OmniX - an OS architecture for omni-programmable systems
Event details
| Date | 03.10.2019 |
| Hour | 16:15 › 17:15 |
| Speaker | Mark Silberstein, Associate Professor at the EE department at the Technion - Israel Institute of Technology |
| Location | |
| Category | Conferences - Seminars |
Abstract:. Future systems will be omni-programmable: alongside CPUs, GPUs, Security accelerators and FPGAs, they will execute user code near-storage, near-network, and near-memory. Ironically, while breaking power and memory walls via hardware specialization and near data processing, emerging programmability wall will become a key impediment for materializing the promised performance and power efficiency benefits of omni-programmable systems. I argue that the root cause of the programming complexity lies in todays CPU-centric operating system (OS) design which is no longer appropriate for omni-programmable systems.
In this talk I will describe the ongoing efforts in my lab to design an accelerator-centric OS called OmniX [HotOS'17], which extends standard OS abstractions into accelerators, while maintaining a coherent view of the system among all the processors. In OmniX, near-data and compute accelerators may directly invoke tasks and access I/O services among themselves, excluding the CPU from the performance-critical data and control plane operations, and turning it into a "yet another" accelerator for sequential computations. I will show how OmniX design principles have been successfully applied to GPUs, Programmable NICs and Intel SGX.
Bio: Mark Silberstein is an Associate Professor at the EE department at the Technion - Israel Institute of Technology where he is heading the Accelerated Computing Systems Lab. His research is centered around OSes for compute and I/O accelerator architectures, which led to several publications in ISCA, ASPLOS, OSDI, PACT, Eurosys and USENIX ATC, all of which strive to systematically minimize or eliminate the dependence of accelerated systems on the host CPU. He is working on practical ways to protect against side channels, in particular Intel SGX, though he was more successful at attacks at first and discovered the Foreshadow speculative execution bug. He is a regular contributor to the SIGARCH blog.
In this talk I will describe the ongoing efforts in my lab to design an accelerator-centric OS called OmniX [HotOS'17], which extends standard OS abstractions into accelerators, while maintaining a coherent view of the system among all the processors. In OmniX, near-data and compute accelerators may directly invoke tasks and access I/O services among themselves, excluding the CPU from the performance-critical data and control plane operations, and turning it into a "yet another" accelerator for sequential computations. I will show how OmniX design principles have been successfully applied to GPUs, Programmable NICs and Intel SGX.
Bio: Mark Silberstein is an Associate Professor at the EE department at the Technion - Israel Institute of Technology where he is heading the Accelerated Computing Systems Lab. His research is centered around OSes for compute and I/O accelerator architectures, which led to several publications in ISCA, ASPLOS, OSDI, PACT, Eurosys and USENIX ATC, all of which strive to systematically minimize or eliminate the dependence of accelerated systems on the host CPU. He is working on practical ways to protect against side channels, in particular Intel SGX, though he was more successful at attacks at first and discovered the Foreshadow speculative execution bug. He is a regular contributor to the SIGARCH blog.
Practical information
- Informed public
- Free
Organizer
- Babak Falsafi
Contact
- Stéphanie Baillargues