New URL for NEMO forge!   http://forge.nemo-ocean.eu

Since March 2022 along with NEMO 4.2 release, the code development moved to a self-hosted GitLab.
This present forge is now archived and remained online for history.
do_loop_substitute.h90 in NEMO/branches/UKMO/dev_r12745_HPC-02_Daley_Tiling_trial_public/src/OCE – NEMO

source: NEMO/branches/UKMO/dev_r12745_HPC-02_Daley_Tiling_trial_public/src/OCE/do_loop_substitute.h90 @ 12879

Last change on this file since 12879 was 12879, checked in by hadcv, 4 years ago

Changes following feedback

File size: 4.9 KB
RevLine 
[12353]1#if defined show_comments
[12340]2! These comments are not intended to be retained during preprocessing; i.e. do not define "show_comments"
[12341]3!!----------------------------------------------------------------------
4!! NEMO/OCE 4.0 , NEMO Consortium (2018)
5!! Software governed by the CeCILL license (see ./LICENSE)
6!!----------------------------------------------------------------------
[12340]7! This header file contains preprocessor definitions and macros used in the do-loop substitutions introduced
8! between version 4.0 and 4.2. The primary aim of these macros is to assist in future applications of tiling
9! to improve performance. This is expected to be achieved by alternative versions of these macros in selected
10! locations. The initial introduction of these macros simply replaces all identifiable nested 2D- and 3D-loops
11! with single line statements (and adjusts indenting accordingly). Do loops are identifiable if they comform
12! to either:
13!                                       DO jk = ....
14!   DO jj = ....                           DO jj = ...
15!      DO ji = ....                           DO ji = ...
[12341]16!         .                   OR                 . 
17!         .                                      .
[12340]18!     END DO                                  END DO
19!   END DO                                 END DO
20!                                       END DO
21! and white-space variants thereof.
22!
23! Additionally, only loops with recognised jj and ji loops limits are treated; these are:
24! Lower limits of 1, 2 or fs_2
25! Upper limits of jpi, jpim1 or fs_jpim1 (for ji) or jpj, jpjm1 or fs_jpjm1 (for jj)
26!
27! The macro naming convention takes the form: DO_2D_BT_LR where:
28!   B is the Bottom offset from the PE's inner domain;
29!   T is the Top    offset from the PE's inner domain;
30!   L is the Left   offset from the PE's inner domain;
31!   R is the Right  offset from the PE's inner domain
32!
33! So, given an inner domain of 2,jpim1 and 2,jpjm1, a typical example would replace:
34!
35!   DO jj = 2, jpj
36!      DO ji = 1, jpim1
[12341]37!         .
38!         .
39!      END DO
[12340]40!   END DO
41!
42! with:
43!
44!   DO_2D_01_10
[12341]45!      .
46!      .
[12340]47!   END_2D
48!
[12341]49! similar conventions apply to the 3D loops macros. jk loop limits are retained through macro arguments and are not restricted. This
[12340]50! includes the possibility of strides for which an extra set of DO_3DS macros are defined.
51!
[12353]52! In the following definitions the inner PE domain is defined by start indices of (___kIs_, __kJs_) and end indices of (__kIe_, __kJe_)
53! The following macros are defined just below: ___kIs_, __kJs_, ___kIsm1_, __kJsm1_, ___kIe_, __kJe_, ___kIep1_, __kJep1_.
54! These names are chosen to, hopefully, avoid any future, unintended matches elsewhere in the code.
[12340]55!
56#endif
[12879]57#define __kIs_     ntsi(ntile)
58#define __kJs_     ntsj(ntile)
59#define __kIsm1_   __kIs_ - nn_hls
60#define __kJsm1_   __kJs_ - nn_hls
[12340]61
[12879]62#define __kIe_     ntei(ntile)
63#define __kJe_     ntej(ntile)
64#define __kIep1_   __kIe_ + nn_hls
65#define __kJep1_   __kJe_ + nn_hls
[12340]66
[12879]67#define A2D        __kIsm1_:__kIep1_,__kJsm1_:__kJep1_
[12765]68
[12353]69#define DO_2D_00_00   DO jj = __kJs_, __kJe_   ;   DO ji = __kIs_, __kIe_
70#define DO_2D_00_01   DO jj = __kJs_, __kJe_   ;   DO ji = __kIs_, __kIep1_
71#define DO_2D_00_10   DO jj = __kJs_, __kJe_   ;   DO ji = __kIsm1_, __kIe_
72#define DO_2D_00_11   DO jj = __kJs_, __kJe_   ;   DO ji = __kIsm1_, __kIep1_
[12340]73 
[12353]74#define DO_2D_01_00   DO jj = __kJs_, __kJep1_   ;   DO ji = __kIs_, __kIe_
75#define DO_2D_01_01   DO jj = __kJs_, __kJep1_   ;   DO ji = __kIs_, __kIep1_
76#define DO_2D_01_10   DO jj = __kJs_, __kJep1_   ;   DO ji = __kIsm1_, __kIe_
77#define DO_2D_01_11   DO jj = __kJs_, __kJep1_   ;   DO ji = __kIsm1_, __kIep1_
[12340]78 
[12353]79#define DO_2D_10_00   DO jj = __kJsm1_, __kJe_   ;   DO ji = __kIs_, __kIe_
80#define DO_2D_10_10   DO jj = __kJsm1_, __kJe_   ;   DO ji = __kIsm1_, __kIe_
81#define DO_2D_10_11   DO jj = __kJsm1_, __kJe_   ;   DO ji = __kIsm1_, __kIep1_
[12340]82 
[12353]83#define DO_2D_11_00   DO jj = __kJsm1_, __kJep1_   ;   DO ji = __kIs_, __kIe_
84#define DO_2D_11_01   DO jj = __kJsm1_, __kJep1_   ;   DO ji = __kIs_, __kIep1_
85#define DO_2D_11_10   DO jj = __kJsm1_, __kJep1_   ;   DO ji = __kIsm1_, __kIe_
86#define DO_2D_11_11   DO jj = __kJsm1_, __kJep1_   ;   DO ji = __kIsm1_, __kIep1_
[12340]87
[12341]88#define DO_3D_00_00(ks,ke)   DO jk = ks, ke   ;   DO_2D_00_00
89#define DO_3D_00_10(ks,ke)   DO jk = ks, ke   ;   DO_2D_00_10
[12340]90 
[12341]91#define DO_3D_01_01(ks,ke)   DO jk = ks, ke   ;   DO_2D_01_01
[12340]92 
[12341]93#define DO_3D_10_00(ks,ke)   DO jk = ks, ke   ;   DO_2D_10_00
94#define DO_3D_10_10(ks,ke)   DO jk = ks, ke   ;   DO_2D_10_10
95#define DO_3D_10_11(ks,ke)   DO jk = ks, ke   ;   DO_2D_10_11
[12340]96 
[12341]97#define DO_3D_11_11(ks,ke)   DO jk = ks, ke   ;   DO_2D_11_11
[12340]98
[12341]99#define DO_3DS_00_00(ks,ke,ki)   DO jk = ks, ke, ki   ;   DO_2D_00_00
100#define DO_3DS_01_01(ks,ke,ki)   DO jk = ks, ke, ki   ;   DO_2D_01_01
101#define DO_3DS_10_10(ks,ke,ki)   DO jk = ks, ke, ki   ;   DO_2D_10_10
102#define DO_3DS_11_11(ks,ke,ki)   DO jk = ks, ke, ki   ;   DO_2D_11_11
[12340]103
[12341]104#define END_2D   END DO   ;   END DO
105#define END_3D   END DO   ;   END DO   ;   END DO
Note: See TracBrowser for help on using the repository browser.