NVIDIA Tesla K80 vs NVIDIA A100 SXM4 40 GB
GPU · Specs Compare
Graphics Card
Release Date
Nov 2014
May 2020
Generation
Tesla
Tesla Ampere
Type
Professional
AI GPU
Bus Interface
PCIe 3.0 x16
PCIe 4.0 x16
Clock Speeds
Base Clock
562 MHz
1095 MHz
Boost Clock
824 MHz
1410 MHz
Memory Clock
1253 MHz
1215 MHz
Memory
Memory Size
12GB
40GB
Memory Type
GDDR5
HBM2e
Memory Bus
384bit
5120bit
Bandwidth
240.6GB/s
1555GB/s
Render Config
Shading Units
2496
6912
TMUs
208
432
ROPs
48
160
L1 Cache
16 KB (per SMX)
192 KB (per SM)
L2 Cache
1536 KB
40 MB
SM Count
—
108
Tensor Cores
—
432
Theoretical Performance
Pixel Rate
42.85 GPixel/s
225.6 GPixel/s
Texture Rate
171.4 GTexel/s
609.1 GTexel/s
FP32 (float)
4.113 TFLOPS
19.49 TFLOPS
FP64 (double)
1371 GFLOPS
9.746 TFLOPS
FP16 (half)
—
77.97 TFLOPS
Graphics Processor
GPU Name
GK210
GA100
GPU Variant
GK210-885-A1
—
Architecture
Kepler 2.0
Ampere
Foundry
TSMC
TSMC
Process Size
28 nm
7 nm
Transistors
7.1 billion
54.2 billion
Die Size
561 mm²
826 mm²
Board Design
TDP
300W
400W
Suggested PSU
700 W
800 W
Outputs
No outputs
No outputs
Power Connectors
1x 8-pin
None
Graphics Features
DirectX
12 (11_1)
N/A
OpenGL
4.6
N/A
OpenCL
3.0
3.0
Vulkan
1.1
N/A
CUDA
3.7
8.0
Shader Model
5.1
N/A
Benchmark
Blender
—
2,186
▲ Specs Compare
Data sourced from official specifications and benchmark tests.