Latency is the most critical performance factor in a system because latency directly affects system data exchange time
Latency means lost time; time that could have been spent more productively producing computational results, but it is instead spent waiting for the data
Latency is the “application stealth tax”, silently extending the elapsed times of individual computational tasks and processes, which then take longer to execute
A3Cube Hybrid Topology Fabric is a
“direct” network, therefore avoiding the need for external top-of-rack switches
It scales to a large number of nodes
It reduces the number of optical links required for
a given global bandwidth
It is based on many
small computing islands connected together using the shortest cabling possible
islands in an ultra short diameter network
A high-radix router is partitioned into
2/3 classes of links.
These classes are used to create two main
(Computing-Island) links (or local links)
The Inter-group links
can be divided into first level and second level.
The group is a collection of computing
nodes directly connected to the router that creates what we call “Computing
Low-cost electrical links are used to
connect the NICs in each PE to their local router and the routers in a group
The maximum group
is governed by the partitioning of the Routers
The first level of group
copper cables, the second level in most cases uses optical cables.
Each router provides both “intra-group”
that connect it to other computing nodes in its group and “inter-group”
known as global links)
that connect it to other groups. The router in a group pools its inter-group
links, enabling each group to be directly connected to all the other groups.