def test_calc_nc():
n_pts = 16
for i in range(100):
# OpenCL
u = numpy.random.uniform(low=1.0, high=10.0,
size=(n_pts,
n_pts)).astype(dtype=numpy.float32)
otf_mask_shift = pyRef.createOTFMask()
nc = numpy.zeros(1, dtype=numpy.float32)
u_buffer = cl.Buffer(context,
cl.mem_flags.READ_ONLY
| cl.mem_flags.COPY_HOST_PTR,
hostbuf=u)
otf_mask_buffer = cl.Buffer(context,
cl.mem_flags.READ_ONLY
| cl.mem_flags.COPY_HOST_PTR,
hostbuf=otf_mask_shift)
nc_buffer = cl.Buffer(context,
cl.mem_flags.WRITE_ONLY
| cl.mem_flags.COPY_HOST_PTR,
hostbuf=nc)
program.calc_nc_test(queue, (1, ), (1, ), u_buffer, otf_mask_buffer,
nc_buffer)
cl.enqueue_copy(queue, nc, nc_buffer).wait()
queue.finish()
# Reference 1
otf_mask = numpy.fft.fftshift(otf_mask_shift.reshape(16, 16))
ncs_sr = ncsC.NCSCSubRegion(r_size=n_pts)
ncs_sr.setOTFMask(otf_mask)
ncs_sr.setU(u)
ref1_nc = ncs_sr.calcNoiseContribution()
ncs_sr.cleanup()
norm_diff = abs(nc[0] - ref1_nc) / abs(ref1_nc)
assert (norm_diff <
1.0e-3), "Difference in results! {0:.6f}".format(norm_diff)
# Reference 2
u_r = numpy.copy(u).flatten()
u_c = numpy.zeros_like(u_r)
u_fft_r = numpy.zeros_like(u_r)
u_fft_c = numpy.zeros_like(u_c)
otf_mask_sqr = (otf_mask_shift * otf_mask_shift).flatten()
pyRef.fft_16x16(u_r, u_c, u_fft_r, u_fft_c)
ref2_nc = pyRef.calcNoiseContribution(u_fft_r, u_fft_c, otf_mask_sqr)
norm_diff = abs(nc[0] - ref2_nc) / abs(ref2_nc)
assert (norm_diff <
1.0e-3), "Difference in results! {0:.6f}".format(norm_diff)
def test_calc_nc_grad_1():
n_pts = 16
for i in range(10):
# OpenCL gradient calculation.
u = numpy.random.uniform(low = 1.0, high = 10.0, size = (n_pts, n_pts)).astype(dtype = numpy.float32)
otf_mask_shift = pyRef.createOTFMask()
grad = numpy.zeros((n_pts, n_pts)).astype(numpy.float32)
u_buffer = cl.Buffer(context, cl.mem_flags.READ_ONLY | cl.mem_flags.COPY_HOST_PTR, hostbuf = u)
otf_mask_buffer = cl.Buffer(context, cl.mem_flags.READ_ONLY | cl.mem_flags.COPY_HOST_PTR, hostbuf = otf_mask_shift)
grad_buffer = cl.Buffer(context, cl.mem_flags.WRITE_ONLY | cl.mem_flags.COPY_HOST_PTR, hostbuf = grad)
program.calc_nc_grad_test(queue, (16,), (16,),
u_buffer,
otf_mask_buffer,
grad_buffer)
cl.enqueue_copy(queue, grad, grad_buffer).wait()
queue.finish()
# Reference 1
otf_mask = numpy.fft.fftshift(otf_mask_shift.reshape(16, 16))
ncs_sr = ncsC.NCSCSubRegion(r_size = n_pts)
ncs_sr.setOTFMask(otf_mask)
ncs_sr.setU(u)
ncs_sr.calcNoiseContribution()
ref1_grad = ncs_sr.calcNCGradient().reshape(grad.shape)
ncs_sr.cleanup()
ref_norm = numpy.abs(ref1_grad)
ref_norm[(ref_norm<1.0)] = 1.0
max_diff = numpy.max(numpy.abs(grad - ref1_grad)/ref_norm)
assert (max_diff < 1.0e-5), "Difference in results! {0:.8f}".format(max_diff)
# Reference 2
u_r = numpy.copy(u).flatten()
u_c = numpy.zeros_like(u_r)
u_fft_r = numpy.zeros_like(u_r)
u_fft_c = numpy.zeros_like(u_r)
ref2_grad = numpy.zeros_like(u_r)
otf_mask_sqr = otf_mask_shift * otf_mask_shift
pyRef.fft_16x16(u_r, u_c, u_fft_r, u_fft_c)
pyRef.calcNCGradientIFFT(u_fft_r, u_fft_c, otf_mask_sqr, ref2_grad)
ref_norm = numpy.abs(ref2_grad)
ref_norm[(ref_norm<1.0)] = 1.0
max_diff = numpy.max(numpy.abs(grad.flatten() - ref2_grad)/ref_norm)
assert (max_diff < 1.0e-5), "Difference in results! {0:.8f}".format(max_diff)
def test_py_ref_fft_16x16():
x_r = numpy.random.uniform(size=256).astype(dtype=numpy.float32)
x_c = numpy.random.uniform(size=256).astype(dtype=numpy.float32)
y_r = numpy.zeros_like(x_r)
y_c = numpy.zeros_like(x_c)
y_r_c = numpy.zeros_like(x_r)
y_c_c = numpy.zeros_like(x_c)
x_r_buffer = cl.Buffer(context,
cl.mem_flags.READ_ONLY | cl.mem_flags.COPY_HOST_PTR,
hostbuf=x_r)
x_c_buffer = cl.Buffer(context,
cl.mem_flags.READ_ONLY | cl.mem_flags.COPY_HOST_PTR,
hostbuf=x_c)
y_r_buffer = cl.Buffer(context,
cl.mem_flags.WRITE_ONLY
| cl.mem_flags.COPY_HOST_PTR,
hostbuf=y_r)
y_c_buffer = cl.Buffer(context,
cl.mem_flags.WRITE_ONLY
| cl.mem_flags.COPY_HOST_PTR,
hostbuf=y_c)
program.fft_16x16_test(queue, (1, ), (1, ), x_r_buffer, x_c_buffer,
y_r_buffer, y_c_buffer)
cl.enqueue_copy(queue, y_r, y_r_buffer).wait()
cl.enqueue_copy(queue, y_c, y_c_buffer).wait()
queue.finish()
pyRef.fft_16x16(x_r, x_c, y_r_c, y_c_c)
assert (numpy.allclose(y_r, y_r_c, atol=1.0e-5))
assert (numpy.allclose(y_c, y_c_c, atol=1.0e-5))