def verify_reduce_map_ele(in_shape, axis, keepdims, type="sum"):
# Build the logic and compile the function
dat_dtype = "float32"
A = tvm.placeholder(shape=in_shape, name="A", dtype=dat_dtype)
A1 = topi.sqrt(topi.exp(A))
out_dtype = "float32"
if type == "sum":
B = topi.sum(A1, axis=axis, keepdims=keepdims)
elif type == "max":
B = topi.max(A1, axis=axis, keepdims=keepdims)
elif type == "min":
B = topi.min(A1, axis=axis, keepdims=keepdims)
elif type == "argmax":
B = topi.argmax(A1, axis=axis, keepdims=keepdims)
out_dtype = "int32"
elif type == "argmin":
B = topi.argmin(A1, axis=axis, keepdims=keepdims)
out_dtype = "int32"
else:
raise NotImplementedError
def check_device(device):
if not tvm.module.enabled(device):
print("Skip because %s is not enabled" % device)
return
with tvm.target.create(device):
s = topi.generic.schedule_reduce(B)
ctx = tvm.context(device, 0)
foo = tvm.build(s, [A, B], device, name="sum")
# Test
in_npy = np.random.uniform(size=in_shape).astype(np.float32)
in_npy_map = np.sqrt(np.exp(in_npy)).astype(np.float32)
if type == "sum":
out_npy = in_npy_map.sum(axis=axis, keepdims=keepdims)
elif type == "max":
out_npy = in_npy_map.max(axis=axis, keepdims=keepdims)
elif type == "min":
out_npy = in_npy_map.min(axis=axis, keepdims=keepdims)
elif type == "argmax":
out_npy = _my_npy_argmax(in_npy_map, axis=axis, keepdims=keepdims)
elif type == "argmin":
out_npy = _my_npy_argmin(in_npy_map, axis=axis, keepdims=keepdims)
else:
raise NotImplementedError
data_tvm = tvm.nd.array(in_npy, ctx=ctx)
out_tvm = tvm.nd.empty(shape=out_npy.shape, ctx=ctx, dtype=out_dtype)
for _ in range(1):
foo(data_tvm, out_tvm)
np.testing.assert_allclose(out_tvm.asnumpy(), out_npy, 1E-3, 1E-3)
check_device("opencl")
check_device("cuda")
check_device("metal")
check_device("rocm")
def verify_reduce_map_ele(in_shape,
axis,
keepdims,
type="sum",
dtype="float32"):
# Build the logic and compile the function
A = tvm.placeholder(shape=in_shape, name="A", dtype=dtype)
A1 = topi.sqrt(topi.exp(A))
out_dtype = dtype
if type == "sum":
B = topi.sum(A1, axis=axis, keepdims=keepdims)
elif type == "all":
B = topi.all(A, axis=axis, keepdims=keepdims)
elif type == "any":
B = topi.any(A, axis=axis, keepdims=keepdims)
elif type == "max":
B = topi.max(A1, axis=axis, keepdims=keepdims)
elif type == "min":
B = topi.min(A1, axis=axis, keepdims=keepdims)
elif type == "argmax":
B = topi.argmax(A1, axis=axis, keepdims=keepdims)
out_dtype = "int32"
elif type == "argmin":
B = topi.argmin(A1, axis=axis, keepdims=keepdims)
out_dtype = "int32"
else:
raise NotImplementedError
def check_device(device):
ctx = tvm.context(device, 0)
if not ctx.exist:
print("Skip because %s is not enabled" % device)
return
print("Running on target: %s" % device)
with tvm.target.create(device):
s = topi.generic.schedule_reduce(B)
foo = tvm.build(s, [A, B], device, name=type)
# Test
if dtype == 'bool':
in_npy_map = in_npy = np.random.choice([True, False],
size=in_shape)
else:
in_npy = np.random.uniform(-1, 1, size=in_shape).astype(dtype)
in_npy_map = np.sqrt(np.exp(in_npy)).astype(dtype)
if type == "sum":
out_npy = in_npy_map.sum(axis=axis, keepdims=keepdims)
elif type == "all" and dtype == 'bool':
out_npy = in_npy_map.all(axis=axis, keepdims=keepdims)
elif type == "any" and dtype == "bool":
out_npy = in_npy_map.any(axis=axis, keepdims=keepdims)
elif type == "max":
out_npy = in_npy_map.max(axis=axis, keepdims=keepdims)
elif type == "min":
out_npy = in_npy_map.min(axis=axis, keepdims=keepdims)
elif type == "argmax":
out_npy = _my_npy_argmax(in_npy_map, axis=axis, keepdims=keepdims)
elif type == "argmin":
out_npy = _my_npy_argmin(in_npy_map, axis=axis, keepdims=keepdims)
else:
raise NotImplementedError
data_tvm = tvm.nd.array(in_npy, ctx=ctx)
out_tvm = tvm.nd.empty(shape=out_npy.shape, ctx=ctx, dtype=out_dtype)
for _ in range(1):
foo(data_tvm, out_tvm)
if type == "argmax" or type == "argmin":
out_tvm_indices = out_tvm.asnumpy()
if keepdims:
out_tvm_indices = np.take(out_tvm_indices,
indices=0,
axis=axis)
if axis is None:
out_tvm_val = in_npy_map.ravel()[out_tvm_indices]
else:
other_indices = tuple(
np.indices(in_shape[0:axis] + in_shape[(axis + 1):]))
sel_indices = other_indices[0:axis] + (
out_tvm_indices, ) + other_indices[axis:]
out_tvm_val = in_npy_map[sel_indices]
if type == "argmax":
tvm.testing.assert_allclose(out_tvm_val,
in_npy_map.max(axis=axis), 1E-3,
1E-3)
elif type == "argmin":
tvm.testing.assert_allclose(out_tvm_val,
in_npy_map.min(axis=axis), 1E-3,
1E-3)
else:
tvm.testing.assert_allclose(out_tvm.asnumpy(), out_npy, 1E-3, 1E-3)
for device in get_all_backend():
check_device(device)
def verify_reduce_map_ele(in_shape, axis, keepdims, type="sum"):
# Build the logic and compile the function
dat_dtype = "float32"
A = tvm.placeholder(shape=in_shape, name="A", dtype=dat_dtype)
A1 = topi.sqrt(topi.exp(A))
out_dtype = "float32"
if type == "sum":
B = topi.sum(A1, axis=axis, keepdims=keepdims)
elif type == "max":
B = topi.max(A1, axis=axis, keepdims=keepdims)
elif type == "min":
B = topi.min(A1, axis=axis, keepdims=keepdims)
elif type == "argmax":
B = topi.argmax(A1, axis=axis, keepdims=keepdims)
out_dtype = "int32"
elif type == "argmin":
B = topi.argmin(A1, axis=axis, keepdims=keepdims)
out_dtype = "int32"
else:
raise NotImplementedError
def check_device(device):
ctx = tvm.context(device, 0)
if not ctx.exist:
print("Skip because %s is not enabled" % device)
return
print("Running on target: %s" % device)
with tvm.target.create(device):
s = topi.generic.schedule_reduce(B)
foo = tvm.build(s, [A, B], device, name=type)
# Test
in_npy = np.random.uniform(size=in_shape).astype(np.float32)
in_npy_map = np.sqrt(np.exp(in_npy)).astype(np.float32)
if type == "sum":
out_npy = in_npy_map.sum(axis=axis, keepdims=keepdims)
elif type == "max":
out_npy = in_npy_map.max(axis=axis, keepdims=keepdims)
elif type == "min":
out_npy = in_npy_map.min(axis=axis, keepdims=keepdims)
elif type == "argmax":
out_npy = _my_npy_argmax(in_npy_map, axis=axis, keepdims=keepdims)
elif type == "argmin":
out_npy = _my_npy_argmin(in_npy_map, axis=axis, keepdims=keepdims)
else:
raise NotImplementedError
data_tvm = tvm.nd.array(in_npy, ctx=ctx)
out_tvm = tvm.nd.empty(shape=out_npy.shape, ctx=ctx, dtype=out_dtype)
for _ in range(1):
foo(data_tvm, out_tvm)
if type == "argmax" or type == "argmin":
out_tvm_indices = out_tvm.asnumpy()
if keepdims:
out_tvm_indices = np.take(out_tvm_indices, indices=0, axis=axis)
if axis is None:
out_tvm_val = in_npy_map.ravel()[out_tvm_indices]
else:
other_indices = tuple(np.indices(in_shape[0:axis] + in_shape[(axis+1):]))
sel_indices = other_indices[0:axis] + (out_tvm_indices,) + other_indices[axis:]
out_tvm_val = in_npy_map[sel_indices]
if type == "argmax":
np.testing.assert_allclose(out_tvm_val, in_npy_map.max(axis=axis), 1E-3, 1E-3)
elif type == "argmin":
np.testing.assert_allclose(out_tvm_val, in_npy_map.min(axis=axis), 1E-3, 1E-3)
else:
np.testing.assert_allclose(out_tvm.asnumpy(), out_npy, 1E-3, 1E-3)
for device in ["cuda", "opencl", "metal", "llvm", "rocm", "vulkan"]:
check_device(device)
