|
||||
File indexing completed on 2018-03-02 18:36:06 UTC
view on githubraw file Latest commit add29e06 on 2018-01-31 20:35:05 UTC4c563c2ee9 Chri*0001 CBOP 0002 C !ROUTINE: GLOBAL_MAX.h 0003 C !INTERFACE: 0004 C include "GLOBAL_MAX.h" 0005 C !DESCRIPTION: 0006 C *==========================================================* 07ef6829ed Jean*0007 C | GLOBAL\_MAX.h 0008 C | o Globals used by Fortran global max routine. 4c563c2ee9 Chri*0009 C *==========================================================* 07ef6829ed Jean*0010 C | The global max shared memory scheme uses global heap data 0011 C | structures (.i.e COMMON blocks ). Each thread writes to 0012 C | an its own element of the shared memory array and then 0013 C | one thread reads all the entries and maxs them. The max 0014 C | result is then read by all threads. 0015 C | Remember - you are working with regions of memory that 0016 C | are being updated concurrently by different threads. 0017 C | What happens, when it happens and who gets to see what 0018 C | happens at what stage depends on the computer systems 0019 C | memory model. Every computer has a different memory model 0020 C | and they are never simple. In all current platforms it is 0021 C | possible for one thread to see events happening in a 0022 C | different order from the order they are written in the 0023 C | code. 0024 C | Unless you understand this it is not a good idea to 0025 C | make modifications te way these header files are setup or 0026 C | the way the global max routines work. 4c563c2ee9 Chri*0027 C *==========================================================* 0028 CEOP 07ef6829ed Jean*0029 COMMON / GMAX_COMMON_R8 / phiGMR8 0030 Real*8 phiGMR8(lShare8, 0:MAX_NO_THREADS ) aea29c8517 Alis*0031 07ef6829ed Jean*0032 COMMON / GMAX_COMMON_R4 / phiGMR4 0033 Real*4 phiGMR4(lShare4, 0:MAX_NO_THREADS ) aea29c8517 Alis*0034 0035 COMMON / GMAX_COMMON_I / phiGMI 07ef6829ed Jean*0036 INTEGER phiGMI (lShare4, 0:MAX_NO_THREADS )
[ Source navigation ] | [ Diff markup ] | [ Identifier search ] | [ general search ] |
This page was automatically generated from https://github.com/MITgcm/MITgcm by the 2.2.1-MITgcm-0.1 LXR engine. The LXR team |