def run(sched_lambda):
return run_tvm(0,
1, {
A: 1 * np.ones(get_shape(A)).astype(np.float32),
B: 2 * np.ones(get_shape(B)).astype(np.float32)
},
C,
scheduling=sched_lambda,
debug=True)
def demo_array1():
with tvm.build_config(instrument_bound_checkers=True):
a = tvm.placeholder((10,), name='a')
b = tvm.placeholder((10,), name='b')
c = tvm.compute((10,), lambda i: a[i+100050000])
npy = run_tvm(0,1,
{ a:np.ones(get_shape(a)).astype(np.float32)
, b:np.ones(get_shape(b)).astype(np.float32)
},c,debug=True)
print(npy.last_data)
def test_reduce():
n = 10
m = 10
A = tvm.placeholder((n, m), name='A')
k = tvm.reduce_axis((0, m), "k")
k2 = tvm.reduce_axis((0, m), "k")
B1 = tvm.compute((n,), lambda i: tvm.sum(A[i,k], axis=[k,k2]), name="B")
# === B1 = tensor_map (\i -> fold1 (+) 0 (map (\k -> A[i,k]) [k_begin..k_end])) A
r=run_tvm(0,1, { A:2*np.ones(get_shape(A)).astype(np.float32)}, B1, debug=True)
print(r.last_data)
def test_compute():
A = tvm.placeholder((10,), name='A')
B = tvm.placeholder((30,), name='B')
C = tvm.compute((30,), lambda i: A[i/3]+B[i], name="C")
r=run_tvm(0,1,
{ A:1*np.ones(get_shape(A)).astype(np.float32)
, B:2*np.ones(get_shape(B)).astype(np.float32)
},
C,
debug=True)
print(r.last_data)
def demo_broadcast():
""" Check that broad works as expected """
num_classes = 10
batch_size = 1
img_h = 28
img_w = 28
img_c = 1
f1_c = 1
x = tvm.placeholder((batch_size, img_h, img_w, img_c), name='x')
b = tvm.placeholder((img_c, ), name='b')
# Plus here will perform auto-broadcast
y = x + topi.broadcast_to(b, (batch_size, 1, 1, img_c))
npy = run_tvm(
0, 1, {
x: np.ones(get_shape(x)).astype(np.float32),
b: np.ones(get_shape(b)).astype(np.float32)
}, y)
print(npy.last_data[0, :, :, 0])