def runTest(self):
nx, ny, nz, str_f, pt0, pt1 = self.args
slidx = common.slices_two_points(pt0, pt1)
str_fs = common.convert_to_tuple(str_f)
# instance
gpu_devices = common_gpu.gpu_device_list(print_info=False)
context = cl.Context(gpu_devices)
device = gpu_devices[0]
fields = Fields(context, device, nx, ny, nz, '', 'single')
getf = GetFields(fields, str_f, pt0, pt1)
# host allocations
ehs = common_random.generate_ehs(nx, ny, nz, fields.dtype)
eh_dict = dict( zip(['ex', 'ey', 'ez', 'hx', 'hy', 'hz'], ehs) )
fields.set_eh_bufs(*ehs)
# verify
getf.get_event().wait()
for str_f in str_fs:
original = eh_dict[str_f][slidx]
copy = getf.get_fields(str_f)
norm = np.linalg.norm(original - copy)
self.assertEqual(norm, 0, '%s, %g' % (self.args, norm))
def runTest(self):
nx, ny, nz, str_f, pt0, pt1 = self.args
slidx = common.slices_two_points(pt0, pt1)
str_fs = common.convert_to_tuple(str_f)
# instance
fields = Fields(0, nx, ny, nz, '', 'single')
getf = GetFields(fields, str_f, pt0, pt1)
# host allocations
ehs = common_random.generate_ehs(nx, ny, nz, fields.dtype)
eh_dict = dict( zip(['ex', 'ey', 'ez', 'hx', 'hy', 'hz'], ehs) )
fields.set_eh_bufs(*ehs)
# verify
getf.wait()
for str_f in str_fs:
original = eh_dict[str_f][slidx]
copy = getf.get_fields(str_f)
norm = np.linalg.norm(original - copy)
self.assertEqual(norm, 0, '%s, %g' % (self.args, norm))
fields.context_pop()
def runTest(self):
nx, ny, nz, str_f, pt0, pt1, is_array = self.args
slice_xyz = common.slices_two_points(pt0, pt1)
# generate random source
if is_array:
shape = common.shape_two_points(pt0, pt1)
value = np.random.rand(*shape).astype(np.float32)
else:
value = np.random.ranf()
# instance
fields = Fields(0, nx, ny, nz, '', 'single')
tfunc = lambda tstep: np.sin(0.03*tstep)
incident = IncidentDirect(fields, str_f, pt0, pt1, tfunc, value)
# host allocations
eh = np.zeros(fields.ns_pitch, dtype=fields.dtype)
# verify
eh[slice_xyz] = fields.dtype(value) * fields.dtype(tfunc(1))
fields.update_e()
fields.update_h()
copy_eh_buf = fields.get_buf(str_f)
copy_eh = np.zeros_like(eh)
cuda.memcpy_dtoh(copy_eh, copy_eh_buf)
original = eh[slice_xyz]
copy = copy_eh[slice_xyz]
norm = np.linalg.norm(original - copy)
self.assertEqual(norm, 0, '%s, %g' % (self.args, norm))
fields.context_pop()
def runTest(self):
nx, ny, nz, str_f, pt0, pt1 = self.args
slidx = common.slice_index_two_points(pt0, pt1)
str_fs = common.convert_to_tuple(str_f)
# instance
gpu_devices = common_gpu.gpu_device_list(print_info=False)
context = cl.Context(gpu_devices)
device = gpu_devices[0]
fields = Fields(context, device, nx, ny, nz, '', 'single')
getf = GetFields(fields, str_f, pt0, pt1)
# host allocations
ehs = common_update.generate_random_ehs(nx, ny, nz, fields.dtype)
eh_dict = dict( zip(['ex', 'ey', 'ez', 'hx', 'hy', 'hz'], ehs) )
fields.set_eh_bufs(*ehs)
# verify
getf.get_event().wait()
for str_f in str_fs:
original = eh_dict[str_f][slidx]
copy = getf.get_fields(str_f)
norm = np.linalg.norm(original - copy)
self.assertEqual(norm, 0, '%s, %g' % (self.args, norm))
def runTest(self):
nx, ny, nz, str_f, pt0, pt1, is_array = self.args
slidx = common.slices_two_points(pt0, pt1)
str_fs = common.convert_to_tuple(str_f)
# instance
gpu_devices = common_gpu.gpu_device_list(print_info=False)
context = cl.Context(gpu_devices)
device = gpu_devices[0]
qtask = QueueTask()
fields = Fields(context, device, qtask, nx, ny, nz, '', 'single')
setf = SetFields(fields, str_f, pt0, pt1, is_array)
# generate random source
if is_array:
shape = common.shape_two_points(pt0, pt1, len(str_fs))
value = np.random.rand(*shape).astype(fields.dtype)
split_value = np.split(value, len(str_fs))
split_value_dict = dict( zip(str_fs, split_value) )
else:
value = np.random.ranf()
# host allocations
ehs = [np.zeros(fields.ns, dtype=fields.dtype) for i in range(6)]
eh_dict = dict( zip(['ex', 'ey', 'ez', 'hx', 'hy', 'hz'], ehs) )
gpu_eh = np.zeros(fields.ns_pitch, dtype=fields.dtype)
# verify
for str_f in str_fs:
if is_array:
eh_dict[str_f][slidx] = split_value_dict[str_f]
else:
eh_dict[str_f][slidx] = value
setf.set_fields(value)
setf.mainf.enqueue_barrier()
for str_f in str_fs:
cl.enqueue_copy(fields.queue, gpu_eh, fields.get_buf(str_f))
original = eh_dict[str_f]
copy = gpu_eh[:,:,fields.slice_z]
norm = np.linalg.norm(original - copy)
self.assertEqual(norm, 0, '%s, %g' % (self.args, norm))
def runTest(self):
axis, nx, ny, nz, precision_float = self.args
gpu_devices = common_gpu.gpu_device_list(print_info=False)
context = cl.Context(gpu_devices)
device = gpu_devices[0]
fields = Fields(context, device, nx, ny, nz, '', precision_float)
pbc = Pbc(fields, axis)
# allocations
ehs = common_update.generate_random_ehs(nx, ny, nz, fields.dtype)
fields.set_eh_bufs(*ehs)
# update
fields.update_e()
fields.update_h()
# verify
getf0, getf1 = {}, {}
strfs_e = {'x':['ey', 'ez'], 'y':['ex', 'ez'], 'z':['ex', 'ey']}[axis]
strfs_h = {'x':['hy', 'hz'], 'y':['hx', 'hz'], 'z':['hx', 'hy']}[axis]
pt0 = (0, 0, 0)
pt1 = { 'x': (0, ny-2, nz-2), \
'y': (nx-2, 0, nz-2), \
'z': (nx-2, ny-2, 0) }[axis]
getf0['e'] = GetFields(fields, strfs_e, pt0, pt1)
pt0 = { 'x': (nx-1, 0, 0), \
'y': (0, ny-1, 0), \
'z': (0, 0, nz-1) }[axis]
pt1 = { 'x': (nx-1, ny-2, nz-2), \
'y': (nx-2, ny-1, nz-2), \
'z': (nx-2, ny-2, nz-1) }[axis]
getf1['e'] = GetFields(fields, strfs_e, pt0, pt1)
pt0 = { 'x': (0, 1, 1), \
'y': (1, 0, 1), \
'z': (1, 1, 0) }[axis]
pt1 = { 'x': (0, ny-1, nz-1), \
'y': (nx-1, 0, nz-1), \
'z': (nx-1, ny-1, 0) }[axis]
getf0['h'] = GetFields(fields, strfs_h, pt0, pt1)
pt0 = { 'x': (nx-1, 1, 1), \
'y': (1, ny-1, 1), \
'z': (1, 1, nz-1) }[axis]
pt1 = (nx-1, ny-1, nz-1)
getf1['h'] = GetFields(fields, strfs_h, pt0, pt1)
for getf in getf0.values() + getf1.values():
getf.get_event().wait()
for eh in ['e', 'h']:
norm = np.linalg.norm( \
getf0[eh].get_fields() - getf1[eh].get_fields() )
self.assertEqual(norm, 0, '%g, %s, %s' % (norm, self.args, eh))
def runTest(self):
nx, ny, nz, str_f, pt0, pt1, is_array = self.args
slidx = common.slices_two_points(pt0, pt1)
str_fs = common.convert_to_tuple(str_f)
# instance
fields = Fields(0, nx, ny, nz, '', 'single')
setf = SetFields(fields, str_f, pt0, pt1, is_array)
# generate random source
if is_array:
shape = common.shape_two_points(pt0, pt1, len(str_fs))
value = np.random.rand(*shape).astype(fields.dtype)
split_value = np.split(value, len(str_fs))
split_value_dict = dict( zip(str_fs, split_value) )
else:
value = np.random.ranf()
# host allocations
ehs = [np.zeros(fields.ns, dtype=fields.dtype) for i in range(6)]
eh_dict = dict( zip(['ex', 'ey', 'ez', 'hx', 'hy', 'hz'], ehs) )
gpu_eh = np.zeros(fields.ns_pitch, dtype=fields.dtype)
# verify
for str_f in str_fs:
if is_array:
eh_dict[str_f][slidx] = split_value_dict[str_f]
else:
eh_dict[str_f][slidx] = value
setf.set_fields(value)
for str_f in str_fs:
cuda.memcpy_dtoh(gpu_eh, fields.get_buf(str_f))
original = eh_dict[str_f]
copy = gpu_eh[:,:,fields.slice_z]
norm = np.linalg.norm(original - copy)
self.assertEqual(norm, 0, '%s, %g' % (self.args, norm))
fields.context_pop()
def runTest(self):
nx, ny, nz, str_f, pt0, pt1, is_array = self.args
slice_xyz = common.slices_two_points(pt0, pt1)
# generate random source
if is_array:
shape = common.shape_two_points(pt0, pt1)
value = np.random.rand(*shape).astype(np.float32)
else:
value = np.random.ranf()
# instance
gpu_devices = common_gpu.gpu_device_list(print_info=False)
context = cl.Context(gpu_devices)
device = gpu_devices[0]
qtask = QueueTask()
fields = Fields(context, device, qtask, nx, ny, nz, '', 'single')
tfunc = lambda tstep: np.sin(0.03*tstep)
incident = IncidentDirect(fields, str_f, pt0, pt1, tfunc, value)
# host allocations
eh = np.zeros(fields.ns_pitch, dtype=fields.dtype)
# verify
eh[slice_xyz] = fields.dtype(value) * fields.dtype(tfunc(1))
fields.update_e()
fields.update_h()
fields.enqueue_barrier()
copy_eh_buf = fields.get_buf(str_f)
copy_eh = np.zeros_like(eh)
cl.enqueue_copy(fields.queue, copy_eh, copy_eh_buf)
original = eh[slice_xyz]
copy = copy_eh[slice_xyz]
norm = np.linalg.norm(original - copy)
self.assertEqual(norm, 0, '%s, %g' % (self.args, norm))
def runTest(self):
nx, ny, nz, str_f, pt0, pt1, is_array = self.args
slice_xyz = common.slice_index_two_points(pt0, pt1)
# generate random source
if is_array:
shape = common.shape_two_points(pt0, pt1)
value = np.random.rand(*shape).astype(np.float32)
else:
value = np.random.ranf()
# instance
gpu_devices = common_gpu.gpu_device_list(print_info=False)
context = cl.Context(gpu_devices)
device = gpu_devices[0]
fields = Fields(context, device, nx, ny, nz, '', 'single')
tfunc = lambda tstep: np.sin(0.03 * tstep)
incident = DirectIncident(fields, str_f, pt0, pt1, tfunc, value)
# host allocations
eh = np.zeros(fields.ns_pitch, dtype=fields.dtype)
# verify
eh[slice_xyz] = fields.dtype(value) * fields.dtype(tfunc(1))
fields.update_e()
fields.update_h()
copy_eh_buf = fields.get_buf(str_f)
copy_eh = np.zeros_like(eh)
cl.enqueue_copy(fields.queue, copy_eh, copy_eh_buf)
original = eh[slice_xyz]
copy = copy_eh[slice_xyz]
norm = np.linalg.norm(original - copy)
self.assertEqual(norm, 0, '%s, %g' % (self.args, norm))
#nx, ny, nz = 240, 256, 256 # 540 MB #nx, ny, nz = 544, 544, 544 # 5527 MB #nx, ny, nz = 512, 512, 512 # 4608 MB #nx, ny, nz = 480, 480, 480 # 3796 MB nx, ny, nz = 240, 256, 256 # 576 MB #nx, ny, nz = 128, 128, 128 # 72 MB coeff_use = 'e' precision_float = 'single' # instances gpu_devices = common_gpu.gpu_device_list(print_info=False) context = cl.Context(gpu_devices) device = gpu_devices[0] fields = Fields(context, device, nx, ny, nz, coeff_use, precision_float) tmax = 250 if is_plot else 1000 if rank == 0: direction = '+' elif rank == size - 1: direction = '-' else: direction = '+-' core = CoreSplit2(fields) #exch = network.ExchangeMpiBlock(fields, core, direction) #exch = network.ExchangeMpiNonBlock(fields, core, direction) exch = network.ExchangeMpiSplit2(fields, core, direction) #core = CoreSplit3(fields) #exch = network.ExchangeMpiSplit3(fields, core, direction, tmax)
# plot
import matplotlib.pyplot as plt
import matplotlib as mpl
mpl.rc('image', interpolation='nearest', origin='lower')
#plt.ion()
fig = plt.figure(figsize=(14, 8))
# gpu device
gpu_devices = common_gpu.gpu_device_list(print_info=False)
context = cl.Context(gpu_devices)
device = gpu_devices[0]
# z-axis
nx, ny, nz = 180, 160, 2
fields = Fields(context, device, nx, ny, nz)
Pbc(fields, 'xyz')
Core(fields)
IncidentDirect(fields, 'ey', (20, 0, 0), (20, ny - 1, nz - 1), tfunc)
IncidentDirect(fields, 'ex', (0, 20, 0), (nx - 1, 20, nz - 1), tfunc)
for tstep in xrange(1, tmax + 1):
fields.update_e()
fields.update_h()
ax1 = fig.add_subplot(2, 3, 1)
getf = GetFields(fields, 'ey', (0, 0, nz / 2), (nx - 1, ny - 1, nz / 2))
getf.get_event().wait()
ax1.imshow(getf.get_fields().T, vmin=-1.1, vmax=1.1)
ax1.set_title('%s, ey[20,:,:]' % repr(fields.ns))
ax1.set_xlabel('x')
#nx, ny, nz = 240, 256, 256 # 540 MB
#nx, ny, nz = 544, 544, 544 # 5527 MB
#nx, ny, nz = 512, 512, 512 # 4608 MB
#nx, ny, nz = 480, 480, 480 # 3796 MB
nx, ny, nz = 800, 256, 256 # 576 MB
#nx, ny, nz = 128, 128, 128 # 72 MB
tmax, tgap = 1000, 10
# instances
gpu_devices = common_gpu.gpu_device_list(print_info=False)
context = cl.Context(gpu_devices)
device = gpu_devices[0]
fields = Fields(context,
device,
nx,
ny,
nz,
coeff_use='e',
precision_float='single')
Core(fields)
print 'ns_pitch', fields.ns_pitch
print 'nbytes (MB)', nx * ny * nz * 9 * 4. / (1024**2)
'''
Pbc(fields, 'xyz')
tfunc = lambda tstep: 40 * np.sin(0.05 * tstep)
IncidentDirect(fields, 'ez', (220, 20, 0), (220, 20, -1), tfunc)
getf = GetFields(fields, 'ez', (0, 0, 0.5), (-1, -1, 0.5))
# plot
from kemp.fdtd3d import common_gpu
from kemp.fdtd3d.gpu import Fields, DirectSrc, GetFields, ExchangeFields
import numpy as np
import pyopencl as cl
nx, ny, nz = 240, 640, 640
tmax, tgap = 200, 10
divide_axes = 'x'
gpu_devices = common_gpu.get_gpu_devices()
context = cl.Context(gpu_devices)
ngpu = len(gpu_devices)
fdtds = [
Fields(context, device, nx, ny, nz, coeff_use='') for device in gpu_devices
]
outputs = [GetFields(fdtds[0], 'ez', (0, 0, nz / 2), (nx - 1, ny - 1, nz / 2))]
outputs += [
GetFields(fdtd, 'ez', (1, 0, nz / 2), (nx - 1, ny - 1, nz / 2))
for fdtd in fdtds[1:]
]
src = DirectSrc(fdtds[1], 'ez', (nx / 5 * 4, ny / 2, 0),
(nx / 5 * 4, ny / 2, nz - 1),
lambda tstep: np.sin(0.1 * tstep))
exch = ExchangeFields(fdtds, 'x')
# Plot
import matplotlib.pyplot as plt
plt.ion()
sys.path.append('/home/kifang')
from kemp.fdtd3d import common_gpu
from kemp.fdtd3d.gpu import Fields, DirectSrc, GetFields, PbcInt
import numpy as np
import pyopencl as cl
nx, ny, nz = 2, 640, 640
tmax, tgap = 1000, 10
gpu_id = 0
gpu_devices = common_gpu.get_gpu_devices()
context = cl.Context(gpu_devices)
device = gpu_devices[gpu_id]
fdtd = Fields(context, device, nx, ny, nz, coeff_use='')
src = DirectSrc(fdtd, 'ex', (1, ny / 5 * 4, nz / 5 * 3),
(1, ny / 5 * 4, nz / 5 * 3), lambda tstep: np.sin(0.1 * tstep))
pbc = PbcInt(fdtd, 'x')
output = GetFields(fdtd, 'ex', (1, 0, 0), (1, ny - 1, nz - 1))
# Plot
import matplotlib.pyplot as plt
plt.ion()
imag = plt.imshow(output.get_fields().T,
cmap=plt.cm.hot,
origin='lower',
vmin=0,
vmax=0.05)
plt.colorbar()
import sys, os
sys.path.append( os.path.expanduser('~') )
from kemp.fdtd3d.gpu import Fields, Core, DirectIncident, GetFields, Pbc
from kemp.fdtd3d.util import common_exchange
nx, ny, nz = 200, 300, 16
tmax, tgap = 200, 10
# instances
from kemp.fdtd3d.util import common_gpu
import pyopencl as cl
gpu_devices = common_gpu.gpu_device_list(print_info=False)
context = cl.Context(gpu_devices)
fields = Fields(context, gpu_devices[0], nx, ny, nz)
#fields = Fields(nx, ny, nz)
core = Core(fields)
pbc = Pbc(fields, 'x')
pbc = Pbc(fields, 'y')
pbc = Pbc(fields, 'z')
print fields.instance_list
tfunc = lambda tstep: np.sin(0.05 * tstep)
incident = DirectIncident(fields, 'ez', (20, 0, 0), (20, ny-1, nz-1), tfunc)
incident = DirectIncident(fields, 'ey', (0, 20, 0), (nx-1, 20, nz-1), tfunc)
#incident = DirectIncident(fields, 'ex', (0, 0, 20), (nx-1, ny-1, 20), tfunc)
getf = GetFields(fields, 'ez', (0, 0, nz/2), (nx-1, ny-1, nz/2))
# for verify pbc
import numpy as np
import pyopencl as cl
import sys, os
sys.path.append(os.path.expanduser('~'))
from kemp.fdtd3d.util import common_gpu
from kemp.fdtd3d.gpu import Fields, Core, Pbc, IncidentDirect, GetFields
nx, ny, nz = 160, 140, 32
tmax, tgap = 150, 10
# instances
gpu_devices = common_gpu.gpu_device_list(print_info=False)
context = cl.Context(gpu_devices)
device = gpu_devices[0]
fields = Fields(context, device, nx, ny, nz)
Core(fields)
Pbc(fields, 'xyz')
'''
tfunc = lambda tstep: np.sin(0.05 * tstep)
IncidentDirect(fields, 'ez', (20, 0, 0), (20, ny-1, nz-1), tfunc)
#IncidentDirect(fields, 'ez', (0, 20, 0), (nx-1, 20, nz-1), tfunc)
getf = GetFields(fields, 'ez', (0, 0, nz/2), (nx-1, ny-1, nz/2))
print fields.instance_list
# plot
import matplotlib.pyplot as plt
plt.ion()
fig = plt.figure(figsize=(12,8))
imag = plt.imshow(np.zeros((nx, ny), fields.dtype).T, interpolation='nearest', origin='lower', vmin=-1.1, vmax=1.1)
def runTest(self):
ufunc, nx, ny, nz, coeff_use, precision_float, tmax = self.args
gpu_devices = common_gpu.gpu_device_list(print_info=False)
context = cl.Context(gpu_devices)
device = gpu_devices[0]
fields = Fields(context, device, nx, ny, nz, coeff_use, precision_float)
core = Core(fields)
# allocations
ns = fields.ns
dtype = fields.dtype
strf_list = ["ex", "ey", "ez", "hx", "hy", "hz"]
ehs = common_update.generate_random_ehs(nx, ny, nz, dtype, ufunc)
fields.set_eh_bufs(*ehs)
ces, chs = common_update.generate_random_cs(coeff_use, nx, ny, nz, dtype)
if "e" in coeff_use:
fields.set_ce_bufs(*ces)
if "h" in coeff_use:
fields.set_ch_bufs(*chs)
tmpf = np.zeros(fields.ns_pitch, dtype=dtype)
# update
if ufunc == "e":
for tstep in xrange(0, tmax):
fields.update_e()
common_update.update_e(ehs, ces)
for strf, eh in zip(strf_list, ehs)[:3]:
cl.enqueue_copy(fields.queue, tmpf, fields.get_buf(strf))
norm = np.linalg.norm(eh - tmpf[:, :, fields.slice_z])
max_diff = np.abs(eh - tmpf[:, :, fields.slice_z]).max()
self.assertEqual(norm, 0, "%s, %s, %g, %g" % (self.args, strf, norm, max_diff))
if fields.pad != 0:
if strf == "ez":
norm2 = np.linalg.norm(tmpf[:, :, -fields.pad :])
else:
norm2 = np.linalg.norm(tmpf[:, :, -fields.pad - 1 :])
self.assertEqual(norm2, 0, "%s, %s, %g, padding" % (self.args, strf, norm2))
elif ufunc == "h":
for tstep in xrange(0, tmax):
fields.update_h()
common_update.update_h(ehs, chs)
for strf, eh in zip(strf_list, ehs)[3:]:
cl.enqueue_copy(fields.queue, tmpf, fields.get_buf(strf))
norm = np.linalg.norm(eh - tmpf[:, :, fields.slice_z])
max_diff = np.abs(eh - tmpf[:, :, fields.slice_z]).max()
self.assertEqual(norm, 0, "%s, %s, %g, %g" % (self.args, strf, norm, max_diff))
if fields.pad != 0:
if strf == "hz":
norm2 = np.linalg.norm(tmpf[:, :, -fields.pad :])
else:
norm2 = np.linalg.norm(tmpf[:, :, -fields.pad :])
self.assertEqual(norm2, 0, "%s, %s, %g, padding" % (self.args, strf, norm2))
def runTest(self):
ufunc, nx, ny, nz, coeff_use, precision_float, tmax = self.args
gpu_devices = common_gpu.gpu_device_list(print_info=False)
context = cl.Context(gpu_devices)
device = gpu_devices[0]
fields = Fields(context, device, nx, ny, nz, coeff_use,
precision_float)
core = Core(fields)
# allocations
ns = fields.ns
dtype = fields.dtype
strf_list = ['ex', 'ey', 'ez', 'hx', 'hy', 'hz']
ehs = common_update.generate_random_ehs(nx, ny, nz, dtype, ufunc)
fields.set_eh_bufs(*ehs)
ces, chs = common_update.generate_random_cs(coeff_use, nx, ny, nz,
dtype)
if 'e' in coeff_use:
fields.set_ce_bufs(*ces)
if 'h' in coeff_use:
fields.set_ch_bufs(*chs)
tmpf = np.zeros(fields.ns_pitch, dtype=dtype)
# update
if ufunc == 'e':
for tstep in xrange(0, tmax):
fields.update_e()
common_update.update_e(ehs, ces)
for strf, eh in zip(strf_list, ehs)[:3]:
cl.enqueue_copy(fields.queue, tmpf, fields.get_buf(strf))
norm = np.linalg.norm(eh - tmpf[:, :, fields.slice_z])
max_diff = np.abs(eh - tmpf[:, :, fields.slice_z]).max()
self.assertEqual(
norm, 0,
'%s, %s, %g, %g' % (self.args, strf, norm, max_diff))
if fields.pad != 0:
if strf == 'ez':
norm2 = np.linalg.norm(tmpf[:, :, -fields.pad:])
else:
norm2 = np.linalg.norm(tmpf[:, :, -fields.pad - 1:])
self.assertEqual(
norm2, 0,
'%s, %s, %g, padding' % (self.args, strf, norm2))
elif ufunc == 'h':
for tstep in xrange(0, tmax):
fields.update_h()
common_update.update_h(ehs, chs)
for strf, eh in zip(strf_list, ehs)[3:]:
cl.enqueue_copy(fields.queue, tmpf, fields.get_buf(strf))
norm = np.linalg.norm(eh - tmpf[:, :, fields.slice_z])
max_diff = np.abs(eh - tmpf[:, :, fields.slice_z]).max()
self.assertEqual(
norm, 0,
'%s, %s, %g, %g' % (self.args, strf, norm, max_diff))
if fields.pad != 0:
if strf == 'hz':
norm2 = np.linalg.norm(tmpf[:, :, -fields.pad:])
else:
norm2 = np.linalg.norm(tmpf[:, :, -fields.pad:])
self.assertEqual(
norm2, 0,
'%s, %s, %g, padding' % (self.args, strf, norm2))
#nx, ny, nz = 240, 256, 256 # 540 MB #nx, ny, nz = 544, 544, 544 # 5527 MB #nx, ny, nz = 512, 512, 512 # 4608 MB #nx, ny, nz = 480, 480, 480 # 3796 MB nx, ny, nz = 800, 256, 256 # 576 MB #nx, ny, nz = 128, 128, 128 # 72 MB coeff_use = 'e' precision_float = 'single' # instances gpu_devices = common_gpu.gpu_device_list(print_info=False) context = cl.Context(gpu_devices) device = gpu_devices[0] qtask = cpu.QueueTask() fields = Fields(context, device, qtask, nx, ny, nz, coeff_use, precision_float) Core(fields) tmax = 250 if is_plot else 1000 if rank == 0: direction = '+' elif rank == size - 1: direction = '-' else: direction = '+-' #exch = node.ExchangeMpiNonBlock(fields, direction) #exch = node.ExchangeMpiBufferBlock(fields, direction) #exch = node.ExchangeMpiBufferBlockSplit(fields, direction) exch = node.ExchangeMpiBufferNonBlockSplitEnqueue(fields, direction, tmax) if '+' in direction: cpu.Core(exch.cpuf_p) if '-' in direction: cpu.Core(exch.cpuf_m)
sys.path.append( os.path.expanduser('~') )
from kemp.fdtd3d.util import common_gpu
from kemp.fdtd3d.gpu import Fields, Core, Pbc, IncidentDirect, GetFields
#nx, ny, nz = 240, 256, 256 # 540 MB
#nx, ny, nz = 544, 544, 544 # 5527 MB
#nx, ny, nz = 512, 512, 512 # 4608 MB
#nx, ny, nz = 480, 480, 480 # 3796 MB
#nx, ny, nz = 256, 256, 256 # 576 MB
nx, ny, nz = 240, 256, 256
#nx, ny, nz = 128, 128, 128 # 72 MB
tmax, tgap = 1000, 10
# instances
fields = Fields(0, nx, ny, nz, coeff_use='e', precision_float='single')
Core(fields)
print 'ns_pitch', fields.ns_pitch
print 'nbytes (MB)', nx*ny*nz * 9 * 4. / (1024**2)
'''
Pbc(fields, 'xyz')
tfunc = lambda tstep: np.sin(0.05 * tstep)
IncidentDirect(fields, 'ez', (20, 0, 0), (20, ny-1, nz-1), tfunc)
#IncidentDirect(fields, 'ez', (0, 20, 0), (nx-1, 20, nz-1), tfunc)
getf = GetFields(fields, 'ez', (0, 0, nz/2), (nx-1, ny-1, nz/2))
print fields.instance_list
values = np.random.rand(*shape_dict[axis]).astype(s.fdtd.dtype)
fset.set_fields(values)
fget = GetFields(s.fdtd, str_fs, pt0, pt1)
fget.get_event().wait()
copy = fget.get_fields()
assert np.linalg.norm(values - copy) == 0
if __name__ == '__main__':
nx, ny, nz = 100, 110, 128
gpu_id = 0
gpu_devices = common_gpu.get_gpu_devices()
context = cl.Context(gpu_devices)
device = gpu_devices[gpu_id]
fdtd = Fields(context, device, nx, ny, nz, coeff_use='')
print('-' * 47 + '\nTest GetFields')
testget = TestGetFields(fdtd, nx, ny, nz)
testget.set_iteration(3)
testget.test()
testget.test_boundary()
print('-' * 47 + '\nTest SetFields')
testset = TestSetFields(fdtd, nx, ny, nz)
testset.set_iteration(3)
testset.test()
testset.test_boundary()
def runTest(self):
nx, ny, nz, str_f, pt0, pt1, is_array = self.args
slice_xyz = common.slices_two_points(pt0, pt1)
# generate random source
if is_array:
shape = common.shape_two_points(pt0, pt1)
value = np.random.rand(*shape).astype(np.float32)
else:
value = np.random.ranf()
# instance
fields = Fields(0, nx, ny, nz, '', 'single')
tfunc = lambda tstep: np.sin(0.03 * tstep)
incident = IncidentDirect(fields, str_f, pt0, pt1, tfunc, value)
# host allocations
eh = np.zeros(fields.ns_pitch, dtype=fields.dtype)
# verify
eh[slice_xyz] = fields.dtype(value) * fields.dtype(tfunc(1))
fields.update_e()
fields.update_h()
copy_eh_buf = fields.get_buf(str_f)
copy_eh = np.zeros_like(eh)
cuda.memcpy_dtoh(copy_eh, copy_eh_buf)
original = eh[slice_xyz]
copy = copy_eh[slice_xyz]
norm = np.linalg.norm(original - copy)
self.assertEqual(norm, 0, '%s, %g' % (self.args, norm))
fields.context_pop()
#nx, ny, nz = 240, 256, 256 # 540 MB
#nx, ny, nz = 544, 544, 544 # 5527 MB
#nx, ny, nz = 512, 512, 512 # 4608 MB
#nx, ny, nz = 480, 480, 480 # 3796 MB
nx, ny, nz = 240, 256, 256 # 576 MB
#nx, ny, nz = 128, 128, 128 # 72 MB
coeff_use = 'e'
precision_float = 'single'
# instances
gpu_devices = common_gpu.gpu_device_list(print_info=False)
context = cl.Context(gpu_devices)
device = gpu_devices[0]
fields = Fields(context, device, nx, ny, nz, coeff_use, precision_float)
Core(fields)
if rank == 0: direction = '+'
elif rank == size - 1: direction = '-'
else: direction = '+-'
exch = ExchangeMpi(fields, direction)
is_master = True if rank == 0 else False
tmax = 150 if is_plot else 1000
if is_plot:
Pbc(fields, 'yz')
getf = GetFields(fields, 'ez', (0, 0, 0.5), (-1, -1, 0.5))
if rank < size - 1:
from kemp.fdtd3d import common_gpu from kemp.fdtd3d.gpu import Fields, DirectSrc, GetFields, PbcInt import numpy as np import pyopencl as cl nx, ny, nz = 2, 640, 640 tmax, tgap = 1000, 10 gpu_id = 0 gpu_devices = common_gpu.get_gpu_devices() context = cl.Context(gpu_devices) device = gpu_devices[gpu_id] fdtd = Fields(context, device, nx, ny, nz, coeff_use='') src = DirectSrc(fdtd, 'ex', (1, ny/5*4, nz/5*3), (1, ny/5*4, nz/5*3), lambda tstep: np.sin(0.1 * tstep)) pbc = PbcInt(fdtd, 'x') output = GetFields(fdtd, 'ex', (1, 0, 0), (1, ny-1, nz-1)) # Plot import matplotlib.pyplot as plt plt.ion() imag = plt.imshow(output.get_fields().T, cmap=plt.cm.hot, origin='lower', vmin=0, vmax=0.05) plt.colorbar() # Main loop from datetime import datetime t0 = datetime.now()
#nx, ny, nz = 240, 256, 256 # 540 MB #nx, ny, nz = 544, 544, 544 # 5527 MB #nx, ny, nz = 512, 512, 512 # 4608 MB #nx, ny, nz = 480, 480, 480 # 3796 MB nx, ny, nz = 800, 256, 256 # 576 MB #nx, ny, nz = 128, 128, 128 # 72 MB coeff_use = 'e' precision_float = 'single' # instances gpu_devices = common_gpu.gpu_device_list(print_info=False) context = cl.Context(gpu_devices) device = gpu_devices[0] qtask = cpu.QueueTask() fields = Fields(context, device, qtask, nx, ny, nz, coeff_use, precision_float) Core(fields) tmax = 250 if is_plot else 1000 if rank == 0: direction = '+' elif rank == size - 1: direction = '-' else: direction = '+-' #exch = node.ExchangeMpiNonBlock(fields, direction) #exch = node.ExchangeMpiBufferBlock(fields, direction) #exch = node.ExchangeMpiBufferBlockSplit(fields, direction) exch = node.ExchangeMpiBufferNonBlockSplitEnqueue(fields, direction, tmax) if '+' in direction: cpu.Core(exch.cpuf_p) if '-' in direction: cpu.Core(exch.cpuf_m)
def runTest(self):
axis, nx, ny, nz, precision_float = self.args
gpu_devices = common_gpu.gpu_device_list(print_info=False)
context = cl.Context(gpu_devices)
device = gpu_devices[0]
fields = Fields(context, device, nx, ny, nz, '', precision_float)
pbc = Pbc(fields, axis)
# allocations
ehs = common_update.generate_random_ehs(nx, ny, nz, fields.dtype)
fields.set_eh_bufs(*ehs)
# update
fields.update_e()
fields.update_h()
# verify
getf0, getf1 = {}, {}
strfs_e = {
'x': ['ey', 'ez'],
'y': ['ex', 'ez'],
'z': ['ex', 'ey']
}[axis]
strfs_h = {
'x': ['hy', 'hz'],
'y': ['hx', 'hz'],
'z': ['hx', 'hy']
}[axis]
pt0 = (0, 0, 0)
pt1 = { 'x': (0, ny-2, nz-2), \
'y': (nx-2, 0, nz-2), \
'z': (nx-2, ny-2, 0) }[axis]
getf0['e'] = GetFields(fields, strfs_e, pt0, pt1)
pt0 = { 'x': (nx-1, 0, 0), \
'y': (0, ny-1, 0), \
'z': (0, 0, nz-1) }[axis]
pt1 = { 'x': (nx-1, ny-2, nz-2), \
'y': (nx-2, ny-1, nz-2), \
'z': (nx-2, ny-2, nz-1) }[axis]
getf1['e'] = GetFields(fields, strfs_e, pt0, pt1)
pt0 = { 'x': (0, 1, 1), \
'y': (1, 0, 1), \
'z': (1, 1, 0) }[axis]
pt1 = { 'x': (0, ny-1, nz-1), \
'y': (nx-1, 0, nz-1), \
'z': (nx-1, ny-1, 0) }[axis]
getf0['h'] = GetFields(fields, strfs_h, pt0, pt1)
pt0 = { 'x': (nx-1, 1, 1), \
'y': (1, ny-1, 1), \
'z': (1, 1, nz-1) }[axis]
pt1 = (nx - 1, ny - 1, nz - 1)
getf1['h'] = GetFields(fields, strfs_h, pt0, pt1)
for getf in getf0.values() + getf1.values():
getf.get_event().wait()
for eh in ['e', 'h']:
norm = np.linalg.norm( \
getf0[eh].get_fields() - getf1[eh].get_fields() )
self.assertEqual(norm, 0, '%g, %s, %s' % (norm, self.args, eh))
