Code Style Release Procedures
Building Building EXTRAS
Develop Branch v19.0.0.0 v20.0.0.0 v20.0.0.2 v20.0.0.3 v20.1.0.0 v20.1.0.1 v20.1.0.5 v21.0.0.0 v21.0.1.0 v21.1.0.0 v21.1.0.1 v21.1.0.2 v21.2.0.0 v21.2.1.0 v21.2.1.1 v22.0.0.0 v22.0.0.1 v22.1.0.0 v23.0.0.0 v23.0.0.1
Standard Library Overview Hello World Tutorial X86 Full-System Tutorial Developing Your Own Components Tutorial How To Create Your Own Board Using The gem5 Standard Library How to use local resources and data sources in gem5
Creating Disk Images Devices m5term Building Linux ARM Kernel Building Android Marshmallow Guest binaries
Ruby Cache Coherence Protocols Garnet 2.0 HeteroGarnet MOESI CMP directory Garnet Synthetic Traffic SLICC MI example Garnet standalone Interconnection network MOESI hammer MOESI CMP token MESI two level CHI Replacement Policies
SimpleCPU O3CPU TraceCPU Minor CPU Model Execution Basics Visualization
VEGA
Garnet Synthetic Traffic Ruby Random Tester
Trace-based Debugging Debugger-based Debugging Debugging Simulated Code Reporting Problems
Architecture Support ARM Implementation ISA Parser X86 microop ISA
Edit this page
authors: Jason Lowe-Power
last edited: 2024-04-16 17:50:15 +0000

Indexing Policies

Indexing policies determine the locations to which a block is mapped based on its address.

The most important methods of indexing policies are getPossibleEntries() and regenerateAddr():

For further information on Cache Indexing Policies, please refer to the wikipedia articles on Placement Policies and Associativity.

Set Associative

The set associative indexing policy is the standard for table-like structures, and can be further divided into Direct-Mapped (or 1-way set-associative), Set-Associative and Full-Associative (N-way set-associative, where N is the number of table entries).

A set associative cache can be seen as a skewed associative cache whose skewing function maps to the same value for every way.

Skewed Associative

The skewed associative indexing policy has a variable mapping based on a hash function, so a value x can be mapped to different sets, based on the way being used. Gem5 implements skewed caches as described in “Skewed-Associative Caches”, from Seznec et al.

Note that there are only a limited number of implemented hashing functions, so if the number of ways is higher than that number then a sub-optimal automatically generated hash function is used.