NVIDIA Tesla K20X vs NVIDIA A10 PCIe
We compared two Professional market GPUs: 6GB VRAM Tesla K20X and 24GB VRAM A10 PCIe to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA A10 PCIe 's Advantages
Released 8 years and 5 months late
Boost Clock1695MHz
More VRAM (24GB vs 6GB)
Larger VRAM bandwidth (600.2GB/s vs 249.6GB/s)
6528 additional rendering cores
Lower TDP (150W vs 235W)
Score
Benchmark
FP32 (float)
Tesla K20X
3.935 TFLOPS
A10 PCIe
+693%
31.24 TFLOPS
Graphics Card
Nov 2012
Release Date
Apr 2021
Tesla
Generation
Tesla
Professional
Type
Professional
PCIe 3.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
-
Base Clock
885 MHz
-
Boost Clock
1695 MHz
1300 MHz
Memory Clock
1563 MHz
Memory
6GB
Memory Size
24GB
GDDR5
Memory Type
GDDR6
384bit
Memory Bus
384bit
249.6GB/s
Bandwidth
600.2GB/s
Render Config
-
-
-
-
SM Count
72
2688
Shading Units
9216
224
TMUs
288
48
ROPs
96
-
Tensor Cores
288
-
RT Cores
72
16 KB (per SMX)
L1 Cache
128 KB (per SM)
1536 KB
L2 Cache
6 MB
-
-
-
Theoretical Performance
40.99 GPixel/s
Pixel Rate
162.7 GPixel/s
164.0 GTexel/s
Texture Rate
488.2 GTexel/s
-
FP16 (half)
31.24 TFLOPS
3.935 TFLOPS
FP32 (float)
31.24 TFLOPS
1312 GFLOPS
FP64 (double)
976.3 GFLOPS
Board Design
235W
TDP
150W
550 W
Suggested PSU
450 W
No outputs
Outputs
No outputs
1x 6-pin + 1x 8-pin
Power Connectors
1x 8-pin
Graphics Processor
GK110
GPU Name
GA102
-
GPU Variant
GA102-890-A1
Kepler
Architecture
Ampere
TSMC
Foundry
Samsung
28 nm
Process Size
8 nm
7.08 billion
Transistors
28.3 billion
561 mm²
Die Size
628 mm²
Graphics Features
12 (11_0)
DirectX
12 Ultimate (12_2)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.1
Vulkan
1.3
3.5
CUDA
8.6
5.1
Shader Model
6.6
