Statistics
| Revision:

root / Pi @ 183

# Date Author Comment
183 10/07/2018 12:11 pm Emmanuel Quemener

Add OpenACC with PGI compiler for Nvidia GPUs

182 06/28/2018 02:22 pm Emmanuel Quemener

Correct to compile.

181 06/11/2018 04:35 am Emmanuel Quemener

Add -k option to perform classical test based on if.

177 04/01/2018 12:02 pm Emmanuel Quemener

Correct CUDA call with direct ccbin compiler call (clang compiles but gcc over 5 not...)

174 03/21/2018 02:29 pm Emmanuel Quemener

Add comments on top of source files.

159 02/03/2018 11:07 am Emmanuel Quemener

Tiny changes.

158 02/03/2018 05:15 am Emmanuel Quemener

Wrong cast in FP64 subroutine.

157 01/25/2018 11:03 am Emmanuel Quemener

Replace *PU by xPU to avoid prolems on files.

156 01/21/2018 06:02 am Emmanuel Quemener

Add INT32, INT64, FP64 possibilities.

154 11/11/2017 03:47 am Emmanuel Quemener

Add granularity on variables and Marsaglia RNG.

153 10/13/2017 11:39 am Emmanuel Quemener

Correct tiny bug on metrology estimation.

152 09/27/2017 11:25 pm Emmanuel Quemener

Add C/OpenCL implementation.

143 10/17/2016 10:42 pm Emmanuel Quemener

Cleaning process.

138 09/29/2016 11:35 am Emmanuel Quemener

Modify the "device.type" in order not to crash with POCL implementation.

131 05/09/2016 03:45 pm Emmanuel Quemener

Change default name of output.

130 05/09/2016 02:30 pm Emmanuel Quemener

Add Pi estimation.

129 03/14/2016 10:27 pm Emmanuel Quemener

Correct some errors on CUDA implementation.

127 03/03/2016 01:22 pm Emmanuel Quemener

Transform from Python 2 to Python 3

126 03/03/2016 10:12 am Emmanuel Quemener

Suppress stdout messages and retreive computing time on master.

125 03/02/2016 03:28 pm Emmanuel Quemener

Suppress stdout messages on slaves and import elapsed on master.

124 02/05/2016 11:58 am Emmanuel Quemener

Add asynchrone MPI communications under Hybrid MPI/OpenMP implementation.

123 01/21/2016 09:38 am Emmanuel Quemener

Identation for XPU parsing.

122 01/06/2016 05:26 pm Emmanuel Quemener

Correct CUDA implementation.

108 11/18/2015 04:03 pm Emmanuel Quemener

Improve MPI distribution.

107 11/09/2015 01:28 pm Emmanuel Quemener

Add MPI and pThreads version to use multiple OpenCL devices.

106 11/07/2015 09:48 pm Emmanuel Quemener

Add MPI version which support multi GPU.

105 11/06/2015 10:38 pm Emmanuel Quemener

Change structure of call for OpenCL Metropolis Routine

104 11/05/2015 10:08 pm Emmanuel Quemener

Internal modifications on statistics.

103 10/31/2015 04:07 am Emmanuel Quemener

Changes on micmac global variables.

102 10/31/2015 03:14 am Emmanuel Quemener

Minor change on doc.

101 10/22/2015 06:37 am Emmanuel Quemener

Major evolution (statistics, etc).

100 10/21/2015 06:37 am Emmanuel Quemener

First revision. Crash on hybrid.

99 10/20/2015 06:22 am Emmanuel Quemener

Add hybrid version.

87 03/27/2015 05:16 pm Emmanuel Quemener

Correct bug with NP=1

86 03/12/2015 03:55 pm Emmanuel Quemener

Licence definition. Change default type and RNG.

85 03/12/2015 11:20 am Emmanuel Quemener

Minor changes on Maximum thread values.

84 03/09/2015 01:58 pm Emmanuel Quemener

Add granularity on variables types and Marsaglia RNG versions. Add licence

83 03/09/2015 01:51 pm Emmanuel Quemener

Add Cecill v2 licence on source code

82 03/04/2015 09:52 am Emmanuel Quemener

Add granularity on variable types and Marsaglia RNG generators.

81 03/04/2015 09:51 am Emmanuel Quemener

Minor change about check.

80 03/04/2015 09:40 am Emmanuel Quemener

Extend granularity on size and Marsaglia RNG generators. Add both asynchrone and synchrone MPI calls.

79 03/03/2015 02:53 pm Emmanuel Quemener

Add granularity choice on type of counters and type of Marsaglia generator.

78 02/06/2015 06:41 pm Emmanuel Quemener

Support for Intel Xeon Phi

77 12/05/2014 06:23 pm Emmanuel Quemener

Replace synchrone to asynchrone MPI calls as in Hybrid version.

76 12/05/2014 06:22 pm Emmanuel Quemener

Replace synchrone to asynchrone MPI Send/Receive. At the beginning only to avoid distribution of tasks
but it was a problem on OpenIB (mlx4_core.log_mtts_per_seg=5 to add in GRUB)

75 11/26/2014 06:04 pm Emmanuel Quemener

Modify output to provide rates.

74 11/23/2014 05:33 pm Emmanuel Quemener

Convert CUDA implementation as OpenCL one.

73 11/23/2014 04:16 pm Emmanuel Quemener

Split MainLoop* by calls on one MainLoop

72 11/22/2014 12:28 am Emmanuel Quemener

Add different Marsaglia RNG.

71 11/17/2014 02:56 pm Emmanuel Quemener

Minor modifications.

70 10/09/2014 05:22 pm Emmanuel Quemener

Add vendor print and strip output on device name.

65 06/24/2014 05:42 pm Emmanuel Quemener

Minor changes

64 06/22/2014 12:35 am Emmanuel Quemener

Add Hybrid MPI/OpenMP version

59 05/15/2014 04:57 pm Emmanuel Quemener

Add comment.

56 05/06/2014 11:06 am Emmanuel Quemener

Add hostname print. Correct bugs.

55 03/26/2014 05:47 pm Emmanuel Quemener

Exception add.

50 02/26/2014 11:07 am Emmanuel Quemener

Add Simple/Double precision in Kernels. Modify output to simplify import in CSV and GNUplot

49 02/10/2014 04:09 pm Emmanuel Quemener

Change Pi estimation from global division to atomic division.

48 02/10/2014 11:30 am Emmanuel Quemener

Add Xeon Phi support for ACCELERATOR type

47 12/04/2013 11:25 am Emmanuel Quemener

Improved version.

46 10/15/2013 10:10 am Emmanuel Quemener

Changes on Device selection and metrology statements.

45 10/15/2013 07:23 am Emmanuel Quemener

Minor changes on output filename.

42 09/30/2013 11:29 am Emmanuel Quemener

Minor changes.

41 09/30/2013 09:14 am Emmanuel Quemener

Change size of iterations variables (in functions)...

40 09/30/2013 09:12 am Emmanuel Quemener

Change size of Iterations variable.

39 09/30/2013 07:27 am Emmanuel Quemener

Minor changes on default values for bench.

38 09/30/2013 05:54 am Emmanuel Quemener

Change minor bug.

37 09/30/2013 05:53 am Emmanuel Quemener

Change minor bug.

36 09/30/2013 05:52 am Emmanuel Quemener

Change optimization to O3.

35 09/30/2013 05:46 am Emmanuel Quemener

Change to O3 optimization.

34 09/30/2013 05:45 am Emmanuel Quemener

Change to O3 optimization.

33 09/30/2013 05:43 am Emmanuel Quemener

Change name of executable.

32 09/30/2013 05:43 am Emmanuel Quemener

Change name of executable.

31 09/29/2013 08:53 pm Emmanuel Quemener

Change atol to atoll to support long long

30 09/29/2013 08:53 pm Emmanuel Quemener

Minor changes.

29 09/29/2013 08:47 pm Emmanuel Quemener

Add architecture information. Add better support on 32bits architecture

28 09/29/2013 08:35 pm Emmanuel Quemener

Minor changes on output information about architecture.

27 09/23/2013 12:00 am Emmanuel Quemener

Minor changes.

26 09/22/2013 11:58 am Emmanuel Quemener

Change unsigned long to long long for 32 bits compatibility.

25 09/21/2013 02:06 pm Emmanuel Quemener

Add support for 32 bits and large number of iterations (use of long long int)

24 09/18/2013 12:22 am Emmanuel Quemener

Delete executable

23 09/18/2013 12:21 am Emmanuel Quemener

Changes to support long (over 2^32 iterations)

22 09/04/2013 06:18 am Emmanuel Quemener

Add script to reduce GProf output to show source code lines.

21 09/04/2013 06:15 am Emmanuel Quemener

Merge INT and LOG elements.
Add sqrt and classical test on quadrant.

20 09/04/2013 06:14 am Emmanuel Quemener
17 06/05/2013 02:36 pm Emmanuel Quemener

Improve choice of GPU/CPU.

16 04/08/2013 12:02 pm Emmanuel Quemener

Modify randint call domain for 32 bits machines.

15 04/08/2013 11:10 am Emmanuel Quemener

Add jobs mention in output process.

14 04/03/2013 05:02 pm Emmanuel Quemener

Delete executables.

13 04/03/2013 05:01 pm Emmanuel Quemener

Modify bench to specify OMP_NUM_THREADS, needed on ARM architecture

12 04/01/2013 09:21 pm Emmanuel Quemener

Add Pthreads implementation.

11 04/01/2013 09:06 pm Emmanuel Quemener

Add script for bench on each implementation.

10 04/01/2013 09:05 pm Emmanuel Quemener

Tiny modifications for input/output

9 03/31/2013 07:46 am Emmanuel Quemener

Add MPI simple version

8 03/31/2013 07:45 am Emmanuel Quemener

Add OpenMP version.

7 03/30/2013 05:50 pm Emmanuel Quemener

Add Pi test for Metrology tests.