AI Accelerator Card SC7 FP300

The SC7 FP300 AI Accelerator Card is a full height, full length and dual slot PCIe Gen4 x16 card that provides 256T INT8 computing power, 128TFLOPS FP16/BF16 computing power, and 16TFLOPS FP32 computing power. The card supports mixed-precision computing.

256T INT8 Computing Power

128TFLOPS FP16/BF16 Computing Power

Supports Mixed Precision Calculations

256 Channels 25fps 1080P Video Hardware Decoding

96 Channels 25fps 1080P Video Hardware Encoding

Up to 8K Resolution of Video and Image Decoding

Adaptable to Various Servers

Adaptable to Different Operating Systems and Mainstream Algorithm Frameworks

Wide Range of Applications and Scenarios

The SC7 FP300 accelerator card has strong performance and can be adapted to various servers to form intelligent analysis clusters by stacking multiple boards. It can be applied in large-scale multi-channel AI computing and analysis to realize video auditing, video structuring, industrial visual inspection and analysis, etc.

Intelligent Cities
Intelligent Traffic
Intelligent Power
Intelligent Oil and Gas
Intelligent Communities
Intelligent Business Hall
Intelligent Manufacturing
Intelligent Storage
Internet

Easy-to-use, Convenient and Efficient

BMNNSDK (BITMAIN Neural Network SDK) one-stop toolkit provides a series of software tools including the underlying driver environment, compiler and inference deployment tool. The easy-to-use and convenient toolkit covers the model optimization, efficient runtime support and other capabilities required for neural network inference. It provides easy-to-use and efficient full-stack solutions for the development and deployment of deep learning applications. BMNNSDK minimizes the development cycle and cost of algorithms and software. Users can quickly deploy deep learning algorithms on various AI hardware products of SOPHGO to facilitate intelligent applications.

Support mainstream programming framework

More

Specifications

Features

AI Accelerator Card SC7 FP300

AI Computing Power

INT8
256 TOPS
FP16 BF16
128 TFLOPS
FP32
16 TFLOPS

Video/JPEG Codec

Video Decoding
H.264 & H.265: 1080p @6400fps
Resolution
7680*4320 / 8K / 4K / 1080P / 720p / D1 /CIF
Video Encoding
H.264 & H.265: 1080p @2400fps
Resolution
4K / 1080P / 720p / D1 /CIF
Image Decoding
JPEG: 3200 images/s @1080P(interleave off)
Max. Resolution
32768*32768

CPU

64-core ARM A53@2.3GHz

Memory

Standard
128GB LPDDR4x 1024bit 546GB/s

PCIe

Physical/Power Interface
PCIe Gen4 X16
Data Link
PCIe Gen4 X16

Power Consumption

Max
300W

Temperature

Range
0℃ ~ 55℃
Heat Dissipation
Passive

Size

Length*Height*Width
Full height, Full length, Double slot

Deep Learning Framework

TensorFlow / PyTorch / Paddle / Caffe / ONNX / MXNet / Tengine / DarkNet

Operation System Support

Ubuntu / CentOs / Debian / UOS / Kylino

Main CPU Support

Compatible with Intel / AMD / and other CPUs