def test_python_stencil_batch_kernel(cl):
input = NamedVideoStream(cl, 'test1')
frame = cl.io.Input([input])
range_frame = cl.streams.Range(frame, ranges=[{'start': 0, 'end': 30}])
test_out = cl.ops.TestPyStencilBatch(frame=range_frame, batch=50)
output = NamedStream(cl, 'test_hist')
output_op = cl.io.Output(test_out, [output])
cl.run(output_op,
PerfParams.estimate(),
cache_mode=CacheMode.Overwrite,
show_progress=False)
next(output.load())
def run(self, cl, device):
input = NamedVideoStream(cl, 'test1_inplace')
frame = cl.io.Input([input])
hist = cl.ops.Histogram(frame=frame, device=device)
output = NamedStream(cl, 'test_hist')
output_op = cl.io.Output(hist, [output])
cl.run(output_op,
PerfParams.estimate(),
cache_mode=CacheMode.Overwrite,
show_progress=False)
next(output.load())
def test_slice_args(cl):
frame = cl.io.Input([NamedVideoStream(cl, 'test1')])
slice_frame = cl.streams.Slice(
frame, [cl.partitioner.ranges([[0, 1], [1, 2], [2, 3]])])
test = cl.ops.TestSliceArgs(frame=slice_frame,
arg=[SliceList([i for i in range(3)])])
unsliced_frame = cl.streams.Unslice(test)
output = NamedStream(cl, 'test_slicing')
output_op = cl.io.Output(unsliced_frame, [output])
cl.run(output_op,
PerfParams.estimate(),
cache_mode=CacheMode.Overwrite,
show_progress=False)
num_rows = 0
list(output.load())
def test_bounded_state(cl):
warmup = 3
frame = cl.io.Input([NamedVideoStream(cl, 'test1')])
increment = cl.ops.TestIncrementBounded(ignore=frame, bounded_state=warmup)
sampled_increment = cl.streams.Gather(increment,
indices=[[0, 10, 25, 26, 27]])
output = NamedStream(cl, 'test_bounded_state')
output_op = cl.io.Output(sampled_increment, [output])
cl.run(output_op,
PerfParams.estimate(),
cache_mode=CacheMode.Overwrite,
show_progress=False)
num_rows = 0
expected_output = [0, warmup, warmup, warmup + 1, warmup + 2]
for buf in output.load():
(val, ) = struct.unpack('=q', buf)
assert val == expected_output[num_rows]
num_rows += 1
assert num_rows == 5
