performance
Differences
This shows you the differences between two versions of the page.
Both sides previous revisionPrevious revisionNext revision | Previous revision | ||
performance [2016/11/23 12:09] – 129.215.62.120 | performance [2020/11/10 13:29] (current) – removed Noctua LiH-HFX results because faulty rschade | ||
---|---|---|---|
Line 5: | Line 5: | ||
The purpose of the CP2K benchmark suite is to provide performance which can be used to guide users towards the best configuration (e.g. machine, number of MPI processors, number of OpenMP threads) for a particular problem, and give a good estimation for the parallel performance of the code for different types of method. Five benchmarks are provided: '' | The purpose of the CP2K benchmark suite is to provide performance which can be used to guide users towards the best configuration (e.g. machine, number of MPI processors, number of OpenMP threads) for a particular problem, and give a good estimation for the parallel performance of the code for different types of method. Five benchmarks are provided: '' | ||
- | We encourage you to contribute benchmark results from your own local cluster or HPC system - just run the inputs and add timings in the relevant sections below. | + | We encourage you to contribute benchmark results from your own local cluster or HPC system - just run the inputs and add timings in the relevant sections below. |
- | If you have any questions or problems running benchmarks or using the scripts please contact | + | If you have any questions or problems running benchmarks or using the scripts please contact Iain Bethune (< |
===== Notes on Results ===== | ===== Notes on Results ===== | ||
Line 23: | Line 23: | ||
=== Description === | === Description === | ||
- | // | + | // |
=== Availability === | === Availability === | ||
The benchmark is available (along with other water systems) from the CP2K source distribution: | The benchmark is available (along with other water systems) from the CP2K source distribution: | ||
- | [[src>cp2k/tests/QS/benchmark/]] | + | [[src>benchmarks/QS/]] |
=== Results === | === Results === | ||
Line 34: | Line 34: | ||
The best configurations are shown below. Click the links to see more detail. | The best configurations are shown below. Click the links to see more detail. | ||
- | ^ Machine Name ^ Architecture ^ Date ^ SVN Revision | + | ^ Machine Name ^ Architecture ^ Date ^ Git Commit |
- | | HECToR | Cray XE6 | 21/1/2014 | 13196 | 39.066 | 512 cores | 2 OMP threads per MPI task | [[performance: | + | | HECToR |
- | | ARCHER | Cray XC30 | 8/1/2014 | 13473 | 18.11 | 576 cores | 1 OMP thread per MPI task | [[performance: | + | | ARCHER |
- | | Magnus | Cray XC40 | 22/10/2014 | 14377 | 17.275 | 384 cores | 1 OMP thread per MPI task | [[performance: | + | | Magnus |
- | | Piz Daint | Cray XC30 | 12/05/2015 | 15268 | 19.885 | 192 cores | 1 OMP thread per MPI task, no GPU | [[performance: | + | | Piz Daint | Cray XC30 | 12/05/2015 | [[commit> |
+ | | Cirrus | ||
+ | | Noctua | ||
==== Fayalite-FIST ==== | ==== Fayalite-FIST ==== | ||
Line 50: | Line 51: | ||
The benchmark is available from the CP2K source distribution: | The benchmark is available from the CP2K source distribution: | ||
- | [[src>cp2k/tests/Fist/benchmark/]] | + | [[src>benchmarks/Fist/]] |
=== Results === | === Results === | ||
Line 56: | Line 57: | ||
The best configurations are shown below. Click the links to see more detail. | The best configurations are shown below. Click the links to see more detail. | ||
- | ^ Machine Name ^ Architecture ^ Date ^ SVN Revision | + | ^ Machine Name ^ Architecture ^ Date ^ Git Commit |
- | | HECToR | Cray XE6 | 21/1/2014 | 13196 | 403.928 | 2048 cores | 4 OMP threads per MPI task | [[performance: | + | | HECToR |
- | | ARCHER | Cray XC30 | 9/1/2014 | 13473 | 197.117 | 576 cores | 6 OMP threads per MPI task | [[performance: | + | | ARCHER |
- | | Magnus | Cray XC40 | 6/11/2014 | 14377 | 150.493 | 768 cores | 6 OMP threads per MPI task | [[performance: | + | | Magnus |
- | | Piz Daint | Cray XC30 | 12/05/2015 | 15268 | 207.972 | 512 cores | 2 OMP threads per MPI task, no GPU | [[performance: | + | | Piz Daint | Cray XC30 | 12/05/2015 | [[commit> |
+ | | Cirrus | ||
+ | | Noctua | ||
==== LiH-HFX ==== | ==== LiH-HFX ==== | ||
Line 67: | Line 69: | ||
=== Description === | === Description === | ||
- | This is a single-point energy calculation using [[Quickstep]] GAPW (Gaussian and Augmented Plane-Waves) with hybrid Hartree-Fock exchange. It consists of a 216 atom Lithium Hydride crystal with 432 electrons in a 12.3 Å< | + | This is a single-point energy calculation using [[Quickstep]] GAPW (Gaussian and Augmented Plane-Waves) with hybrid Hartree-Fock exchange. It consists of a 216 atom Lithium Hydride crystal with 432 electrons in a 12.3 Å< |
=== Availability === | === Availability === | ||
- | The benchmark is available from [[src>cp2k/tests/ | + | The benchmark is available from [[src>benchmarks/QS_LiH_HFX/]]. |
=== Results === | === Results === | ||
Line 77: | Line 79: | ||
The best configurations are shown below. Click the links to see more detail. | The best configurations are shown below. Click the links to see more detail. | ||
- | ^ Machine Name ^ Architecture ^ Date ^ SVN Revision | + | ^ Machine Name ^ Architecture ^ Date ^ Git Commit |
- | | HECToR | Cray XE6 | 21/1/2014 | 13196 | 121.362 | 65536 cores | 8 OMP threads per MPI task | [[performance: | + | | HECToR |
- | | ARCHER | Cray XC30 | 9/1/2014 | 13473 | 51.172 | 49152 cores | 6 OMP threads per MPI task | [[performance: | + | | ARCHER |
- | | Magnus | Cray XC40 | 10/11/2014 | 14377 | 62.075 | 24576 cores | 4 OMP threads per MPI task | [[performance: | + | | Magnus |
- | | Piz Daint | Cray XC30 | 12/05/2015 | 15268 | 66.051 | 32768 cores | 4 OMP threads per MPI task, no GPU | [[performance: | + | | Piz Daint | Cray XC30 | 12/05/2015 | [[commit> |
+ | | Cirrus | ||
+ | (*) Prior to r14945, a bug resulted in an underestimation of the number of ERIs which should be computed (by roughly 50% for this benchmark. | ||
==== H2O-DFT-LS ==== | ==== H2O-DFT-LS ==== | ||
Line 92: | Line 95: | ||
=== Availability === | === Availability === | ||
- | The benchmark input file is available here. It is a slightly modified version of the more general one in the CP2K SVN at, where the problem size can be tuned by a parameter NREP: [[src>cp2k/tests/ | + | The benchmark input file used to generate these results |
+ | |||
+ | It is a slightly modified version of the more general one in the CP2K github | ||
=== Results === | === Results === | ||
Line 98: | Line 103: | ||
The best configurations are shown below. Click the links to see more detail. | The best configurations are shown below. Click the links to see more detail. | ||
- | ^ Machine Name ^ Architecture ^ Date ^ SVN Revision | + | ^ Machine Name ^ Architecture ^ Date ^ Git Commit |
- | | HECToR | Cray XE6 | 16/1/2014 | 13196 | 98.256 | 65536 cores | 8 OMP threads per MPI task | [[performance: | + | | HECToR |
- | | ARCHER | Cray XC30 | 8/1/2014 | 13473 | 28.476 | 49152 cores | 4 OMP threads per MPI task | [[performance: | + | | ARCHER |
- | | Magnus | Cray XC40 | 3/12/2014 | 14377 | 30.921 | 24576 cores | 2 OMP threads per MPI task | [[performance: | + | | Magnus |
- | | Piz Daint | Cray XC30 | 12/05/2015 | 15268 | 27.900 | 32768 cores | 2 OMP threads per MPI task, no GPU | [[performance: | + | | Piz Daint | Cray XC30 | 12/05/2015 | [[commit> |
+ | | Cirrus | ||
+ | | Noctua | ||
==== H2O-64-RI-MP2 ==== | ==== H2O-64-RI-MP2 ==== | ||
Line 113: | Line 119: | ||
=== Availability === | === Availability === | ||
- | The benchmark is in the CP2K SVN at: [[src>cp2k/tests/ | + | The benchmark is in the CP2K github |
=== Results === | === Results === | ||
Line 119: | Line 125: | ||
The best configurations are shown below. Click the links to see more detail. | The best configurations are shown below. Click the links to see more detail. | ||
- | ^ Machine Name ^ Architecture ^ Date ^ SVN Revision | + | ^ Machine Name ^ Architecture ^ Date ^ Git Commit |
- | | HECToR | Cray XE6 | 13/1/2014 | 13196 | 141.633 | 49152 cores | 8 OMP threads per MPI task | [[performance: | + | | HECToR |
- | | ARCHER | Cray XC30 | 9/1/2014 | 13473 | 83.945 | 36864 cores | 4 OMP threads per MPI task | [[performance: | + | | ARCHER |
- | | Magnus | Cray XC40 | 4/11/2014 | 14377 | 63.891 | 24576 cores | 6 OMP threads per MPI task | [[performance: | + | | Magnus |
- | | Piz Daint | Cray XC30 | 12/05/2015 | 15268 | 48.15 | 32768 cores | 8 OMP threads per MPI task, no GPU | [[performance: | + | | Piz Daint | Cray XC30 | 12/05/2015 | [[commit> |
+ | | Cirrus | ||
+ | | Noctua |
performance.1479902953.txt.gz · Last modified: 2020/08/21 10:15 (external edit)