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, 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.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) )
for strf, eh in eh_dict.items():
cl.enqueue_copy(fields.queue, fields.get_buf(strf), eh)
# 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):
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.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):
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))