chn/bscpkgs
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
721 Commits 1 Branch 0 Tags 1.8 MiB
e0197950a6
Commit Graph

189 Commits

Author SHA1 Message Date
Rodrigo Arias Mallo
e1433fedb8 nbody: refactor experiments into common.nix 2021-04-20 17:13:29 +02:00
Rodrigo Arias Mallo
f729fc4006 nbody: rename granularity experiment file 2021-04-19 17:27:52 +02:00
Antoni Navarro
03298228e4 nbody: add strong scaling experiment 2021-04-19 17:27:52 +02:00
Antoni Navarro
58294d4467 nbody: add "nodes or sockets" experiment 2021-04-19 17:27:52 +02:00
Antoni Navarro
48a61dc292 nbody: update indexes 2021-04-19 17:27:52 +02:00
Antoni Navarro
5815a9af09 nbody: move "old" experiments to another folder 2021-04-19 17:27:52 +02:00
Antoni Navarro
ea66d7e4e0 nbody: update granularity tests 2021-04-19 17:27:52 +02:00
Rodrigo Arias Mallo
866d4561d3 hpcg: remove old experiments 2021-04-19 16:01:11 +02:00
Rodrigo Arias Mallo
9a88319153 hpcg: add granularity experiment 2021-04-19 16:00:55 +02:00
Rodrigo Arias Mallo
a96839d11a hpcg: merge weak scaling and add size experiment 
The scaling.nix file defines both the strong and weak experiments by
using the parameter "enableStrong".
 2021-04-19 15:57:31 +02:00
Rodrigo Arias Mallo
a71ae9c2c6 hpcg: avoid mismatching names for gen units 2021-04-16 16:15:16 +02:00
Rodrigo Arias Mallo
d490ef2694 hpcg: remove unused extrae.xml file 2021-04-16 16:14:48 +02:00
Rodrigo Arias Mallo
b4e37a15a9 hpcg: refactor ss and gen using a common file 
- The file gen.nix now provides an experiment for each unit, to reduce
  the evaluation time.

- The pipeline is specified in the common.nix file only.

- The input dataset path is no longer symlinked, but is specified in the
  "--load" argument.

- The size is renamed to "sizePerTask" instead of "n".
 2021-04-16 11:51:34 +02:00
Raúl Peñacoba
4d629fe8f7 hpcg: remove old comments 2021-04-16 09:32:28 +02:00
Raúl Peñacoba
f5c8d0cb88 hpcg: choose a smaller strong scaling problem size 2021-04-16 09:32:28 +02:00
Raúl Peñacoba
cb6577b439 hpcg: add strongscaling 
HPCG rounds problem size axis when its value is < 16
 2021-04-16 09:32:28 +02:00
Raúl Peñacoba
b60a46b683 hpcg: add weakscaling over some nblocks to check which axis is better 2021-04-16 09:32:28 +02:00
Raúl Peñacoba
1a6075a2b1 hpcg: add first granularity/scalability exps for tampi+isend+oss+task 
- oss.nix runs valid hpcg layouts whereas slices.nix does not
 2021-04-16 09:32:28 +02:00
Rodrigo Arias Mallo
fb0dee4b61 exp: move exit1 experiment to slurm 2021-04-16 09:29:33 +02:00
Rodrigo Arias Mallo
2151e20bd6 exp: add exit1 experiment 
Tests unit bad exits
 2021-04-16 09:29:33 +02:00
Rodrigo Arias Mallo
0cf35decc5 osu: add mtu and eager experiments 2021-04-16 09:29:33 +02:00
Rodrigo Arias Mallo
f842f1e01d slurm: add sigsegv experiment 
Ensure that we can catch a sigsegv signal before and after the
MPI_Finalize call.
 2021-04-16 09:29:33 +02:00
Rodrigo Arias Mallo
dd75a840ce fwi: use enableIO instead of ioFreq 2021-04-12 20:09:17 +02:00
Rodrigo Arias Mallo
e49e3b087f fwi: rename big io experiment 2021-04-12 19:49:31 +02:00
Rodrigo Arias Mallo
59040d9355 fwi: fix inverted resources 2021-04-12 19:31:35 +02:00
Rodrigo Arias Mallo
6422741cb7 fwi: merge io experiments into one file 
The enableExtended parameter control if the experiment runs with
multiple nodes or only one.
 2021-04-12 19:27:45 +02:00
Rodrigo Arias Mallo
99beac9b23 fwi: generate the model in every node 
As we are using local storage, we need a copy of the input in every
node. The current method is to run the generator only in the rank which
has assigned the cpu 0 in the mask.
 2021-04-12 19:01:10 +02:00
Rodrigo Arias Mallo
58dc277d3d fwi: refactor ss-io with common.nix 
Also, keep the names short and consistent.
 2021-04-12 17:57:46 +02:00
Rodrigo Arias Mallo
47b326c646 fwi: generate the input at runtime 2021-04-12 17:46:07 +02:00
Rodrigo Arias Mallo
4afda7dbfb fwi: use common.nix in sync_io experiment 2021-04-12 16:27:18 +02:00
Rodrigo Arias Mallo
02a103565c fwi: use common.nix in reuse experiment 2021-04-12 15:48:59 +02:00
Rodrigo Arias Mallo
788dd13ebd fwi: merge mpi pure experiment 
The getResources function is used to assign the proper cpu binding
depending on the version. However, additional contraints are required to
ensure that we have enough points in Y.

By default the mpi+send+seq branch is disabled.
 2021-04-12 15:37:39 +02:00
Rodrigo Arias Mallo
41665bc6fc fwi: refactor config generation into common.nix 2021-04-12 15:01:25 +02:00
Rodrigo Arias Mallo
9aa07993b2 fwi: refactor ss and granularity experiments 
A common.nix file contains the shared stages
 2021-04-12 14:41:26 +02:00
Rodrigo Arias Mallo
e0a68c077c fwi: merge forkjoin ss experiment into one file 
Additional options are only active with enableExtended = true
 2021-04-12 12:51:10 +02:00
Aleix Roca Nonell
989f6ee018 fwi: adjust input size to meet timing constraints 
The previous iniput size for both granularity and strong scaling tests
where too big to meet the timing constrains needed for garlic. This
patch sets a new, smaller, input size.

Also, a minor cleanup is applied to the rest of the fwi experiments
and figures.
 2021-04-07 12:44:14 +02:00
Aleix Roca Nonell
3e5a56ebdb fwi: add tampi non-blocking variant 2021-04-07 12:44:14 +02:00
Aleix Roca Nonell
3ef4a505d3 fwi: add strong scalability tests 2021-04-07 12:44:14 +02:00
Aleix Roca Nonell
aadce016e1 fwi: add granularity and data reuse experiments 
The data reuse experiment shows the effect of poor data locality versus
task granularity.
 2021-04-07 12:44:14 +02:00
Aleix Roca Nonell
1d9a5c4721 fwi: fix input derivation 
The fwiInput derivation must be the same used when compiled the fwi app
as the fwi-input used in the experiment.
 2021-04-07 12:44:14 +02:00
Rodrigo Arias Mallo
11e400abb5 fwi: remove old experiment 2021-04-07 12:44:14 +02:00
Rodrigo Arias Mallo
7a6cbd3a9e fwi: update test experiment 2021-04-07 12:44:14 +02:00
Rodrigo Arias Mallo
bfbbc294ae fwi: split into input and solver 
All branches compile with several hacks.
 2021-04-07 12:44:13 +02:00
Rodrigo Arias Mallo
9bea3cc264 fwi: add oss experiment 2021-04-07 12:44:13 +02:00
Rodrigo Arias Mallo
f10f8472ac fwi: add seq test experiment 2021-04-07 12:44:13 +02:00
Rodrigo Arias Mallo
312656ce54 heat: rename granul -> granularity experiment 2021-04-06 18:42:49 +02:00
Rodrigo Arias Mallo
d1c32869c1 heat: split granularity with extended mode 
The HWC version is not yet complete.
 2021-04-06 18:38:15 +02:00
Rodrigo Arias Mallo
f8122f3c8b heat: use the hcut tool to limit the cpus 2021-04-06 11:05:56 +02:00
Rodrigo Arias Mallo
d68ce914ba heat: use cut to partition the trace 
The awk script doesn't take in consideration the events close to the cut
points, which are significative with low parallelism.
 2021-04-06 11:05:51 +02:00
Rodrigo Arias Mallo
cb482fa3ea heat: remove perf from the ctf experiment 
As we would be extracting perf stats from the trace processing steps.
 2021-04-06 11:05:10 +02:00