def thread_scaling_test(dry_run, target_dir, exp_name, group='', param_l=[]):
from scripts.conf.conf import machine_info, machine_conf
from scripts.pluto.pluto_utils import run_pluto_test, tee
import itertools, os, pickle
from os.path import join as jpath
target_dir = jpath(os.path.abspath("."),target_dir)
#update the pinning information to use all cores
th_max = machine_info['n_cores']
const_pin_args = machine_conf['pinning_args']
# machine_info['hostname']=='IVB_10core'
kernels_limits = {'3d25pt':1089, '3d7pt':1217, '3d25pt_var':577, '3d7pt_var':769}
increment = 64
if(machine_info['hostname']=='Haswell_18core'):
kernels_limits = {'3d25pt':1281, '3d7pt':1409, '3d25pt_var':769, '3d7pt_var':897}
increment = 128
points = dict()
points['3d7pt'] = [896]
points['3d25pt'] = [896]
points['3d7pt_var'] = [768]
points['3d25pt_var'] = [768]
count=0
for kernel in ['3d7pt', '3d7pt_var', '3d25pt', '3d25pt_var']:
for N in points[kernel]:
# get the tuned parameters
if(dry_run==1):
nt=32; param=[-1,-1,-1]
if (kernel, N, 'MEM') in param_l.keys(): # use the tuned params of memory results
param, nt = param_l[(kernel, N, 'MEM')]
nt_r = nt*2
else:
print "Tuning required for stencil:%s N:%d"%(kernel, N)
continue
for th in list(range(1,1+th_max)):
outfile=('pluto_kernel_%s_N%d_th%d_%s_%s.txt' % (kernel, N, th, group, exp_name[-13:]))
outfile = jpath(target_dir, outfile)
machine_conf['pinning_args'] = const_pin_args + str(th-1)
nt = max(30, int(nt_r*float(th)/float(th_max)) )
if(dry_run==0):
fp = open(outfile, 'w')
tee(fp, outfile)
# print outfile, param
test_str, telapsed = run_pluto_test(dry_run=dry_run, kernel=kernel, nx=N, ny=N, nz=N, nt=nt, params=param, outfile=outfile)
if(dry_run==0):
tee(fp, test_str)
fp.close()
count = count+1
return count
def igs_test(dry_run, target_dir, exp_name, group='', param_l=[]):
from scripts.conf.conf import machine_info
from scripts.pluto.pluto_utils import run_pluto_test
import itertools, os, pickle
from os.path import join as jpath
target_dir = jpath(os.path.abspath("."),target_dir)
# machine_info['hostname']=='IVB_10core'
kernels_limits = {'3d25pt':1089, '3d7pt':1217, '3d25pt_var':577, '3d7pt_var':769}
increment = 64
if(machine_info['hostname']=='Haswell_18core'):
kernels_limits = {'3d25pt':1281, '3d7pt':1409, '3d25pt_var':769, '3d7pt_var':897}
increment = 128
points = dict()
points['3d7pt'] = [64] + list(range(128, 5000, increment))
points['3d7pt_var'] = points['3d7pt']
points['3d25pt'] = points['3d7pt']
points['3d25pt_var'] = points['3d7pt']
count=0
#for kernel in ['3d7pt', '3d7pt_var', '3d25pt']:#, '3d25pt_var']:
for kernel in [ '3d25pt', '3d25pt_var']:
for N in points[kernel]:
if (N < kernels_limits[kernel]):
outfile=('pluto_kernel_%s_N%d_%s_%s.txt' % (kernel, N, group, exp_name[-13:]))
outfile = jpath(target_dir, outfile)
if(dry_run==1):
nt=32; param=[-1,-1,-1]
# nt = max(int(k_time_scale[kernel]/(N**3/1e6)), 30)
if (kernel, N, group) in param_l.keys():
continue # results exist for this test case
if (kernel, N, 'MEM') in param_l.keys(): # use the tuned params of memory results
if(dry_run==0): fp = open(outfile, 'w')
param, nt = param_l[(kernel, N, 'MEM')]
nt = nt*2
else:
# continue
if(dry_run==0):
fp = open(outfile, 'w')
param, nt, tune_res = pluto_tuner(kernel=kernel, nx=N, ny=N, nz=N, fp=fp)
with open(outfile[:-3]+'p', 'w') as fpickle:
pickle.dump(tune_res, fpickle)
if(dry_run==0): tee(fp, outfile)
# print outfile, param
test_str, telapsed = run_pluto_test(dry_run=dry_run, kernel=kernel, nx=N, ny=N, nz=N, nt=nt, params=param, outfile=outfile)
if(dry_run==0):
tee(fp, test_str)
fp.close()
count = count+1
return count
def thread_scaling_test(dry_run, target_dir, exp_name, group='', param_l=[]):
from scripts.conf.conf import machine_info, machine_conf
from scripts.pluto.pluto_utils import run_pluto_test, tee
import itertools, os, pickle
from os.path import join as jpath
target_dir = jpath(os.path.abspath("."), target_dir)
#update the pinning information to use all cores
th_max = machine_info['n_cores']
const_pin_args = machine_conf['pinning_args']
# machine_info['hostname']=='IVB_10core'
kernels_limits = {
'3d25pt': 1089,
'3d7pt': 1217,
'3d25pt_var': 577,
'3d7pt_var': 769
}
increment = 64
if (machine_info['hostname'] == 'Haswell_18core'):
kernels_limits = {
'3d25pt': 1281,
'3d7pt': 1409,
'3d25pt_var': 769,
'3d7pt_var': 897
}
increment = 128
points = dict()
points['3d7pt'] = [896]
points['3d25pt'] = [896]
points['3d7pt_var'] = [768]
points['3d25pt_var'] = [768]
count = 0
for kernel in ['3d7pt', '3d7pt_var', '3d25pt', '3d25pt_var']:
for N in points[kernel]:
# get the tuned parameters
if (dry_run == 1):
nt = 32
param = [-1, -1, -1]
if (kernel, N, 'MEM'
) in param_l.keys(): # use the tuned params of memory results
param, nt = param_l[(kernel, N, 'MEM')]
nt_r = nt * 2
else:
print "Tuning required for stencil:%s N:%d" % (kernel, N)
continue
for th in list(range(1, 1 + th_max)):
outfile = ('pluto_kernel_%s_N%d_th%d_%s_%s.txt' %
(kernel, N, th, group, exp_name[-13:]))
outfile = jpath(target_dir, outfile)
machine_conf['pinning_args'] = const_pin_args + str(th - 1)
nt = max(30, int(nt_r * float(th) / float(th_max)))
if (dry_run == 0):
fp = open(outfile, 'w')
tee(fp, outfile)
# print outfile, param
test_str, telapsed = run_pluto_test(dry_run=dry_run,
kernel=kernel,
nx=N,
ny=N,
nz=N,
nt=nt,
params=param,
outfile=outfile)
if (dry_run == 0):
tee(fp, test_str)
fp.close()
count = count + 1
return count
def igs_test(dry_run, target_dir, exp_name, group='', param_l=[]):
from scripts.conf.conf import machine_info
from scripts.pluto.pluto_utils import run_pluto_test
import itertools, os, pickle
from os.path import join as jpath
target_dir = jpath(os.path.abspath("."), target_dir)
# machine_info['hostname']=='IVB_10core'
kernels_limits = {
'3d25pt': 1089,
'3d7pt': 1217,
'3d25pt_var': 577,
'3d7pt_var': 769
}
increment = 64
if (machine_info['hostname'] == 'Haswell_18core'):
kernels_limits = {
'3d25pt': 1281,
'3d7pt': 1409,
'3d25pt_var': 769,
'3d7pt_var': 897
}
increment = 128
points = dict()
points['3d7pt'] = [64] + list(range(128, 5000, increment))
points['3d7pt_var'] = points['3d7pt']
points['3d25pt'] = points['3d7pt']
points['3d25pt_var'] = points['3d7pt']
count = 0
#for kernel in ['3d7pt', '3d7pt_var', '3d25pt']:#, '3d25pt_var']:
for kernel in ['3d25pt', '3d25pt_var']:
for N in points[kernel]:
if (N < kernels_limits[kernel]):
outfile = ('pluto_kernel_%s_N%d_%s_%s.txt' %
(kernel, N, group, exp_name[-13:]))
outfile = jpath(target_dir, outfile)
if (dry_run == 1):
nt = 32
param = [-1, -1, -1]
# nt = max(int(k_time_scale[kernel]/(N**3/1e6)), 30)
if (kernel, N, group) in param_l.keys():
continue # results exist for this test case
if (kernel, N, 'MEM') in param_l.keys(
): # use the tuned params of memory results
if (dry_run == 0): fp = open(outfile, 'w')
param, nt = param_l[(kernel, N, 'MEM')]
nt = nt * 2
else:
# continue
if (dry_run == 0):
fp = open(outfile, 'w')
param, nt, tune_res = pluto_tuner(kernel=kernel,
nx=N,
ny=N,
nz=N,
fp=fp)
with open(outfile[:-3] + 'p', 'w') as fpickle:
pickle.dump(tune_res, fpickle)
if (dry_run == 0): tee(fp, outfile)
# print outfile, param
test_str, telapsed = run_pluto_test(dry_run=dry_run,
kernel=kernel,
nx=N,
ny=N,
nz=N,
nt=nt,
params=param,
outfile=outfile)
if (dry_run == 0):
tee(fp, test_str)
fp.close()
count = count + 1
return count
