BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY: On PCIe Performance - Rolf Neugebauer (Docker\, Inc)
DTSTART:20160317T150000Z
DTEND:20160317T160000Z
UID:TALK63075@talks.cam.ac.uk
CONTACT:Eiko Yoneki
DESCRIPTION:Providing network connectivity at 40Gb/s and above is challeng
 ing. The PCIe interface used by most 40G NICs is being pushed to the limit
  for small packets and the DMA engines have to sustain fairly high transac
 tion rates.  Host features such as a integrated (uncore) memory and PCIe c
 ontrollers and tighter integration of the PCIe root complex with the cache
  subsystem (e.g.\, Intel's DDIO) lead to non-uniform access to host memory
  for PCIe devices. IO-MMUs and their TLBs are also interposed into the dat
 a path\, potentially affecting performance.\n\nIn this talk\, we present a
  methodology and a set of PCIe micro-benchmarks which are designed to eval
 uate the impact of these technologies.  The micro-benchmarks are currently
  implemented on Netronome's NFP-3200\, NFP-4000\, and NFP-6000 series of n
 etwork cards and we present detailed data on the impact and the evolution 
 of above technologies over several generations of Intel processors and chi
 psets.  The methodology is more generally applicable and can be used to co
 mpare the performance of different DMA engines as well as evaluating diffe
 rent processor architectures.\n\nBio: Rolf is a Member of Technical Staff 
 at Docker Inc. Previously he was a Distinguished Engineer at Netronome whe
 re he led the driver team\, responsible for Linux and Windows network devi
 ce drivers as well as the corresponding firmware for Netronome's highly pr
 ogrammable 10-100Gb/s NICs.  He also worked on a transparent offload/accel
 eration prototype for Open vSwitch\, developed a domain specific language 
 used widely internally during silicon and system software development\, an
 d implemented the layer three (IP) control plane for a Next Generation Fir
 ewall product.  Previously he was a Researcher at Intel Research were he w
 as one the original authors of the Xen hypervisor and also led an internal
  project on IO virtualisation.  Rolf holds a PhD from the University of Gl
 asgow.  For his dissertation he applied theories of congestion pricing to 
 resource management in operating systems.
LOCATION:FW26\, Computer Laboratory\, William Gates Building
END:VEVENT
END:VCALENDAR