Subversion Repositories an-fpga-implementation-of-low-latency-noc-based-mpsoc

= SynFull Models

Several models are provided for you that have been generated based on ideal network traces as described in the paper.
These models are for a variety of PARSEC and SPLASH-2 benchmarks.
The model files themselves are in text format, so you can see the actual raw values that were modelled.
The code takes these values and converts them into probability distributions (with the exception of the Markov probability matrices). 

== Manually Changing Model Data

You can potentially change the values found in the model files to create your own custom model, however I have not experimented with this.
You should also be careful, as the traffic generator expects certain values for certain parts of the model.
I would be weary of changing the Markov probabilities, for example, but changing the volume distributions (e.g. WRITE_INJECTION) is probably harmless.

== Model Description

The model files are divided into several sections with different headers.
Simple headers act as name-value pairs, while complex headers have a BEGIN and END and usually identify some probability distribution.
A description for each of these headers can be found below.

=== Simple Headers

HIER_CLASSES:: The number of macro phases in the model file.
TIME_SPAN:: The number of cycles long each macro phase is.
MEMORY:: The memory the Markov chain supports (currently, only 1 is supported).
NUM_NODES:: The number of nodes in the simulation (i.e. sources and destinations).
NUM_CLASSES:: The number of micro phases for a given macro phase.
RESOLUTION:: The number of cycles long each micro phase is.

=== Complex Headers

HIER_BEGIN_ID:: The micro model for the given macro phase begins after this line.
HIER_MARKOV:: The transition probability matrix for macro phases (Markov Chain).
HIER_MARKOV_STEADY:: The Markov chain's steady state for macro phases.
MARKOV:: The transition probability matrix for micro phases (Markov Chain).
MARKOV_STEADY:: The Markov chain's steady state for micro phases (not used).
*_SPATIAL:: The spatial injection distribution (i.e. who injects) per message type.
*_FLOWS:: The flow injection distribution (i.e. destinations) per message type.
*_INJECTION:: The volume distributions per message type. Starts at zero.
FORWARD_PROB:: The probability a directory forwards a request.
FORWARD_FLOWS:: The flow injection distribution for forwarded requests.
INVALIDATE_PROB::       The volume distribution for invalidates at each message type.
INVALIDATE_FLOWS:: The flow injection distribution for invalidates at each directory.