Home GPU Comparison NVIDIA Tesla K80 vs NVIDIA A100 PCIe

NVIDIA Tesla K80 vs NVIDIA A100 PCIe

AI GPU We compared a Professional market GPU: 12GB VRAM Tesla K80 and a GPU: 40GB VRAM A100 PCIe to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.

Main Differences

NVIDIA A100 PCIe 's Advantages
Released 5 years and 7 months late
Boost Clock has increased by 71% (1410MHz vs 824MHz)
More VRAM (40GB vs 12GB)
Larger VRAM bandwidth (1555GB/s vs 240.6GB/s)
4416 additional rendering cores
Lower TDP (250W vs 300W)

Score

Benchmark

FP32 (float)
Tesla K80
4.113 TFLOPS
A100 PCIe +373%
19.49 TFLOPS
VS

Graphics Card

Nov 2014
Release Date
Jun 2020
Tesla
Generation
Tesla
Professional
Type
AI GPU
PCIe 3.0 x16
Bus Interface
PCIe 4.0 x16

Clock Speeds

562 MHz
Base Clock
765 MHz
824 MHz
Boost Clock
1410 MHz
1253 MHz
Memory Clock
1215 MHz

Memory

12GB
Memory Size
40GB
GDDR5
Memory Type
HBM2e
384bit
Memory Bus
5120bit
240.6GB/s
Bandwidth
1555GB/s

Render Config

-
SM Count
108
-
Compute Units
-
2496
Shading Units
6912
208
TMUs
432
48
ROPs
160
-
Tensor Cores
432
-
RT Cores
-
16 KB (per SMX)
L1 Cache
192 KB (per SM)
1536 KB
L2 Cache
40 MB

Theoretical Performance

42.85 GPixel/s
Pixel Rate
225.6 GPixel/s
171.4 GTexel/s
Texture Rate
609.1 GTexel/s
-
FP16 (half)
77.97 TFLOPS
4.113 TFLOPS
FP32 (float)
19.49 TFLOPS
1371 GFLOPS
FP64 (double)
9.746 TFLOPS

Graphics Processor

GK210
GPU Name
GA100
GK210-885-A1
GPU Variant
-
Kepler 2.0
Architecture
Ampere
TSMC
Foundry
TSMC
28 nm
Process Size
7 nm
7.1 billion
Transistors
54.2 billion
561 mm²
Die Size
826 mm²

Board Design

300W
TDP
250W
700 W
Suggested PSU
600 W
No outputs
Outputs
No outputs
1x 8-pin
Power Connectors
8-pin EPS

Graphics Features

12 (11_1)
DirectX
N/A
4.6
OpenGL
N/A
3.0
OpenCL
3.0
1.1
Vulkan
N/A
3.7
CUDA
8.0
5.1
Shader Model
N/A

Related GPU Comparisons

© 2024 - TopCPU.net   Contact Us Privacy Policy