Vivante Corporation today announces that its GPU GraphiVisor solution will be featured in a white paper and sponsorship at the Jon Peddie Research Virtualize Conference. GraphiVisor is at the heart of solutions that must be both high-performance and secure, such as in Automotive applications, where feature-rich user experiences must exist in the same system as safety-critical functions with no tolerance for error or tampering. GraphiVisor will work alongside traditional security measures such as 2-step authentication, encryption and network security for truly secure systems in applications where some systems must be designed to have uninhibited, immediate access to the GPU and even a small error-margin is unacceptable, and a new level of hardware isolation is necessary. Vivante IP provides that option with two GPUs that can operate in isolation on one system.
Vivante is excited to be a part of the 2015 Virtualize Conference, with a best practices panel on virtualization options that will include Rick Tewell of Freescale Semiconductor, who heads the Graphics Architecture team for the i.MX product lines. Freescale has adopted Vivante's dual-GPU isolation technology in the i.MX6 Quad to allow one Microcontroller solution for multiple graphics applications that have varying requirements for safety and real-time performance.
"Vehicles are becoming increasingly reliant on high-tech systems for essential information and safety features, such as Advanced Driver Assistance Systems, while at the same time consumers demand increasingly impressive user interfaces that seamlessly interface with other user technology," said Wei-Jin Dai, CEO of Vivante Corporation. "GraphiVisor allows Vivante GPUs to maintain isolated, secure systems to satisfy both demands."
In Depth: two dual-GPU resource states
When the GPU is combined, so that all shader cores can operate in one context, the architecture has the full features of a dual-core GPU. When the GPU is virtualized, there is a secure Memory Management Unit (additional state bit) and secure bus interface with secure page tables that determines the type of surface and access patterns allowed. This allows the GPU core(s) to be virtualized across multiple OSes and applications and blocked off from each other. Secure transactions are allowed through a secure path and non-secure Read/Writes can go through the standard MMU and ACE-Lite/AXI interface. The whole process is strictly controlled by the platform and implemented in hardware.
For more information about virtualization and the 2015 Virtualize Conference, visit this page.
Recommended for You
Latest News Posts
- The first official pictures of Radeon RX Vega leaked
- AMD Vega 20 with 32GB of HBM2 teased with Vega 10/11/12
- Coolest thing you'll see today: 360° video from a rocket
- Intel hits record $14.8 billion second quarter earnings
- Battlegrounds on Xbox One X: 30-40FPS with 100 in server
- Fnatic Gear RUSH G1 Mechanical Gaming Keyboard Review
- Asrock A88M-G/3.1 + A10-7860K = freezes in the idle state
- ASUS GeForce GTX 1060 Dual 3G: Mid-Range On The Cheap
- AMD Ryzen 3 1300X and Ryzen 3 1200 CPU Review
- Lian-Li PC-O5SW...Watercooling and dimensions
- Toshiba introduces TR200 SATA retail SSD series with 64-layer 3D flash memory
- Need for Speed Payback takes cars from scrap to stock to supercar in new trailer
- Visbit releases Unity SDK and web VR player for its all-in-one VR streaming service, bringing high quality VR streaming to the masses
- GWENT Gamescom 2017 tournament announced
- Toshiba NVMe SSDs now available with Lenovo's new ThinkSystem and ThinkAgile servers