Scheduled Downtime
On Tuesday 24 October 2023 @ 5pm MT the forums will be in read only mode in preparation for the downtime. On Wednesday 25 October 2023 @ 5am MT, this website will be down for maintenance and expected to return online later in the morning.
Normal Operations
The forums are back online with normal operations. If you notice any issues or errors related to the forums, please reach out to help@ucar.edu

Running the entire CESM only on the Intel MIC?

A

aketh_tm@gmail_com

Member
i have been interested in knowing if there is a way to run the entire CESM(any component set and any resolution) entirely on the Intel MIC (use native mode execution only along with MPI)?Does adding the -mmic option in the CFLAGS and FFLAGS alone suffice OR is there more to be done?
 
J

jedwards

CSEG and Liaisons
Staff member
Port to the INTEL mic is a work in progress.  Here is the current set of flags for that port: 

-DFORTRANUNDERSCORE -DNO_R16
-openmp
-openmp
-openmp
-free
-fixed -132
-O0 -g -check uninit -check bounds -check pointers -fpe0
-O2
-mmic -fp-model source -convert big_endian -assume byterecl -ftz -traceback -assume realloc_lhs
-mmic -O2 -fp-model precise -DFORTRANUNDERSCOR
--host=x86_64-k1om-linux --build=x86_64-unknown-linux
-O0 -mmic
-r8
ifort
icc
icpc
mpiifort
mpiicc
mpiicpc
FORTRAN
-cxxlib
TRUE
TRUE
-DCPRINTEL
-mmic
$(shell $(NETCDF_PATH)/bin/nf-config --flibs)
 
J

jedwards

CSEG and Liaisons
Staff member
Port to the INTEL mic is a work in progress.  Here is the current set of flags for that port: 

-DFORTRANUNDERSCORE -DNO_R16
-openmp
-openmp
-openmp
-free
-fixed -132
-O0 -g -check uninit -check bounds -check pointers -fpe0
-O2
-mmic -fp-model source -convert big_endian -assume byterecl -ftz -traceback -assume realloc_lhs
-mmic -O2 -fp-model precise -DFORTRANUNDERSCOR
--host=x86_64-k1om-linux --build=x86_64-unknown-linux
-O0 -mmic
-r8
ifort
icc
icpc
mpiifort
mpiicc
mpiicpc
FORTRAN
-cxxlib
TRUE
TRUE
-DCPRINTEL
-mmic
$(shell $(NETCDF_PATH)/bin/nf-config --flibs)
 
J

jedwards

CSEG and Liaisons
Staff member
Port to the INTEL mic is a work in progress.  Here is the current set of flags for that port: 

-DFORTRANUNDERSCORE -DNO_R16
-openmp
-openmp
-openmp
-free
-fixed -132
-O0 -g -check uninit -check bounds -check pointers -fpe0
-O2
-mmic -fp-model source -convert big_endian -assume byterecl -ftz -traceback -assume realloc_lhs
-mmic -O2 -fp-model precise -DFORTRANUNDERSCOR
--host=x86_64-k1om-linux --build=x86_64-unknown-linux
-O0 -mmic
-r8
ifort
icc
icpc
mpiifort
mpiicc
mpiicpc
FORTRAN
-cxxlib
TRUE
TRUE
-DCPRINTEL
-mmic
$(shell $(NETCDF_PATH)/bin/nf-config --flibs)
 
J

jedwards

CSEG and Liaisons
Staff member
Port to the INTEL mic is a work in progress.  Here is the current set of flags for that port: 

-DFORTRANUNDERSCORE -DNO_R16
-openmp
-openmp
-openmp
-free
-fixed -132
-O0 -g -check uninit -check bounds -check pointers -fpe0
-O2
-mmic -fp-model source -convert big_endian -assume byterecl -ftz -traceback -assume realloc_lhs
-mmic -O2 -fp-model precise -DFORTRANUNDERSCOR
--host=x86_64-k1om-linux --build=x86_64-unknown-linux
-O0 -mmic
-r8
ifort
icc
icpc
mpiifort
mpiicc
mpiicpc
FORTRAN
-cxxlib
TRUE
TRUE
-DCPRINTEL
-mmic
$(shell $(NETCDF_PATH)/bin/nf-config --flibs)
 
J

jedwards

CSEG and Liaisons
Staff member
Yes unless you have access to a system that already has them built.   Our experience with the first generation intel mic archtecture lead us to conclude that it wasn't a proper platform for CESM - we are targeting the next generation of this archtecture as a potentially viable platform.   
 
J

jedwards

CSEG and Liaisons
Staff member
Yes unless you have access to a system that already has them built.   Our experience with the first generation intel mic archtecture lead us to conclude that it wasn't a proper platform for CESM - we are targeting the next generation of this archtecture as a potentially viable platform.   
 
J

jedwards

CSEG and Liaisons
Staff member
Yes unless you have access to a system that already has them built.   Our experience with the first generation intel mic archtecture lead us to conclude that it wasn't a proper platform for CESM - we are targeting the next generation of this archtecture as a potentially viable platform.   
 
J

jedwards

CSEG and Liaisons
Staff member
Yes unless you have access to a system that already has them built.   Our experience with the first generation intel mic archtecture lead us to conclude that it wasn't a proper platform for CESM - we are targeting the next generation of this archtecture as a potentially viable platform.   
 
P

prathamandwal@gmail_com

New Member
Hi ,I have built CESM for XEON phi ,The build was successful.while I am running it ,I am getting following response
===================================================================================
=   BAD TERMINATION OF ONE OF YOUR APPLICATION PROCESSES
=   PID 155105 RUNNING AT node1-mic0
=   EXIT CODE: 11
=   CLEANING UP REMAINING PROCESSES
=   YOU CAN IGNORE THE BELOW CLEANUP MESSAGES
===================================================================================
APPLICATION TERMINATED WITH THE EXIT STRING: Segmentation fault (signal 11)

 I tried checking at the run folder for the logs ,but there are no logs generated ,Can you guide me atleast identify the reason for this error.Also I am running CAM-CLUBB at .5 resolution ,Is it because the MIC card is running out of memory ?regardsPratha  
 
P

prathamandwal@gmail_com

New Member
Hi ,I have built CESM for XEON phi ,The build was successful.while I am running it ,I am getting following response
===================================================================================
=   BAD TERMINATION OF ONE OF YOUR APPLICATION PROCESSES
=   PID 155105 RUNNING AT node1-mic0
=   EXIT CODE: 11
=   CLEANING UP REMAINING PROCESSES
=   YOU CAN IGNORE THE BELOW CLEANUP MESSAGES
===================================================================================
APPLICATION TERMINATED WITH THE EXIT STRING: Segmentation fault (signal 11)

 I tried checking at the run folder for the logs ,but there are no logs generated ,Can you guide me atleast identify the reason for this error.Also I am running CAM-CLUBB at .5 resolution ,Is it because the MIC card is running out of memory ?regardsPratha  
 
P

prathamandwal@gmail_com

New Member
Hi ,I have built CESM for XEON phi ,The build was successful.while I am running it ,I am getting following response
===================================================================================
=   BAD TERMINATION OF ONE OF YOUR APPLICATION PROCESSES
=   PID 155105 RUNNING AT node1-mic0
=   EXIT CODE: 11
=   CLEANING UP REMAINING PROCESSES
=   YOU CAN IGNORE THE BELOW CLEANUP MESSAGES
===================================================================================
APPLICATION TERMINATED WITH THE EXIT STRING: Segmentation fault (signal 11)

 I tried checking at the run folder for the logs ,but there are no logs generated ,Can you guide me atleast identify the reason for this error.Also I am running CAM-CLUBB at .5 resolution ,Is it because the MIC card is running out of memory ?regardsPratha  
 
You must log in or register to reply here.
Top