ruisongzhou / cachemiss-simulation Goto Github PK
View Code? Open in Web Editor NEWThis project forked from jaycool/cachemiss-simulation
Cache Miss Simulator (NetBeans Project)
This project forked from jaycool/cachemiss-simulation
Cache Miss Simulator (NetBeans Project)
Cache Miss Simulator for Tree Structured Architecture This project implments a tree-structured cache simulator with the support of the following features: 1. Cache replacement policies: LRU, FIFO, Random, ARC, LRFU, Batch Recyle Cache (HDD, SSD). 2. Various Object Size: The objects are allowed to be of various size, not restricted to unique object size. 3. Flexible Cache Architecture: The user can specify the architecture of the caches. 4. Various Workload Generator: Uniform access, Zipf Access, B-C Access. 5. Various Cache Operations: LCE, MCD, MCD. 6. Flexibility of defining warming files for each cache. 7. Flexibility of defining processing time, and latency. ================================ 1. TO GENERATE SOME WORKLOADS: ================================ java -jar CacheMissSimulator.jar -usage 1 -config workload-configuration.json The above command has two arguments, -usage 1: generate workload, and -config: configuration file location workload-configuration.json is a JSON file which specifies the workload. { "clients" : [ {"id" : 0, "workloadType": 1, "workLoadLength" : 10000, "distinctObject": 1000}, {"id" : 1, "workloadType": 2, "workLoadLength" : 10000, "distinctObject": 1000, "b":"0.8", "c":"0.2"}, {"id" : 2, "workloadType": 3, "workLoadLength" : 10000, "distinctObject": 1000, "a":"0.1"} ], "outputDir" : "workload-dir/" } The above configuration file says that generate THREE workloads, and output to "workload-dir/" The first workload is a UNIFORM access workload, there are total 10000 objects, and there are 1000 distinct objects. The second workload is a B-C access workload, there are total 10000 objects, and there are 1000 distinct objects. The third workload is a ZIPF access workload, there are total 10000 objects, and there are 1000 distinct objects. ================================ 2. TO SIMULATE THE CACHE MISSES: ================================ java -jar CacheMissSimulator.jar -usage 2 -config simulation-configuration.json The above command has two arguments, -usage 2: simulate cache miss, and -config: configuration file location { "clients": [ {"id": "0", "cacheSize": "500", "cacheType": "6", "inputWorkloadAddress": "workload-dir/0.txt", "parent": "4"}, {"id": "1", "cacheSize": "500", "cacheType": "4", "inputWorkloadAddress": "workload-dir/0.txt", "parent": "4"}, {"id": "2", "cacheSize": "500", "cacheType": "1", "inputWorkloadAddress": "workload-dir/1.txt", "parent": "5"}, {"id": "3", "cacheSize": "500", "cacheType": "3", "inputWorkloadAddress": "workload-dir/2.txt", "parent": "5"}, {"id": "4", "cacheSize": "500", "cacheType": "3"}, {"id": "5", "cacheSize": "500", "cacheType": "3"} ] } There are 6 caches in total. cache 0, cache 1, cache 2, cache 3 are the first level cache. cache 4 is the second level cache, and it is connected to cache 0, cache 1. cache 5 is the second level cache, and it is connected to cache 2, cache 3. For caches without parent cache, we assume the cache is connected to the ROOT (contains everything). cacheType specifies the cachetype, for more details, refer to CacheType.java. ============================= 3. TO IMPLEMENT OWN CACHE: ============================= One must extends the Cache.java and implements the abstract method.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.