Change *PU to xPU
Add Ising exploration using Chessboard approach.
Adapt to Stretch Debian Distribution
Modification in order to execute Debian Stretch
Much efficient version.
device.type replacement
Cleaning process.
Improve distribution and Viriel verification.
Modified version of Runge Kutta
Integration of other methods of Differential solves.
Modify the initial conditions for speed.
Modify the "device.type" in order not to crash with POCL implementation.
Deeply modified version to match MESA implementation.
Add exploration of pow versions.
Add pragma for FP64
Add new option.
Add Kinetic & Potential.
Add FP64 choice.
Change default name of output.
Add Pi estimation.
Correct some errors on CUDA implementation.
Migration to Python 3.
Transform from Python 2 to Python 3
Suppress stdout messages and retreive computing time on master.
Suppress stdout messages on slaves and import elapsed on master.
Add asynchrone MPI communications under Hybrid MPI/OpenMP implementation.
Identation for XPU parsing.
Correct CUDA implementation.
Deep changes on memory use.
Change values on default execution.
Plot in 3D results.
First working version.
Minor changes.
Add broken version of NBody Runge Kutta resolution.
Minor changes
Add env python to launch.
Add input values, improve core, add metrology.
Remove test files.
For EPIDEVOMATH ANT Project
Improve MPI distribution.
Add MPI and pThreads version to use multiple OpenCL devices.
Add MPI version which support multi GPU.
Change structure of call for OpenCL Metropolis Routine
Internal modifications on statistics.
Changes on micmac global variables.
Minor change on doc.
Major evolution (statistics, etc).
First revision. Crash on hybrid.
Add hybrid version.
Change output for help.
Change default value of iterations.
Change default value.
Add global and local version.
Print the critical temperature before display the curve.
Add MPI version
Rename to Ising2D-Serial.py
Correct bug with NP=1
Licence definition. Change default type and RNG.
Minor changes on Maximum thread values.
Add granularity on variables types and Marsaglia RNG versions. Add licence
Add Cecill v2 licence on source code
Add granularity on variable types and Marsaglia RNG generators.
Minor change about check.
Extend granularity on size and Marsaglia RNG generators. Add both asynchrone and synchrone MPI calls.
Add granularity choice on type of counters and type of Marsaglia generator.
Support for Intel Xeon Phi
Replace synchrone to asynchrone MPI calls as in Hybrid version.
Replace synchrone to asynchrone MPI Send/Receive. At the beginning only to avoid distribution of tasksbut it was a problem on OpenIB (mlx4_core.log_mtts_per_seg=5 to add in GRUB)
Modify output to provide rates.
Convert CUDA implementation as OpenCL one.
Split MainLoop* by calls on one MainLoop
Add different Marsaglia RNG.
Minor modifications.
Add vendor print and strip output on device name.
Add print of Platform vendor on startup
Suppress extra explorations to keep only atomic ones...
Suppress function with no use.
Add Distributed splutter version with atomic version of increment.
Add Hybrid MPI/OpenMP version
Add CUDA version for Sparse a Dense exploration.
Add Sparse mode.
Correct size of allocation.
Add boundaries.
Add comment.
Remove log files.
Add Splutter version to test memory access and effenciency of RNG
Add hostname print. Correct bugs.
Exception add.
Add selection of platform/device under OpenCL
Clean clBLAS portion code.
Add clBLAS for OpenCL use.
Add Simple/Double precision in Kernels. Modify output to simplify import in CSV and GNUplot