def run_complex_reduce_test(self,
shape,
axis,
n,
op='sum',
dtype=np.complex64):
a = ((np.random.random(size=shape)*2-1)*127).astype(np.int8).astype(dtype) \
+ 1j*((np.random.random(size=shape)*2-1)*127).astype(np.int8).astype(dtype)
if op[:3] == 'pwr':
b_gold = pwrscrunch(a.astype(np.complex64), n, axis,
NP_OPS[op[3:]]).astype(np.float32)
else:
b_gold = scrunch(a.astype(np.complex64), n, axis, NP_OPS[op])
a = bf.asarray(a, space='cuda')
b = bf.empty_like(b_gold, space='cuda')
bf.reduce(a, b, op)
#for _ in xrange(10):
# bf.reduce(a, b, op)
#bf.device.stream_synchronize();
#t0 = time.time()
#nrep = 30
#for _ in xrange(nrep):
# bf.reduce(a, b, op)
#bf.device.stream_synchronize();
#dt = time.time() - t0
#print nrep * (a.nbytes + b.nbytes) / dt / 1e9, 'GB/s', shape, axis, n, dtype
b = b.copy('system')
np.testing.assert_allclose(b,
b_gold,
rtol=1e-3 if op[:3] == 'pwr' else 1e-7)
def run_reduce_test(self, shape, axis, n, op='sum', dtype=np.float32):
a = ((np.random.random(size=shape) * 2 - 1) * 127).astype(
np.int8).astype(dtype)
if op[:3] == 'pwr':
b_gold = pwrscrunch(a.astype(np.float32), n, axis, NP_OPS[op[3:]])
else:
b_gold = scrunch(a.astype(np.float32), n, axis, NP_OPS[op])
a = bf.asarray(a, space='cuda_managed')
b = bf.empty_like(b_gold, space='cuda_managed')
bf.reduce(a, b, op)
stream_synchronize()
np.testing.assert_allclose(b, b_gold)
def on_data(self, ispan, ospan):
idata, odata = ispan.data, ospan.data
bf.reduce(idata, odata, self.op)