Movatterモバイル変換


[0]ホーム

URL:


Report an Error

NVIDIA GRID A100B

Graphics Processor
GA100
Cores
6912
TMUs
432
ROPs
192
Memory Size
48 GB
Memory Type
HBM2e
Bus Width
6144 bit
GPU Chip
GPU Chip
GPU
Placeholders or estimates used where official details are unavailable
(specs unknown)
The GRID A100B was a professional graphics card by NVIDIA, launched on May 14th, 2020. Built on the 7 nm process, and based on the GA100 graphics processor, the card does not support DirectX. Since GRID A100B does not support DirectX 11 or DirectX 12, it might not be able to run all the latest games. The GA100 graphics processor is a large chip with a die area of 826 mm² and 54,200 million transistors. It features 6912 shading units, 432 texture mapping units, and 192 ROPs. Also included are 432 tensor cores which help improve the speed of machine learning applications. NVIDIA has paired 48 GB HBM2e memory with the GRID A100B, which are connected using a 6144-bit memory interface. The GPU is operating at a frequency of 900 MHz, which can be boosted up to 1005 MHz, memory is running at 1215 MHz.
Its power draw is rated at 400 W maximum. This device has no display connectivity, as it is not designed to have monitors connected to it. GRID A100B is connected to the rest of the system using a PCI-Express 4.0 x16 interface.

Graphics Processor

GPU Name
GA100
Architecture
Ampere
Foundry
TSMC
Process Size
7 nm
Transistors
54,200 million
Density
65.6M / mm²
Die Size
826 mm²
Chip Package
BGA-2743

Graphics Card

Release Date
May 14th, 2020
Generation
GRID
(Ax)
Production
End-of-life
Driver Support
Active
Bus Interface
PCIe 4.0 x16

Relative Performance

GRID A100B
100%
Based on TPU review data: "Performance Summary" at 1920x1080, 4K for RTX 3080 and faster.
Performance estimated based on architecture, shader count and clocks.

Clock Speeds

Base Clock
900 MHz
Boost Clock
1005 MHz
Memory Clock
1215 MHz
2.4 Gbps effective

Memory

Memory Size
48 GB
Memory Type
HBM2e
Memory Bus
6144 bit
Bandwidth
1.87 TB/s

Render Config

Shading Units
6912
TMUs
432
ROPs
192
SM Count
108
Tensor Cores
432
L1 Cache
192 KB (per SM)
L2 Cache
48 MB

Theoretical Performance

Pixel Rate
193.0 GPixel/s
Texture Rate
434.2 GTexel/s
FP16 (half)
55.57 TFLOPS(4:1)
FP32 (float)
13.89 TFLOPS
FP64 (double)
6.947 TFLOPS(1:2)

Board Design

Slot Width
IGP
TDP
400 W
Suggested PSU
800 W
Outputs
No outputs
Power Connectors
None

Graphics Features

DirectX
N/A
OpenGL
N/A
OpenCL
3.0
Vulkan
N/A
CUDA
8.0
Shader Model
N/A

GA100 GPU Notes

Tensor Cores: 3rd Gen
NVENC: No Support
NVDEC: 4th Gen x5
PureVideo HD: VP10
VDPAU: Feature Set J

Latest Drivers:
Windows 10 / 11 (x64):
Quadro Release: Latest
Data Center Release: Latest
Nov 29th, 2025 16:05 JSTchange timezone
Sign in /Register

Latest GPU Drivers

New Forum Posts

Popular Reviews

TPU on YouTube

Controversial News Posts


[8]ページ先頭

©2009-2025 Movatter.jp