Commit Graph

  • bfa6c581c3 Copy necessary values for force calculation into cuda memory Maximilian Gaul 2021-11-09 08:37:37 +0100
  • f8b9a095cf Add working version of force.s Rafael Ravedutti 2021-11-09 01:23:15 +0100
  • b2dada6179 Fix param references and assembler errors for force.s Rafael Ravedutti 2021-11-09 00:05:42 +0100
  • d8c8733cb2 Update asm force again Rafael Ravedutti 2021-11-08 23:32:24 +0100
  • cf7ea1460c Update asm version to be integrated Rafael Ravedutti 2021-11-08 22:31:58 +0100
  • fd886e77eb Added make config for NVCC Maximilian Gaul 2021-11-08 20:32:12 +0100
  • 9b615cf0b3 Update force kernel to be integrated Rafael Ravedutti 2021-11-08 14:05:29 +0100
  • ec556eb117 Add EAM without explicit types and update fp for PBC atoms Rafael Ravedutti 2021-11-03 00:57:24 +0100
  • 0f1e824507 Fix integration with mass and add VTK output Rafael Ravedutti 2021-10-29 16:52:19 +0200
  • d9c9cba12d Set EAM parameters for same case as miniMD Rafael Ravedutti 2021-10-27 01:38:56 +0200
  • 70cc6aeb19 Add first working version of EAM Rafael Ravedutti 2021-10-26 13:55:14 +0200
  • 7db14b2ffe Merge branch 'master' of github.com:RRZE-HPC/MD-Bench Rafael Ravedutti 2021-10-26 12:34:43 +0200
  • d7056f09f4 Fix illegal accesses due to invalid type of ghost atoms Rafael Ravedutti 2021-10-26 12:34:35 +0200
  • 70e24d7c2c Merge branch 'master' of github.com:RRZE-HPC/MD-Bench Jan Eitzinger 2021-10-26 09:16:31 +0200
  • 3c3d27b48a Introduce separate version for traced force routine. Jan Eitzinger 2021-10-26 09:11:17 +0200
  • 99d6a4bdd8 Fix Funcfl reference to avoid segfaults Rafael Ravedutti 2021-10-26 01:40:02 +0200
  • 40ddc9ad50 Fix errors introduced by last changes Rafael Ravedutti 2021-10-26 01:19:11 +0200
  • 2dac10469c Add EAM force field Rafael Ravedutti 2021-10-26 00:40:39 +0200
  • 9d16bb46c8 Include average neighbors and SIMD iterations per atom on stats Rafael Ravedutti 2021-10-20 22:43:08 +0200
  • 557c5e4d3f IUpdate logbook again and do not check for variant on ATOMS_LOOP_RUNS effect Rafael Ravedutti 2021-10-14 00:46:30 +0200
  • 40bbaac078 Add hardware information on logbook Rafael Ravedutti 2021-10-13 22:27:34 +0200
  • c46e4ee4df Include ATOMS_LOOP_RUNS option in config.mk file Rafael Ravedutti 2021-10-12 23:35:58 +0200
  • 43ba28e130 Add ATOMS_LOOP_RUNS option and statistics to stub variant Rafael Ravedutti 2021-10-12 22:39:54 +0200
  • 55d346510e Compute statistics, useful data volume and cycles per SIMD iteration Rafael Ravedutti 2021-10-12 15:04:08 +0200
  • f295f54fca Add useful data volume calculation for force kernel Rafael Ravedutti 2021-10-11 16:57:02 +0200
  • 4e0390404a Add correct version (without traces) of CACHES_PMC results with and without force calculation on casclakesp2 Rafael Ravedutti 2021-10-06 16:08:46 +0200
  • b1f8e91f0f Add cache measurements for versions with and without force computation Rafael Ravedutti 2021-10-04 18:13:17 +0200
  • 749c4d55ab Provide trace output for all reneighboring steps Rafael Ravedutti 2021-10-04 16:47:07 +0200
  • 2889577a3b Add neighbor lists capacity to index tracer file Rafael Ravedutti 2021-08-10 17:28:59 +0200
  • b8d71090aa Add number of atoms in index tracer file Rafael Ravedutti 2021-08-10 16:43:51 +0200
  • 6b75c158d6 Include atom reference on index tracer and add only_mem ASM version Rafael Ravedutti 2021-08-10 01:19:26 +0200
  • 9d79f0248f Add config option to switch between asm syntaxes Rafael Ravedutti 2021-08-09 21:37:18 +0200
  • effd961f29 Add cache sets histogram script, update gather plot script and add results for icx32 Rafael Ravedutti 2021-07-29 17:01:30 +0200
  • 57041ceed2 Add likwid-perfctr run with CACHES_PMC for 1 timestep on casclakesp2 Rafael Ravedutti 2021-07-16 00:24:43 +0200
  • 8e1542c87d Sort elements within vector to fix distance calculation on index tracer Rafael Ravedutti 2021-07-15 23:51:00 +0200
  • d97fc577b0 Add first version of index and distance tracer Rafael Ravedutti 2021-07-09 23:49:14 +0200
  • e6062e8f79 Update script to plot stubbed data and add results for casclakesp2 with AoS Rafael Ravedutti 2021-07-03 03:07:35 +0200
  • eef44e97d7 Update cache settings for casclakesp2 and results Rafael Ravedutti 2021-07-02 02:57:31 +0200
  • 4bde1944cf Update script for plotting gather data and AOS results for casclakesp2 Rafael Ravedutti 2021-07-01 20:02:59 +0200
  • 5534f1b195 Modify gather script to include raw data and update results without prefetchers Rafael Ravedutti 2021-06-30 16:09:34 +0200
  • ecb5ccf6ff Adjust likwid markers for force region Rafael Ravedutti 2021-06-30 13:44:02 +0200
  • 06aae5593b Add script to plot gather data Rafael Ravedutti 2021-06-25 02:02:08 +0200
  • 7ae22a5695 Add forces reading operation on memory tracer and include ampersand in TRACER_PRINT Rafael Ravedutti 2021-06-21 22:56:44 +0200
  • 0bb7e3c61f Add cache simulator script and first results Rafael Ravedutti 2021-06-17 03:07:34 +0200
  • 0a2ec6376c Add memory tracer and update config.mk with all options Rafael Ravedutti 2021-06-16 00:56:00 +0200
  • 933f7c7bba Update README.md to fix lists Rafael Ravedutti 2021-06-11 16:42:23 +0200
  • 977bc68699 Add README.md for utilities Rafael Ravedutti 2021-06-11 16:38:53 +0200
  • 91661a79e6 Add plot script and move scripts to util directory Rafael Ravedutti 2021-06-11 15:34:19 +0200
  • 1a18341d84 Merge pull request #3 from RRZE-HPC/stub Jan Eitzinger 2021-06-11 09:50:05 +0200
  • c6f3f9afa1 Set ICC as default Jan Eitzinger 2021-06-11 09:48:41 +0200
  • b6d4753c2a Add LIKWID Option. Allow to overwrite with asm variant. Jan Eitzinger 2021-06-11 09:38:34 +0200
  • b8b364d265 Move analysis and result files to log directory Rafael Ravedutti 2021-06-11 02:16:10 +0200
  • 0482e4f09a Avoid resize messages on run_stub output and build objects from assembly files Rafael Ravedutti 2021-05-22 03:26:56 +0200
  • abc844947d Add results with small number of unit cells and higher number of neighbors Rafael Ravedutti 2021-05-20 20:38:53 +0200
  • f8e5415195 Add results for casclakesp2 and skylakesp2 with iln=100,1000 Rafael Ravedutti 2021-05-20 00:47:30 +0200
  • 56ad09156b Fix explicit types for stubbed version Rafael Ravedutti 2021-05-20 00:08:10 +0200
  • 4496e91125 Add version with explicit types for atoms Rafael Ravedutti 2021-05-19 23:51:02 +0200
  • f7f7ae2002 Update soa_broadep2_iln1000 results Rafael Ravedutti 2021-05-16 23:58:52 +0200
  • 6704089f7d Update .gitignore Rafael Ravedutti 2021-05-16 23:52:59 +0200
  • 6c4168fdb5 Add OSACA analysis and ASM code for AVX2 with AoS, lt600 variant Rafael Ravedutti 2021-05-08 01:03:44 +0200
  • 6c03ea3f3c Adjust output when computing invalid values Rafael Ravedutti 2021-05-07 02:31:53 +0200
  • 9c28ff1e9e Add arch_analysis directory and first AVX2 results Rafael Ravedutti 2021-05-06 23:18:28 +0200
  • 327cc302b8 Create avx512 directory for analysis Rafael Ravedutti 2021-05-06 14:00:08 +0200
  • e53d9961ef Fix compilation when INTERNAL_LOOP_NTIMES is not set and create avx512 directory Rafael Ravedutti 2021-05-06 13:59:02 +0200
  • 79e9de019f Update README.md moebiusband73 2021-05-05 09:58:46 +0200
  • 59886dba77 Update README.md moebiusband73 2021-05-05 09:55:22 +0200
  • 15de65303e Add version iterating most internal loop multiple times Rafael Ravedutti 2021-05-05 03:04:41 +0200
  • faf1e2ae85 Update results and assembly for SoA Rafael Ravedutti 2021-04-30 15:58:54 +0200
  • 0a81407948 Fix invalid values for cycles per neighbor Rafael Ravedutti 2021-04-29 20:29:00 +0200
  • 11b2d4bcc1 Update results for arch_analysis and stub script Rafael Ravedutti 2021-04-29 17:57:37 +0200
  • 02ff7de18f Add markers for all kernel variants Rafael Ravedutti 2021-04-28 23:19:06 +0200
  • 10dacc5a4e Add force for AoS data layout with markers Rafael Ravedutti 2021-04-28 17:48:40 +0200
  • 5cb341ab1f Add IACA output for SOA Rafael Ravedutti 2021-04-27 01:04:31 +0200
  • d0d2bf8a0c Add OSACA output for SOA Rafael Ravedutti 2021-04-27 00:36:34 +0200
  • 1a195a30e2 Add script to get stub results for several configurations Rafael Ravedutti 2021-04-22 20:24:50 +0200
  • c356336dbd Show cycles per atom and neighbor Rafael Ravedutti 2021-04-22 16:50:22 +0200
  • 4c53519c73 Add output as CSV Rafael Ravedutti 2021-04-22 01:22:18 +0200
  • fd108d97d8 Fix problem when atoms_per_unit_cell is less or equal than 4 Rafael Ravedutti 2021-04-22 00:07:42 +0200
  • 3c7dbc833a Allow any values for atoms_per_unit_cell Rafael Ravedutti 2021-04-21 13:01:06 +0200
  • d3121ee08f Adjust computeForce parameters for stub Rafael Ravedutti 2021-04-21 11:28:02 +0200
  • 5131b7bcaa Add comments for second kernel variant on Intel AOS assembly Rafael Ravedutti 2021-04-16 16:31:27 +0200
  • e656490a38 Add annotated assembly files Rafael Ravedutti 2021-04-16 12:44:18 +0200
  • 78e6e5c773 Merge master branch into stub Rafael Ravedutti 2021-04-15 20:12:36 +0200
  • 06ba3b2726 Restructure timing and instrumentation. Add performance metric. Jan Eitzinger 2021-04-15 14:55:02 +0200
  • a0699dde4c Merge branch 'master' into stub Rafael Ravedutti 2021-04-12 23:10:36 +0200
  • 35273c491b Introduce generic variant targets Jan Eitzinger 2021-04-12 08:24:27 +0200
  • 706f1c38f2 Update stubbed force calculation Rafael Ravedutti 2021-04-07 00:46:51 +0200
  • 77a0774208 Improve stubbed force calculation version Rafael Ravedutti 2021-03-30 22:17:30 +0200
  • 7efd30791a Add version with stubbed force calculation Rafael Ravedutti 2021-03-30 01:54:56 +0200
  • 2bc3120112 Put force kernel in separate compilation unit Jan Eitzinger 2021-03-25 06:49:28 +0100
  • dcfa1c4135 Merge pull request #2 from RRZE-HPC/aos moebiusband73 2021-03-24 08:50:29 +0100
  • 32b23a2ebd Set defaults for GCC Jan Eitzinger 2021-03-24 08:48:27 +0100
  • d026028439 Streamline build system Jan Eitzinger 2021-03-24 08:43:44 +0100
  • 4b481bb407 Fix macros for AoS Rafael Ravedutti 2021-03-23 16:21:08 +0100
  • fc1fc9fd45 Port pbc to new macros. Enable debugging flags. Jan Eitzinger 2021-03-23 10:03:55 +0100
  • 6679b6c8aa Simplify macros for data structure access. Jan Eitzinger 2021-03-23 09:26:41 +0100
  • cb0ae2b0bb Replace inline calls by macros Rafael Ravedutti 2021-03-22 21:51:47 +0100
  • 3f7edb5dbf Add support for AoS data layout Rafael Ravedutti 2021-03-20 18:32:50 +0100
  • b39957421c Include Likwid Markers. Allow to switch between SP and DP floats. Jan Eitzinger 2020-11-05 12:41:44 +0100
  • b45ab26e03 Update README.md moebiusband73 2020-09-07 07:42:45 +0200