… This makes the packets appear as if they were directed to the … -processor for ADPCM (adaptive
pulse code modulation) acceleration, while the packet processor has a co-processor for …

… a directed acyclic … ) packets, our system can process packets at line-speed (100 Gbps) on
a single core that is half-idle. This makes it clear that the challenge is processing many packets …

… (1) Switching Unit The Switching Unit (SU) is a three-by-three packet switch which is an
element of a processor connected omega network. It switches data independently of and …

… Since a process might want to look at every packet on a … copies the packet for the application;
if it is false the packet is … (used by CSPF) and a directed acyclic control flow graph or CFG (…

… into a set of independent directed-cycle free … processor array, where for one packet per
processor injected into the network, a maximum buffering requirement was many tens of packets …

… To leverage this fact, we treat packet forwarding as a matching process, with all packets … to
process the same packet, which one gets it first? We believe that prior work on kernel packet fil…

… flit is an abbreviation for “flow control unit,” a fixed-size segment of a packet) crossing a link
by a … This process will be repeated at the next downstream router until the packet reaches its …

… packet switch distributes network control among small processors, referred to as interface
units, … It uses the address fields of each packet to provide routing information corresponding to …

… NetBind modifies the machine language code of components at run time, directing the …
from one processing unit to another (that takes place when a packet is being processed), ‘…

… packet buffer is attached to a packet processor, which is either an ASIC or network processor
that processes packets (… , it can be integrated into the packet processor (as shown in Fig. 1), …