Archived
1
0
forked from rarias/bscpkgs

hpcg: add first granularity/scalability exps for tampi+isend+oss+task

- oss.nix runs valid hpcg layouts whereas slices.nix does not
This commit is contained in:
Raúl Peñacoba
2021-02-23 18:24:21 +01:00
committed by Rodrigo Arias Mallo
parent 12ff1fd506
commit 1a6075a2b1
14 changed files with 665 additions and 148 deletions

View File

@@ -5,7 +5,6 @@
, targetMachine
, stages
, garlicTools
, resultFromTrebuchet
}:
with stdenv.lib;
@@ -14,28 +13,23 @@ with garlicTools;
let
# Generate the complete configuration for each unit
genConf = with bsc; c: targetMachine.config // rec {
genConf = c: targetMachine.config // rec {
expName = "${c.expName}.gen";
unitName = "${expName}.n${toString n.x}";
inherit (targetMachine.config) hw;
# hpcg options
cc = bsc.icc;
mcxx = bsc.mcxx;
nanos6 = bsc.nanos6;
mpi = null; # TODO: Remove this for oss
# Only the n and gitBranch options are inherited
inherit (c) n gitBranch;
inherit (c) n nprocs disableAspectRatio nodes ntasksPerNode gitBranch;
# Repeat the execution of each unit 30 times
loops = 1;
# Resources
qos = "debug";
ntasksPerNode = 1;
nodes = 1;
time = "02:00:00";
# ntasksPerNode = hw.socketsPerNode;
# nodes = 2;
time = "00:30:00";
# task in one socket
cpusPerTask = hw.cpusPerSocket;
jobName = unitName;
@@ -43,25 +37,24 @@ let
exec = {nextStage, conf, ...}: with conf; stages.exec {
inherit nextStage;
env = "NANOS6_DEPENDENCIES=discrete";
argv = [
"--nx=${toString n.x}"
"--ny=${toString n.y}"
"--nz=${toString n.z}"
# The nblocks is ignored
#"--nblocks=${toString nblocks}"
"--nx=${toString conf.n.x}"
"--ny=${toString conf.n.y}"
"--nz=${toString conf.n.z}"
"--npx=${toString conf.nprocs.x}"
"--npy=${toString conf.nprocs.y}"
"--npz=${toString conf.nprocs.z}"
# nblocks and ncomms are ignored
"--nblocks=1"
"--ncomms=1"
# Store the results in the same directory
"--store=."
];
] ++ optional (conf.disableAspectRatio) "--no-ar=1";
};
program = {nextStage, conf, ...}: with conf;
let
customPkgs = stdexp.replaceMpi conf.mpi;
in
customPkgs.apps.hpcg.override {
inherit cc nanos6 mcxx gitBranch;
};
program = {nextStage, conf, ...}: bsc.apps.hpcg.override {
inherit (conf) gitBranch;
};
pipeline = stdexp.stdPipeline ++ [ exec program ];
@@ -78,7 +71,7 @@ let
inputExp = getExperimentStage inputTre;
# Then load the result. This is only used to ensure that we have the
# results, so it has been executed.
inputRes = resultFromTrebuchet inputTre;
inputRes = inputTre.result;
# We also need the unit, to compute the path.
inputUnit = stages.unit {
conf = genConf conf;
@@ -95,7 +88,9 @@ let
# ${inputRes}
# Then we simply link the input result directory in "input"
ln -s ${relPath} input
# We use || true because all ranks will execute this and
# the execution will fail
ln -sf ${relPath} input || true
'';
};

View File

@@ -21,7 +21,7 @@ let
n = c.n;
cc = bsc.icc;
mpi = bsc.impi;
gitBranch = "garlic/mpi+omp";
gitBranch = "garlic/mpi+send+omp+fork";
# Repeat the execution of each unit 30 times
loops = 30;

View File

@@ -22,7 +22,7 @@ let
nblocks = c.nblocks;
cc = bsc.icc;
mpi = null; # TODO: Remove this for omp
gitBranch = "garlic/omp";
gitBranch = "garlic/omp+fork";
# Repeat the execution of each unit 30 times
loops = 30;

View File

@@ -0,0 +1,89 @@
{
stdenv
, stdexp
, bsc
, targetMachine
, stages
, genInput
}:
with stdenv.lib;
let
# Initial variable configuration
varConf = {
n = [ { x = 192; y = 192; z = 192; } ];
nprocs = [
{ x = 2; y = 1; z = 1; }
# { x = 2; y = 2; z = 1; }
# { x = 2; y = 2; z = 2; }
# { x = 4; y = 2; z = 2; }
# { x = 4; y = 4; z = 2; }
];
nblocks = [ 12 24 48 96 192 384 768 1536 ];
# nblocks = [ 384 ];
ncommblocks = [ 1 ];
# nodes = [ 1 ];
# nodes = [ 1 2 4 8 16 ];
};
# Generate the complete configuration for each unit
genConf = c: targetMachine.config // rec {
expName = "hpcg.oss";
unitName = "${expName}.nb${toString nblocks}";
inherit (targetMachine.config) hw;
# hpcg options
inherit (c) n nprocs nblocks ncommblocks;
gitBranch = "garlic/tampi+isend+oss+task";
# Repeat the execution of each unit 30 times
loops = 3;
disableAspectRatio = false;
# Resources
qos = "debug";
ntasksPerNode = hw.socketsPerNode;
time = "02:00:00";
# task in one socket
cpusPerTask = hw.cpusPerSocket;
nodes = (nprocs.x * nprocs.y * nprocs.z) / ntasksPerNode;
jobName = "hpcg-${toString n.x}-${toString n.y}-${toString n.z}-${gitBranch}";
};
# Compute the array of configurations
configs = stdexp.buildConfigs {
inherit varConf genConf;
};
input = genInput configs;
exec = {nextStage, conf, ...}: stages.exec {
inherit nextStage;
argv = [
"--nx=${toString conf.n.x}"
"--ny=${toString conf.n.y}"
"--nz=${toString conf.n.z}"
"--npx=${toString conf.nprocs.x}"
"--npy=${toString conf.nprocs.y}"
"--npz=${toString conf.nprocs.z}"
"--nblocks=${toString conf.nblocks}"
"--ncomms=${toString conf.ncommblocks}"
# The input symlink is generated by the input stage, which is generated by
# the genInput function.
"--load=input"
];
};
program = {nextStage, conf, ...}: bsc.apps.hpcg.override {
inherit (conf) gitBranch;
};
pipeline = stdexp.stdPipeline ++ [ input exec program ];
in
stdexp.genExperiment { inherit configs pipeline; }

View File

@@ -11,39 +11,46 @@ with stdenv.lib;
let
# Initial variable configuration
varConf = with bsc; {
# FIXME: Temporally reduce the input size until we can load a precomputed
# input in each run, otherwise the execution time is very large.
#n = [ { x = 104; y = 104; z = 104; } ];
n = [ { x = 256; y = 288; z = 288; } ];
nblocks = [ 12 24 48 96 192 384 ];
varConf = {
n = [ { x = 192; y = 192; z = 192; } ];
nprocs = [
{ x = 2; y = 1; z = 1; }
{ x = 2; y = 2; z = 1; }
{ x = 2; y = 2; z = 2; }
{ x = 4; y = 2; z = 2; }
{ x = 4; y = 4; z = 2; }
];
# nblocks = [ 12 24 48 96 192 384 768 1536 ];
nblocks = [ 384 768 1536 ];
ncommblocks = [ 1 ];
# nodes = [ 1 ];
# nodes = [ 1 2 4 8 16 ];
};
# Generate the complete configuration for each unit
genConf = with bsc; c: targetMachine.config // rec {
genConf = c: targetMachine.config // rec {
expName = "hpcg.oss";
unitName = "${expName}.nb${toString nblocks}";
inherit (targetMachine.config) hw;
# hpcg options
n = c.n;
nblocks = c.nblocks;
cc = bsc.icc;
mcxx = bsc.mcxx;
nanos6 = bsc.nanos6;
mpi = null; # TODO: Remove this for oss
gitBranch = "garlic/oss";
inherit (c) n nprocs nblocks ncommblocks;
gitBranch = "garlic/tampi+isend+oss+task";
# Repeat the execution of each unit 30 times
loops = 30;
loops = 3;
disableAspectRatio = false;
# Resources
qos = "debug";
ntasksPerNode = 1;
nodes = 1;
ntasksPerNode = hw.socketsPerNode;
time = "02:00:00";
# task in one socket
cpusPerTask = hw.cpusPerSocket;
nodes = (nprocs.x * nprocs.y * nprocs.z) / ntasksPerNode;
jobName = "hpcg-${toString n.x}-${toString n.y}-${toString n.z}-${gitBranch}";
};
@@ -54,31 +61,29 @@ let
input = genInput configs;
exec = {nextStage, conf, ...}: with conf; stages.exec {
exec = {nextStage, conf, ...}: stages.exec {
inherit nextStage;
env = "NANOS6_DEPENDENCIES=discrete";
argv = [
"--nx=${toString n.x}"
"--ny=${toString n.y}"
"--nz=${toString n.z}"
"--nblocks=${toString nblocks}"
"--nx=${toString conf.n.x}"
"--ny=${toString conf.n.y}"
"--nz=${toString conf.n.z}"
"--npx=${toString conf.nprocs.x}"
"--npy=${toString conf.nprocs.y}"
"--npz=${toString conf.nprocs.z}"
"--nblocks=${toString conf.nblocks}"
"--ncomms=${toString conf.ncommblocks}"
# The input symlink is generated by the input stage, which is generated by
# the genInput function.
"--load=input"
];
};
program = {nextStage, conf, ...}: with conf;
let
customPkgs = stdexp.replaceMpi conf.mpi;
in
customPkgs.apps.hpcg.override {
inherit cc nanos6 mcxx gitBranch;
};
program = {nextStage, conf, ...}: bsc.apps.hpcg.override {
inherit (conf) gitBranch;
};
pipeline = stdexp.stdPipeline ++ [ input exec program ];
in
#{ inherit configs pipeline; }
stdexp.genExperiment { inherit configs pipeline; }

View File

@@ -0,0 +1,89 @@
{
stdenv
, stdexp
, bsc
, targetMachine
, stages
, genInput
}:
with stdenv.lib;
let
# Initial variable configuration
varConf = {
n = [ { x = 192; y = 192; z = 192; } ];
nprocs = [
{ x = 2; y = 1; z = 1; }
{ x = 2; y = 2; z = 1; }
{ x = 2; y = 2; z = 2; }
{ x = 4; y = 2; z = 2; }
{ x = 4; y = 4; z = 2; }
];
# nblocks = [ 12 24 48 96 192 384 768 1536 ];
nblocks = [ 384 768 1536 ];
ncommblocks = [ 1 ];
# nodes = [ 1 ];
# nodes = [ 1 2 4 8 16 ];
};
# Generate the complete configuration for each unit
genConf = c: targetMachine.config // rec {
expName = "hpcg.oss";
unitName = "${expName}.nb${toString nblocks}";
inherit (targetMachine.config) hw;
# hpcg options
inherit (c) n nprocs nblocks ncommblocks;
gitBranch = "garlic/tampi+isend+oss+task";
# Repeat the execution of each unit 30 times
loops = 10;
disableAspectRatio = false;
# Resources
qos = "debug";
ntasksPerNode = hw.socketsPerNode;
time = "02:00:00";
# task in one socket
cpusPerTask = hw.cpusPerSocket;
nodes = (nprocs.x * nprocs.y * nprocs.z) / ntasksPerNode;
jobName = "hpcg-${toString n.x}-${toString n.y}-${toString n.z}-${gitBranch}";
};
# Compute the array of configurations
configs = stdexp.buildConfigs {
inherit varConf genConf;
};
input = genInput configs;
exec = {nextStage, conf, ...}: stages.exec {
inherit nextStage;
argv = [
"--nx=${toString conf.n.x}"
"--ny=${toString conf.n.y}"
"--nz=${toString conf.n.z}"
"--npx=${toString conf.nprocs.x}"
"--npy=${toString conf.nprocs.y}"
"--npz=${toString conf.nprocs.z}"
"--nblocks=${toString conf.nblocks}"
"--ncomms=${toString conf.ncommblocks}"
# The input symlink is generated by the input stage, which is generated by
# the genInput function.
"--load=input"
];
};
program = {nextStage, conf, ...}: bsc.apps.hpcg.override {
inherit (conf) gitBranch;
};
pipeline = stdexp.stdPipeline ++ [ input exec program ];
in
stdexp.genExperiment { inherit configs pipeline; }

View File

@@ -0,0 +1,91 @@
{
stdenv
, stdexp
, bsc
, targetMachine
, stages
, genInput
}:
with stdenv.lib;
let
# Initial variable configuration
varConf = {
n = [ { x = 192; y = 192; z = 192; } ];
nprocs = [
{ x = 2; y = 1; z = 1; }
{ x = 4; y = 1; z = 1; }
{ x = 8; y = 1; z = 1; }
{ x = 16; y = 1; z = 1; }
{ x = 32; y = 1; z = 1; }
];
# nblocks = [ 12 24 48 96 192 384 768 1536 ];
nblocks = [ 384 ];
ncommblocks = [ 1 ];
# nodes = [ 1 ];
# nodes = [ 1 2 4 8 16 ];
};
# Generate the complete configuration for each unit
genConf = c: targetMachine.config // rec {
expName = "hpcg.oss";
unitName = "${expName}.nb${toString nblocks}";
inherit (targetMachine.config) hw;
# hpcg options
inherit (c) n nprocs nblocks ncommblocks;
gitBranch = "garlic/tampi+isend+oss+task";
# Repeat the execution of each unit 30 times
loops = 3;
disableAspectRatio = true;
# Resources
qos = "debug";
ntasksPerNode = hw.socketsPerNode;
time = "02:00:00";
# task in one socket
cpusPerTask = hw.cpusPerSocket;
nodes = (nprocs.x * nprocs.y * nprocs.z) / ntasksPerNode;
jobName = "hpcg-${toString n.x}-${toString n.y}-${toString n.z}-${gitBranch}";
};
# Compute the array of configurations
configs = stdexp.buildConfigs {
inherit varConf genConf;
};
input = genInput configs;
exec = {nextStage, conf, ...}: stages.exec {
inherit nextStage;
argv = [
"--nx=${toString conf.n.x}"
"--ny=${toString conf.n.y}"
"--nz=${toString conf.n.z}"
# Distribute all processes in X axis
"--npx=${toString conf.nprocs.x}"
"--npy=${toString conf.nprocs.y}"
"--npz=${toString conf.nprocs.z}"
"--nblocks=${toString conf.nblocks}"
"--ncomms=${toString conf.ncommblocks}"
# The input symlink is generated by the input stage, which is generated by
# the genInput function.
"--load=input"
# Disable HPCG Aspect Ratio to run any mpi layout
] ++ optional (conf.disableAspectRatio) "--no-ar=1";
};
program = {nextStage, conf, ...}: bsc.apps.hpcg.override {
inherit (conf) gitBranch;
};
pipeline = stdexp.stdPipeline ++ [ input exec program ];
in
stdexp.genExperiment { inherit configs pipeline; }

View File

@@ -55,12 +55,23 @@
# inherit (bsc.garlic.pp) resultFromTrebuchet;
#};
genInput = callPackage ./hpcg/gen.nix {
inherit (bsc.garlic.pp) resultFromTrebuchet;
};
oss = callPackage ./hpcg/oss.nix {
inherit genInput;
};
ossGranularity = callPackage ./hpcg/oss.granularity.192.nix {
inherit genInput;
};
ossScalability = callPackage ./hpcg/oss.scalability.192.nix {
inherit genInput;
};
# slices = callPackage ./hpcg/slices.nix {
# inherit genInput;
# };
};
heat = rec {