Commit Graph

70 Commits

Author SHA1 Message Date
Jan Eitzinger b6d4753c2a Add LIKWID Option. Allow to overwrite with asm variant. 2021-06-11 09:38:34 +02:00
Rafael Ravedutti b8b364d265 Move analysis and result files to log directory
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2021-06-11 02:16:10 +02:00
Rafael Ravedutti 0482e4f09a Avoid resize messages on run_stub output and build objects from assembly files
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2021-05-22 03:26:56 +02:00
Rafael Ravedutti abc844947d Add results with small number of unit cells and higher number of neighbors
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2021-05-20 20:38:53 +02:00
Rafael Ravedutti f8e5415195 Add results for casclakesp2 and skylakesp2 with iln=100,1000
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2021-05-20 00:47:30 +02:00
Rafael Ravedutti 56ad09156b Fix explicit types for stubbed version
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2021-05-20 00:08:10 +02:00
Rafael Ravedutti 4496e91125 Add version with explicit types for atoms
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2021-05-19 23:51:02 +02:00
Rafael Ravedutti f7f7ae2002 Update soa_broadep2_iln1000 results
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2021-05-16 23:58:52 +02:00
Rafael Ravedutti 6704089f7d Update .gitignore
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2021-05-16 23:52:59 +02:00
Rafael Ravedutti 6c4168fdb5 Add OSACA analysis and ASM code for AVX2 with AoS, lt600 variant
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2021-05-08 01:03:44 +02:00
Rafael Ravedutti 6c03ea3f3c Adjust output when computing invalid values
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2021-05-07 02:31:53 +02:00
Rafael Ravedutti 9c28ff1e9e Add arch_analysis directory and first AVX2 results
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2021-05-06 23:18:28 +02:00
Rafael Ravedutti 327cc302b8 Create avx512 directory for analysis
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2021-05-06 14:00:08 +02:00
Rafael Ravedutti e53d9961ef Fix compilation when INTERNAL_LOOP_NTIMES is not set and create avx512 directory
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2021-05-06 13:59:02 +02:00
Rafael Ravedutti 15de65303e Add version iterating most internal loop multiple times
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2021-05-05 03:04:41 +02:00
Rafael Ravedutti faf1e2ae85 Update results and assembly for SoA
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2021-04-30 15:58:54 +02:00
Rafael Ravedutti 0a81407948 Fix invalid values for cycles per neighbor
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2021-04-29 20:29:00 +02:00
Rafael Ravedutti 11b2d4bcc1 Update results for arch_analysis and stub script
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2021-04-29 17:57:37 +02:00
Rafael Ravedutti 02ff7de18f Add markers for all kernel variants
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2021-04-28 23:19:06 +02:00
Rafael Ravedutti 10dacc5a4e Add force for AoS data layout with markers
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2021-04-28 17:48:40 +02:00
Rafael Ravedutti 5cb341ab1f Add IACA output for SOA
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2021-04-27 01:04:31 +02:00
Rafael Ravedutti d0d2bf8a0c Add OSACA output for SOA
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2021-04-27 00:36:34 +02:00
Rafael Ravedutti 1a195a30e2 Add script to get stub results for several configurations
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2021-04-22 20:24:50 +02:00
Rafael Ravedutti c356336dbd Show cycles per atom and neighbor
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2021-04-22 16:50:22 +02:00
Rafael Ravedutti 4c53519c73 Add output as CSV
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2021-04-22 01:22:18 +02:00
Rafael Ravedutti fd108d97d8 Fix problem when atoms_per_unit_cell is less or equal than 4
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2021-04-22 00:07:42 +02:00
Rafael Ravedutti 3c7dbc833a Allow any values for atoms_per_unit_cell
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2021-04-21 13:01:06 +02:00
Rafael Ravedutti d3121ee08f Adjust computeForce parameters for stub
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2021-04-21 11:28:02 +02:00
Rafael Ravedutti 5131b7bcaa Add comments for second kernel variant on Intel AOS assembly
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2021-04-16 16:31:27 +02:00
Rafael Ravedutti e656490a38 Add annotated assembly files
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2021-04-16 12:44:18 +02:00
Rafael Ravedutti 78e6e5c773 Merge master branch into stub
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2021-04-15 20:12:36 +02:00
Jan Eitzinger 06ba3b2726 Restructure timing and instrumentation. Add performance metric. 2021-04-15 14:55:02 +02:00
Rafael Ravedutti a0699dde4c Merge branch 'master' into stub 2021-04-12 23:10:36 +02:00
Jan Eitzinger 35273c491b Introduce generic variant targets
Change Makefiles to allow multiple binary targets specified by VARIANT
environment variabel. For specified variants a matching main-<VARIANT>.c
source file must be present.
2021-04-12 08:24:27 +02:00
Rafael Ravedutti 706f1c38f2 Update stubbed force calculation
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2021-04-07 00:46:51 +02:00
Rafael Ravedutti 77a0774208 Improve stubbed force calculation version
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2021-03-30 22:17:30 +02:00
Rafael Ravedutti 7efd30791a Add version with stubbed force calculation
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2021-03-30 01:54:56 +02:00
Jan Eitzinger 2bc3120112 Put force kernel in separate compilation unit 2021-03-25 06:49:28 +01:00
moebiusband73 dcfa1c4135 Merge pull request #2 from RRZE-HPC/aos
Aos
2021-03-24 08:50:29 +01:00
Jan Eitzinger 32b23a2ebd Set defaults for GCC 2021-03-24 08:48:27 +01:00
Jan Eitzinger d026028439 Streamline build system 2021-03-24 08:43:44 +01:00
Rafael Ravedutti 4b481bb407 Fix macros for AoS
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2021-03-23 16:21:08 +01:00
Jan Eitzinger fc1fc9fd45 Port pbc to new macros. Enable debugging flags. 2021-03-23 10:03:55 +01:00
Jan Eitzinger 6679b6c8aa Simplify macros for data structure access.
Still segvaults for AoS.
2021-03-23 09:26:41 +01:00
Rafael Ravedutti cb0ae2b0bb Replace inline calls by macros
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2021-03-22 21:51:47 +01:00
Rafael Ravedutti 3f7edb5dbf Add support for AoS data layout
Signed-off-by: Rafael Ravedutti <rafaelravedutti@gmail.com>
2021-03-20 18:32:50 +01:00
Jan Eitzinger b39957421c Include Likwid Markers. Allow to switch between SP and DP floats. 2020-11-05 12:41:44 +01:00
moebiusband73 b45ab26e03 Update README.md 2020-09-07 07:42:45 +02:00
Jan Eitzinger fb0ef3fa12 Adapt ICC build config 2020-08-19 13:53:44 +02:00
Jan Eitzinger 0fd51e8a9c Add OpenMP parallelization for computeForce. 2020-08-19 11:19:16 +02:00