Skip to main content
NT

NETINT Technologies

NETINT Technologies develops Smart VPUs, specialized ASICs for ultra-high-density video encoding that enable a single 1RU server to process up to 160 broadcast-quality live streams while consuming significantly less power. This technology reduces total cost of ownership by over 90% compared to traditional CPU-based solutions, addressing the high operational expenses faced by video streaming platforms.

Vancouver, CanadaFounded 20151117K+ followers
Updated 4 months ago

Funding

Funding not disclosed

Funding rounds are not available yet.

Founders

Founder details are not available yet.

Product

Problem

High-volume video streaming platforms face significant operational expenses due to the power consumption and hardware requirements of traditional CPU-based video encoding solutions. These costs can make it difficult for streaming platforms to maintain profitability.

Solution

NETINT Technologies addresses this challenge with its Smart VPUs (Video Processing Units), which are application-specific integrated circuits (ASICs) designed for ultra-high-density video encoding. These VPUs enable a single 1RU server to process a large number of broadcast-quality live streams while significantly reducing power consumption compared to CPU-based solutions. By increasing encoding density without expanding rack footprint, NETINT's Smart VPUs cut streaming OPEX by over 80%. This allows video platforms to increase output and decrease expenses, achieving profitability without sacrificing video quality or latency. The VPUs are designed for easy drop-in replacement into enterprise-class NVMe servers, offering a simple upgrade path.

Target Audience

The primary customers are video streaming service platforms, cloud gaming providers, and CDN networks that require high-volume, low-latency video processing.

Features

  • ASIC-based architecture for high-efficiency video encoding and decoding
  • Support for multiple codecs including H.264, HEVC, JPEG, YUV, and AV1
  • Real-time encoding throughput up to 320x 1080p30, 80x 4Kp30, or 20x 8Kp30
  • Low latency of 8 ms
  • On-chip AI acceleration up to 150 TOPS for tasks like region of interest encoding, scene detection, and object detection
  • Compatibility with various operating systems and CPUs (x86 and ARM)
  • NVMe interface for universal operating system and kernel compatibility
  • Support for capped bitrate (CRF), flexible GOP, scaling, cropping, padding, and video overlay
This profile is AI-generated and may contain inaccuracies.