NVIDIA A100 SXM4 80 GB vs AMD Zhongshan Subor Z+ GPU
GPU Specs Compare
Graphics Card
Release Date
Nov 2020
Aug 2018
Generation
Tesla Ampere
Console GPU
Type
AI GPU
Game console
Bus Interface
PCIe 4.0 x16
-
Clock Speeds
Base Clock
1275 MHz
-
Boost Clock
1410 MHz
-
Memory Clock
1593 MHz
1200 MHz
Memory
Memory Size
80GB
8GB
Memory Type
HBM2e
GDDR5
Memory Bus
5120bit
256bit
Bandwidth
2039GB/s
153.6GB/s
Render Config
SM Count
108
-
Shading Units
6912
1536
TMUs
432
96
ROPs
160
32
Tensor Cores
432
-
L1 Cache
192 KB (per SM)
-
L2 Cache
40 MB
-
Compute Units
-
24
Theoretical Performance
Pixel Rate
225.6 GPixel/s
41.60 GPixel/s
Texture Rate
609.1 GTexel/s
124.8 GTexel/s
FP16 (half)
77.97 TFLOPS
7.987 TFLOPS
FP32 (float)
19.49 TFLOPS
3.994 TFLOPS
FP64 (double)
9.746 TFLOPS
249.6 GFLOPS
Graphics Processor
GPU Name
GA100
Fenghuang
Architecture
Ampere
GCN 5.0
Foundry
TSMC
TSMC
Process Size
7 nm
14 nm
Transistors
54.2 billion
Unknown
Die Size
826 mm²
397 mm²
GPU Variant
-
Zhongshan Subor
Board Design
TDP
400W
100W
Suggested PSU
800 W
-
Outputs
No outputs
No outputs
Power Connectors
None
-
Graphics Features
DirectX
N/A
12 (12_1)
OpenGL
N/A
4.6
OpenCL
3.0
2.1
Vulkan
N/A
1.2
CUDA
8.0
-
Shader Model
N/A
6.2