NVIDIA Tesla K20X vs NVIDIA GRID A100B
We compared two Professional market GPUs: 6GB VRAM Tesla K20X and 48GB VRAM GRID A100B 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 400W)
NVIDIA GRID A100B 's Advantages
Released 7 years and 6 months late
Boost Clock1005MHz
More VRAM (48GB vs 6GB)
Larger VRAM bandwidth (1866GB/s vs 249.6GB/s)
4224 additional rendering cores
Score
Benchmark
FP32 (float)
Tesla K20X
3.935 TFLOPS
GRID A100B
+252%
13.89 TFLOPS
Graphics Card
Nov 2012
Release Date
May 2020
Tesla
Generation
GRID
Professional
Type
Professional
PCIe 3.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
-
Base Clock
900 MHz
-
Boost Clock
1005 MHz
1300 MHz
Memory Clock
1215 MHz
Memory
6GB
Memory Size
48GB
GDDR5
Memory Type
HBM2e
384bit
Memory Bus
6144bit
249.6GB/s
Bandwidth
1866GB/s
Render Config
-
-
-
-
SM Count
108
2688
Shading Units
6912
224
TMUs
432
48
ROPs
192
-
Tensor Cores
432
-
-
-
16 KB (per SMX)
L1 Cache
192 KB (per SM)
1536 KB
L2 Cache
48 MB
-
-
-
Theoretical Performance
40.99 GPixel/s
Pixel Rate
193.0 GPixel/s
164.0 GTexel/s
Texture Rate
434.2 GTexel/s
-
FP16 (half)
55.57 TFLOPS
3.935 TFLOPS
FP32 (float)
13.89 TFLOPS
1312 GFLOPS
FP64 (double)
6.947 TFLOPS
Board Design
235W
TDP
400W
550 W
Suggested PSU
800 W
No outputs
Outputs
No outputs
1x 6-pin + 1x 8-pin
Power Connectors
None
Graphics Processor
GK110
GPU Name
GA100
-
-
-
Kepler
Architecture
Ampere
TSMC
Foundry
TSMC
28 nm
Process Size
7 nm
7.08 billion
Transistors
54.2 billion
561 mm²
Die Size
826 mm²
Graphics Features
12 (11_0)
DirectX
N/A
4.6
OpenGL
N/A
3.0
OpenCL
3.0
1.1
Vulkan
N/A
3.5
CUDA
8.0
5.1
Shader Model
N/A
