Skip to content

Pull in updates in Ykacc to master #1

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
johnmauff wants to merge 228 commits into
base: master
from
Open

Pull in updates in Ykacc to master #1

Changes from all commits
Commits
Show all changes
228 commits
Select commit Hold shift + click to select a range
5bd029d
Updated to include r4 and r8 version.
johnmauff Oct 2, 2015
afc514f
Initial import of advance_clubb_core.
johnmauff Oct 21, 2015
fa16adf
Adding new CLUBB kernel advance_windm_edsclrm
johnmauff Oct 21, 2015
0357ef5
Added LAPACK routines to advance_clubb_core
johnmauff Oct 27, 2015
9413700
Added the MG2r kernel.
johnmauff Oct 27, 2015
b12a7be
added two MPAS kernels: cu_tiedtke and rrtmg_lw
Dec 24, 2015
3398bf2
renamed Makefiles
Dec 24, 2015
14f89e0
updated MPAS kernels for verification and perturbation outputs
Dec 29, 2015
cf7837d
added CLUBB_pdf_closure_execution_part kernel
Jan 4, 2016
949bcbc
renamed Makefile to Makefile.kgen
Jan 4, 2016
64f7379
removed Makefile
Jan 4, 2016
861fd18
Added three CLUBB kernels: CLUBB_adv_clubb_core, CLUBB_adv_windm_edsc…
Jan 7, 2016
25cb3a4
Update README.txt
grnydawn Jan 7, 2016
5b8f433
added Python test script
Feb 9, 2016
7d793a4
updated test_kernels for testing kernels on multiple platforms
Apr 28, 2016
2337362
added checmPreProc kernels: vector and scalar versions
May 9, 2016
e523044
moved four clubb kernels
Jun 13, 2016
4756545
added clubb_tend_cam kernel
Jun 15, 2016
c389793
Merge branch 'master' into renew
Jun 15, 2016
335a5b3
updated test_kernels.py to have -f and -c options
Jun 15, 2016
b1f43d2
Merge branch 'master' into renew
Jun 15, 2016
ae0093e
restructuring repo.
Jun 23, 2016
f3c3d2f
keep restructuring repo
Jun 23, 2016
23a4856
restructed repo
Jun 23, 2016
757f086
updated readme
Jun 26, 2016
1c550db
working on readme
Jun 27, 2016
4ba2cf1
Update README.rst
grnydawn Jun 27, 2016
73a28b6
added dirtree.png
Jun 27, 2016
77c75ce
Update README.rst
grnydawn Jun 27, 2016
b96e955
Update README.rst
grnydawn Jun 27, 2016
d74ff91
Update README.rst
grnydawn Jun 27, 2016
aca37c8
Update README.rst
grnydawn Jun 27, 2016
be293f7
Update README.rst
grnydawn Jun 27, 2016
6ce1896
Update README.rst
grnydawn Jun 27, 2016
4fe4898
Update README.rst
grnydawn Jun 27, 2016
985a6fa
Update README.rst
grnydawn Jun 27, 2016
48b7ae4
Update README.mk
grnydawn Jun 27, 2016
a40dcab
added plot.png
Jun 27, 2016
ba3bf2c
Merge branch 'renew' of ssh://github.com/NCAR/kernelOptimization into…
Jun 27, 2016
23e4346
Update README.rst
grnydawn Jun 27, 2016
9b8f1f6
Update README.rst
grnydawn Jun 27, 2016
0f0c876
removed readme.mk
Jun 27, 2016
2962343
updates test_kernels.py
Jun 27, 2016
bba1e56
Update README.rst
grnydawn Jun 27, 2016
fc81d9f
Update README.rst
grnydawn Jun 27, 2016
51a77a9
added pgi and intel makefiles
Jun 27, 2016
4ae9418
removed generic makefiles
Jun 27, 2016
d543d09
Merge branch 'renew'
Jun 27, 2016
02f6faf
Update README.rst
grnydawn Jul 11, 2016
2e5c972
Added CHEM versions. Both vector and scalar updated.
sherimickelson Jul 20, 2016
53a720d
Merge pull request #1 from NCAR/update_CHEM_versions
grnydawn Jul 20, 2016
7b72cfc
updated Makefile.intel and Makefile.pgi for kernels
Aug 5, 2016
8c8cd3b
Merge branch 'master' of https://github.com/NCAR/kernelOptimization
Aug 5, 2016
5f555d7
Clean Makefiles and create one for each arch for each version
sherimickelson Aug 8, 2016
6653970
renamed CHEM kernels
Aug 24, 2016
30fb62b
Merge branch 'renameCHEM'
Aug 24, 2016
1eaf0dc
Add Macros file which will hopefully make the code more modular.
johnmauff Aug 31, 2016
16353fc
Updates to the v03 version of the code.
johnmauff Aug 31, 2016
d2455fe
Added a new version of the code v04.
johnmauff Aug 31, 2016
47c0365
Adding v00 into repository.
johnmauff Aug 31, 2016
9b77f7a
More updates to the vector version of the implicit chemmistry solver.
johnmauff Aug 31, 2016
758e42a
testing push
Sep 1, 2016
4d0c6e0
recover README.rst
Sep 1, 2016
2f52f87
Initial WACCM_imp_sol_vector/v05 commit - includes minor changes to
briandobbins Mar 30, 2018
c813487
Minor fixes for building on Arm, including a dummy 'getpid' function
briandobbins Apr 11, 2018
b50bdcb
Minor change to makefile removing FC_FLAGS from link stage
briandobbins Apr 11, 2018
8558513
Another minor change to the Macros file here, adding ARMPL and MKL link
briandobbins Apr 11, 2018
3e8547c
Initial commit of v02 version - includes Macros file, moves all Fortran
briandobbins Apr 11, 2018
511be77
Minor addition of a README.txt in the v02 directory
briandobbins Apr 11, 2018
e40c57c
Initial v02 for PROT_sw_rad kernel - moves all files to F90 format for
briandobbins Apr 11, 2018
e08471a
Initial v02 version, includes MPI + barrier, Arm support, minor changes
briandobbins Apr 11, 2018
b4318d3
Initial version of MG2_opt with arm, MPI+barrier, Macros, etc changes -
briandobbins Apr 11, 2018
d9739d4
Initial v02 commit for HOMME_laplace_sphere_wk kernel - has MPI, Macros,
briandobbins Apr 11, 2018
f906eef
Initial v02 checkin - adds MPI+barrier, Macros, Arm support, and fixes
briandobbins Apr 11, 2018
573acc7
Addition of elefunt to the kernel list, and added symbolic links under
briandobbins Apr 11, 2018
d6d2410
Minor changes to elefunt Makefiles and Macros file for POP kernel to …
Apr 12, 2018
3c29e19
Minor fix - removing extraenous '_MPI' from #endif block
briandobbins Apr 12, 2018
9ad698f
Minor makefile fix - LDFLAGs -> LDFLAG
Apr 16, 2018
eaf3318
added classifier script; working on folding analyzer
Apr 17, 2018
fddb49a
Merge branch 'master' of https://github.com/NCAR/kernelOptimization
Apr 17, 2018
24a8cf6
copying kernels into temporary directory
Apr 19, 2018
7130273
Added a new version of the kernel which supports 4-byte reals. 4-byt…
johnmauff Apr 27, 2018
f885bbf
Created an MG2 kernel that uses 4-byte reals.
johnmauff May 1, 2018
7adcd42
Added support for NEC Aurora into the makefiles.
johnmauff Aug 2, 2018
6081af5
New version of CLUBB kernel.
johnmauff Aug 3, 2018
4059e6b
Merge branch 'master' of https://github.com/NCAR/kernelOptimization
johnmauff Aug 3, 2018
c3a57fb
Fixes for mo_taumol03.F90 - error in loop (1,ncol -> startCol,ncol) &
briandobbins Aug 7, 2018
a7fffba
Fix to array indices in setting up initial values
briandobbins Aug 9, 2018
ad40f04
Adding new v03 which contains the NEC optimizations
johnmauff Aug 14, 2018
6b83d68
Updates to v03 and some other random changes.
johnmauff Aug 15, 2018
b421b40
Merge branch 'master' of https://github.com/NCAR/kernelOptimization
johnmauff Aug 15, 2018
f728062
NEC specific optimizations.
johnmauff Aug 15, 2018
122108f
Something changed.
johnmauff Aug 15, 2018
15d8dff
Merge branch 'master' of https://github.com/NCAR/kernelOptimization
johnmauff Aug 15, 2018
390ea59
added CESM2_MG2 kernel
Aug 15, 2018
e624e66
added pcols128 data for CESM_MG2 kernel
Aug 16, 2018
e2cf6df
Port to NEC for the CESM2_MG2 kernel completed.
johnmauff Aug 16, 2018
e1ebc2e
Added new version v01. Currently just a copy of orig.
johnmauff Aug 16, 2018
b7c98c5
Merge branch 'master' of https://github.com/NCAR/kernelOptimization
johnmauff Aug 16, 2018
2194c03
Minor MG2 modifications.
johnmauff Aug 16, 2018
b226004
Version 02 for the NEC optimization work.
johnmauff Aug 16, 2018
83c4283
Updated the most critical saturation vapor pressure calculations.
johnmauff Aug 16, 2018
1d647e9
Added a number of low level vector functions.
johnmauff Aug 16, 2018
f46fac1
Local changes.
johnmauff Aug 16, 2018
aab1963
Merge branch 'master' of https://github.com/NCAR/kernelOptimization
johnmauff Aug 16, 2018
3536af9
New version of CESM2_MG2 which contains a number of NEC specific opti…
johnmauff Aug 17, 2018
edaf2b2
Merge branch 'master' of https://github.com/NCAR/kernelOptimization
johnmauff Aug 17, 2018
88af4b1
Cleaned up some files that should not have been included in the commit.
johnmauff Aug 17, 2018
3d9f924
More aggressive long vector optimizations.
johnmauff Aug 17, 2018
90f7d7f
added CESM2 MG2 kernel run on 72 cores of Cheyenne(NCAR) with various…
Aug 20, 2018
5819f26
Merge branch 'master' of https://github.com/NCAR/kernelOptimization
Aug 20, 2018
e4c46d8
removed dupulicatd CESM MG2 kernel
Aug 20, 2018
68ac6d2
Added version 05.
johnmauff Aug 21, 2018
6c78179
Merge branch 'master' of https://github.com/NCAR/kernelOptimization
johnmauff Aug 21, 2018
ebf2744
Change the Makefile so that it points at the data from 72 cores. Als…
johnmauff Aug 21, 2018
4bc40b2
Vectorization of the rising_factorial function as well as proper cast…
johnmauff Aug 21, 2018
bc38d6f
Created v06 which is actually the old v05. Version v05 now has a simp…
johnmauff Aug 22, 2018
52c6b12
New version v07. Look at optimizing the sedmentation loop.
johnmauff Aug 22, 2018
15f6c51
added CESM2 MG2 data files with pcols=192 and pcols=384
Aug 22, 2018
27f6c88
Merge branch 'master' of https://github.com/NCAR/kernelOptimization
johnmauff Aug 22, 2018
e68ec1c
Several new versions of the NEC optimization branch
johnmauff Aug 22, 2018
5d8517a
New NEC changes.
johnmauff Aug 23, 2018
fe1d557
Added new method of doing the sedementation loop update..
johnmauff Aug 24, 2018
9878351
Added a subroutine UpdateTendencies for code modularity
johnmauff Aug 24, 2018
546b2bc
New version which reproduces the previous answers.
johnmauff Aug 30, 2018
c9cfa9f
Changed something.
johnmauff Aug 30, 2018
0855aed
Some random debugging changes.
johnmauff Aug 30, 2018
32ded41
Merge branch 'master' of https://github.com/NCAR/kernelOptimization
johnmauff Aug 30, 2018
13b61b0
Better performance on NEC using mask.
johnmauff Aug 30, 2018
cdadc4d
Created v10 for NEC optimizations.
johnmauff Sep 6, 2018
9e27cf9
Replaced missing files from v09.
johnmauff Sep 6, 2018
ba8d3eb
New code version this addresses vectorization in EVAPORATE_SUBLIMATE_…
johnmauff Sep 6, 2018
e5878dd
Added old compiler flags into the Makefile
johnmauff Sep 6, 2018
342e64e
Added new link in silver to CESM2_MG2
johnmauff Sep 6, 2018
4d2083c
Added v12 which will support either R4 or R8 calculations.
johnmauff Sep 7, 2018
40542fd
asdfadsf
johnmauff Sep 7, 2018
1de9a7a
Merge branch 'master' of https://github.com/NCAR/kernelOptimization
johnmauff Sep 7, 2018
e012f55
added CESM2_CSLAM kernel
Sep 7, 2018
726cf91
Merge branch 'master' of https://github.com/NCAR/kernelOptimization
Sep 7, 2018
7949abc
4-byte version of CESM2_MG2
johnmauff Sep 10, 2018
628df61
Merge branch 'master' of https://github.com/NCAR/kernelOptimization
johnmauff Sep 10, 2018
2bac062
Original version of CESM2_MG2 with 4-byte support.
johnmauff Sep 10, 2018
6a8653f
Changed qsmall paramemeter for 4-byte reals.
johnmauff Sep 12, 2018
204d886
added CESM kernel license files to CESM kernels
Sep 12, 2018
89507e9
added CESM2_MG2 v2
Sep 24, 2018
ade7245
Replaced the SIMD directives.
johnmauff Sep 24, 2018
feab4b0
Improved vectorization in slope_limiter
johnmauff Sep 24, 2018
05078e4
Updated compiler flags for Arm and GNU compilers on Arm (thanks to As…
briandobbins Oct 4, 2018
f6ba3fe
Merge branch 'master' of https://github.com/NCAR/kernelOptimization
briandobbins Oct 4, 2018
d20a0cf
Changed WACCM to use a compiler flags (-D _VECLEN=<n>) to set vector …
briandobbins Oct 4, 2018
666dc4f
Addressed issues associated with DEBUG=true
johnmauff Nov 2, 2018
bc896c5
Local changes
Jan 8, 2019
0aa8712
Merge branch 'master' of https://github.com/NCAR/kernelOptimization
Jan 8, 2019
15b72e4
Added MPI support.
johnmauff Jan 15, 2019
922fdc7
added cache pollution version of CESM2_MG2/micro_mg_cam.F90 of orig a…
Jan 15, 2019
9e87dc8
Merge branch 'master' of https://github.com/NCAR/kernelOptimization
Jan 23, 2019
b76f101
Cleanup in preparation for NWSC-3 benchmark definition.
Jan 23, 2019
f6659f0
Added version v14.
Jan 23, 2019
5a19095
Cleaned-upMPI execution output
johnmauff Jan 24, 2019
2676144
Cleanup so that only 50% of cases need to pass.
johnmauff Jan 24, 2019
8e69326
Updated compiler flags in Macros.
johnmauff Jan 28, 2019
f3c81c7
Polished up version v05
johnmauff Jan 30, 2019
05667a2
Address RMS definition error.
Jan 30, 2019
7dae5e7
Added a second loop in mo_prod_loss.F90
johnmauff Jan 31, 2019
d972d18
Created double loop version.
johnmauff Jan 31, 2019
92ec3bd
Couple of minor fixes identfied on NEC.
johnmauff Jan 31, 2019
d585ce8
added CESM2_CLUBB kernel
Feb 7, 2019
9e606f3
updated README
Feb 7, 2019
fa90a12
Added v01 code version of CLUBB
johnmauff Feb 7, 2019
16b46c9
updated README in CESM2_CLUBB kernel
Feb 7, 2019
0d19477
updated note in CESM2_CLUBB kernel Makefile
Feb 7, 2019
5800ce5
Merge with origin master
johnmauff Feb 7, 2019
74395c7
Merge branch 'master' of https://github.com/NCAR/kernelOptimization
johnmauff Feb 7, 2019
64ee339
Added LAPACK routines.
johnmauff Feb 7, 2019
8541b92
More cleanup of CLUBB kernel.
johnmauff Feb 7, 2019
0983848
New version of DART_WRF_large kernel.
johnmauff Feb 13, 2019
a780019
Addition of DART_WRF_large kernel.
johnmauff Feb 13, 2019
527a332
Update to the CESM2_CLUBB kernel.
johnmauff Feb 14, 2019
53ffb17
Minor tweaks & fixes to enable running w/ GNU compiler
briandobbins Feb 14, 2019
6774f59
Quick fix of Intel compiler flags
briandobbins Feb 14, 2019
76aaca4
Reduced the total number of input data files used for the CESM2_MG2 b…
johnmauff Feb 26, 2019
861fe87
Minor update to deal with NEC and GNU compilers
johnmauff Mar 1, 2019
efd4795
Modifications so that it works with GNU and ARM compilers - includes …
briandobbins Mar 1, 2019
4b5acfc
Merge branch 'master' of https://github.com/NCAR/kernelOptimization
johnmauff Mar 7, 2019
338f803
added CESM2_2_BETA02_CLUBB kernel
Jun 21, 2019
065ce12
added CESM2_SILHS_UWM_V2 kernel
Jul 10, 2019
be97877
removed unused line
Jul 10, 2019
5f74c27
updated compiler options for blas files in CESM2_SILHS_UWM_V2
Jul 10, 2019
18660c0
Deleted a core file.
johnmauff Jul 17, 2019
72fe469
changed number of iters for better timing accuracy
johnmauff Jul 17, 2019
b61218f
added CESM2_SILHS_PSUBCOLS144_UWM_V2 kernel
Aug 1, 2019
787509b
Merge branch 'master' of https://github.com/NCAR/kernelOptimization
johnmauff Aug 2, 2019
1690a20
Single kernel with different input files.
johnmauff Aug 2, 2019
9ed992d
Remove psubcol=144 kernel.
johnmauff Aug 2, 2019
3c3f05f
Minor mods to Makefile.
johnmauff Aug 2, 2019
614a7ff
Added v01 which uses MKL libraries for optimization.
johnmauff Aug 8, 2019
4445f07
Added support for PGI compiler flags.
johnmauff Aug 21, 2019
84ce333
added strmv.f lapack file in CESM2_SILHS_UWM_V2 kernel
Aug 21, 2019
3b15b48
Added GPU support through OpenACC in v02
johnmauff Aug 28, 2019
e9ec66b
Correct execution on GPU both p100 and v100
johnmauff Sep 10, 2019
87fcc04
Merge branch 'master' of https://github.com/NCAR/kernelOptimization
johnmauff Sep 10, 2019
3bab7a2
Cleanup from GPU port.
johnmauff Sep 11, 2019
073a6b4
Cleanup.
johnmauff Sep 12, 2019
1044b3d
Addition of new version.
johnmauff Sep 12, 2019
68c62f1
Update from v03
johnmauff Oct 1, 2019
f8d12ad
Added OpenACC directives
johnmauff Oct 4, 2019
6ac7d91
Updates to OpenACC port.
johnmauff Oct 4, 2019
c4b4d4f
More additions
johnmauff Oct 4, 2019
ef64eba
added cesm2_mg2/v16; used .acc parallel for a small region of codes i…
Oct 8, 2019
d94cdc7
openacc version is about 50% faster than pgi-compiled cpu version; po…
Oct 16, 2019
7ab2387
Broke appart the giant K loop.
johnmauff Oct 30, 2019
36dd589
Updates to GPUized version.
johnmauff Nov 5, 2019
61be1ef
Code to attempt to address AUTO alloation error
johnmauff Nov 6, 2019
7f7302c
GPUized more regions of the code.
johnmauff Nov 8, 2019
48edc58
created v18 folder; working on porting the main loop in micro_mg_tend
Nov 8, 2019
eea83f4
Merge branch 'master' of https://github.com/NCAR/kernelOptimization i…
Nov 8, 2019
baf4717
Cleanup of excessive OpenACC directives.
johnmauff Nov 21, 2019
c7fde1c
Creating data regions
johnmauff Nov 21, 2019
fe7748b
Moved some more computations onto the GPU.
johnmauff Dec 3, 2019
d944b40
Updated to include to include a lot of data directives.
johnmauff Dec 5, 2019
e514a59
More code updates.
johnmauff Dec 6, 2019
368a8cf
Update to GPU version.
johnmauff Dec 6, 2019
43cd131
Cleanup of OpenACC version
johnmauff Dec 11, 2019
264803c
Saved version of code before change to the IO routines.
johnmauff Dec 13, 2019
ee66f1e
Added support for larger problem sizes.
johnmauff Dec 13, 2019
363ad75
Removed all the data movment from timing loop.
johnmauff Dec 20, 2019
db56435
A bit of cleanup.
johnmauff Dec 20, 2019
7cf9269
Recent updates for GPU opimizations.
johnmauff Jan 9, 2020

Sorry, this diff is taking too long to generate.

It may be too large to display on GitHub.