RaftLib is a portable parallel processing system that aims to provide extreme performance while increasing programmer productivity. It enables a programmer to assemble a massively parallel program (both local and distributed) using simple iostream-like operators. RaftLib handles threading, memory allocation, memory placement, and auto-parallelization of compute kernels. It enables applications to be constructed from chains of compute kernels forming a task and pipeline parallel compute graph. Programs are authored in C++ (although other language bindings are planned).
Example
Here is a Hello World example for demonstration purposes:3
#include <raft> #include <raftio> #include <cstdlib> #include <string> class hi : public raft::kernel { public: hi() : raft::kernel() { output.addPort< std::string >( "0" ); } virtual raft::kstatus run() { output[ "0" ].push( std::string( "Hello World\n" ) ); return( raft::stop ); } }; int main( int argc, char **argv ) { /** instantiate print kernel **/ raft::print< std::string > p; /** instantiate hello world kernel **/ hi hello; /** make a map object **/ raft::map m; /** add kernels to map, both hello and p are executed concurrently **/ m += hello >> p; /** execute the map **/ m.exe(); return( EXIT_SUCCESS ); }External links
- The RaftLib Project Page
- RaftLib User Wiki
- Project GitHub Repository
- CPPNow RaftLib Tutorial Session
- A Short Introduction to Stream Processing
- Parallel BZip2 Implementation Using RaftLib
References
"RaftLib: A C++ Template Library for High Performance Stream Parallel Processing" (PDF). Retrieved 2016-08-10. http://www.jonathanbeard.io/pdf/blc15.pdf ↩
"Online Modeling and Tuning of Parallel Stream Processing Systems" (PDF). Retrieved 2016-08-10. http://www.jonathanbeard.io//pdf/beard-thesis.pdf ↩
"Hello World Example". Retrieved 2016-08-10. http://raftlib.io ↩