def test_subset_minmax(self):
from pycuda.curandom import rand as curand
l_a = 200000
gran = 5
l_m = l_a - l_a // gran + 1
if has_double_support():
dtypes = [np.float64, np.float32, np.int32]
else:
dtypes = [np.float32, np.int32]
for dtype in dtypes:
a_gpu = curand((l_a, ), dtype)
a = a_gpu.get()
meaningful_indices_gpu = gpuarray.zeros(l_m, dtype=np.int32)
meaningful_indices = meaningful_indices_gpu.get()
j = 0
for i in range(len(meaningful_indices)):
meaningful_indices[i] = j
j = j + 1
if j % gran == 0:
j = j + 1
meaningful_indices_gpu = gpuarray.to_gpu(meaningful_indices)
b = a[meaningful_indices]
min_a = np.min(b)
min_a_gpu = gpuarray.subset_min(meaningful_indices_gpu,
a_gpu).get()
assert min_a_gpu == min_a
def test_subset_minmax(self):
from pycuda.curandom import rand as curand
l_a = 200000
gran = 5
l_m = l_a - l_a // gran + 1
if has_double_support():
dtypes = [np.float64, np.float32, np.int32]
else:
dtypes = [np.float32, np.int32]
for dtype in dtypes:
a_gpu = curand((l_a,), dtype)
a = a_gpu.get()
meaningful_indices_gpu = gpuarray.zeros(l_m, dtype=np.int32)
meaningful_indices = meaningful_indices_gpu.get()
j = 0
for i in range(len(meaningful_indices)):
meaningful_indices[i] = j
j = j + 1
if j % gran == 0:
j = j + 1
meaningful_indices_gpu = gpuarray.to_gpu(meaningful_indices)
b = a[meaningful_indices]
min_a = np.min(b)
min_a_gpu = gpuarray.subset_min(meaningful_indices_gpu, a_gpu).get()
assert min_a_gpu == min_a
def map_nodal_min(self, op, field_expr):
return gpuarray.subset_min(
self.executor.discr._meaningful_volume_indices(),
self.rec(field_expr)).get()
def map_nodal_min(self, op, field_expr):
return gpuarray.subset_min(
self.executor.discr._meaningful_volume_indices(),
self.rec(field_expr)).get()
