NVIDIA GA100 Graphics Processing Unit (GPU)

Specs based on NVIDIA A100 SXM 80GB
Overview
Manufacturer
NVIDIA
Release Date
November 16th, 2020
Graphics Processing Unit
Architecture
Ampere
Fabrication Process
7 nm FinFET
Die Size
826 mm2
Transistors Count
54.2B
Transistors Density
65.6M TRAN/mm2
CUDAs (FP16)
27648
CUDAs (FP64)
3456
Tensor Cores
432
CUDAs
6912
SM
108
GPCs
7
TMUs
432
Clocks
Base Clock
1410 MHz
Memory Configuration
Memory Size
81920 MB
Memory Type
HBM2
Memory Bus Width
5120-bit
Memory Bandwidth
2,048.0 GB/s
Performance
Texture Fillrate
609.1 GTexel/s
SPFP Performance
19.5 TFLOPS
Performance per W
48.7 GFLOPS/W
Performance per mm2
23.6 GFLOPS/mm2
Physical
Interface
SXM 4.0
Typical Thermal Design Power
400 W
API Support
DirectX
12.2
Vulkan
1.2
OpenGL
4.6
OpenCL
2.1




 ModelGPU ModelUnified CoresBoost ClockMemory ClockMemory Config.
 NVIDIA HGX A100 (16-GPU) GA100
 
110592
 
1410 MHz
 
2 Gbps
 
10240 GB HB2 5120b
 NVIDIA DGX A100 GA100
 
55296
 
1410 MHz
 
2 Gbps
 
2560 GB HB2 5120b
 NVIDIA HGX A100 (8-GPU) GA100
 
55296
 
1410 MHz
 
2 Gbps
 
2560 GB HB2 5120b
 NVIDIA HGX A100 (4-GPU) GA100
 
27648
 
1410 MHz
 
2 Gbps
 
640 GB HB2 5120b
 NVIDIA A100 SXM 80GB GA100-884
 
6912
 
1410 MHz
 
3 Gbps
 
80 GB HB2 5120b
 NVIDIA A100 PCIe GA100
 
6912
 
1410 MHz
 
2 Gbps
 
40 GB HB2 5120b
 NVIDIA A100 SXM 40GB GA100-884
 
6912
 
1410 MHz
 
2 Gbps
 
40 GB HB2 5120b
 NVIDIA EGX A100 GA100 TBC TBC TBC TBC