def _compile(self, inputs):
for node, data in zip(self._inputs, inputs):
dtype = node.tensor.shape.dtype
shape = edsl.LogicalShape(dtype, data.shape)
node.tensor.bind(shape)
outputs = [x.tensor for x in self._outputs]
updates = [(x[0].tensor, x[1].tensor) for x in self._updates]
program = edsl.Program(self._name, outputs, updates)
return plaidml_exec.Executable(program, [x.tensor for x in self._inputs])
def run(program, inputs):
def make_buffer(tensor):
# convert LogicalShape into TensorShape
shape = plaidml.TensorShape(tensor.shape.dtype,
tensor.shape.int_dims)
return plaidml.Buffer(device, shape)
ibindings = [(x, make_buffer(x)) for x, y in inputs]
obindings = [(x, make_buffer(x)) for x in program.outputs]
exe = plaidml_exec.Executable(program, device, target, ibindings,
obindings)
return [x.as_ndarray() for x in exe([y for x, y in inputs])]
def toroidal_shell_integral(n, minval, maxval, eps, benchmark=False):
coordvals = np.linspace(minval, maxval, n, dtype=np.float32)
delta = (maxval - minval) / (n - 1) # grid spacing
X_data = coordvals.reshape(n, 1, 1)
Y_data = coordvals.reshape(1, n, 1)
Z_data = coordvals.reshape(1, 1, n)
X = edsl.Tensor(edsl.LogicalShape(plaidml.DType.FLOAT32, X_data.shape))
Y = edsl.Tensor(edsl.LogicalShape(plaidml.DType.FLOAT32, Y_data.shape))
Z = edsl.Tensor(edsl.LogicalShape(plaidml.DType.FLOAT32, Z_data.shape))
# f-rep of torodial shell f(x, y, z) = (sqrt(x^2 + y^2) - 1)^2 + z^2 + (0.1)^2
F = sq(edsl.sqrt(sq(X) + sq(Y)) - 1.0) + sq(Z) - sq(0.1)
# moment of inertia about z axis at each point g(x, y, z) = x^2 + y^2
G = sq(X) + sq(Y)
DFDX = partial(F, 'x', delta)
DFDY = partial(F, 'y', delta)
DFDZ = partial(F, 'z', delta)
# chi: occupancy function: 1 inside the region (f<0), 0 outside the region (f>0)
DCHIDX = partial_chi(F, 'x', delta)
DCHIDY = partial_chi(F, 'y', delta)
DCHIDZ = partial_chi(F, 'z', delta)
NUMER = DFDX * DCHIDX + DFDY * DCHIDY + DFDZ * DCHIDZ
DENOM = edsl.sqrt(sq(DFDX) + sq(DFDY) + sq(DFDZ))
H = edsl.select(DENOM < eps, 0, NUMER / DENOM)
O = sum(-G * H)
program = edsl.Program('toroidal_shell_integral', [O])
executable = plaidml_exec.Executable(program, [X, Y, Z])
def run():
outputs = executable([X_data, Y_data, Z_data])
return outputs[0].as_ndarray()
if benchmark:
# the first run will compile and run
print('compiling...')
result = run()
# subsequent runs should not include compile time
print('running...')
ITERATIONS = 100
elapsed = timeit.timeit(run, number=ITERATIONS)
print('runtime:', elapsed / ITERATIONS)
else:
result = run()
return result * (delta**3)
def _compile(self, inputs):
for node, data in zip(self._inputs, inputs):
dtype = node.tensor.shape.dtype
shape = edsl.LogicalShape(dtype, data.shape)
node.tensor.bind(shape)
outputs = [x.tensor for x in self._outputs]
updates = [(x[0].tensor, x[1].tensor) for x in self._updates]
program = edsl.Program(self._name, outputs, updates)
def make_buffer(tensor):
# convert LogicalShape into TensorShape
shape = plaidml.TensorShape(tensor.shape.dtype, tensor.shape.int_dims)
return plaidml.Buffer(_device, shape)
input_bindings = [(x.tensor, make_buffer(x.tensor)) for x in self._inputs]
output_bindings = [(x, make_buffer(x)) for x in program.outputs]
return plaidml_exec.Executable(program, _device, _target, input_bindings, output_bindings)
