Hi, I'd like to compile and run ET on the new TACC cluster Stampede. Did anybody run ET on stampede? I see that there are already simfactory scripts for stampede in the ET development version, but I'm not sure if they have been already fully tested (I see that there are comments about job submission not having been tested yet).
I'm also curious to know if you think that the hybrid approach can be of any use for ET/GRHydro (or ET/Whisky) on that machine. I'm not very familiar with the Intel Phi coprocessor and MIC programming (but it seems similar to GPU, except for being much easier to use).
Thanks, Bruno
Dr. Bruno Giacomazzo JILA - University of Colorado 440 UCB Boulder, CO 80309 USA
Tel. : +1 303-492-5170 Fax : +1 303-492-5235 email : bruno.giacomazzo@jila.colorado.edu web: http://www.brunogiacomazzo.org
---------------------------------------------------------------------- There are only 10 types of people in the world: Those who understand binary, and those who don't ----------------------------------------------------------------------
Bruno
I'm currently testing the Einstein Toolkit on Stampede. Even without the MICs, this is a very nice and fast system, almost ideal for the ET. The scripts in Simfactory should almost work; I will update them in the coming days. (The system was unavailable in the past days, so I couldn't test them recently.)
The MICs (Xeon Phis) can be used in two ways. One can view them as an accelerator (like a GPU), and then offload certain calculations there. Unfortunately neither CUDA nor OpenCL are available there, hence one has to use PGI's OpenACC and deal with PGI's compiler that has serious problems with OpenMP.
The other option is to view the Xeon Phis as regular processors. I believe that I/O will be quite slow from them, and MPI does not (yet?) fully work there, but apart from this, one can run the ET there directly. The small caches and in-order execution will make for some challenges; in particular, multi-threading e.g. via OpenMP will be a must.
In the end, I assume that one would want to use them either as accelerator (if not via OpenCL then via something equivalent, just different), or as regular compute nodes where Carpet will have to be enhanced to handle the different CPU speeds between Xeons and Xeon Phis.
-erik
On Tue, Jan 8, 2013 at 2:35 PM, Bruno Giacomazzo < bruno.giacomazzo@jila.colorado.edu> wrote:
Hi, I'd like to compile and run ET on the new TACC cluster Stampede. Did anybody run ET on stampede? I see that there are already simfactory scripts for stampede in the ET development version, but I'm not sure if they have been already fully tested (I see that there are comments about job submission not having been tested yet).
I'm also curious to know if you think that the hybrid approach can be of any use for ET/GRHydro (or ET/Whisky) on that machine. I'm not very familiar with the Intel Phi coprocessor and MIC programming (but it seems similar to GPU, except for being much easier to use).
Thanks, Bruno
Dr. Bruno Giacomazzo JILA - University of Colorado 440 UCB Boulder, CO 80309 USA
Tel. : +1 303-492-5170 Fax : +1 303-492-5235 email : bruno.giacomazzo@jila.colorado.edu web: http://www.brunogiacomazzo.org
There are only 10 types of people in the world: Those who understand binary, and those who don't
Users mailing list Users@einsteintoolkit.org http://lists.einsteintoolkit.org/mailman/listinfo/users
Hi Erik, thanks a lot for the info. I will then wait for your updated Simfactory scripts before compiling on it.
Cheers, Bruno
On Jan 8, 2013, at 12:58 PM, Erik Schnetter wrote:
Bruno
I'm currently testing the Einstein Toolkit on Stampede. Even without the MICs, this is a very nice and fast system, almost ideal for the ET. The scripts in Simfactory should almost work; I will update them in the coming days. (The system was unavailable in the past days, so I couldn't test them recently.)
The MICs (Xeon Phis) can be used in two ways. One can view them as an accelerator (like a GPU), and then offload certain calculations there. Unfortunately neither CUDA nor OpenCL are available there, hence one has to use PGI's OpenACC and deal with PGI's compiler that has serious problems with OpenMP.
The other option is to view the Xeon Phis as regular processors. I believe that I/O will be quite slow from them, and MPI does not (yet?) fully work there, but apart from this, one can run the ET there directly. The small caches and in-order execution will make for some challenges; in particular, multi-threading e.g. via OpenMP will be a must.
In the end, I assume that one would want to use them either as accelerator (if not via OpenCL then via something equivalent, just different), or as regular compute nodes where Carpet will have to be enhanced to handle the different CPU speeds between Xeons and Xeon Phis.
-erik
On Tue, Jan 8, 2013 at 2:35 PM, Bruno Giacomazzo bruno.giacomazzo@jila.colorado.edu wrote: Hi, I'd like to compile and run ET on the new TACC cluster Stampede. Did anybody run ET on stampede? I see that there are already simfactory scripts for stampede in the ET development version, but I'm not sure if they have been already fully tested (I see that there are comments about job submission not having been tested yet).
I'm also curious to know if you think that the hybrid approach can be of any use for ET/GRHydro (or ET/Whisky) on that machine. I'm not very familiar with the Intel Phi coprocessor and MIC programming (but it seems similar to GPU, except for being much easier to use).
Thanks, Bruno
Dr. Bruno Giacomazzo JILA - University of Colorado 440 UCB Boulder, CO 80309 USA
Tel. : +1 303-492-5170 Fax : +1 303-492-5235 email : bruno.giacomazzo@jila.colorado.edu web: http://www.brunogiacomazzo.org
There are only 10 types of people in the world: Those who understand binary, and those who don't
Users mailing list Users@einsteintoolkit.org http://lists.einsteintoolkit.org/mailman/listinfo/users
-- Erik Schnetter schnetter@cct.lsu.edu http://www.perimeterinstitute.ca/personal/eschnetter/
Dr. Bruno Giacomazzo JILA - University of Colorado 440 UCB Boulder, CO 80309 USA
Tel. : +1 303-492-5170 Fax : +1 303-492-5235 email : bruno.giacomazzo@jila.colorado.edu web: http://www.brunogiacomazzo.org
---------------------------------------------------------------------- There are only 10 types of people in the world: Those who understand binary, and those who don't ----------------------------------------------------------------------
Hi Erik, I'm trying to test the Orsted version of ET on stampede. I'm able to compile using the option file that you created for the development version (except that I needed to add -U__STRICT_ANSI__ to CFLAGS otherwise the PITTNullCode/SphericalHarmonicRecon/src/util/fftwfilter util would not compile properly because it doesn't find M_PI).
I have some problems with some of the testsuites. Some of them fail because of segfaults. For example EinsteinEvolve/GRHydro/test/GRHydro_test_tov_ppm_ML.par crashed with a segfault. If I look with gdb at the core file, this is the info I get:
Program terminated with signal 11, Segmentation fault. #0 0x0000000000c6feb3 in L__ZN129_INTERNAL_106__work_01052_tg803155_EinsteinToolkit_Orsted_Cactus_configs_sim_build_ML_BSSN_ML_BSSN_convertFromADMBase_cc_ca14dd0a31ML_BSSN_convertFromADMBase_BodyEPK4_cGHiiPKdS4_S4_PKiS6_iPrKPd_196__par_region0_2_306 () at /work/01052/tg803155/EinsteinToolkit/Orsted/Cactus/arrangements/McLachlan/ML_BSSN/src/ML_BSSN_convertFromADMBase.cc:332 332 vec_store_nta_partial(alpha[index],alphaL);
Any idea? Is anyone using the latest stable ET release on Stampede?
Thanks, Bruno
On Jan 8, 2013, at 2:03 PM, Bruno Giacomazzo wrote:
Hi Erik, thanks a lot for the info. I will then wait for your updated Simfactory scripts before compiling on it.
Cheers, Bruno
On Jan 8, 2013, at 12:58 PM, Erik Schnetter wrote:
Bruno
I'm currently testing the Einstein Toolkit on Stampede. Even without the MICs, this is a very nice and fast system, almost ideal for the ET. The scripts in Simfactory should almost work; I will update them in the coming days. (The system was unavailable in the past days, so I couldn't test them recently.)
The MICs (Xeon Phis) can be used in two ways. One can view them as an accelerator (like a GPU), and then offload certain calculations there. Unfortunately neither CUDA nor OpenCL are available there, hence one has to use PGI's OpenACC and deal with PGI's compiler that has serious problems with OpenMP.
The other option is to view the Xeon Phis as regular processors. I believe that I/O will be quite slow from them, and MPI does not (yet?) fully work there, but apart from this, one can run the ET there directly. The small caches and in-order execution will make for some challenges; in particular, multi-threading e.g. via OpenMP will be a must.
In the end, I assume that one would want to use them either as accelerator (if not via OpenCL then via something equivalent, just different), or as regular compute nodes where Carpet will have to be enhanced to handle the different CPU speeds between Xeons and Xeon Phis.
-erik
On Tue, Jan 8, 2013 at 2:35 PM, Bruno Giacomazzo bruno.giacomazzo@jila.colorado.edu wrote: Hi, I'd like to compile and run ET on the new TACC cluster Stampede. Did anybody run ET on stampede? I see that there are already simfactory scripts for stampede in the ET development version, but I'm not sure if they have been already fully tested (I see that there are comments about job submission not having been tested yet).
I'm also curious to know if you think that the hybrid approach can be of any use for ET/GRHydro (or ET/Whisky) on that machine. I'm not very familiar with the Intel Phi coprocessor and MIC programming (but it seems similar to GPU, except for being much easier to use).
Thanks, Bruno
Dr. Bruno Giacomazzo JILA - University of Colorado 440 UCB Boulder, CO 80309 USA
Tel. : +1 303-492-5170 Fax : +1 303-492-5235 email : bruno.giacomazzo@jila.colorado.edu web: http://www.brunogiacomazzo.org
There are only 10 types of people in the world: Those who understand binary, and those who don't
Users mailing list Users@einsteintoolkit.org http://lists.einsteintoolkit.org/mailman/listinfo/users
-- Erik Schnetter schnetter@cct.lsu.edu http://www.perimeterinstitute.ca/personal/eschnetter/
Dr. Bruno Giacomazzo JILA - University of Colorado 440 UCB Boulder, CO 80309 USA
Tel. : +1 303-492-5170 Fax : +1 303-492-5235 email : bruno.giacomazzo@jila.colorado.edu web: http://www.brunogiacomazzo.org
There are only 10 types of people in the world: Those who understand binary, and those who don't
Dr. Bruno Giacomazzo JILA - University of Colorado 440 UCB Boulder, CO 80309 USA
Tel. : +1 303-492-5170 Fax : +1 303-492-5235 email : bruno.giacomazzo@jila.colorado.edu web: http://www.brunogiacomazzo.org
---------------------------------------------------------------------- There are only 10 types of people in the world: Those who understand binary, and those who don't ----------------------------------------------------------------------
On 02/04/2013 05:36 PM, Bruno Giacomazzo wrote:
Hi Erik, I'm trying to test the Orsted version of ET on stampede. I'm able to compile using the option file that you created for the development version (except that I needed to add -U__STRICT_ANSI__ to CFLAGS otherwise the PITTNullCode/SphericalHarmonicRecon/src/util/fftwfilter util would not compile properly because it doesn't find M_PI).
I have some problems with some of the testsuites. Some of them fail because of segfaults. For example EinsteinEvolve/GRHydro/test/GRHydro_test_tov_ppm_ML.par crashed with a segfault. If I look with gdb at the core file, this is the info I get:
Program terminated with signal 11, Segmentation fault. #0 0x0000000000c6feb3 in L__ZN129_INTERNAL_106__work_01052_tg803155_EinsteinToolkit_Orsted_Cactus_configs_sim_build_ML_BSSN_ML_BSSN_convertFromADMBase_cc_ca14dd0a31ML_BSSN_convertFromADMBase_BodyEPK4_cGHiiPKdS4_S4_PKiS6_iPrKPd_196__par_region0_2_306 () at /work/01052/tg803155/EinsteinToolkit/Orsted/Cactus/arrangements/McLachlan/ML_BSSN/src/ML_BSSN_convertFromADMBase.cc:332 332vec_store_nta_partial(alpha[index],alphaL);
Any idea? Is anyone using the latest stable ET release on Stampede?
I've done tests of vacuum BBHs on stampede (not full runs with many restarts). So far, no problems. I used MPI_DIR = /opt/apps/intel13/mvapich2/1.9 rather than the MPI options under simfactory.
Thanks, Bruno
On Jan 8, 2013, at 2:03 PM, Bruno Giacomazzo wrote:
Hi Erik, thanks a lot for the info. I will then wait for your updated Simfactory scripts before compiling on it.
Cheers, Bruno
On Jan 8, 2013, at 12:58 PM, Erik Schnetter wrote:
Bruno
I'm currently testing the Einstein Toolkit on Stampede. Even without the MICs, this is a very nice and fast system, almost ideal for the ET. The scripts in Simfactory should almost work; I will update them in the coming days. (The system was unavailable in the past days, so I couldn't test them recently.)
The MICs (Xeon Phis) can be used in two ways. One can view them as an accelerator (like a GPU), and then offload certain calculations there. Unfortunately neither CUDA nor OpenCL are available there, hence one has to use PGI's OpenACC and deal with PGI's compiler that has serious problems with OpenMP.
The other option is to view the Xeon Phis as regular processors. I believe that I/O will be quite slow from them, and MPI does not (yet?) fully work there, but apart from this, one can run the ET there directly. The small caches and in-order execution will make for some challenges; in particular, multi-threading e.g. via OpenMP will be a must.
In the end, I assume that one would want to use them either as accelerator (if not via OpenCL then via something equivalent, just different), or as regular compute nodes where Carpet will have to be enhanced to handle the different CPU speeds between Xeons and Xeon Phis.
-erik
On Tue, Jan 8, 2013 at 2:35 PM, Bruno Giacomazzo <bruno.giacomazzo@jila.colorado.edu mailto:bruno.giacomazzo@jila.colorado.edu> wrote:
Hi, I'd like to compile and run ET on the new TACC cluster Stampede. Did anybody run ET on stampede? I see that there are already simfactory scripts for stampede in the ET development version, but I'm not sure if they have been already fully tested (I see that there are comments about job submission not having been tested yet). I'm also curious to know if you think that the hybrid approach can be of any use for ET/GRHydro (or ET/Whisky) on that machine. I'm not very familiar with the Intel Phi coprocessor and MIC programming (but it seems similar to GPU, except for being much easier to use). Thanks, Bruno Dr. Bruno Giacomazzo JILA - University of Colorado 440 UCB Boulder, CO 80309 USA Tel. : +1 303-492-5170 <tel:%2B1%C2%A0303-492-5170> Fax : +1 303-492-5235 <tel:%2B1%C2%A0303-492-5235> email : bruno.giacomazzo@jila.colorado.edu <mailto:bruno.giacomazzo@jila.colorado.edu> web: http://www.brunogiacomazzo.org <http://www.brunogiacomazzo.org/> ---------------------------------------------------------------------- There are only 10 types of people in the world: Those who understand binary, and those who don't ---------------------------------------------------------------------- _______________________________________________ Users mailing list Users@einsteintoolkit.org <mailto:Users@einsteintoolkit.org> http://lists.einsteintoolkit.org/mailman/listinfo/users-- Erik Schnetter <schnetter@cct.lsu.edu mailto:schnetter@cct.lsu.edu> http://www.perimeterinstitute.ca/personal/eschnetter/
Dr. Bruno Giacomazzo JILA - University of Colorado 440 UCB Boulder, CO 80309 USA
Tel. : +1 303-492-5170 Fax : +1 303-492-5235 email : bruno.giacomazzo@jila.colorado.edu mailto:bruno.giacomazzo@jila.colorado.edu web: http://www.brunogiacomazzo.org http://www.brunogiacomazzo.org/
There are only 10 types of people in the world: Those who understand binary, and those who don't
Dr. Bruno Giacomazzo JILA - University of Colorado 440 UCB Boulder, CO 80309 USA
Tel. : +1 303-492-5170 Fax : +1 303-492-5235 email : bruno.giacomazzo@jila.colorado.edu mailto:bruno.giacomazzo@jila.colorado.edu web: http://www.brunogiacomazzo.org
There are only 10 types of people in the world: Those who understand binary, and those who don't
Users mailing list Users@einsteintoolkit.org http://lists.einsteintoolkit.org/mailman/listinfo/users
Bruno
This may be an error in thorn Vectors, or in LoopControl. You could try updating Vectors from the trunk. LoopControl has probably changed too much to be useful for you.
The different MPI version that Yosef mentioned is unrelated. Simfactory uses the MPI version that can be used with the MICs, which is probably not relevant for you. You could try Yosef's MPI suggestion and compare performance.
Are you accidentally setting VECTORISE_ALIGNED_ARRAYS?
-erik
On Mon, Feb 4, 2013 at 5:36 PM, Bruno Giacomazzo < bruno.giacomazzo@jila.colorado.edu> wrote:
Hi Erik, I'm trying to test the Orsted version of ET on stampede. I'm able to compile using the option file that you created for the development version (except that I needed to add -U__STRICT_ANSI__ to CFLAGS otherwise the PITTNullCode/SphericalHarmonicRecon/src/util/fftwfilter util would not compile properly because it doesn't find M_PI).
I have some problems with some of the testsuites. Some of them fail because of segfaults. For example EinsteinEvolve/GRHydro/test/GRHydro_test_tov_ppm_ML.par crashed with a segfault. If I look with gdb at the core file, this is the info I get:
Program terminated with signal 11, Segmentation fault. #0 0x0000000000c6feb3 in L__ZN129_INTERNAL_106__work_01052_tg803155_EinsteinToolkit_Orsted_Cactus_configs_sim_build_ML_BSSN_ML_BSSN_convertFromADMBase_cc_ca14dd0a31ML_BSSN_convertFromADMBase_BodyEPK4_cGHiiPKdS4_S4_PKiS6_iPrKPd_196__par_region0_2_306 () at /work/01052/tg803155/EinsteinToolkit/Orsted/Cactus/arrangements/McLachlan/ML_BSSN/src/ML_BSSN_convertFromADMBase.cc:332 332 vec_store_nta_partial(alpha[index],alphaL);
Any idea? Is anyone using the latest stable ET release on Stampede?
Thanks, Bruno
On Jan 8, 2013, at 2:03 PM, Bruno Giacomazzo wrote:
Hi Erik, thanks a lot for the info. I will then wait for your updated Simfactory scripts before compiling on it.
Cheers, Bruno
On Jan 8, 2013, at 12:58 PM, Erik Schnetter wrote:
Bruno
I'm currently testing the Einstein Toolkit on Stampede. Even without the MICs, this is a very nice and fast system, almost ideal for the ET. The scripts in Simfactory should almost work; I will update them in the coming days. (The system was unavailable in the past days, so I couldn't test them recently.)
The MICs (Xeon Phis) can be used in two ways. One can view them as an accelerator (like a GPU), and then offload certain calculations there. Unfortunately neither CUDA nor OpenCL are available there, hence one has to use PGI's OpenACC and deal with PGI's compiler that has serious problems with OpenMP.
The other option is to view the Xeon Phis as regular processors. I believe that I/O will be quite slow from them, and MPI does not (yet?) fully work there, but apart from this, one can run the ET there directly. The small caches and in-order execution will make for some challenges; in particular, multi-threading e.g. via OpenMP will be a must.
In the end, I assume that one would want to use them either as accelerator (if not via OpenCL then via something equivalent, just different), or as regular compute nodes where Carpet will have to be enhanced to handle the different CPU speeds between Xeons and Xeon Phis.
-erik
On Tue, Jan 8, 2013 at 2:35 PM, Bruno Giacomazzo < bruno.giacomazzo@jila.colorado.edu> wrote:
Hi, I'd like to compile and run ET on the new TACC cluster Stampede. Did anybody run ET on stampede? I see that there are already simfactory scripts for stampede in the ET development version, but I'm not sure if they have been already fully tested (I see that there are comments about job submission not having been tested yet).
I'm also curious to know if you think that the hybrid approach can be of any use for ET/GRHydro (or ET/Whisky) on that machine. I'm not very familiar with the Intel Phi coprocessor and MIC programming (but it seems similar to GPU, except for being much easier to use).
Thanks, Bruno
Dr. Bruno Giacomazzo JILA - University of Colorado 440 UCB Boulder, CO 80309 USA
Tel. : +1 303-492-5170 Fax : +1 303-492-5235 email : bruno.giacomazzo@jila.colorado.edu web: http://www.brunogiacomazzo.org
There are only 10 types of people in the world: Those who understand binary, and those who don't
Users mailing list Users@einsteintoolkit.org http://lists.einsteintoolkit.org/mailman/listinfo/users
-- Erik Schnetter schnetter@cct.lsu.edu http://www.perimeterinstitute.ca/personal/eschnetter/
Dr. Bruno Giacomazzo JILA - University of Colorado 440 UCB Boulder, CO 80309 USA
Tel. : +1 303-492-5170 Fax : +1 303-492-5235 email : bruno.giacomazzo@jila.colorado.edu web: http://www.brunogiacomazzo.org
There are only 10 types of people in the world: Those who understand binary, and those who don't
Dr. Bruno Giacomazzo JILA - University of Colorado 440 UCB Boulder, CO 80309 USA
Tel. : +1 303-492-5170 Fax : +1 303-492-5235 email : bruno.giacomazzo@jila.colorado.edu web: http://www.brunogiacomazzo.org
There are only 10 types of people in the world: Those who understand binary, and those who don't
Hi Erik,
On Feb 4, 2013, at 5:16 PM, Erik Schnetter wrote:
Bruno
This may be an error in thorn Vectors, or in LoopControl. You could try updating Vectors from the trunk. LoopControl has probably changed too much to be useful for you.
thanks for the info.
The different MPI version that Yosef mentioned is unrelated. Simfactory uses the MPI version that can be used with the MICs, which is probably not relevant for you. You could try Yosef's MPI suggestion and compare performance.
Are you accidentally setting VECTORISE_ALIGNED_ARRAYS?
no, these are the options I have:
VECTORISE = yes VECTORISE_ALIGNED_ARRAYS = no VECTORISE_INLINE = no
Cheers, Bruno
-erik
On Mon, Feb 4, 2013 at 5:36 PM, Bruno Giacomazzo bruno.giacomazzo@jila.colorado.edu wrote: Hi Erik, I'm trying to test the Orsted version of ET on stampede. I'm able to compile using the option file that you created for the development version (except that I needed to add -U__STRICT_ANSI__ to CFLAGS otherwise the PITTNullCode/SphericalHarmonicRecon/src/util/fftwfilter util would not compile properly because it doesn't find M_PI).
I have some problems with some of the testsuites. Some of them fail because of segfaults. For example EinsteinEvolve/GRHydro/test/GRHydro_test_tov_ppm_ML.par crashed with a segfault. If I look with gdb at the core file, this is the info I get:
Program terminated with signal 11, Segmentation fault. #0 0x0000000000c6feb3 in L__ZN129_INTERNAL_106__work_01052_tg803155_EinsteinToolkit_Orsted_Cactus_configs_sim_build_ML_BSSN_ML_BSSN_convertFromADMBase_cc_ca14dd0a31ML_BSSN_convertFromADMBase_BodyEPK4_cGHiiPKdS4_S4_PKiS6_iPrKPd_196__par_region0_2_306 () at /work/01052/tg803155/EinsteinToolkit/Orsted/Cactus/arrangements/McLachlan/ML_BSSN/src/ML_BSSN_convertFromADMBase.cc:332 332 vec_store_nta_partial(alpha[index],alphaL);
Any idea? Is anyone using the latest stable ET release on Stampede?
Thanks, Bruno
On Jan 8, 2013, at 2:03 PM, Bruno Giacomazzo wrote:
Hi Erik, thanks a lot for the info. I will then wait for your updated Simfactory scripts before compiling on it.
Cheers, Bruno
On Jan 8, 2013, at 12:58 PM, Erik Schnetter wrote:
Bruno
I'm currently testing the Einstein Toolkit on Stampede. Even without the MICs, this is a very nice and fast system, almost ideal for the ET. The scripts in Simfactory should almost work; I will update them in the coming days. (The system was unavailable in the past days, so I couldn't test them recently.)
The MICs (Xeon Phis) can be used in two ways. One can view them as an accelerator (like a GPU), and then offload certain calculations there. Unfortunately neither CUDA nor OpenCL are available there, hence one has to use PGI's OpenACC and deal with PGI's compiler that has serious problems with OpenMP.
The other option is to view the Xeon Phis as regular processors. I believe that I/O will be quite slow from them, and MPI does not (yet?) fully work there, but apart from this, one can run the ET there directly. The small caches and in-order execution will make for some challenges; in particular, multi-threading e.g. via OpenMP will be a must.
In the end, I assume that one would want to use them either as accelerator (if not via OpenCL then via something equivalent, just different), or as regular compute nodes where Carpet will have to be enhanced to handle the different CPU speeds between Xeons and Xeon Phis.
-erik
On Tue, Jan 8, 2013 at 2:35 PM, Bruno Giacomazzo bruno.giacomazzo@jila.colorado.edu wrote: Hi, I'd like to compile and run ET on the new TACC cluster Stampede. Did anybody run ET on stampede? I see that there are already simfactory scripts for stampede in the ET development version, but I'm not sure if they have been already fully tested (I see that there are comments about job submission not having been tested yet).
I'm also curious to know if you think that the hybrid approach can be of any use for ET/GRHydro (or ET/Whisky) on that machine. I'm not very familiar with the Intel Phi coprocessor and MIC programming (but it seems similar to GPU, except for being much easier to use).
Thanks, Bruno
Dr. Bruno Giacomazzo JILA - University of Colorado 440 UCB Boulder, CO 80309 USA
Tel. : +1 303-492-5170 Fax : +1 303-492-5235 email : bruno.giacomazzo@jila.colorado.edu web: http://www.brunogiacomazzo.org
There are only 10 types of people in the world: Those who understand binary, and those who don't
Users mailing list Users@einsteintoolkit.org http://lists.einsteintoolkit.org/mailman/listinfo/users
-- Erik Schnetter schnetter@cct.lsu.edu http://www.perimeterinstitute.ca/personal/eschnetter/
Dr. Bruno Giacomazzo JILA - University of Colorado 440 UCB Boulder, CO 80309 USA
Tel. : +1 303-492-5170 Fax : +1 303-492-5235 email : bruno.giacomazzo@jila.colorado.edu web: http://www.brunogiacomazzo.org
There are only 10 types of people in the world: Those who understand binary, and those who don't
Dr. Bruno Giacomazzo JILA - University of Colorado 440 UCB Boulder, CO 80309 USA
Tel. : +1 303-492-5170 Fax : +1 303-492-5235 email : bruno.giacomazzo@jila.colorado.edu web: http://www.brunogiacomazzo.org
There are only 10 types of people in the world: Those who understand binary, and those who don't
-- Erik Schnetter schnetter@cct.lsu.edu http://www.perimeterinstitute.ca/personal/eschnetter/
Dr. Bruno Giacomazzo JILA - University of Colorado 440 UCB Boulder, CO 80309 USA
Tel. : +1 303-492-5170 Fax : +1 303-492-5235 email : bruno.giacomazzo@jila.colorado.edu web: http://www.brunogiacomazzo.org
---------------------------------------------------------------------- There are only 10 types of people in the world: Those who understand binary, and those who don't ----------------------------------------------------------------------
On Mon, Feb 4, 2013 at 5:36 PM, Bruno Giacomazzo < bruno.giacomazzo@jila.colorado.edu> wrote:
Hi Erik, I'm trying to test the Orsted version of ET on stampede. I'm able to compile using the option file that you created for the development version (except that I needed to add -U__STRICT_ANSI__ to CFLAGS otherwise the PITTNullCode/SphericalHarmonicRecon/src/util/fftwfilter util would not compile properly because it doesn't find M_PI).
I just checked -- I do not need to add this flag on Stampede.
-erik
Erik,
On Feb 4, 2013, at 9:28 PM, Erik Schnetter wrote:
On Mon, Feb 4, 2013 at 5:36 PM, Bruno Giacomazzo bruno.giacomazzo@jila.colorado.edu wrote: Hi Erik, I'm trying to test the Orsted version of ET on stampede. I'm able to compile using the option file that you created for the development version (except that I needed to add -U__STRICT_ANSI__ to CFLAGS otherwise the PITTNullCode/SphericalHarmonicRecon/src/util/fftwfilter util would not compile properly because it doesn't find M_PI).
I just checked -- I do not need to add this flag on Stampede.
do you use Orsted or Development? I use Orsted. Anyway, I needed that flag only to compile one of the SphericalHarmonicRecon utilities, not the cactus executable.
Cheers, Bruno
Dr. Bruno Giacomazzo JILA - University of Colorado 440 UCB Boulder, CO 80309 USA
Tel. : +1 303-492-5170 Fax : +1 303-492-5235 email : bruno.giacomazzo@jila.colorado.edu web: http://www.brunogiacomazzo.org
---------------------------------------------------------------------- There are only 10 types of people in the world: Those who understand binary, and those who don't ----------------------------------------------------------------------
On Feb 5, 2013, at 10:38 AM, Bruno Giacomazzo wrote:
Erik,
On Feb 4, 2013, at 9:28 PM, Erik Schnetter wrote:
On Mon, Feb 4, 2013 at 5:36 PM, Bruno Giacomazzo bruno.giacomazzo@jila.colorado.edu wrote: Hi Erik, I'm trying to test the Orsted version of ET on stampede. I'm able to compile using the option file that you created for the development version (except that I needed to add -U__STRICT_ANSI__ to CFLAGS otherwise the PITTNullCode/SphericalHarmonicRecon/src/util/fftwfilter util would not compile properly because it doesn't find M_PI).
I just checked -- I do not need to add this flag on Stampede.
do you use Orsted or Development? I use Orsted. Anyway, I needed that flag only to compile one of the SphericalHarmonicRecon utilities, not the cactus executable.
actually, I need to add that flag also with the development version (but only in order to be able to compile that utility).
Cheers, Bruno
Dr. Bruno Giacomazzo JILA - University of Colorado 440 UCB Boulder, CO 80309 USA
Tel. : +1 303-492-5170 Fax : +1 303-492-5235 email : bruno.giacomazzo@jila.colorado.edu web: http://www.brunogiacomazzo.org
---------------------------------------------------------------------- There are only 10 types of people in the world: Those who understand binary, and those who don't ----------------------------------------------------------------------
users@lists.einsteintoolkit.org
-
Bruno Giacomazzo -
Erik Schnetter -
Yosef Zlochower