
GPU Name
GK110
TU102-875-A1
GPU Variant
-
Turing
Architecture
Kepler
TSMC
Foundry
TSMC
12 nm
Process Size
28 nm
18.6 billion
Transistors
7.08 billion
754 mm²
Die Size
561 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 (11_0)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.3
Vulkan
1.1
7.5
CUDA
3.5
6.6
Shader Model
5.1
