2 \defgroup SimGrid_API SimGrid modules */
4 /** \defgroup XBT_API XBT
6 \brief The core toolbox of SimGrid, containing usefull datatypes,
7 portability support and so on.
11 /** \defgroup SURF_API SURF
13 \brief Kernel of all the simulators used in SimGrid, and associated models.
15 SURF provides the core functionnalities to simulate a virtual
16 platform. It is very low-level and is not intended to be used as
17 such but rather to serve as a basis for higher-level simulators.
18 We're still working on it and the structure is a little bit
21 It is where platform models are encoded. If you need a model that is not
22 encoded yet, please tell me (<arnaud.legrand@imag.fr>) and we'll
23 see if it is feasible or not (hopefully it should be but who knows).
25 Please note that as it is not really intended for public use,
26 this module is only partially documented.
29 /** \defgroup MSG_API MSG
31 \brief Simple programming environment
33 MSG was the first distributed programming environment provided within
34 SimGrid. While almost realistic, it remains quite simple (simplistic?).
36 \section MSG_who Who should use this (and who shouldn't)
38 You should use this module if you want to study some heuristics for a
39 given problem you don't really want to implement.
40 If you want to use DAGs, have a look at the \ref SD_API programming
42 If you want to get a real (but experimental) implementation of your solution, have a look
43 at the \ref GRAS_API one. If you want to study an existing MPI program,
44 have a look at the \ref SMPI_API one. If none of those programming
45 environments fits your needs, you may consider implementing your own
46 directly on top of \ref SURF_API (but you probably want to contact us
51 /** \defgroup GRAS_API GRAS
53 \brief Realistic programming environment (Grid Reality And Simulation)
55 GRAS provides a complete API to implement distributed application on top
56 of heterogeneous plateforms. In addition to the SimGrid implementation
57 of this interface (allowing you to work on your application within the
58 comfort of the simulator), an implementation suited to real platforms is
59 also provided (allowing you to really use your application once you're
60 done with developing it). It may still contain rought corners as
61 GRAS is not the most used part of SimGrid, however.
63 GRAS thus constitute a complete grid application developement framework,
64 encompassing both developer helping tools (the simulator and associated
65 tools) and an efficient while portable execution runtime.
67 \section GRAS_who Who should use this (and who shouldn't)
69 You should use this programming environment if you want to develop real
70 applications, ie if the final result of your work is a program which
71 may eventually be distributed. Rember however that GRAS is
72 considered as experimental at this point. Help would be welcomed
73 to improve this sorry situation...
75 If you just want to study some heuristics for a given problem you don't
76 want to implement really (ie, if your result would be a theorem), have a
77 look at the \ref MSG_API one, or the \ref SD_API one if you need to use DAGs.
78 If you want to study an existing MPI program, have a look at the
80 If none of those programming environments fits your needs, you may
81 consider implementing your own directly on top of \ref SURF_API (but you
82 probably want to contact us before).
85 /** \defgroup AMOK_API AMOK
87 \brief Distributed toolkit built over \ref GRAS_API (Advanced Metacomputing Overlay Kit)
89 AMOK provides several tools useful to most applications built on top of GRAS,
90 but yet not belonging to GRAS itself. It is planned that those modules will be
91 changed to real plugins one day, allowing users to load only the needed parts at
92 run time. For now, they live in another library against which you should link your
96 /** \defgroup SMPI_API SMPI
98 \brief Programming environment for the simulation of MPI applications
100 Once implemented, this programming environment will allow you to study
101 within the simulator any MPI application without having to modify them
102 for that. In other words, it will constitute an emulation solution for
105 \section SMPI_who Who should use this (and who shouldn't)
107 You should use this programming environment of the SimGrid suite if you
108 want to study existing MPI applications.
109 If you want to work on a distributed application, have a look at the
110 \ref GRAS_API environment.
111 If you want to study some heuristics for a given problem (and if your
112 goal is to produce theorems, not code), have a look at the \ref MSG_API
113 environment, or the \ref SD_API one if you need to use DAGs.
114 If none of those programming environments fits your needs, you may
115 consider implementing your own directly on top of \ref SURF_API (but you
116 probably want to contact us before).
121 /** \defgroup SD_API SimDag
123 \brief Programming environment for DAG applications
125 SimDag provides some functionnalities to simulate parallel task scheduling
126 with DAGs models (Direct Acyclic Graphs).
127 The old versions of SimGrid were based on DAGs. But the DAG part (named SG)
128 was removed in SimGrid 3 because the new kernel (\ref SURF_API) was implemented. \ref SURF_API
129 was much faster and more flexible than SG and did not use DAGs.
130 SimDag is a new implementation of DAGs handling and it is built on top of \ref SURF_API.
132 \section SD_who Who should use this (and who shouldn't)
134 You should use this programming environment of the SimGrid suite if you want
135 to study algorithms and heuristics with DAGs of parallel tasks.
136 If you don't need to use DAGs for your simulation, have a look at the
137 \ref MSG_API programming environment.
138 If you want to implement a real distributed application, have a look at the
139 \ref GRAS_API programming environment.
140 If you want to study an existing MPI program, have a look at the
142 If none of those programming environments fits your needs, you may
143 consider implementing your own directly on top of \ref SURF_API (but you
144 probably want to contact us before).