b = a
@dp.map(_[0:W])
def compute_tmp_again(i):
a << tmp[i]
b >> tmp[i]
b = a + a
@dp.map(_[0:W])
def compute_output(i):
a << tmp[i]
b >> B[i]
b = a + a
if __name__ == '__main__':
W.set(3)
A = dp.ndarray([W])
B = dp.ndarray([W])
A[:] = np.mgrid[0:W.get()]
B[:] = dp.float32(0.0)
raw_prog(A, B)
diff = np.linalg.norm(4 * A - B) / W.get()
print("Difference:", diff)
print("==== Program end ====")
exit(0 if diff <= 1e-5 else 1)
W = dp.symbol('W')
@dp.program
def indirection(A, x, B):
@dp.map(_[0:W])
def ind(i):
bla << A[x[i]]
out >> B[i]
out = bla
if __name__ == '__main__':
W.set(5)
A = dp.ndarray([W * W])
B = dp.ndarray([W])
x = dp.ndarray([W], dtype=dp.uint32)
A[:] = np.arange(10, 10 + W.get() * W.get())
B[:] = dp.float32(0)
x[:] = np.random.randint(0, W.get() * W.get(), W.get())
indirection(A, x, B, W=W)
print(x)
print(B)
B_ref = np.array([A[x[i]] for i in range(W.get())], dtype=B.dtype)
diff = np.linalg.norm(B - B_ref)
exit(0 if diff == 0 else 1)
dace.reduce(lambda a, b: a + b, tmp, sum)
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument("W", type=int, nargs="?", default=128)
parser.add_argument("H", type=int, nargs="?", default=128)
args = vars(parser.parse_args())
W.set(args["W"])
H.set(args["H"])
print('Map-Reduce Test %dx%d' % (W.get(), H.get()))
A = dace.ndarray([1, H, 1, W, 1], dtype=dace.float32)
B = dace.ndarray([H, W], dtype=dace.float32)
res = dace.ndarray([1], dtype=dace.float32)
A[:] = np.random.rand(1, H.get(), 1, W.get(), 1).astype(dace.float32.type)
B[:] = dace.float32(0)
res[:] = dace.float32(0)
mapreduce_test_3(A, B, res)
diff = np.linalg.norm(5 * A.reshape((H.get(), W.get())) - B) / (H.get() *
W.get())
diff_res = abs((np.sum(B) - res[0])).view(type=np.ndarray)
print("Difference:", diff, diff_res)
print("==== Program end ====")
exit(0 if diff <= 1e-5 and diff_res <= 1 else 1)
A_row[-1] = dace.uint32(nnz_last_row)
A_row = np.cumsum(A_row, dtype=np.uint32)
# Fill column data
for i in range(H.get() - 1):
A_col[nnz_per_row*i:nnz_per_row*(i+1)] = \
np.sort(np.random.choice(W.get(), nnz_per_row, replace=False))
# Fill column data for last row
A_col[nnz_per_row * (H.get() - 1):] = np.sort(
np.random.choice(W.get(), nnz_last_row, replace=False))
A_val[:] = np.random.rand(nnz.get()).astype(dace.float32.type)
#########################
x[:] = np.random.rand(W.get()).astype(dace.float32.type)
b[:] = dace.float32(0)
# Setup regression
A_sparse = scipy.sparse.csr_matrix((A_val, A_col, A_row),
shape=(H.get(), W.get()))
spmv(A_row, A_col, A_val, x, b)
if dace.Config.get_bool('profiling'):
dace.timethis('spmv', 'scipy', 0, A_sparse.dot, x)
diff = np.linalg.norm(A_sparse.dot(x) - b) / float(H.get())
print("Difference:", diff)
print("==== Program end ====")
exit(0 if diff <= 1e-5 else 1)
@dace.program
def prog(A, B):
no = dace.define_local([number], dace.float32)
number = dace.define_local([W], dace.float32)
f(A, number)
@dace.map(_[0:W])
def bla2(i):
inp << number[i]
out >> B[i]
out = 2 * inp
if __name__ == '__main__':
W.set(3)
A = dace.ndarray([W])
B = dace.ndarray([W])
A[:] = np.mgrid[0:W.get()]
B[:] = dace.float32(0.0)
prog(A, B)
diff = np.linalg.norm(4 * A - B) / W.get()
print("Difference:", diff)
print("==== Program end ====")
exit(0 if diff <= 1e-5 else 1)
import numpy as np
import dace as dp
from dace.sdfg import SDFG
from dace.memlet import Memlet
# Constructs an SDFG with two consecutive tasklets
if __name__ == '__main__':
print('Multidimensional offset and stride test')
# Externals (parameters, symbols)
N = dp.symbol('N')
N.set(20)
input = dp.ndarray([N, N], dp.float32)
output = dp.ndarray([4, 3], dp.float32)
input[:] = (np.random.rand(N.get(), N.get()) * 5).astype(dp.float32.type)
output[:] = dp.float32(0)
# Construct SDFG
mysdfg = SDFG('offset_stride')
state = mysdfg.add_state()
A_ = state.add_array('A', [6, 6],
dp.float32,
offset=[2, 3],
strides=[N, N])
B_ = state.add_array('B', [3, 2],
dp.float32,
offset=[-1, -1],
strides=[4, 3])
map_entry, map_exit = state.add_map('mymap', [('i', '1:4'), ('j', '1:3')])
tasklet = state.add_tasklet('mytasklet', {'a'}, {'b'}, 'b = a')
def reset_tmp(y, x):
out >> tmp[y, x]
out = dace.float32(0.0)
dace.reduce(lambda a, b: a + b, A, red2)
dace.reduce(lambda a, b: a + b, B[2:H - 2, 5, :], red1[0])
dace.reduce(lambda a, b: a + b, B[3:H - 3, 5:7, :], red1[1:], axis=(2, 0))
dace.reduce(lambda a, b: a - b, B[2:H - 2, 5, :], red1[0])
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument("W", type=int, nargs="?", default=20)
parser.add_argument("H", type=int, nargs="?", default=20)
args = vars(parser.parse_args())
A = dace.ndarray([W, H], dtype=dace.float32)
B = dace.ndarray([H, W, H], dtype=dace.float32)
red1 = dace.ndarray([3], dtype=dace.float32)
red2 = dace.ndarray([1], dtype=dace.float32)
W.set(args["W"])
H.set(args["H"])
print('Conflict Resolution Test %dx%d' % (W.get(), H.get()))
A[:] = np.random.rand(H.get(), W.get()).astype(dace.float32.type)
B[:] = np.random.rand(H.get(), W.get(), H.get()).astype(dace.float32.type)
red1[:] = dace.float32(0)
red2[:] = dace.float32(0)
confres_test.compile(A, B, red1, red2)
print("==== Program end ====")
def dot(A: dace.float32[N], B: dace.float32[N], out: dace.float32[1]):
@dace.map
def product(i: _[0:N]):
a << A[i]
b << B[i]
o >> out(1, lambda x, y: x + y)
o = a * b
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument("N", type=int, nargs="?", default=64)
args = vars(parser.parse_args())
N.set(args["N"])
A = dace.ndarray([N], dtype=dace.float32)
B = dace.ndarray([N], dtype=dace.float32)
out_AB = dace.scalar(dace.float32)
print('Dot product %d' % (N.get()))
A[:] = np.random.rand(N.get()).astype(dace.float32.type)
B[:] = np.random.rand(N.get()).astype(dace.float32.type)
out_AB[0] = dace.float32(0)
dot(A, B, out_AB)
diff_ab = np.linalg.norm(np.dot(A, B) - out_AB) / float(N.get())
print("Difference (A*B):", diff_ab)
exit(0 if (diff_ab <= 1e-5) else 1)
kernel[0, 2] * input[0, 2] + kernel[1, 0] * input[1, 0] +
kernel[1, 1] * input[1, 1] + kernel[1, 2] * input[1, 2] +
kernel[2, 0] * input[2, 0] + kernel[2, 1] * input[2, 1] +
kernel[2, 2] * input[2, 2])
if __name__ == "__main__":
print("==== Program start ====")
print('Conv2D %dx%d' % (N.get(), N.get()))
A = dace.ndarray([N, N], dtype=dace.float32)
B = dace.ndarray([N, N], dtype=dace.float32)
# Initialize arrays: Randomize A, zero B
A[:] = dace.float32(0)
B[:] = dace.float32(0)
A[1:N.get() - 1, 1:N.get() - 1] = np.random.rand(dace.eval(N - 2),
dace.eval(N - 2)).astype(
dace.float32.type)
regression = np.ndarray([N.get() - 2, N.get() - 2], dtype=np.float32)
regression[:] = A[1:N.get() - 1, 1:N.get() - 1]
#print(A.view(type=np.ndarray))
#############################################
# Run DaCe program
sdfg = stencil3x3.to_sdfg()
sdfg.add_constants({'kernel': KERNEL})
sdfg(A=A, B=B, N=N)
N = dace.symbol('N')
@dace.program(dace.float32[N], dace.float32[N])
def cudahello(V, Vout):
# Transient variable
@dace.map(_[0:N])
def multiplication(i):
in_V << V[i]
out >> Vout[i]
out = in_V * 2.0
if __name__ == "__main__":
N.set(52)
print('Vector double CUDA %d' % (N.get()))
V = dace.ndarray([N], dace.float32)
Vout = dace.ndarray([N], dace.float32)
V[:] = np.random.rand(N.get()).astype(dace.float32.type)
Vout[:] = dace.float32(0)
cudahello(V, Vout)
diff = np.linalg.norm(2 * V - Vout) / N.get()
print("Difference:", diff)
print("==== Program end ====")
exit(0 if diff <= 1e-5 else 1)