warp-lang 1.0.0b5__py3-none-manylinux2014_x86_64.whl → 1.0.0b6__py3-none-manylinux2014_x86_64.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- docs/conf.py +3 -4
- examples/env/env_ant.py +1 -1
- examples/env/env_cartpole.py +1 -1
- examples/env/env_humanoid.py +1 -1
- examples/example_dem.py +28 -26
- examples/example_diffray.py +37 -30
- examples/example_fluid.py +7 -3
- examples/example_jacobian_ik.py +1 -1
- examples/example_mesh_intersect.py +10 -7
- examples/example_nvdb.py +3 -3
- examples/example_render_opengl.py +19 -10
- examples/example_sim_cartpole.py +9 -5
- examples/example_sim_cloth.py +29 -25
- examples/example_sim_fk_grad.py +2 -2
- examples/example_sim_fk_grad_torch.py +3 -3
- examples/example_sim_grad_bounce.py +11 -8
- examples/example_sim_grad_cloth.py +12 -9
- examples/example_sim_granular.py +2 -2
- examples/example_sim_granular_collision_sdf.py +13 -13
- examples/example_sim_neo_hookean.py +3 -3
- examples/example_sim_particle_chain.py +2 -2
- examples/example_sim_quadruped.py +8 -5
- examples/example_sim_rigid_chain.py +8 -5
- examples/example_sim_rigid_contact.py +13 -10
- examples/example_sim_rigid_fem.py +2 -2
- examples/example_sim_rigid_gyroscopic.py +2 -2
- examples/example_sim_rigid_kinematics.py +1 -1
- examples/example_sim_trajopt.py +3 -2
- examples/fem/example_apic_fluid.py +5 -7
- examples/fem/example_diffusion_mgpu.py +18 -16
- warp/__init__.py +3 -2
- warp/bin/warp.so +0 -0
- warp/build_dll.py +29 -9
- warp/builtins.py +206 -7
- warp/codegen.py +58 -38
- warp/config.py +3 -1
- warp/context.py +234 -128
- warp/fem/__init__.py +2 -2
- warp/fem/cache.py +2 -1
- warp/fem/field/nodal_field.py +18 -17
- warp/fem/geometry/hexmesh.py +11 -6
- warp/fem/geometry/quadmesh_2d.py +16 -12
- warp/fem/geometry/tetmesh.py +19 -8
- warp/fem/geometry/trimesh_2d.py +18 -7
- warp/fem/integrate.py +341 -196
- warp/fem/quadrature/__init__.py +1 -1
- warp/fem/quadrature/pic_quadrature.py +138 -53
- warp/fem/quadrature/quadrature.py +81 -9
- warp/fem/space/__init__.py +1 -1
- warp/fem/space/basis_space.py +169 -51
- warp/fem/space/grid_2d_function_space.py +2 -2
- warp/fem/space/grid_3d_function_space.py +2 -2
- warp/fem/space/hexmesh_function_space.py +2 -2
- warp/fem/space/partition.py +9 -6
- warp/fem/space/quadmesh_2d_function_space.py +2 -2
- warp/fem/space/shape/cube_shape_function.py +27 -15
- warp/fem/space/shape/square_shape_function.py +29 -18
- warp/fem/space/tetmesh_function_space.py +2 -2
- warp/fem/space/topology.py +10 -0
- warp/fem/space/trimesh_2d_function_space.py +2 -2
- warp/fem/utils.py +10 -5
- warp/native/array.h +49 -8
- warp/native/builtin.h +31 -14
- warp/native/cuda_util.cpp +8 -3
- warp/native/cuda_util.h +1 -0
- warp/native/exports.h +1177 -1108
- warp/native/intersect.h +4 -4
- warp/native/intersect_adj.h +8 -8
- warp/native/mat.h +65 -6
- warp/native/mesh.h +126 -5
- warp/native/quat.h +28 -4
- warp/native/vec.h +76 -14
- warp/native/warp.cu +1 -6
- warp/render/render_opengl.py +261 -109
- warp/sim/import_mjcf.py +13 -7
- warp/sim/import_urdf.py +14 -14
- warp/sim/inertia.py +17 -18
- warp/sim/model.py +67 -67
- warp/sim/render.py +1 -1
- warp/sparse.py +6 -6
- warp/stubs.py +19 -81
- warp/tape.py +1 -1
- warp/tests/__main__.py +3 -6
- warp/tests/{test_class_kernel.py → aux_test_class_kernel.py} +9 -1
- warp/tests/aux_test_conditional_unequal_types_kernels.py +21 -0
- warp/tests/{test_dependent.py → aux_test_dependent.py} +2 -2
- warp/tests/{test_reference.py → aux_test_reference.py} +1 -1
- warp/tests/aux_test_unresolved_func.py +14 -0
- warp/tests/aux_test_unresolved_symbol.py +14 -0
- warp/tests/{test_kinematics.py → disabled_kinematics.py} +10 -12
- warp/tests/run_coverage_serial.py +31 -0
- warp/tests/test_adam.py +102 -106
- warp/tests/test_arithmetic.py +39 -40
- warp/tests/test_array.py +46 -48
- warp/tests/test_array_reduce.py +25 -19
- warp/tests/test_atomic.py +62 -26
- warp/tests/test_bool.py +16 -11
- warp/tests/test_builtins_resolution.py +1292 -0
- warp/tests/test_bvh.py +9 -12
- warp/tests/test_closest_point_edge_edge.py +53 -57
- warp/tests/test_codegen.py +164 -134
- warp/tests/test_compile_consts.py +13 -19
- warp/tests/test_conditional.py +30 -32
- warp/tests/test_copy.py +9 -12
- warp/tests/test_ctypes.py +90 -98
- warp/tests/test_dense.py +20 -14
- warp/tests/test_devices.py +34 -35
- warp/tests/test_dlpack.py +74 -75
- warp/tests/test_examples.py +215 -97
- warp/tests/test_fabricarray.py +15 -21
- warp/tests/test_fast_math.py +14 -11
- warp/tests/test_fem.py +280 -97
- warp/tests/test_fp16.py +19 -15
- warp/tests/test_func.py +177 -194
- warp/tests/test_generics.py +71 -77
- warp/tests/test_grad.py +83 -32
- warp/tests/test_grad_customs.py +7 -9
- warp/tests/test_hash_grid.py +6 -10
- warp/tests/test_import.py +9 -23
- warp/tests/test_indexedarray.py +19 -21
- warp/tests/test_intersect.py +15 -9
- warp/tests/test_large.py +17 -19
- warp/tests/test_launch.py +14 -17
- warp/tests/test_lerp.py +63 -63
- warp/tests/test_lvalue.py +84 -35
- warp/tests/test_marching_cubes.py +9 -13
- warp/tests/test_mat.py +388 -3004
- warp/tests/test_mat_lite.py +9 -12
- warp/tests/test_mat_scalar_ops.py +2889 -0
- warp/tests/test_math.py +10 -11
- warp/tests/test_matmul.py +104 -100
- warp/tests/test_matmul_lite.py +72 -98
- warp/tests/test_mesh.py +35 -32
- warp/tests/test_mesh_query_aabb.py +18 -25
- warp/tests/test_mesh_query_point.py +39 -23
- warp/tests/test_mesh_query_ray.py +9 -21
- warp/tests/test_mlp.py +8 -9
- warp/tests/test_model.py +89 -93
- warp/tests/test_modules_lite.py +15 -25
- warp/tests/test_multigpu.py +87 -114
- warp/tests/test_noise.py +10 -12
- warp/tests/test_operators.py +14 -21
- warp/tests/test_options.py +10 -11
- warp/tests/test_pinned.py +16 -18
- warp/tests/test_print.py +16 -20
- warp/tests/test_quat.py +121 -88
- warp/tests/test_rand.py +12 -13
- warp/tests/test_reload.py +27 -32
- warp/tests/test_rounding.py +7 -10
- warp/tests/test_runlength_encode.py +105 -106
- warp/tests/test_smoothstep.py +8 -9
- warp/tests/test_snippet.py +13 -22
- warp/tests/test_sparse.py +30 -29
- warp/tests/test_spatial.py +179 -174
- warp/tests/test_streams.py +100 -107
- warp/tests/test_struct.py +98 -67
- warp/tests/test_tape.py +11 -17
- warp/tests/test_torch.py +89 -86
- warp/tests/test_transient_module.py +9 -12
- warp/tests/test_types.py +328 -50
- warp/tests/test_utils.py +217 -218
- warp/tests/test_vec.py +133 -2133
- warp/tests/test_vec_lite.py +8 -11
- warp/tests/test_vec_scalar_ops.py +2099 -0
- warp/tests/test_volume.py +391 -382
- warp/tests/test_volume_write.py +122 -135
- warp/tests/unittest_serial.py +35 -0
- warp/tests/unittest_suites.py +291 -0
- warp/tests/{test_base.py → unittest_utils.py} +138 -25
- warp/tests/{test_misc.py → unused_test_misc.py} +13 -5
- warp/tests/{test_debug.py → walkthough_debug.py} +2 -15
- warp/thirdparty/unittest_parallel.py +257 -54
- warp/types.py +119 -98
- warp/utils.py +14 -0
- {warp_lang-1.0.0b5.dist-info → warp_lang-1.0.0b6.dist-info}/METADATA +2 -1
- {warp_lang-1.0.0b5.dist-info → warp_lang-1.0.0b6.dist-info}/RECORD +182 -178
- {warp_lang-1.0.0b5.dist-info → warp_lang-1.0.0b6.dist-info}/WHEEL +1 -1
- warp/tests/test_all.py +0 -239
- warp/tests/test_conditional_unequal_types_kernels.py +0 -14
- warp/tests/test_coverage.py +0 -38
- warp/tests/test_unresolved_func.py +0 -7
- warp/tests/test_unresolved_symbol.py +0 -7
- /warp/tests/{test_compile_consts_dummy.py → aux_test_compile_consts_dummy.py} +0 -0
- /warp/tests/{test_reference_reference.py → aux_test_reference_reference.py} +0 -0
- /warp/tests/{test_square.py → aux_test_square.py} +0 -0
- {warp_lang-1.0.0b5.dist-info → warp_lang-1.0.0b6.dist-info}/LICENSE.md +0 -0
- {warp_lang-1.0.0b5.dist-info → warp_lang-1.0.0b6.dist-info}/top_level.txt +0 -0
warp/tests/test_vec.py
CHANGED
|
@@ -8,8 +8,9 @@
|
|
|
8
8
|
import unittest
|
|
9
9
|
|
|
10
10
|
import numpy as np
|
|
11
|
+
|
|
11
12
|
import warp as wp
|
|
12
|
-
from warp.tests.
|
|
13
|
+
from warp.tests.unittest_utils import *
|
|
13
14
|
|
|
14
15
|
wp.init()
|
|
15
16
|
|
|
@@ -29,12 +30,8 @@ np_unsigned_int_types = [
|
|
|
29
30
|
np.ubyte,
|
|
30
31
|
]
|
|
31
32
|
|
|
32
|
-
np_int_types = np_signed_int_types + np_unsigned_int_types
|
|
33
|
-
|
|
34
33
|
np_float_types = [np.float16, np.float32, np.float64]
|
|
35
34
|
|
|
36
|
-
np_scalar_types = np_int_types + np_float_types
|
|
37
|
-
|
|
38
35
|
|
|
39
36
|
def randvals(rng, shape, dtype):
|
|
40
37
|
if dtype in np_float_types:
|
|
@@ -54,521 +51,6 @@ def getkernel(func, suffix=""):
|
|
|
54
51
|
return kernel_cache[key]
|
|
55
52
|
|
|
56
53
|
|
|
57
|
-
def get_select_kernel(dtype):
|
|
58
|
-
def output_select_kernel_fn(
|
|
59
|
-
input: wp.array(dtype=dtype),
|
|
60
|
-
index: int,
|
|
61
|
-
out: wp.array(dtype=dtype),
|
|
62
|
-
):
|
|
63
|
-
out[0] = input[index]
|
|
64
|
-
|
|
65
|
-
return getkernel(output_select_kernel_fn, suffix=dtype.__name__)
|
|
66
|
-
|
|
67
|
-
|
|
68
|
-
def get_select_kernel2(dtype):
|
|
69
|
-
def output_select_kernel2_fn(
|
|
70
|
-
input: wp.array(dtype=dtype, ndim=2),
|
|
71
|
-
index0: int,
|
|
72
|
-
index1: int,
|
|
73
|
-
out: wp.array(dtype=dtype),
|
|
74
|
-
):
|
|
75
|
-
out[0] = input[index0, index1]
|
|
76
|
-
|
|
77
|
-
return getkernel(output_select_kernel2_fn, suffix=dtype.__name__)
|
|
78
|
-
|
|
79
|
-
|
|
80
|
-
def test_arrays(test, device, dtype):
|
|
81
|
-
rng = np.random.default_rng(123)
|
|
82
|
-
|
|
83
|
-
wptype = wp.types.np_dtype_to_warp_type[np.dtype(dtype)]
|
|
84
|
-
vec2 = wp.types.vector(length=2, dtype=wptype)
|
|
85
|
-
vec3 = wp.types.vector(length=3, dtype=wptype)
|
|
86
|
-
vec4 = wp.types.vector(length=4, dtype=wptype)
|
|
87
|
-
vec5 = wp.types.vector(length=5, dtype=wptype)
|
|
88
|
-
|
|
89
|
-
v2_np = randvals(rng, (10, 2), dtype)
|
|
90
|
-
v3_np = randvals(rng, (10, 3), dtype)
|
|
91
|
-
v4_np = randvals(rng, (10, 4), dtype)
|
|
92
|
-
v5_np = randvals(rng, (10, 5), dtype)
|
|
93
|
-
|
|
94
|
-
v2 = wp.array(v2_np, dtype=vec2, requires_grad=True, device=device)
|
|
95
|
-
v3 = wp.array(v3_np, dtype=vec3, requires_grad=True, device=device)
|
|
96
|
-
v4 = wp.array(v4_np, dtype=vec4, requires_grad=True, device=device)
|
|
97
|
-
v5 = wp.array(v5_np, dtype=vec5, requires_grad=True, device=device)
|
|
98
|
-
|
|
99
|
-
assert_np_equal(v2.numpy(), v2_np, tol=1.0e-6)
|
|
100
|
-
assert_np_equal(v3.numpy(), v3_np, tol=1.0e-6)
|
|
101
|
-
assert_np_equal(v4.numpy(), v4_np, tol=1.0e-6)
|
|
102
|
-
assert_np_equal(v5.numpy(), v5_np, tol=1.0e-6)
|
|
103
|
-
|
|
104
|
-
vec2 = wp.types.vector(length=2, dtype=wptype)
|
|
105
|
-
vec3 = wp.types.vector(length=3, dtype=wptype)
|
|
106
|
-
vec4 = wp.types.vector(length=4, dtype=wptype)
|
|
107
|
-
|
|
108
|
-
v2 = wp.array(v2_np, dtype=vec2, requires_grad=True, device=device)
|
|
109
|
-
v3 = wp.array(v3_np, dtype=vec3, requires_grad=True, device=device)
|
|
110
|
-
v4 = wp.array(v4_np, dtype=vec4, requires_grad=True, device=device)
|
|
111
|
-
|
|
112
|
-
assert_np_equal(v2.numpy(), v2_np, tol=1.0e-6)
|
|
113
|
-
assert_np_equal(v3.numpy(), v3_np, tol=1.0e-6)
|
|
114
|
-
assert_np_equal(v4.numpy(), v4_np, tol=1.0e-6)
|
|
115
|
-
|
|
116
|
-
|
|
117
|
-
def test_components(test, device, dtype):
|
|
118
|
-
# test accessing vector components from Python - this is especially important
|
|
119
|
-
# for float16, which requires special handling internally
|
|
120
|
-
|
|
121
|
-
wptype = wp.types.np_dtype_to_warp_type[np.dtype(dtype)]
|
|
122
|
-
vec3 = wp.types.vector(length=3, dtype=wptype)
|
|
123
|
-
|
|
124
|
-
v = vec3(1, 2, 3)
|
|
125
|
-
|
|
126
|
-
# test __getitem__ for individual components
|
|
127
|
-
test.assertEqual(v[0], 1)
|
|
128
|
-
test.assertEqual(v[1], 2)
|
|
129
|
-
test.assertEqual(v[2], 3)
|
|
130
|
-
|
|
131
|
-
# test __getitem__ for slices
|
|
132
|
-
s = v[:]
|
|
133
|
-
test.assertEqual(s[0], 1)
|
|
134
|
-
test.assertEqual(s[1], 2)
|
|
135
|
-
test.assertEqual(s[2], 3)
|
|
136
|
-
|
|
137
|
-
s = v[1:]
|
|
138
|
-
test.assertEqual(s[0], 2)
|
|
139
|
-
test.assertEqual(s[1], 3)
|
|
140
|
-
|
|
141
|
-
s = v[:2]
|
|
142
|
-
test.assertEqual(s[0], 1)
|
|
143
|
-
test.assertEqual(s[1], 2)
|
|
144
|
-
|
|
145
|
-
s = v[::2]
|
|
146
|
-
test.assertEqual(s[0], 1)
|
|
147
|
-
test.assertEqual(s[1], 3)
|
|
148
|
-
|
|
149
|
-
# test __setitem__ for individual components
|
|
150
|
-
v[0] = 4
|
|
151
|
-
v[1] = 5
|
|
152
|
-
v[2] = 6
|
|
153
|
-
test.assertEqual(v[0], 4)
|
|
154
|
-
test.assertEqual(v[1], 5)
|
|
155
|
-
test.assertEqual(v[2], 6)
|
|
156
|
-
|
|
157
|
-
# test __setitem__ for slices
|
|
158
|
-
v[:] = [7, 8, 9]
|
|
159
|
-
test.assertEqual(v[0], 7)
|
|
160
|
-
test.assertEqual(v[1], 8)
|
|
161
|
-
test.assertEqual(v[2], 9)
|
|
162
|
-
|
|
163
|
-
v[1:] = [10, 11]
|
|
164
|
-
test.assertEqual(v[0], 7)
|
|
165
|
-
test.assertEqual(v[1], 10)
|
|
166
|
-
test.assertEqual(v[2], 11)
|
|
167
|
-
|
|
168
|
-
v[:2] = [12, 13]
|
|
169
|
-
test.assertEqual(v[0], 12)
|
|
170
|
-
test.assertEqual(v[1], 13)
|
|
171
|
-
test.assertEqual(v[2], 11)
|
|
172
|
-
|
|
173
|
-
v[::2] = [14, 15]
|
|
174
|
-
test.assertEqual(v[0], 14)
|
|
175
|
-
test.assertEqual(v[1], 13)
|
|
176
|
-
test.assertEqual(v[2], 15)
|
|
177
|
-
|
|
178
|
-
|
|
179
|
-
def test_anon_type_instance(test, device, dtype, register_kernels=False):
|
|
180
|
-
rng = np.random.default_rng(123)
|
|
181
|
-
|
|
182
|
-
tol = {
|
|
183
|
-
np.float16: 5.0e-3,
|
|
184
|
-
np.float32: 1.0e-6,
|
|
185
|
-
np.float64: 1.0e-8,
|
|
186
|
-
}.get(dtype, 0)
|
|
187
|
-
|
|
188
|
-
wptype = wp.types.np_dtype_to_warp_type[np.dtype(dtype)]
|
|
189
|
-
|
|
190
|
-
def check_scalar_init(
|
|
191
|
-
input: wp.array(dtype=wptype),
|
|
192
|
-
output: wp.array(dtype=wptype),
|
|
193
|
-
):
|
|
194
|
-
v2result = wp.vector(input[0], length=2)
|
|
195
|
-
v3result = wp.vector(input[1], length=3)
|
|
196
|
-
v4result = wp.vector(input[2], length=4)
|
|
197
|
-
v5result = wp.vector(input[3], length=5)
|
|
198
|
-
|
|
199
|
-
idx = 0
|
|
200
|
-
for i in range(2):
|
|
201
|
-
output[idx] = wptype(2) * v2result[i]
|
|
202
|
-
idx = idx + 1
|
|
203
|
-
for i in range(3):
|
|
204
|
-
output[idx] = wptype(2) * v3result[i]
|
|
205
|
-
idx = idx + 1
|
|
206
|
-
for i in range(4):
|
|
207
|
-
output[idx] = wptype(2) * v4result[i]
|
|
208
|
-
idx = idx + 1
|
|
209
|
-
for i in range(5):
|
|
210
|
-
output[idx] = wptype(2) * v5result[i]
|
|
211
|
-
idx = idx + 1
|
|
212
|
-
|
|
213
|
-
def check_component_init(
|
|
214
|
-
input: wp.array(dtype=wptype),
|
|
215
|
-
output: wp.array(dtype=wptype),
|
|
216
|
-
):
|
|
217
|
-
v2result = wp.vector(input[0], input[1])
|
|
218
|
-
v3result = wp.vector(input[2], input[3], input[4])
|
|
219
|
-
v4result = wp.vector(input[5], input[6], input[7], input[8])
|
|
220
|
-
v5result = wp.vector(input[9], input[10], input[11], input[12], input[13])
|
|
221
|
-
|
|
222
|
-
idx = 0
|
|
223
|
-
for i in range(2):
|
|
224
|
-
output[idx] = wptype(2) * v2result[i]
|
|
225
|
-
idx = idx + 1
|
|
226
|
-
for i in range(3):
|
|
227
|
-
output[idx] = wptype(2) * v3result[i]
|
|
228
|
-
idx = idx + 1
|
|
229
|
-
for i in range(4):
|
|
230
|
-
output[idx] = wptype(2) * v4result[i]
|
|
231
|
-
idx = idx + 1
|
|
232
|
-
for i in range(5):
|
|
233
|
-
output[idx] = wptype(2) * v5result[i]
|
|
234
|
-
idx = idx + 1
|
|
235
|
-
|
|
236
|
-
scalar_kernel = getkernel(check_scalar_init, suffix=dtype.__name__)
|
|
237
|
-
component_kernel = getkernel(check_component_init, suffix=dtype.__name__)
|
|
238
|
-
output_select_kernel = get_select_kernel(wptype)
|
|
239
|
-
|
|
240
|
-
if register_kernels:
|
|
241
|
-
return
|
|
242
|
-
|
|
243
|
-
input = wp.array(randvals(rng, [4], dtype), requires_grad=True, device=device)
|
|
244
|
-
output = wp.zeros(2 + 3 + 4 + 5, dtype=wptype, requires_grad=True, device=device)
|
|
245
|
-
|
|
246
|
-
wp.launch(scalar_kernel, dim=1, inputs=[input], outputs=[output], device=device)
|
|
247
|
-
|
|
248
|
-
assert_np_equal(output.numpy()[:2], 2 * np.array([input.numpy()[0]] * 2), tol=1.0e-6)
|
|
249
|
-
assert_np_equal(output.numpy()[2:5], 2 * np.array([input.numpy()[1]] * 3), tol=1.0e-6)
|
|
250
|
-
assert_np_equal(output.numpy()[5:9], 2 * np.array([input.numpy()[2]] * 4), tol=1.0e-6)
|
|
251
|
-
assert_np_equal(output.numpy()[9:], 2 * np.array([input.numpy()[3]] * 5), tol=1.0e-6)
|
|
252
|
-
|
|
253
|
-
if dtype in np_float_types:
|
|
254
|
-
out = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
255
|
-
for i in range(len(output)):
|
|
256
|
-
tape = wp.Tape()
|
|
257
|
-
with tape:
|
|
258
|
-
wp.launch(scalar_kernel, dim=1, inputs=[input], outputs=[output], device=device)
|
|
259
|
-
wp.launch(output_select_kernel, dim=1, inputs=[output, i], outputs=[out], device=device)
|
|
260
|
-
|
|
261
|
-
tape.backward(loss=out)
|
|
262
|
-
expected = np.zeros_like(input.numpy())
|
|
263
|
-
if i < 2:
|
|
264
|
-
expected[0] = 2
|
|
265
|
-
elif i < 5:
|
|
266
|
-
expected[1] = 2
|
|
267
|
-
elif i < 9:
|
|
268
|
-
expected[2] = 2
|
|
269
|
-
else:
|
|
270
|
-
expected[3] = 2
|
|
271
|
-
|
|
272
|
-
assert_np_equal(tape.gradients[input].numpy(), expected, tol=tol)
|
|
273
|
-
|
|
274
|
-
tape.reset()
|
|
275
|
-
tape.zero()
|
|
276
|
-
|
|
277
|
-
input = wp.array(randvals(rng, [2 + 3 + 4 + 5], dtype), requires_grad=True, device=device)
|
|
278
|
-
output = wp.zeros(2 + 3 + 4 + 5, dtype=wptype, requires_grad=True, device=device)
|
|
279
|
-
|
|
280
|
-
wp.launch(component_kernel, dim=1, inputs=[input], outputs=[output], device=device)
|
|
281
|
-
|
|
282
|
-
assert_np_equal(output.numpy(), 2 * input.numpy(), tol=1.0e-6)
|
|
283
|
-
|
|
284
|
-
if dtype in np_float_types:
|
|
285
|
-
out = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
286
|
-
for i in range(len(output)):
|
|
287
|
-
tape = wp.Tape()
|
|
288
|
-
with tape:
|
|
289
|
-
wp.launch(component_kernel, dim=1, inputs=[input], outputs=[output], device=device)
|
|
290
|
-
wp.launch(output_select_kernel, dim=1, inputs=[output, i], outputs=[out], device=device)
|
|
291
|
-
|
|
292
|
-
tape.backward(loss=out)
|
|
293
|
-
expected = np.zeros_like(input.numpy())
|
|
294
|
-
expected[i] = 2
|
|
295
|
-
|
|
296
|
-
assert_np_equal(tape.gradients[input].numpy(), expected, tol=tol)
|
|
297
|
-
|
|
298
|
-
tape.reset()
|
|
299
|
-
tape.zero()
|
|
300
|
-
|
|
301
|
-
|
|
302
|
-
def test_constants(test, device, dtype, register_kernels=False):
|
|
303
|
-
wptype = wp.types.np_dtype_to_warp_type[np.dtype(dtype)]
|
|
304
|
-
vec2 = wp.types.vector(length=2, dtype=wptype)
|
|
305
|
-
vec3 = wp.types.vector(length=3, dtype=wptype)
|
|
306
|
-
vec4 = wp.types.vector(length=4, dtype=wptype)
|
|
307
|
-
vec5 = wp.types.vector(length=5, dtype=wptype)
|
|
308
|
-
|
|
309
|
-
cv2 = wp.constant(vec2(1, 2))
|
|
310
|
-
cv3 = wp.constant(vec3(1, 2, 3))
|
|
311
|
-
cv4 = wp.constant(vec4(1, 2, 3, 4))
|
|
312
|
-
cv5 = wp.constant(vec5(1, 2, 3, 4, 5))
|
|
313
|
-
|
|
314
|
-
def check_vector_constants():
|
|
315
|
-
wp.expect_eq(cv2, vec2(wptype(1), wptype(2)))
|
|
316
|
-
wp.expect_eq(cv3, vec3(wptype(1), wptype(2), wptype(3)))
|
|
317
|
-
wp.expect_eq(cv4, vec4(wptype(1), wptype(2), wptype(3), wptype(4)))
|
|
318
|
-
wp.expect_eq(cv5, vec5(wptype(1), wptype(2), wptype(3), wptype(4), wptype(5)))
|
|
319
|
-
|
|
320
|
-
kernel = getkernel(check_vector_constants, suffix=dtype.__name__)
|
|
321
|
-
|
|
322
|
-
if register_kernels:
|
|
323
|
-
return
|
|
324
|
-
|
|
325
|
-
wp.launch(kernel, dim=1, inputs=[])
|
|
326
|
-
|
|
327
|
-
|
|
328
|
-
def test_constructors(test, device, dtype, register_kernels=False):
|
|
329
|
-
rng = np.random.default_rng(123)
|
|
330
|
-
|
|
331
|
-
tol = {
|
|
332
|
-
np.float16: 5.0e-3,
|
|
333
|
-
np.float32: 1.0e-6,
|
|
334
|
-
np.float64: 1.0e-8,
|
|
335
|
-
}.get(dtype, 0)
|
|
336
|
-
|
|
337
|
-
wptype = wp.types.np_dtype_to_warp_type[np.dtype(dtype)]
|
|
338
|
-
vec2 = wp.types.vector(length=2, dtype=wptype)
|
|
339
|
-
vec3 = wp.types.vector(length=3, dtype=wptype)
|
|
340
|
-
vec4 = wp.types.vector(length=4, dtype=wptype)
|
|
341
|
-
vec5 = wp.types.vector(length=5, dtype=wptype)
|
|
342
|
-
|
|
343
|
-
def check_scalar_constructor(
|
|
344
|
-
input: wp.array(dtype=wptype),
|
|
345
|
-
v2: wp.array(dtype=vec2),
|
|
346
|
-
v3: wp.array(dtype=vec3),
|
|
347
|
-
v4: wp.array(dtype=vec4),
|
|
348
|
-
v5: wp.array(dtype=vec5),
|
|
349
|
-
v20: wp.array(dtype=wptype),
|
|
350
|
-
v21: wp.array(dtype=wptype),
|
|
351
|
-
v30: wp.array(dtype=wptype),
|
|
352
|
-
v31: wp.array(dtype=wptype),
|
|
353
|
-
v32: wp.array(dtype=wptype),
|
|
354
|
-
v40: wp.array(dtype=wptype),
|
|
355
|
-
v41: wp.array(dtype=wptype),
|
|
356
|
-
v42: wp.array(dtype=wptype),
|
|
357
|
-
v43: wp.array(dtype=wptype),
|
|
358
|
-
v50: wp.array(dtype=wptype),
|
|
359
|
-
v51: wp.array(dtype=wptype),
|
|
360
|
-
v52: wp.array(dtype=wptype),
|
|
361
|
-
v53: wp.array(dtype=wptype),
|
|
362
|
-
v54: wp.array(dtype=wptype),
|
|
363
|
-
):
|
|
364
|
-
v2result = vec2(input[0])
|
|
365
|
-
v3result = vec3(input[0])
|
|
366
|
-
v4result = vec4(input[0])
|
|
367
|
-
v5result = vec5(input[0])
|
|
368
|
-
|
|
369
|
-
v2[0] = v2result
|
|
370
|
-
v3[0] = v3result
|
|
371
|
-
v4[0] = v4result
|
|
372
|
-
v5[0] = v5result
|
|
373
|
-
|
|
374
|
-
# multiply outputs by 2 so we've got something to backpropagate
|
|
375
|
-
v20[0] = wptype(2) * v2result[0]
|
|
376
|
-
v21[0] = wptype(2) * v2result[1]
|
|
377
|
-
|
|
378
|
-
v30[0] = wptype(2) * v3result[0]
|
|
379
|
-
v31[0] = wptype(2) * v3result[1]
|
|
380
|
-
v32[0] = wptype(2) * v3result[2]
|
|
381
|
-
|
|
382
|
-
v40[0] = wptype(2) * v4result[0]
|
|
383
|
-
v41[0] = wptype(2) * v4result[1]
|
|
384
|
-
v42[0] = wptype(2) * v4result[2]
|
|
385
|
-
v43[0] = wptype(2) * v4result[3]
|
|
386
|
-
|
|
387
|
-
v50[0] = wptype(2) * v5result[0]
|
|
388
|
-
v51[0] = wptype(2) * v5result[1]
|
|
389
|
-
v52[0] = wptype(2) * v5result[2]
|
|
390
|
-
v53[0] = wptype(2) * v5result[3]
|
|
391
|
-
v54[0] = wptype(2) * v5result[4]
|
|
392
|
-
|
|
393
|
-
def check_vector_constructors(
|
|
394
|
-
input: wp.array(dtype=wptype),
|
|
395
|
-
v2: wp.array(dtype=vec2),
|
|
396
|
-
v3: wp.array(dtype=vec3),
|
|
397
|
-
v4: wp.array(dtype=vec4),
|
|
398
|
-
v5: wp.array(dtype=vec5),
|
|
399
|
-
v20: wp.array(dtype=wptype),
|
|
400
|
-
v21: wp.array(dtype=wptype),
|
|
401
|
-
v30: wp.array(dtype=wptype),
|
|
402
|
-
v31: wp.array(dtype=wptype),
|
|
403
|
-
v32: wp.array(dtype=wptype),
|
|
404
|
-
v40: wp.array(dtype=wptype),
|
|
405
|
-
v41: wp.array(dtype=wptype),
|
|
406
|
-
v42: wp.array(dtype=wptype),
|
|
407
|
-
v43: wp.array(dtype=wptype),
|
|
408
|
-
v50: wp.array(dtype=wptype),
|
|
409
|
-
v51: wp.array(dtype=wptype),
|
|
410
|
-
v52: wp.array(dtype=wptype),
|
|
411
|
-
v53: wp.array(dtype=wptype),
|
|
412
|
-
v54: wp.array(dtype=wptype),
|
|
413
|
-
):
|
|
414
|
-
v2result = vec2(input[0], input[1])
|
|
415
|
-
v3result = vec3(input[2], input[3], input[4])
|
|
416
|
-
v4result = vec4(input[5], input[6], input[7], input[8])
|
|
417
|
-
v5result = vec5(input[9], input[10], input[11], input[12], input[13])
|
|
418
|
-
|
|
419
|
-
v2[0] = v2result
|
|
420
|
-
v3[0] = v3result
|
|
421
|
-
v4[0] = v4result
|
|
422
|
-
v5[0] = v5result
|
|
423
|
-
|
|
424
|
-
# multiply the output by 2 so we've got something to backpropagate:
|
|
425
|
-
v20[0] = wptype(2) * v2result[0]
|
|
426
|
-
v21[0] = wptype(2) * v2result[1]
|
|
427
|
-
|
|
428
|
-
v30[0] = wptype(2) * v3result[0]
|
|
429
|
-
v31[0] = wptype(2) * v3result[1]
|
|
430
|
-
v32[0] = wptype(2) * v3result[2]
|
|
431
|
-
|
|
432
|
-
v40[0] = wptype(2) * v4result[0]
|
|
433
|
-
v41[0] = wptype(2) * v4result[1]
|
|
434
|
-
v42[0] = wptype(2) * v4result[2]
|
|
435
|
-
v43[0] = wptype(2) * v4result[3]
|
|
436
|
-
|
|
437
|
-
v50[0] = wptype(2) * v5result[0]
|
|
438
|
-
v51[0] = wptype(2) * v5result[1]
|
|
439
|
-
v52[0] = wptype(2) * v5result[2]
|
|
440
|
-
v53[0] = wptype(2) * v5result[3]
|
|
441
|
-
v54[0] = wptype(2) * v5result[4]
|
|
442
|
-
|
|
443
|
-
vec_kernel = getkernel(check_vector_constructors, suffix=dtype.__name__)
|
|
444
|
-
kernel = getkernel(check_scalar_constructor, suffix=dtype.__name__)
|
|
445
|
-
|
|
446
|
-
if register_kernels:
|
|
447
|
-
return
|
|
448
|
-
|
|
449
|
-
input = wp.array(randvals(rng, [1], dtype), requires_grad=True, device=device)
|
|
450
|
-
v2 = wp.zeros(1, dtype=vec2, device=device)
|
|
451
|
-
v3 = wp.zeros(1, dtype=vec3, device=device)
|
|
452
|
-
v4 = wp.zeros(1, dtype=vec4, device=device)
|
|
453
|
-
v5 = wp.zeros(1, dtype=vec5, device=device)
|
|
454
|
-
v20 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
455
|
-
v21 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
456
|
-
v30 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
457
|
-
v31 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
458
|
-
v32 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
459
|
-
v40 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
460
|
-
v41 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
461
|
-
v42 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
462
|
-
v43 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
463
|
-
v50 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
464
|
-
v51 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
465
|
-
v52 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
466
|
-
v53 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
467
|
-
v54 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
468
|
-
|
|
469
|
-
tape = wp.Tape()
|
|
470
|
-
with tape:
|
|
471
|
-
wp.launch(
|
|
472
|
-
kernel,
|
|
473
|
-
dim=1,
|
|
474
|
-
inputs=[input],
|
|
475
|
-
outputs=[v2, v3, v4, v5, v20, v21, v30, v31, v32, v40, v41, v42, v43, v50, v51, v52, v53, v54],
|
|
476
|
-
device=device,
|
|
477
|
-
)
|
|
478
|
-
|
|
479
|
-
if dtype in np_float_types:
|
|
480
|
-
for l in [v20, v21]:
|
|
481
|
-
tape.backward(loss=l)
|
|
482
|
-
test.assertEqual(tape.gradients[input].numpy()[0], 2.0)
|
|
483
|
-
tape.zero()
|
|
484
|
-
|
|
485
|
-
for l in [v30, v31, v32]:
|
|
486
|
-
tape.backward(loss=l)
|
|
487
|
-
test.assertEqual(tape.gradients[input].numpy()[0], 2.0)
|
|
488
|
-
tape.zero()
|
|
489
|
-
|
|
490
|
-
for l in [v40, v41, v42, v43]:
|
|
491
|
-
tape.backward(loss=l)
|
|
492
|
-
test.assertEqual(tape.gradients[input].numpy()[0], 2.0)
|
|
493
|
-
tape.zero()
|
|
494
|
-
|
|
495
|
-
for l in [v50, v51, v52, v53, v54]:
|
|
496
|
-
tape.backward(loss=l)
|
|
497
|
-
test.assertEqual(tape.gradients[input].numpy()[0], 2.0)
|
|
498
|
-
tape.zero()
|
|
499
|
-
|
|
500
|
-
val = input.numpy()[0]
|
|
501
|
-
assert_np_equal(v2.numpy()[0], np.array([val, val]), tol=1.0e-6)
|
|
502
|
-
assert_np_equal(v3.numpy()[0], np.array([val, val, val]), tol=1.0e-6)
|
|
503
|
-
assert_np_equal(v4.numpy()[0], np.array([val, val, val, val]), tol=1.0e-6)
|
|
504
|
-
assert_np_equal(v5.numpy()[0], np.array([val, val, val, val, val]), tol=1.0e-6)
|
|
505
|
-
|
|
506
|
-
assert_np_equal(v20.numpy()[0], 2 * val, tol=1.0e-6)
|
|
507
|
-
assert_np_equal(v21.numpy()[0], 2 * val, tol=1.0e-6)
|
|
508
|
-
assert_np_equal(v30.numpy()[0], 2 * val, tol=1.0e-6)
|
|
509
|
-
assert_np_equal(v31.numpy()[0], 2 * val, tol=1.0e-6)
|
|
510
|
-
assert_np_equal(v32.numpy()[0], 2 * val, tol=1.0e-6)
|
|
511
|
-
assert_np_equal(v40.numpy()[0], 2 * val, tol=1.0e-6)
|
|
512
|
-
assert_np_equal(v41.numpy()[0], 2 * val, tol=1.0e-6)
|
|
513
|
-
assert_np_equal(v42.numpy()[0], 2 * val, tol=1.0e-6)
|
|
514
|
-
assert_np_equal(v43.numpy()[0], 2 * val, tol=1.0e-6)
|
|
515
|
-
assert_np_equal(v50.numpy()[0], 2 * val, tol=1.0e-6)
|
|
516
|
-
assert_np_equal(v51.numpy()[0], 2 * val, tol=1.0e-6)
|
|
517
|
-
assert_np_equal(v52.numpy()[0], 2 * val, tol=1.0e-6)
|
|
518
|
-
assert_np_equal(v53.numpy()[0], 2 * val, tol=1.0e-6)
|
|
519
|
-
assert_np_equal(v54.numpy()[0], 2 * val, tol=1.0e-6)
|
|
520
|
-
|
|
521
|
-
input = wp.array(randvals(rng, [14], dtype), requires_grad=True, device=device)
|
|
522
|
-
tape = wp.Tape()
|
|
523
|
-
with tape:
|
|
524
|
-
wp.launch(
|
|
525
|
-
vec_kernel,
|
|
526
|
-
dim=1,
|
|
527
|
-
inputs=[input],
|
|
528
|
-
outputs=[v2, v3, v4, v5, v20, v21, v30, v31, v32, v40, v41, v42, v43, v50, v51, v52, v53, v54],
|
|
529
|
-
device=device,
|
|
530
|
-
)
|
|
531
|
-
|
|
532
|
-
if dtype in np_float_types:
|
|
533
|
-
for i, l in enumerate([v20, v21, v30, v31, v32, v40, v41, v42, v43, v50, v51, v52, v53, v54]):
|
|
534
|
-
tape.backward(loss=l)
|
|
535
|
-
grad = tape.gradients[input].numpy()
|
|
536
|
-
expected_grad = np.zeros_like(grad)
|
|
537
|
-
expected_grad[i] = 2
|
|
538
|
-
assert_np_equal(grad, expected_grad, tol=tol)
|
|
539
|
-
tape.zero()
|
|
540
|
-
|
|
541
|
-
assert_np_equal(v2.numpy()[0, 0], input.numpy()[0], tol=tol)
|
|
542
|
-
assert_np_equal(v2.numpy()[0, 1], input.numpy()[1], tol=tol)
|
|
543
|
-
assert_np_equal(v3.numpy()[0, 0], input.numpy()[2], tol=tol)
|
|
544
|
-
assert_np_equal(v3.numpy()[0, 1], input.numpy()[3], tol=tol)
|
|
545
|
-
assert_np_equal(v3.numpy()[0, 2], input.numpy()[4], tol=tol)
|
|
546
|
-
assert_np_equal(v4.numpy()[0, 0], input.numpy()[5], tol=tol)
|
|
547
|
-
assert_np_equal(v4.numpy()[0, 1], input.numpy()[6], tol=tol)
|
|
548
|
-
assert_np_equal(v4.numpy()[0, 2], input.numpy()[7], tol=tol)
|
|
549
|
-
assert_np_equal(v4.numpy()[0, 3], input.numpy()[8], tol=tol)
|
|
550
|
-
assert_np_equal(v5.numpy()[0, 0], input.numpy()[9], tol=tol)
|
|
551
|
-
assert_np_equal(v5.numpy()[0, 1], input.numpy()[10], tol=tol)
|
|
552
|
-
assert_np_equal(v5.numpy()[0, 2], input.numpy()[11], tol=tol)
|
|
553
|
-
assert_np_equal(v5.numpy()[0, 3], input.numpy()[12], tol=tol)
|
|
554
|
-
assert_np_equal(v5.numpy()[0, 4], input.numpy()[13], tol=tol)
|
|
555
|
-
|
|
556
|
-
assert_np_equal(v20.numpy()[0], 2 * input.numpy()[0], tol=tol)
|
|
557
|
-
assert_np_equal(v21.numpy()[0], 2 * input.numpy()[1], tol=tol)
|
|
558
|
-
assert_np_equal(v30.numpy()[0], 2 * input.numpy()[2], tol=tol)
|
|
559
|
-
assert_np_equal(v31.numpy()[0], 2 * input.numpy()[3], tol=tol)
|
|
560
|
-
assert_np_equal(v32.numpy()[0], 2 * input.numpy()[4], tol=tol)
|
|
561
|
-
assert_np_equal(v40.numpy()[0], 2 * input.numpy()[5], tol=tol)
|
|
562
|
-
assert_np_equal(v41.numpy()[0], 2 * input.numpy()[6], tol=tol)
|
|
563
|
-
assert_np_equal(v42.numpy()[0], 2 * input.numpy()[7], tol=tol)
|
|
564
|
-
assert_np_equal(v43.numpy()[0], 2 * input.numpy()[8], tol=tol)
|
|
565
|
-
assert_np_equal(v50.numpy()[0], 2 * input.numpy()[9], tol=tol)
|
|
566
|
-
assert_np_equal(v51.numpy()[0], 2 * input.numpy()[10], tol=tol)
|
|
567
|
-
assert_np_equal(v52.numpy()[0], 2 * input.numpy()[11], tol=tol)
|
|
568
|
-
assert_np_equal(v53.numpy()[0], 2 * input.numpy()[12], tol=tol)
|
|
569
|
-
assert_np_equal(v54.numpy()[0], 2 * input.numpy()[13], tol=tol)
|
|
570
|
-
|
|
571
|
-
|
|
572
54
|
def test_anon_constructor_error_dtype_keyword_missing(test, device):
|
|
573
55
|
@wp.kernel
|
|
574
56
|
def kernel():
|
|
@@ -710,1093 +192,21 @@ def test_tpl_constructor_error_numeric_args_mismatch(test, device):
|
|
|
710
192
|
)
|
|
711
193
|
|
|
712
194
|
|
|
713
|
-
def test_tpl_ops_with_anon(test, device):
|
|
714
|
-
vec3i = wp.vec(3, dtype=int)
|
|
715
|
-
|
|
716
|
-
v = wp.vec3i(1, 2, 3)
|
|
717
|
-
v += vec3i(2, 3, 4)
|
|
718
|
-
v -= vec3i(3, 4, 5)
|
|
719
|
-
test.assertSequenceEqual(v, (0, 1, 2))
|
|
720
|
-
|
|
721
|
-
v = vec3i(1, 2, 3)
|
|
722
|
-
v += wp.vec3i(2, 3, 4)
|
|
723
|
-
v -= wp.vec3i(3, 4, 5)
|
|
724
|
-
test.assertSequenceEqual(v, (0, 1, 2))
|
|
725
|
-
|
|
726
|
-
|
|
727
|
-
def test_indexing(test, device, dtype, register_kernels=False):
|
|
728
|
-
rng = np.random.default_rng(123)
|
|
729
|
-
|
|
730
|
-
tol = {
|
|
731
|
-
np.float16: 5.0e-3,
|
|
732
|
-
np.float32: 1.0e-6,
|
|
733
|
-
np.float64: 1.0e-8,
|
|
734
|
-
}.get(dtype, 0)
|
|
735
|
-
|
|
736
|
-
wptype = wp.types.np_dtype_to_warp_type[np.dtype(dtype)]
|
|
737
|
-
vec2 = wp.types.vector(length=2, dtype=wptype)
|
|
738
|
-
vec3 = wp.types.vector(length=3, dtype=wptype)
|
|
739
|
-
vec4 = wp.types.vector(length=4, dtype=wptype)
|
|
740
|
-
vec5 = wp.types.vector(length=5, dtype=wptype)
|
|
741
|
-
|
|
742
|
-
def check_indexing(
|
|
743
|
-
v2: wp.array(dtype=vec2),
|
|
744
|
-
v3: wp.array(dtype=vec3),
|
|
745
|
-
v4: wp.array(dtype=vec4),
|
|
746
|
-
v5: wp.array(dtype=vec5),
|
|
747
|
-
v20: wp.array(dtype=wptype),
|
|
748
|
-
v21: wp.array(dtype=wptype),
|
|
749
|
-
v30: wp.array(dtype=wptype),
|
|
750
|
-
v31: wp.array(dtype=wptype),
|
|
751
|
-
v32: wp.array(dtype=wptype),
|
|
752
|
-
v40: wp.array(dtype=wptype),
|
|
753
|
-
v41: wp.array(dtype=wptype),
|
|
754
|
-
v42: wp.array(dtype=wptype),
|
|
755
|
-
v43: wp.array(dtype=wptype),
|
|
756
|
-
v50: wp.array(dtype=wptype),
|
|
757
|
-
v51: wp.array(dtype=wptype),
|
|
758
|
-
v52: wp.array(dtype=wptype),
|
|
759
|
-
v53: wp.array(dtype=wptype),
|
|
760
|
-
v54: wp.array(dtype=wptype),
|
|
761
|
-
):
|
|
762
|
-
# multiply outputs by 2 so we've got something to backpropagate:
|
|
763
|
-
v20[0] = wptype(2) * v2[0][0]
|
|
764
|
-
v21[0] = wptype(2) * v2[0][1]
|
|
765
|
-
|
|
766
|
-
v30[0] = wptype(2) * v3[0][0]
|
|
767
|
-
v31[0] = wptype(2) * v3[0][1]
|
|
768
|
-
v32[0] = wptype(2) * v3[0][2]
|
|
769
|
-
|
|
770
|
-
v40[0] = wptype(2) * v4[0][0]
|
|
771
|
-
v41[0] = wptype(2) * v4[0][1]
|
|
772
|
-
v42[0] = wptype(2) * v4[0][2]
|
|
773
|
-
v43[0] = wptype(2) * v4[0][3]
|
|
774
|
-
|
|
775
|
-
v50[0] = wptype(2) * v5[0][0]
|
|
776
|
-
v51[0] = wptype(2) * v5[0][1]
|
|
777
|
-
v52[0] = wptype(2) * v5[0][2]
|
|
778
|
-
v53[0] = wptype(2) * v5[0][3]
|
|
779
|
-
v54[0] = wptype(2) * v5[0][4]
|
|
780
|
-
|
|
781
|
-
kernel = getkernel(check_indexing, suffix=dtype.__name__)
|
|
782
|
-
|
|
783
|
-
if register_kernels:
|
|
784
|
-
return
|
|
785
|
-
|
|
786
|
-
v2 = wp.array(randvals(rng, (1, 2), dtype), dtype=vec2, requires_grad=True, device=device)
|
|
787
|
-
v3 = wp.array(randvals(rng, (1, 3), dtype), dtype=vec3, requires_grad=True, device=device)
|
|
788
|
-
v4 = wp.array(randvals(rng, (1, 4), dtype), dtype=vec4, requires_grad=True, device=device)
|
|
789
|
-
v5 = wp.array(randvals(rng, (1, 5), dtype), dtype=vec5, requires_grad=True, device=device)
|
|
790
|
-
v20 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
791
|
-
v21 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
792
|
-
v30 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
793
|
-
v31 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
794
|
-
v32 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
795
|
-
v40 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
796
|
-
v41 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
797
|
-
v42 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
798
|
-
v43 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
799
|
-
v50 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
800
|
-
v51 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
801
|
-
v52 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
802
|
-
v53 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
803
|
-
v54 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
804
|
-
|
|
805
|
-
tape = wp.Tape()
|
|
806
|
-
with tape:
|
|
807
|
-
wp.launch(
|
|
808
|
-
kernel,
|
|
809
|
-
dim=1,
|
|
810
|
-
inputs=[v2, v3, v4, v5],
|
|
811
|
-
outputs=[v20, v21, v30, v31, v32, v40, v41, v42, v43, v50, v51, v52, v53, v54],
|
|
812
|
-
device=device,
|
|
813
|
-
)
|
|
814
|
-
|
|
815
|
-
if dtype in np_float_types:
|
|
816
|
-
for i, l in enumerate([v20, v21, v30, v31, v32, v40, v41, v42, v43, v50, v51, v52, v53, v54]):
|
|
817
|
-
tape.backward(loss=l)
|
|
818
|
-
allgrads = np.concatenate([tape.gradients[v].numpy()[0] for v in [v2, v3, v4, v5]])
|
|
819
|
-
expected_grads = np.zeros_like(allgrads)
|
|
820
|
-
expected_grads[i] = 2
|
|
821
|
-
assert_np_equal(allgrads, expected_grads, tol=tol)
|
|
822
|
-
tape.zero()
|
|
823
|
-
|
|
824
|
-
assert_np_equal(v20.numpy()[0], 2.0 * v2.numpy()[0, 0], tol=tol)
|
|
825
|
-
assert_np_equal(v21.numpy()[0], 2.0 * v2.numpy()[0, 1], tol=tol)
|
|
826
|
-
assert_np_equal(v30.numpy()[0], 2.0 * v3.numpy()[0, 0], tol=tol)
|
|
827
|
-
assert_np_equal(v31.numpy()[0], 2.0 * v3.numpy()[0, 1], tol=tol)
|
|
828
|
-
assert_np_equal(v32.numpy()[0], 2.0 * v3.numpy()[0, 2], tol=tol)
|
|
829
|
-
assert_np_equal(v40.numpy()[0], 2.0 * v4.numpy()[0, 0], tol=tol)
|
|
830
|
-
assert_np_equal(v41.numpy()[0], 2.0 * v4.numpy()[0, 1], tol=tol)
|
|
831
|
-
assert_np_equal(v42.numpy()[0], 2.0 * v4.numpy()[0, 2], tol=tol)
|
|
832
|
-
assert_np_equal(v43.numpy()[0], 2.0 * v4.numpy()[0, 3], tol=tol)
|
|
833
|
-
assert_np_equal(v50.numpy()[0], 2.0 * v5.numpy()[0, 0], tol=tol)
|
|
834
|
-
assert_np_equal(v51.numpy()[0], 2.0 * v5.numpy()[0, 1], tol=tol)
|
|
835
|
-
assert_np_equal(v52.numpy()[0], 2.0 * v5.numpy()[0, 2], tol=tol)
|
|
836
|
-
assert_np_equal(v53.numpy()[0], 2.0 * v5.numpy()[0, 3], tol=tol)
|
|
837
|
-
assert_np_equal(v54.numpy()[0], 2.0 * v5.numpy()[0, 4], tol=tol)
|
|
838
|
-
|
|
839
|
-
|
|
840
|
-
def test_equality(test, device, dtype, register_kernels=False):
|
|
841
|
-
wptype = wp.types.np_dtype_to_warp_type[np.dtype(dtype)]
|
|
842
|
-
vec2 = wp.types.vector(length=2, dtype=wptype)
|
|
843
|
-
vec3 = wp.types.vector(length=3, dtype=wptype)
|
|
844
|
-
vec4 = wp.types.vector(length=4, dtype=wptype)
|
|
845
|
-
vec5 = wp.types.vector(length=5, dtype=wptype)
|
|
846
|
-
|
|
847
|
-
def check_equality(
|
|
848
|
-
v20: wp.array(dtype=vec2),
|
|
849
|
-
v21: wp.array(dtype=vec2),
|
|
850
|
-
v22: wp.array(dtype=vec2),
|
|
851
|
-
v30: wp.array(dtype=vec3),
|
|
852
|
-
v31: wp.array(dtype=vec3),
|
|
853
|
-
v32: wp.array(dtype=vec3),
|
|
854
|
-
v33: wp.array(dtype=vec3),
|
|
855
|
-
v40: wp.array(dtype=vec4),
|
|
856
|
-
v41: wp.array(dtype=vec4),
|
|
857
|
-
v42: wp.array(dtype=vec4),
|
|
858
|
-
v43: wp.array(dtype=vec4),
|
|
859
|
-
v44: wp.array(dtype=vec4),
|
|
860
|
-
v50: wp.array(dtype=vec5),
|
|
861
|
-
v51: wp.array(dtype=vec5),
|
|
862
|
-
v52: wp.array(dtype=vec5),
|
|
863
|
-
v53: wp.array(dtype=vec5),
|
|
864
|
-
v54: wp.array(dtype=vec5),
|
|
865
|
-
v55: wp.array(dtype=vec5),
|
|
866
|
-
):
|
|
867
|
-
wp.expect_eq(v20[0], v20[0])
|
|
868
|
-
wp.expect_neq(v21[0], v20[0])
|
|
869
|
-
wp.expect_neq(v22[0], v20[0])
|
|
870
|
-
|
|
871
|
-
wp.expect_eq(v30[0], v30[0])
|
|
872
|
-
wp.expect_neq(v31[0], v30[0])
|
|
873
|
-
wp.expect_neq(v32[0], v30[0])
|
|
874
|
-
wp.expect_neq(v33[0], v30[0])
|
|
875
|
-
|
|
876
|
-
wp.expect_eq(v40[0], v40[0])
|
|
877
|
-
wp.expect_neq(v41[0], v40[0])
|
|
878
|
-
wp.expect_neq(v42[0], v40[0])
|
|
879
|
-
wp.expect_neq(v43[0], v40[0])
|
|
880
|
-
wp.expect_neq(v44[0], v40[0])
|
|
881
|
-
|
|
882
|
-
wp.expect_eq(v50[0], v50[0])
|
|
883
|
-
wp.expect_neq(v51[0], v50[0])
|
|
884
|
-
wp.expect_neq(v52[0], v50[0])
|
|
885
|
-
wp.expect_neq(v53[0], v50[0])
|
|
886
|
-
wp.expect_neq(v54[0], v50[0])
|
|
887
|
-
wp.expect_neq(v55[0], v50[0])
|
|
888
|
-
|
|
889
|
-
kernel = getkernel(check_equality, suffix=dtype.__name__)
|
|
890
|
-
|
|
891
|
-
if register_kernels:
|
|
892
|
-
return
|
|
893
|
-
|
|
894
|
-
v20 = wp.array([1.0, 2.0], dtype=vec2, requires_grad=True, device=device)
|
|
895
|
-
v21 = wp.array([1.0, 3.0], dtype=vec2, requires_grad=True, device=device)
|
|
896
|
-
v22 = wp.array([3.0, 2.0], dtype=vec2, requires_grad=True, device=device)
|
|
897
|
-
|
|
898
|
-
v30 = wp.array([1.0, 2.0, 3.0], dtype=vec3, requires_grad=True, device=device)
|
|
899
|
-
v31 = wp.array([-1.0, 2.0, 3.0], dtype=vec3, requires_grad=True, device=device)
|
|
900
|
-
v32 = wp.array([1.0, -2.0, 3.0], dtype=vec3, requires_grad=True, device=device)
|
|
901
|
-
v33 = wp.array([1.0, 2.0, -3.0], dtype=vec3, requires_grad=True, device=device)
|
|
902
|
-
|
|
903
|
-
v40 = wp.array([1.0, 2.0, 3.0, 4.0], dtype=vec4, requires_grad=True, device=device)
|
|
904
|
-
v41 = wp.array([-1.0, 2.0, 3.0, 4.0], dtype=vec4, requires_grad=True, device=device)
|
|
905
|
-
v42 = wp.array([1.0, -2.0, 3.0, 4.0], dtype=vec4, requires_grad=True, device=device)
|
|
906
|
-
v43 = wp.array([1.0, 2.0, -3.0, 4.0], dtype=vec4, requires_grad=True, device=device)
|
|
907
|
-
v44 = wp.array([1.0, 2.0, 3.0, -4.0], dtype=vec4, requires_grad=True, device=device)
|
|
908
|
-
|
|
909
|
-
v50 = wp.array([1.0, 2.0, 3.0, 4.0, 5.0], dtype=vec5, requires_grad=True, device=device)
|
|
910
|
-
v51 = wp.array([-1.0, 2.0, 3.0, 4.0, 5.0], dtype=vec5, requires_grad=True, device=device)
|
|
911
|
-
v52 = wp.array([1.0, -2.0, 3.0, 4.0, 5.0], dtype=vec5, requires_grad=True, device=device)
|
|
912
|
-
v53 = wp.array([1.0, 2.0, -3.0, 4.0, 5.0], dtype=vec5, requires_grad=True, device=device)
|
|
913
|
-
v54 = wp.array([1.0, 2.0, 3.0, -4.0, 5.0], dtype=vec5, requires_grad=True, device=device)
|
|
914
|
-
v55 = wp.array([1.0, 2.0, 3.0, 4.0, -5.0], dtype=vec5, requires_grad=True, device=device)
|
|
915
|
-
wp.launch(
|
|
916
|
-
kernel,
|
|
917
|
-
dim=1,
|
|
918
|
-
inputs=[
|
|
919
|
-
v20,
|
|
920
|
-
v21,
|
|
921
|
-
v22,
|
|
922
|
-
v30,
|
|
923
|
-
v31,
|
|
924
|
-
v32,
|
|
925
|
-
v33,
|
|
926
|
-
v40,
|
|
927
|
-
v41,
|
|
928
|
-
v42,
|
|
929
|
-
v43,
|
|
930
|
-
v44,
|
|
931
|
-
v50,
|
|
932
|
-
v51,
|
|
933
|
-
v52,
|
|
934
|
-
v53,
|
|
935
|
-
v54,
|
|
936
|
-
v55,
|
|
937
|
-
],
|
|
938
|
-
outputs=[],
|
|
939
|
-
device=device,
|
|
940
|
-
)
|
|
941
|
-
|
|
942
|
-
|
|
943
|
-
def test_negation(test, device, dtype, register_kernels=False):
|
|
944
|
-
rng = np.random.default_rng(123)
|
|
945
|
-
|
|
946
|
-
tol = {
|
|
947
|
-
np.float16: 5.0e-3,
|
|
948
|
-
np.float32: 1.0e-6,
|
|
949
|
-
np.float64: 1.0e-8,
|
|
950
|
-
}.get(dtype, 0)
|
|
951
|
-
|
|
952
|
-
wptype = wp.types.np_dtype_to_warp_type[np.dtype(dtype)]
|
|
953
|
-
vec2 = wp.types.vector(length=2, dtype=wptype)
|
|
954
|
-
vec3 = wp.types.vector(length=3, dtype=wptype)
|
|
955
|
-
vec4 = wp.types.vector(length=4, dtype=wptype)
|
|
956
|
-
vec5 = wp.types.vector(length=5, dtype=wptype)
|
|
957
|
-
|
|
958
|
-
def check_negation(
|
|
959
|
-
v2: wp.array(dtype=vec2),
|
|
960
|
-
v3: wp.array(dtype=vec3),
|
|
961
|
-
v4: wp.array(dtype=vec4),
|
|
962
|
-
v5: wp.array(dtype=vec5),
|
|
963
|
-
v2out: wp.array(dtype=vec2),
|
|
964
|
-
v3out: wp.array(dtype=vec3),
|
|
965
|
-
v4out: wp.array(dtype=vec4),
|
|
966
|
-
v5out: wp.array(dtype=vec5),
|
|
967
|
-
v20: wp.array(dtype=wptype),
|
|
968
|
-
v21: wp.array(dtype=wptype),
|
|
969
|
-
v30: wp.array(dtype=wptype),
|
|
970
|
-
v31: wp.array(dtype=wptype),
|
|
971
|
-
v32: wp.array(dtype=wptype),
|
|
972
|
-
v40: wp.array(dtype=wptype),
|
|
973
|
-
v41: wp.array(dtype=wptype),
|
|
974
|
-
v42: wp.array(dtype=wptype),
|
|
975
|
-
v43: wp.array(dtype=wptype),
|
|
976
|
-
v50: wp.array(dtype=wptype),
|
|
977
|
-
v51: wp.array(dtype=wptype),
|
|
978
|
-
v52: wp.array(dtype=wptype),
|
|
979
|
-
v53: wp.array(dtype=wptype),
|
|
980
|
-
v54: wp.array(dtype=wptype),
|
|
981
|
-
):
|
|
982
|
-
v2result = -v2[0]
|
|
983
|
-
v3result = -v3[0]
|
|
984
|
-
v4result = -v4[0]
|
|
985
|
-
v5result = -v5[0]
|
|
986
|
-
|
|
987
|
-
v2out[0] = v2result
|
|
988
|
-
v3out[0] = v3result
|
|
989
|
-
v4out[0] = v4result
|
|
990
|
-
v5out[0] = v5result
|
|
991
|
-
|
|
992
|
-
# multiply these outputs by 2 so we've got something to backpropagate:
|
|
993
|
-
v20[0] = wptype(2) * v2result[0]
|
|
994
|
-
v21[0] = wptype(2) * v2result[1]
|
|
995
|
-
|
|
996
|
-
v30[0] = wptype(2) * v3result[0]
|
|
997
|
-
v31[0] = wptype(2) * v3result[1]
|
|
998
|
-
v32[0] = wptype(2) * v3result[2]
|
|
999
|
-
|
|
1000
|
-
v40[0] = wptype(2) * v4result[0]
|
|
1001
|
-
v41[0] = wptype(2) * v4result[1]
|
|
1002
|
-
v42[0] = wptype(2) * v4result[2]
|
|
1003
|
-
v43[0] = wptype(2) * v4result[3]
|
|
1004
|
-
|
|
1005
|
-
v50[0] = wptype(2) * v5result[0]
|
|
1006
|
-
v51[0] = wptype(2) * v5result[1]
|
|
1007
|
-
v52[0] = wptype(2) * v5result[2]
|
|
1008
|
-
v53[0] = wptype(2) * v5result[3]
|
|
1009
|
-
v54[0] = wptype(2) * v5result[4]
|
|
1010
|
-
|
|
1011
|
-
kernel = getkernel(check_negation, suffix=dtype.__name__)
|
|
1012
|
-
|
|
1013
|
-
if register_kernels:
|
|
1014
|
-
return
|
|
1015
|
-
|
|
1016
|
-
v2 = wp.array(randvals(rng, (1, 2), dtype), dtype=vec2, requires_grad=True, device=device)
|
|
1017
|
-
v3 = wp.array(randvals(rng, (1, 3), dtype), dtype=vec3, requires_grad=True, device=device)
|
|
1018
|
-
v4 = wp.array(randvals(rng, (1, 4), dtype), dtype=vec4, requires_grad=True, device=device)
|
|
1019
|
-
v5_np = randvals(rng, (1, 5), dtype)
|
|
1020
|
-
v5 = wp.array(v5_np, dtype=vec5, requires_grad=True, device=device)
|
|
1021
|
-
|
|
1022
|
-
v2out = wp.zeros(1, dtype=vec2, device=device)
|
|
1023
|
-
v3out = wp.zeros(1, dtype=vec3, device=device)
|
|
1024
|
-
v4out = wp.zeros(1, dtype=vec4, device=device)
|
|
1025
|
-
v5out = wp.zeros(1, dtype=vec5, device=device)
|
|
1026
|
-
v20 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1027
|
-
v21 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1028
|
-
v30 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1029
|
-
v31 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1030
|
-
v32 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1031
|
-
v40 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1032
|
-
v41 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1033
|
-
v42 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1034
|
-
v43 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1035
|
-
v50 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1036
|
-
v51 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1037
|
-
v52 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1038
|
-
v53 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1039
|
-
v54 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1040
|
-
|
|
1041
|
-
tape = wp.Tape()
|
|
1042
|
-
with tape:
|
|
1043
|
-
wp.launch(
|
|
1044
|
-
kernel,
|
|
1045
|
-
dim=1,
|
|
1046
|
-
inputs=[v2, v3, v4, v5],
|
|
1047
|
-
outputs=[v2out, v3out, v4out, v5out, v20, v21, v30, v31, v32, v40, v41, v42, v43, v50, v51, v52, v53, v54],
|
|
1048
|
-
device=device,
|
|
1049
|
-
)
|
|
1050
|
-
|
|
1051
|
-
if dtype in np_float_types:
|
|
1052
|
-
for i, l in enumerate([v20, v21, v30, v31, v32, v40, v41, v42, v43, v50, v51, v52, v53, v54]):
|
|
1053
|
-
tape.backward(loss=l)
|
|
1054
|
-
allgrads = np.concatenate([tape.gradients[v].numpy()[0] for v in [v2, v3, v4, v5]])
|
|
1055
|
-
expected_grads = np.zeros_like(allgrads)
|
|
1056
|
-
expected_grads[i] = -2
|
|
1057
|
-
assert_np_equal(allgrads, expected_grads, tol=tol)
|
|
1058
|
-
tape.zero()
|
|
1059
|
-
|
|
1060
|
-
assert_np_equal(v2out.numpy()[0], -v2.numpy()[0], tol=tol)
|
|
1061
|
-
assert_np_equal(v3out.numpy()[0], -v3.numpy()[0], tol=tol)
|
|
1062
|
-
assert_np_equal(v4out.numpy()[0], -v4.numpy()[0], tol=tol)
|
|
1063
|
-
assert_np_equal(v5out.numpy()[0], -v5.numpy()[0], tol=tol)
|
|
1064
|
-
|
|
1065
|
-
|
|
1066
|
-
def test_scalar_multiplication(test, device, dtype, register_kernels=False):
|
|
1067
|
-
rng = np.random.default_rng(123)
|
|
1068
|
-
|
|
1069
|
-
tol = {
|
|
1070
|
-
np.float16: 5.0e-3,
|
|
1071
|
-
np.float32: 1.0e-6,
|
|
1072
|
-
np.float64: 1.0e-8,
|
|
1073
|
-
}.get(dtype, 0)
|
|
1074
|
-
|
|
1075
|
-
wptype = wp.types.np_dtype_to_warp_type[np.dtype(dtype)]
|
|
1076
|
-
vec2 = wp.types.vector(length=2, dtype=wptype)
|
|
1077
|
-
vec3 = wp.types.vector(length=3, dtype=wptype)
|
|
1078
|
-
vec4 = wp.types.vector(length=4, dtype=wptype)
|
|
1079
|
-
vec5 = wp.types.vector(length=5, dtype=wptype)
|
|
1080
|
-
|
|
1081
|
-
def check_mul(
|
|
1082
|
-
s: wp.array(dtype=wptype),
|
|
1083
|
-
v2: wp.array(dtype=vec2),
|
|
1084
|
-
v3: wp.array(dtype=vec3),
|
|
1085
|
-
v4: wp.array(dtype=vec4),
|
|
1086
|
-
v5: wp.array(dtype=vec5),
|
|
1087
|
-
v20: wp.array(dtype=wptype),
|
|
1088
|
-
v21: wp.array(dtype=wptype),
|
|
1089
|
-
v30: wp.array(dtype=wptype),
|
|
1090
|
-
v31: wp.array(dtype=wptype),
|
|
1091
|
-
v32: wp.array(dtype=wptype),
|
|
1092
|
-
v40: wp.array(dtype=wptype),
|
|
1093
|
-
v41: wp.array(dtype=wptype),
|
|
1094
|
-
v42: wp.array(dtype=wptype),
|
|
1095
|
-
v43: wp.array(dtype=wptype),
|
|
1096
|
-
v50: wp.array(dtype=wptype),
|
|
1097
|
-
v51: wp.array(dtype=wptype),
|
|
1098
|
-
v52: wp.array(dtype=wptype),
|
|
1099
|
-
v53: wp.array(dtype=wptype),
|
|
1100
|
-
v54: wp.array(dtype=wptype),
|
|
1101
|
-
):
|
|
1102
|
-
v2result = s[0] * v2[0]
|
|
1103
|
-
v3result = s[0] * v3[0]
|
|
1104
|
-
v4result = s[0] * v4[0]
|
|
1105
|
-
v5result = s[0] * v5[0]
|
|
1106
|
-
|
|
1107
|
-
# multiply outputs by 2 so we've got something to backpropagate:
|
|
1108
|
-
v20[0] = wptype(2) * v2result[0]
|
|
1109
|
-
v21[0] = wptype(2) * v2result[1]
|
|
1110
|
-
|
|
1111
|
-
v30[0] = wptype(2) * v3result[0]
|
|
1112
|
-
v31[0] = wptype(2) * v3result[1]
|
|
1113
|
-
v32[0] = wptype(2) * v3result[2]
|
|
1114
|
-
|
|
1115
|
-
v40[0] = wptype(2) * v4result[0]
|
|
1116
|
-
v41[0] = wptype(2) * v4result[1]
|
|
1117
|
-
v42[0] = wptype(2) * v4result[2]
|
|
1118
|
-
v43[0] = wptype(2) * v4result[3]
|
|
1119
|
-
|
|
1120
|
-
v50[0] = wptype(2) * v5result[0]
|
|
1121
|
-
v51[0] = wptype(2) * v5result[1]
|
|
1122
|
-
v52[0] = wptype(2) * v5result[2]
|
|
1123
|
-
v53[0] = wptype(2) * v5result[3]
|
|
1124
|
-
v54[0] = wptype(2) * v5result[4]
|
|
1125
|
-
|
|
1126
|
-
kernel = getkernel(check_mul, suffix=dtype.__name__)
|
|
1127
|
-
|
|
1128
|
-
if register_kernels:
|
|
1129
|
-
return
|
|
1130
|
-
|
|
1131
|
-
s = wp.array(randvals(rng, [1], dtype), requires_grad=True, device=device)
|
|
1132
|
-
v2 = wp.array(randvals(rng, (1, 2), dtype), dtype=vec2, requires_grad=True, device=device)
|
|
1133
|
-
v3 = wp.array(randvals(rng, (1, 3), dtype), dtype=vec3, requires_grad=True, device=device)
|
|
1134
|
-
v4 = wp.array(randvals(rng, (1, 4), dtype), dtype=vec4, requires_grad=True, device=device)
|
|
1135
|
-
v5 = wp.array(randvals(rng, (1, 5), dtype), dtype=vec5, requires_grad=True, device=device)
|
|
1136
|
-
v20 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1137
|
-
v21 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1138
|
-
v30 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1139
|
-
v31 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1140
|
-
v32 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1141
|
-
v40 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1142
|
-
v41 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1143
|
-
v42 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1144
|
-
v43 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1145
|
-
v50 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1146
|
-
v51 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1147
|
-
v52 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1148
|
-
v53 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1149
|
-
v54 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1150
|
-
tape = wp.Tape()
|
|
1151
|
-
with tape:
|
|
1152
|
-
wp.launch(
|
|
1153
|
-
kernel,
|
|
1154
|
-
dim=1,
|
|
1155
|
-
inputs=[
|
|
1156
|
-
s,
|
|
1157
|
-
v2,
|
|
1158
|
-
v3,
|
|
1159
|
-
v4,
|
|
1160
|
-
v5,
|
|
1161
|
-
],
|
|
1162
|
-
outputs=[v20, v21, v30, v31, v32, v40, v41, v42, v43, v50, v51, v52, v53, v54],
|
|
1163
|
-
device=device,
|
|
1164
|
-
)
|
|
1165
|
-
|
|
1166
|
-
assert_np_equal(v20.numpy()[0], 2 * s.numpy()[0] * v2.numpy()[0, 0], tol=tol)
|
|
1167
|
-
assert_np_equal(v21.numpy()[0], 2 * s.numpy()[0] * v2.numpy()[0, 1], tol=tol)
|
|
1168
|
-
|
|
1169
|
-
assert_np_equal(v30.numpy()[0], 2 * s.numpy()[0] * v3.numpy()[0, 0], tol=10 * tol)
|
|
1170
|
-
assert_np_equal(v31.numpy()[0], 2 * s.numpy()[0] * v3.numpy()[0, 1], tol=10 * tol)
|
|
1171
|
-
assert_np_equal(v32.numpy()[0], 2 * s.numpy()[0] * v3.numpy()[0, 2], tol=10 * tol)
|
|
1172
|
-
|
|
1173
|
-
assert_np_equal(v40.numpy()[0], 2 * s.numpy()[0] * v4.numpy()[0, 0], tol=10 * tol)
|
|
1174
|
-
assert_np_equal(v41.numpy()[0], 2 * s.numpy()[0] * v4.numpy()[0, 1], tol=10 * tol)
|
|
1175
|
-
assert_np_equal(v42.numpy()[0], 2 * s.numpy()[0] * v4.numpy()[0, 2], tol=10 * tol)
|
|
1176
|
-
assert_np_equal(v43.numpy()[0], 2 * s.numpy()[0] * v4.numpy()[0, 3], tol=10 * tol)
|
|
1177
|
-
|
|
1178
|
-
assert_np_equal(v50.numpy()[0], 2 * s.numpy()[0] * v5.numpy()[0, 0], tol=10 * tol)
|
|
1179
|
-
assert_np_equal(v51.numpy()[0], 2 * s.numpy()[0] * v5.numpy()[0, 1], tol=10 * tol)
|
|
1180
|
-
assert_np_equal(v52.numpy()[0], 2 * s.numpy()[0] * v5.numpy()[0, 2], tol=10 * tol)
|
|
1181
|
-
assert_np_equal(v53.numpy()[0], 2 * s.numpy()[0] * v5.numpy()[0, 3], tol=10 * tol)
|
|
1182
|
-
assert_np_equal(v54.numpy()[0], 2 * s.numpy()[0] * v5.numpy()[0, 4], tol=10 * tol)
|
|
1183
|
-
|
|
1184
|
-
incmps = np.concatenate([v.numpy()[0] for v in [v2, v3, v4, v5]])
|
|
1185
|
-
|
|
1186
|
-
if dtype in np_float_types:
|
|
1187
|
-
for i, l in enumerate([v20, v21, v30, v31, v32, v40, v41, v42, v43]):
|
|
1188
|
-
tape.backward(loss=l)
|
|
1189
|
-
sgrad = tape.gradients[s].numpy()[0]
|
|
1190
|
-
assert_np_equal(sgrad, 2 * incmps[i], tol=10 * tol)
|
|
1191
|
-
allgrads = np.concatenate([tape.gradients[v].numpy()[0] for v in [v2, v3, v4]])
|
|
1192
|
-
expected_grads = np.zeros_like(allgrads)
|
|
1193
|
-
expected_grads[i] = s.numpy()[0] * 2
|
|
1194
|
-
assert_np_equal(allgrads, expected_grads, tol=10 * tol)
|
|
1195
|
-
tape.zero()
|
|
1196
|
-
|
|
1197
|
-
|
|
1198
|
-
def test_scalar_multiplication_rightmul(test, device, dtype, register_kernels=False):
|
|
1199
|
-
rng = np.random.default_rng(123)
|
|
1200
|
-
|
|
1201
|
-
tol = {
|
|
1202
|
-
np.float16: 5.0e-3,
|
|
1203
|
-
np.float32: 1.0e-6,
|
|
1204
|
-
np.float64: 1.0e-8,
|
|
1205
|
-
}.get(dtype, 0)
|
|
1206
|
-
|
|
1207
|
-
wptype = wp.types.np_dtype_to_warp_type[np.dtype(dtype)]
|
|
1208
|
-
vec2 = wp.types.vector(length=2, dtype=wptype)
|
|
1209
|
-
vec3 = wp.types.vector(length=3, dtype=wptype)
|
|
1210
|
-
vec4 = wp.types.vector(length=4, dtype=wptype)
|
|
1211
|
-
vec5 = wp.types.vector(length=5, dtype=wptype)
|
|
1212
|
-
|
|
1213
|
-
def check_rightmul(
|
|
1214
|
-
s: wp.array(dtype=wptype),
|
|
1215
|
-
v2: wp.array(dtype=vec2),
|
|
1216
|
-
v3: wp.array(dtype=vec3),
|
|
1217
|
-
v4: wp.array(dtype=vec4),
|
|
1218
|
-
v5: wp.array(dtype=vec5),
|
|
1219
|
-
v20: wp.array(dtype=wptype),
|
|
1220
|
-
v21: wp.array(dtype=wptype),
|
|
1221
|
-
v30: wp.array(dtype=wptype),
|
|
1222
|
-
v31: wp.array(dtype=wptype),
|
|
1223
|
-
v32: wp.array(dtype=wptype),
|
|
1224
|
-
v40: wp.array(dtype=wptype),
|
|
1225
|
-
v41: wp.array(dtype=wptype),
|
|
1226
|
-
v42: wp.array(dtype=wptype),
|
|
1227
|
-
v43: wp.array(dtype=wptype),
|
|
1228
|
-
v50: wp.array(dtype=wptype),
|
|
1229
|
-
v51: wp.array(dtype=wptype),
|
|
1230
|
-
v52: wp.array(dtype=wptype),
|
|
1231
|
-
v53: wp.array(dtype=wptype),
|
|
1232
|
-
v54: wp.array(dtype=wptype),
|
|
1233
|
-
):
|
|
1234
|
-
v2result = v2[0] * s[0]
|
|
1235
|
-
v3result = v3[0] * s[0]
|
|
1236
|
-
v4result = v4[0] * s[0]
|
|
1237
|
-
v5result = v5[0] * s[0]
|
|
1238
|
-
|
|
1239
|
-
# multiply outputs by 2 so we've got something to backpropagate:
|
|
1240
|
-
v20[0] = wptype(2) * v2result[0]
|
|
1241
|
-
v21[0] = wptype(2) * v2result[1]
|
|
1242
|
-
|
|
1243
|
-
v30[0] = wptype(2) * v3result[0]
|
|
1244
|
-
v31[0] = wptype(2) * v3result[1]
|
|
1245
|
-
v32[0] = wptype(2) * v3result[2]
|
|
1246
|
-
|
|
1247
|
-
v40[0] = wptype(2) * v4result[0]
|
|
1248
|
-
v41[0] = wptype(2) * v4result[1]
|
|
1249
|
-
v42[0] = wptype(2) * v4result[2]
|
|
1250
|
-
v43[0] = wptype(2) * v4result[3]
|
|
1251
|
-
|
|
1252
|
-
v50[0] = wptype(2) * v5result[0]
|
|
1253
|
-
v51[0] = wptype(2) * v5result[1]
|
|
1254
|
-
v52[0] = wptype(2) * v5result[2]
|
|
1255
|
-
v53[0] = wptype(2) * v5result[3]
|
|
1256
|
-
v54[0] = wptype(2) * v5result[4]
|
|
1257
|
-
|
|
1258
|
-
kernel = getkernel(check_rightmul, suffix=dtype.__name__)
|
|
1259
|
-
|
|
1260
|
-
if register_kernels:
|
|
1261
|
-
return
|
|
1262
|
-
|
|
1263
|
-
s = wp.array(randvals(rng, [1], dtype), requires_grad=True, device=device)
|
|
1264
|
-
v2 = wp.array(randvals(rng, (1, 2), dtype), dtype=vec2, requires_grad=True, device=device)
|
|
1265
|
-
v3 = wp.array(randvals(rng, (1, 3), dtype), dtype=vec3, requires_grad=True, device=device)
|
|
1266
|
-
v4 = wp.array(randvals(rng, (1, 4), dtype), dtype=vec4, requires_grad=True, device=device)
|
|
1267
|
-
v5 = wp.array(randvals(rng, (1, 5), dtype), dtype=vec5, requires_grad=True, device=device)
|
|
1268
|
-
v20 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1269
|
-
v21 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1270
|
-
v30 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1271
|
-
v31 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1272
|
-
v32 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1273
|
-
v40 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1274
|
-
v41 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1275
|
-
v42 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1276
|
-
v43 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1277
|
-
v50 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1278
|
-
v51 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1279
|
-
v52 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1280
|
-
v53 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1281
|
-
v54 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1282
|
-
tape = wp.Tape()
|
|
1283
|
-
with tape:
|
|
1284
|
-
wp.launch(
|
|
1285
|
-
kernel,
|
|
1286
|
-
dim=1,
|
|
1287
|
-
inputs=[
|
|
1288
|
-
s,
|
|
1289
|
-
v2,
|
|
1290
|
-
v3,
|
|
1291
|
-
v4,
|
|
1292
|
-
v5,
|
|
1293
|
-
],
|
|
1294
|
-
outputs=[v20, v21, v30, v31, v32, v40, v41, v42, v43, v50, v51, v52, v53, v54],
|
|
1295
|
-
device=device,
|
|
1296
|
-
)
|
|
1297
|
-
|
|
1298
|
-
assert_np_equal(v20.numpy()[0], 2 * s.numpy()[0] * v2.numpy()[0, 0], tol=tol)
|
|
1299
|
-
assert_np_equal(v21.numpy()[0], 2 * s.numpy()[0] * v2.numpy()[0, 1], tol=tol)
|
|
1300
|
-
|
|
1301
|
-
assert_np_equal(v30.numpy()[0], 2 * s.numpy()[0] * v3.numpy()[0, 0], tol=10 * tol)
|
|
1302
|
-
assert_np_equal(v31.numpy()[0], 2 * s.numpy()[0] * v3.numpy()[0, 1], tol=10 * tol)
|
|
1303
|
-
assert_np_equal(v32.numpy()[0], 2 * s.numpy()[0] * v3.numpy()[0, 2], tol=10 * tol)
|
|
1304
|
-
|
|
1305
|
-
assert_np_equal(v40.numpy()[0], 2 * s.numpy()[0] * v4.numpy()[0, 0], tol=10 * tol)
|
|
1306
|
-
assert_np_equal(v41.numpy()[0], 2 * s.numpy()[0] * v4.numpy()[0, 1], tol=10 * tol)
|
|
1307
|
-
assert_np_equal(v42.numpy()[0], 2 * s.numpy()[0] * v4.numpy()[0, 2], tol=10 * tol)
|
|
1308
|
-
assert_np_equal(v43.numpy()[0], 2 * s.numpy()[0] * v4.numpy()[0, 3], tol=10 * tol)
|
|
1309
|
-
|
|
1310
|
-
assert_np_equal(v50.numpy()[0], 2 * s.numpy()[0] * v5.numpy()[0, 0], tol=10 * tol)
|
|
1311
|
-
assert_np_equal(v51.numpy()[0], 2 * s.numpy()[0] * v5.numpy()[0, 1], tol=10 * tol)
|
|
1312
|
-
assert_np_equal(v52.numpy()[0], 2 * s.numpy()[0] * v5.numpy()[0, 2], tol=10 * tol)
|
|
1313
|
-
assert_np_equal(v53.numpy()[0], 2 * s.numpy()[0] * v5.numpy()[0, 3], tol=10 * tol)
|
|
1314
|
-
assert_np_equal(v54.numpy()[0], 2 * s.numpy()[0] * v5.numpy()[0, 4], tol=10 * tol)
|
|
1315
|
-
|
|
1316
|
-
incmps = np.concatenate([v.numpy()[0] for v in [v2, v3, v4, v5]])
|
|
1317
|
-
|
|
1318
|
-
if dtype in np_float_types:
|
|
1319
|
-
for i, l in enumerate([v20, v21, v30, v31, v32, v40, v41, v42, v43]):
|
|
1320
|
-
tape.backward(loss=l)
|
|
1321
|
-
sgrad = tape.gradients[s].numpy()[0]
|
|
1322
|
-
assert_np_equal(sgrad, 2 * incmps[i], tol=10 * tol)
|
|
1323
|
-
allgrads = np.concatenate([tape.gradients[v].numpy()[0] for v in [v2, v3, v4]])
|
|
1324
|
-
expected_grads = np.zeros_like(allgrads)
|
|
1325
|
-
expected_grads[i] = s.numpy()[0] * 2
|
|
1326
|
-
assert_np_equal(allgrads, expected_grads, tol=10 * tol)
|
|
1327
|
-
tape.zero()
|
|
1328
|
-
|
|
1329
|
-
|
|
1330
|
-
def test_cw_multiplication(test, device, dtype, register_kernels=False):
|
|
1331
|
-
rng = np.random.default_rng(123)
|
|
1332
|
-
|
|
1333
|
-
tol = {
|
|
1334
|
-
np.float16: 5.0e-3,
|
|
1335
|
-
np.float32: 1.0e-6,
|
|
1336
|
-
np.float64: 1.0e-8,
|
|
1337
|
-
}.get(dtype, 0)
|
|
1338
|
-
|
|
1339
|
-
wptype = wp.types.np_dtype_to_warp_type[np.dtype(dtype)]
|
|
1340
|
-
vec2 = wp.types.vector(length=2, dtype=wptype)
|
|
1341
|
-
vec3 = wp.types.vector(length=3, dtype=wptype)
|
|
1342
|
-
vec4 = wp.types.vector(length=4, dtype=wptype)
|
|
1343
|
-
vec5 = wp.types.vector(length=5, dtype=wptype)
|
|
1344
|
-
|
|
1345
|
-
def check_cw_mul(
|
|
1346
|
-
s2: wp.array(dtype=vec2),
|
|
1347
|
-
s3: wp.array(dtype=vec3),
|
|
1348
|
-
s4: wp.array(dtype=vec4),
|
|
1349
|
-
s5: wp.array(dtype=vec5),
|
|
1350
|
-
v2: wp.array(dtype=vec2),
|
|
1351
|
-
v3: wp.array(dtype=vec3),
|
|
1352
|
-
v4: wp.array(dtype=vec4),
|
|
1353
|
-
v5: wp.array(dtype=vec5),
|
|
1354
|
-
v20: wp.array(dtype=wptype),
|
|
1355
|
-
v21: wp.array(dtype=wptype),
|
|
1356
|
-
v30: wp.array(dtype=wptype),
|
|
1357
|
-
v31: wp.array(dtype=wptype),
|
|
1358
|
-
v32: wp.array(dtype=wptype),
|
|
1359
|
-
v40: wp.array(dtype=wptype),
|
|
1360
|
-
v41: wp.array(dtype=wptype),
|
|
1361
|
-
v42: wp.array(dtype=wptype),
|
|
1362
|
-
v43: wp.array(dtype=wptype),
|
|
1363
|
-
v50: wp.array(dtype=wptype),
|
|
1364
|
-
v51: wp.array(dtype=wptype),
|
|
1365
|
-
v52: wp.array(dtype=wptype),
|
|
1366
|
-
v53: wp.array(dtype=wptype),
|
|
1367
|
-
v54: wp.array(dtype=wptype),
|
|
1368
|
-
):
|
|
1369
|
-
v2result = wp.cw_mul(s2[0], v2[0])
|
|
1370
|
-
v3result = wp.cw_mul(s3[0], v3[0])
|
|
1371
|
-
v4result = wp.cw_mul(s4[0], v4[0])
|
|
1372
|
-
v5result = wp.cw_mul(s5[0], v5[0])
|
|
1373
|
-
|
|
1374
|
-
v20[0] = wptype(2) * v2result[0]
|
|
1375
|
-
v21[0] = wptype(2) * v2result[1]
|
|
1376
|
-
|
|
1377
|
-
v30[0] = wptype(2) * v3result[0]
|
|
1378
|
-
v31[0] = wptype(2) * v3result[1]
|
|
1379
|
-
v32[0] = wptype(2) * v3result[2]
|
|
1380
|
-
|
|
1381
|
-
v40[0] = wptype(2) * v4result[0]
|
|
1382
|
-
v41[0] = wptype(2) * v4result[1]
|
|
1383
|
-
v42[0] = wptype(2) * v4result[2]
|
|
1384
|
-
v43[0] = wptype(2) * v4result[3]
|
|
1385
|
-
|
|
1386
|
-
v50[0] = wptype(2) * v5result[0]
|
|
1387
|
-
v51[0] = wptype(2) * v5result[1]
|
|
1388
|
-
v52[0] = wptype(2) * v5result[2]
|
|
1389
|
-
v53[0] = wptype(2) * v5result[3]
|
|
1390
|
-
v54[0] = wptype(2) * v5result[4]
|
|
1391
|
-
|
|
1392
|
-
kernel = getkernel(check_cw_mul, suffix=dtype.__name__)
|
|
1393
|
-
|
|
1394
|
-
if register_kernels:
|
|
1395
|
-
return
|
|
1396
|
-
|
|
1397
|
-
s2 = wp.array(randvals(rng, (1, 2), dtype), dtype=vec2, requires_grad=True, device=device)
|
|
1398
|
-
s3 = wp.array(randvals(rng, (1, 3), dtype), dtype=vec3, requires_grad=True, device=device)
|
|
1399
|
-
s4 = wp.array(randvals(rng, (1, 4), dtype), dtype=vec4, requires_grad=True, device=device)
|
|
1400
|
-
s5 = wp.array(randvals(rng, (1, 5), dtype), dtype=vec5, requires_grad=True, device=device)
|
|
1401
|
-
v2 = wp.array(randvals(rng, (1, 2), dtype), dtype=vec2, requires_grad=True, device=device)
|
|
1402
|
-
v3 = wp.array(randvals(rng, (1, 3), dtype), dtype=vec3, requires_grad=True, device=device)
|
|
1403
|
-
v4 = wp.array(randvals(rng, (1, 4), dtype), dtype=vec4, requires_grad=True, device=device)
|
|
1404
|
-
v5 = wp.array(randvals(rng, (1, 5), dtype), dtype=vec5, requires_grad=True, device=device)
|
|
1405
|
-
v20 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1406
|
-
v21 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1407
|
-
v30 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1408
|
-
v31 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1409
|
-
v32 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1410
|
-
v40 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1411
|
-
v41 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1412
|
-
v42 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1413
|
-
v43 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1414
|
-
v50 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1415
|
-
v51 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1416
|
-
v52 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1417
|
-
v53 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1418
|
-
v54 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1419
|
-
tape = wp.Tape()
|
|
1420
|
-
with tape:
|
|
1421
|
-
wp.launch(
|
|
1422
|
-
kernel,
|
|
1423
|
-
dim=1,
|
|
1424
|
-
inputs=[
|
|
1425
|
-
s2,
|
|
1426
|
-
s3,
|
|
1427
|
-
s4,
|
|
1428
|
-
s5,
|
|
1429
|
-
v2,
|
|
1430
|
-
v3,
|
|
1431
|
-
v4,
|
|
1432
|
-
v5,
|
|
1433
|
-
],
|
|
1434
|
-
outputs=[v20, v21, v30, v31, v32, v40, v41, v42, v43, v50, v51, v52, v53, v54],
|
|
1435
|
-
device=device,
|
|
1436
|
-
)
|
|
1437
|
-
|
|
1438
|
-
assert_np_equal(v20.numpy()[0], 2 * s2.numpy()[0, 0] * v2.numpy()[0, 0], tol=10 * tol)
|
|
1439
|
-
assert_np_equal(v21.numpy()[0], 2 * s2.numpy()[0, 1] * v2.numpy()[0, 1], tol=10 * tol)
|
|
1440
|
-
|
|
1441
|
-
assert_np_equal(v30.numpy()[0], 2 * s3.numpy()[0, 0] * v3.numpy()[0, 0], tol=10 * tol)
|
|
1442
|
-
assert_np_equal(v31.numpy()[0], 2 * s3.numpy()[0, 1] * v3.numpy()[0, 1], tol=10 * tol)
|
|
1443
|
-
assert_np_equal(v32.numpy()[0], 2 * s3.numpy()[0, 2] * v3.numpy()[0, 2], tol=10 * tol)
|
|
1444
|
-
|
|
1445
|
-
assert_np_equal(v40.numpy()[0], 2 * s4.numpy()[0, 0] * v4.numpy()[0, 0], tol=10 * tol)
|
|
1446
|
-
assert_np_equal(v41.numpy()[0], 2 * s4.numpy()[0, 1] * v4.numpy()[0, 1], tol=10 * tol)
|
|
1447
|
-
assert_np_equal(v42.numpy()[0], 2 * s4.numpy()[0, 2] * v4.numpy()[0, 2], tol=10 * tol)
|
|
1448
|
-
assert_np_equal(v43.numpy()[0], 2 * s4.numpy()[0, 3] * v4.numpy()[0, 3], tol=10 * tol)
|
|
1449
|
-
|
|
1450
|
-
assert_np_equal(v50.numpy()[0], 2 * s5.numpy()[0, 0] * v5.numpy()[0, 0], tol=10 * tol)
|
|
1451
|
-
assert_np_equal(v51.numpy()[0], 2 * s5.numpy()[0, 1] * v5.numpy()[0, 1], tol=10 * tol)
|
|
1452
|
-
assert_np_equal(v52.numpy()[0], 2 * s5.numpy()[0, 2] * v5.numpy()[0, 2], tol=10 * tol)
|
|
1453
|
-
assert_np_equal(v53.numpy()[0], 2 * s5.numpy()[0, 3] * v5.numpy()[0, 3], tol=10 * tol)
|
|
1454
|
-
assert_np_equal(v54.numpy()[0], 2 * s5.numpy()[0, 4] * v5.numpy()[0, 4], tol=10 * tol)
|
|
1455
|
-
|
|
1456
|
-
incmps = np.concatenate([v.numpy()[0] for v in [v2, v3, v4, v5]])
|
|
1457
|
-
scmps = np.concatenate([v.numpy()[0] for v in [s2, s3, s4, s5]])
|
|
1458
|
-
|
|
1459
|
-
if dtype in np_float_types:
|
|
1460
|
-
for i, l in enumerate([v20, v21, v30, v31, v32, v40, v41, v42, v43, v50, v51, v52, v53, v54]):
|
|
1461
|
-
tape.backward(loss=l)
|
|
1462
|
-
sgrads = np.concatenate([tape.gradients[v].numpy()[0] for v in [s2, s3, s4, s5]])
|
|
1463
|
-
expected_grads = np.zeros_like(sgrads)
|
|
1464
|
-
expected_grads[i] = incmps[i] * 2
|
|
1465
|
-
assert_np_equal(sgrads, expected_grads, tol=10 * tol)
|
|
1466
|
-
|
|
1467
|
-
allgrads = np.concatenate([tape.gradients[v].numpy()[0] for v in [v2, v3, v4, v5]])
|
|
1468
|
-
expected_grads = np.zeros_like(allgrads)
|
|
1469
|
-
expected_grads[i] = scmps[i] * 2
|
|
1470
|
-
assert_np_equal(allgrads, expected_grads, tol=10 * tol)
|
|
1471
|
-
|
|
1472
|
-
tape.zero()
|
|
1473
|
-
|
|
1474
|
-
|
|
1475
|
-
def test_scalar_division(test, device, dtype, register_kernels=False):
|
|
1476
|
-
rng = np.random.default_rng(123)
|
|
1477
|
-
|
|
1478
|
-
tol = {
|
|
1479
|
-
np.float16: 5.0e-3,
|
|
1480
|
-
np.float32: 1.0e-6,
|
|
1481
|
-
np.float64: 1.0e-8,
|
|
1482
|
-
}.get(dtype, 0)
|
|
1483
|
-
|
|
1484
|
-
wptype = wp.types.np_dtype_to_warp_type[np.dtype(dtype)]
|
|
1485
|
-
vec2 = wp.types.vector(length=2, dtype=wptype)
|
|
1486
|
-
vec3 = wp.types.vector(length=3, dtype=wptype)
|
|
1487
|
-
vec4 = wp.types.vector(length=4, dtype=wptype)
|
|
1488
|
-
vec5 = wp.types.vector(length=5, dtype=wptype)
|
|
1489
|
-
|
|
1490
|
-
def check_div(
|
|
1491
|
-
s: wp.array(dtype=wptype),
|
|
1492
|
-
v2: wp.array(dtype=vec2),
|
|
1493
|
-
v3: wp.array(dtype=vec3),
|
|
1494
|
-
v4: wp.array(dtype=vec4),
|
|
1495
|
-
v5: wp.array(dtype=vec5),
|
|
1496
|
-
v20: wp.array(dtype=wptype),
|
|
1497
|
-
v21: wp.array(dtype=wptype),
|
|
1498
|
-
v30: wp.array(dtype=wptype),
|
|
1499
|
-
v31: wp.array(dtype=wptype),
|
|
1500
|
-
v32: wp.array(dtype=wptype),
|
|
1501
|
-
v40: wp.array(dtype=wptype),
|
|
1502
|
-
v41: wp.array(dtype=wptype),
|
|
1503
|
-
v42: wp.array(dtype=wptype),
|
|
1504
|
-
v43: wp.array(dtype=wptype),
|
|
1505
|
-
v50: wp.array(dtype=wptype),
|
|
1506
|
-
v51: wp.array(dtype=wptype),
|
|
1507
|
-
v52: wp.array(dtype=wptype),
|
|
1508
|
-
v53: wp.array(dtype=wptype),
|
|
1509
|
-
v54: wp.array(dtype=wptype),
|
|
1510
|
-
):
|
|
1511
|
-
v2result = v2[0] / s[0]
|
|
1512
|
-
v3result = v3[0] / s[0]
|
|
1513
|
-
v4result = v4[0] / s[0]
|
|
1514
|
-
v5result = v5[0] / s[0]
|
|
1515
|
-
|
|
1516
|
-
v20[0] = wptype(2) * v2result[0]
|
|
1517
|
-
v21[0] = wptype(2) * v2result[1]
|
|
1518
|
-
|
|
1519
|
-
v30[0] = wptype(2) * v3result[0]
|
|
1520
|
-
v31[0] = wptype(2) * v3result[1]
|
|
1521
|
-
v32[0] = wptype(2) * v3result[2]
|
|
1522
|
-
|
|
1523
|
-
v40[0] = wptype(2) * v4result[0]
|
|
1524
|
-
v41[0] = wptype(2) * v4result[1]
|
|
1525
|
-
v42[0] = wptype(2) * v4result[2]
|
|
1526
|
-
v43[0] = wptype(2) * v4result[3]
|
|
1527
|
-
|
|
1528
|
-
v50[0] = wptype(2) * v5result[0]
|
|
1529
|
-
v51[0] = wptype(2) * v5result[1]
|
|
1530
|
-
v52[0] = wptype(2) * v5result[2]
|
|
1531
|
-
v53[0] = wptype(2) * v5result[3]
|
|
1532
|
-
v54[0] = wptype(2) * v5result[4]
|
|
1533
|
-
|
|
1534
|
-
kernel = getkernel(check_div, suffix=dtype.__name__)
|
|
1535
|
-
|
|
1536
|
-
if register_kernels:
|
|
1537
|
-
return
|
|
1538
|
-
|
|
1539
|
-
s = wp.array(randvals(rng, [1], dtype), requires_grad=True, device=device)
|
|
1540
|
-
v2 = wp.array(randvals(rng, (1, 2), dtype), dtype=vec2, requires_grad=True, device=device)
|
|
1541
|
-
v3 = wp.array(randvals(rng, (1, 3), dtype), dtype=vec3, requires_grad=True, device=device)
|
|
1542
|
-
v4 = wp.array(randvals(rng, (1, 4), dtype), dtype=vec4, requires_grad=True, device=device)
|
|
1543
|
-
v5 = wp.array(randvals(rng, (1, 5), dtype), dtype=vec5, requires_grad=True, device=device)
|
|
1544
|
-
v20 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1545
|
-
v21 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1546
|
-
v30 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1547
|
-
v31 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1548
|
-
v32 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1549
|
-
v40 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1550
|
-
v41 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1551
|
-
v42 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1552
|
-
v43 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1553
|
-
v50 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1554
|
-
v51 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1555
|
-
v52 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1556
|
-
v53 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1557
|
-
v54 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1558
|
-
tape = wp.Tape()
|
|
1559
|
-
with tape:
|
|
1560
|
-
wp.launch(
|
|
1561
|
-
kernel,
|
|
1562
|
-
dim=1,
|
|
1563
|
-
inputs=[
|
|
1564
|
-
s,
|
|
1565
|
-
v2,
|
|
1566
|
-
v3,
|
|
1567
|
-
v4,
|
|
1568
|
-
v5,
|
|
1569
|
-
],
|
|
1570
|
-
outputs=[v20, v21, v30, v31, v32, v40, v41, v42, v43, v50, v51, v52, v53, v54],
|
|
1571
|
-
device=device,
|
|
1572
|
-
)
|
|
1573
|
-
|
|
1574
|
-
if dtype in np_int_types:
|
|
1575
|
-
assert_np_equal(v20.numpy()[0], 2 * (v2.numpy()[0, 0] // (s.numpy()[0])), tol=tol)
|
|
1576
|
-
assert_np_equal(v21.numpy()[0], 2 * (v2.numpy()[0, 1] // (s.numpy()[0])), tol=tol)
|
|
1577
|
-
|
|
1578
|
-
assert_np_equal(v30.numpy()[0], 2 * (v3.numpy()[0, 0] // (s.numpy()[0])), tol=10 * tol)
|
|
1579
|
-
assert_np_equal(v31.numpy()[0], 2 * (v3.numpy()[0, 1] // (s.numpy()[0])), tol=10 * tol)
|
|
1580
|
-
assert_np_equal(v32.numpy()[0], 2 * (v3.numpy()[0, 2] // (s.numpy()[0])), tol=10 * tol)
|
|
1581
|
-
|
|
1582
|
-
assert_np_equal(v40.numpy()[0], 2 * (v4.numpy()[0, 0] // (s.numpy()[0])), tol=10 * tol)
|
|
1583
|
-
assert_np_equal(v41.numpy()[0], 2 * (v4.numpy()[0, 1] // (s.numpy()[0])), tol=10 * tol)
|
|
1584
|
-
assert_np_equal(v42.numpy()[0], 2 * (v4.numpy()[0, 2] // (s.numpy()[0])), tol=10 * tol)
|
|
1585
|
-
assert_np_equal(v43.numpy()[0], 2 * (v4.numpy()[0, 3] // (s.numpy()[0])), tol=10 * tol)
|
|
1586
|
-
|
|
1587
|
-
assert_np_equal(v50.numpy()[0], 2 * (v5.numpy()[0, 0] // (s.numpy()[0])), tol=10 * tol)
|
|
1588
|
-
assert_np_equal(v51.numpy()[0], 2 * (v5.numpy()[0, 1] // (s.numpy()[0])), tol=10 * tol)
|
|
1589
|
-
assert_np_equal(v52.numpy()[0], 2 * (v5.numpy()[0, 2] // (s.numpy()[0])), tol=10 * tol)
|
|
1590
|
-
assert_np_equal(v53.numpy()[0], 2 * (v5.numpy()[0, 3] // (s.numpy()[0])), tol=10 * tol)
|
|
1591
|
-
assert_np_equal(v54.numpy()[0], 2 * (v5.numpy()[0, 4] // (s.numpy()[0])), tol=10 * tol)
|
|
1592
|
-
|
|
1593
|
-
else:
|
|
1594
|
-
assert_np_equal(v20.numpy()[0], 2 * v2.numpy()[0, 0] / (s.numpy()[0]), tol=tol)
|
|
1595
|
-
assert_np_equal(v21.numpy()[0], 2 * v2.numpy()[0, 1] / (s.numpy()[0]), tol=tol)
|
|
1596
|
-
|
|
1597
|
-
assert_np_equal(v30.numpy()[0], 2 * v3.numpy()[0, 0] / (s.numpy()[0]), tol=10 * tol)
|
|
1598
|
-
assert_np_equal(v31.numpy()[0], 2 * v3.numpy()[0, 1] / (s.numpy()[0]), tol=10 * tol)
|
|
1599
|
-
assert_np_equal(v32.numpy()[0], 2 * v3.numpy()[0, 2] / (s.numpy()[0]), tol=10 * tol)
|
|
1600
|
-
|
|
1601
|
-
assert_np_equal(v40.numpy()[0], 2 * v4.numpy()[0, 0] / (s.numpy()[0]), tol=10 * tol)
|
|
1602
|
-
assert_np_equal(v41.numpy()[0], 2 * v4.numpy()[0, 1] / (s.numpy()[0]), tol=10 * tol)
|
|
1603
|
-
assert_np_equal(v42.numpy()[0], 2 * v4.numpy()[0, 2] / (s.numpy()[0]), tol=10 * tol)
|
|
1604
|
-
assert_np_equal(v43.numpy()[0], 2 * v4.numpy()[0, 3] / (s.numpy()[0]), tol=10 * tol)
|
|
1605
|
-
|
|
1606
|
-
assert_np_equal(v50.numpy()[0], 2 * v5.numpy()[0, 0] / (s.numpy()[0]), tol=10 * tol)
|
|
1607
|
-
assert_np_equal(v51.numpy()[0], 2 * v5.numpy()[0, 1] / (s.numpy()[0]), tol=10 * tol)
|
|
1608
|
-
assert_np_equal(v52.numpy()[0], 2 * v5.numpy()[0, 2] / (s.numpy()[0]), tol=10 * tol)
|
|
1609
|
-
assert_np_equal(v53.numpy()[0], 2 * v5.numpy()[0, 3] / (s.numpy()[0]), tol=10 * tol)
|
|
1610
|
-
assert_np_equal(v54.numpy()[0], 2 * v5.numpy()[0, 4] / (s.numpy()[0]), tol=10 * tol)
|
|
1611
|
-
|
|
1612
|
-
incmps = np.concatenate([v.numpy()[0] for v in [v2, v3, v4, v5]])
|
|
1613
|
-
|
|
1614
|
-
if dtype in np_float_types:
|
|
1615
|
-
for i, l in enumerate([v20, v21, v30, v31, v32, v40, v41, v42, v43, v50, v51, v52, v53, v54]):
|
|
1616
|
-
tape.backward(loss=l)
|
|
1617
|
-
sgrad = tape.gradients[s].numpy()[0]
|
|
1618
|
-
|
|
1619
|
-
# d/ds v/s = -v/s^2
|
|
1620
|
-
assert_np_equal(sgrad, -2 * incmps[i] / (s.numpy()[0] * s.numpy()[0]), tol=10 * tol)
|
|
1621
|
-
|
|
1622
|
-
allgrads = np.concatenate([tape.gradients[v].numpy()[0] for v in [v2, v3, v4, v5]])
|
|
1623
|
-
expected_grads = np.zeros_like(allgrads)
|
|
1624
|
-
expected_grads[i] = 2 / s.numpy()[0]
|
|
1625
|
-
|
|
1626
|
-
# d/dv v/s = 1/s
|
|
1627
|
-
assert_np_equal(allgrads, expected_grads, tol=tol)
|
|
1628
|
-
tape.zero()
|
|
1629
|
-
|
|
1630
|
-
|
|
1631
|
-
def test_cw_division(test, device, dtype, register_kernels=False):
|
|
1632
|
-
rng = np.random.default_rng(123)
|
|
1633
|
-
|
|
1634
|
-
tol = {
|
|
1635
|
-
np.float16: 1.0e-2,
|
|
1636
|
-
np.float32: 1.0e-6,
|
|
1637
|
-
np.float64: 1.0e-8,
|
|
1638
|
-
}.get(dtype, 0)
|
|
1639
|
-
|
|
1640
|
-
wptype = wp.types.np_dtype_to_warp_type[np.dtype(dtype)]
|
|
1641
|
-
vec2 = wp.types.vector(length=2, dtype=wptype)
|
|
1642
|
-
vec3 = wp.types.vector(length=3, dtype=wptype)
|
|
1643
|
-
vec4 = wp.types.vector(length=4, dtype=wptype)
|
|
1644
|
-
vec5 = wp.types.vector(length=5, dtype=wptype)
|
|
1645
|
-
|
|
1646
|
-
def check_cw_div(
|
|
1647
|
-
s2: wp.array(dtype=vec2),
|
|
1648
|
-
s3: wp.array(dtype=vec3),
|
|
1649
|
-
s4: wp.array(dtype=vec4),
|
|
1650
|
-
s5: wp.array(dtype=vec5),
|
|
1651
|
-
v2: wp.array(dtype=vec2),
|
|
1652
|
-
v3: wp.array(dtype=vec3),
|
|
1653
|
-
v4: wp.array(dtype=vec4),
|
|
1654
|
-
v5: wp.array(dtype=vec5),
|
|
1655
|
-
v20: wp.array(dtype=wptype),
|
|
1656
|
-
v21: wp.array(dtype=wptype),
|
|
1657
|
-
v30: wp.array(dtype=wptype),
|
|
1658
|
-
v31: wp.array(dtype=wptype),
|
|
1659
|
-
v32: wp.array(dtype=wptype),
|
|
1660
|
-
v40: wp.array(dtype=wptype),
|
|
1661
|
-
v41: wp.array(dtype=wptype),
|
|
1662
|
-
v42: wp.array(dtype=wptype),
|
|
1663
|
-
v43: wp.array(dtype=wptype),
|
|
1664
|
-
v50: wp.array(dtype=wptype),
|
|
1665
|
-
v51: wp.array(dtype=wptype),
|
|
1666
|
-
v52: wp.array(dtype=wptype),
|
|
1667
|
-
v53: wp.array(dtype=wptype),
|
|
1668
|
-
v54: wp.array(dtype=wptype),
|
|
1669
|
-
):
|
|
1670
|
-
v2result = wp.cw_div(v2[0], s2[0])
|
|
1671
|
-
v3result = wp.cw_div(v3[0], s3[0])
|
|
1672
|
-
v4result = wp.cw_div(v4[0], s4[0])
|
|
1673
|
-
v5result = wp.cw_div(v5[0], s5[0])
|
|
1674
|
-
|
|
1675
|
-
v20[0] = wptype(2) * v2result[0]
|
|
1676
|
-
v21[0] = wptype(2) * v2result[1]
|
|
1677
|
-
|
|
1678
|
-
v30[0] = wptype(2) * v3result[0]
|
|
1679
|
-
v31[0] = wptype(2) * v3result[1]
|
|
1680
|
-
v32[0] = wptype(2) * v3result[2]
|
|
1681
|
-
|
|
1682
|
-
v40[0] = wptype(2) * v4result[0]
|
|
1683
|
-
v41[0] = wptype(2) * v4result[1]
|
|
1684
|
-
v42[0] = wptype(2) * v4result[2]
|
|
1685
|
-
v43[0] = wptype(2) * v4result[3]
|
|
1686
|
-
|
|
1687
|
-
v50[0] = wptype(2) * v5result[0]
|
|
1688
|
-
v51[0] = wptype(2) * v5result[1]
|
|
1689
|
-
v52[0] = wptype(2) * v5result[2]
|
|
1690
|
-
v53[0] = wptype(2) * v5result[3]
|
|
1691
|
-
v54[0] = wptype(2) * v5result[4]
|
|
1692
|
-
|
|
1693
|
-
kernel = getkernel(check_cw_div, suffix=dtype.__name__)
|
|
1694
|
-
|
|
1695
|
-
if register_kernels:
|
|
1696
|
-
return
|
|
1697
|
-
|
|
1698
|
-
s2 = wp.array(randvals(rng, (1, 2), dtype), dtype=vec2, requires_grad=True, device=device)
|
|
1699
|
-
s3 = wp.array(randvals(rng, (1, 3), dtype), dtype=vec3, requires_grad=True, device=device)
|
|
1700
|
-
s4 = wp.array(randvals(rng, (1, 4), dtype), dtype=vec4, requires_grad=True, device=device)
|
|
1701
|
-
s5 = wp.array(randvals(rng, (1, 5), dtype), dtype=vec5, requires_grad=True, device=device)
|
|
1702
|
-
v2 = wp.array(randvals(rng, (1, 2), dtype), dtype=vec2, requires_grad=True, device=device)
|
|
1703
|
-
v3 = wp.array(randvals(rng, (1, 3), dtype), dtype=vec3, requires_grad=True, device=device)
|
|
1704
|
-
v4 = wp.array(randvals(rng, (1, 4), dtype), dtype=vec4, requires_grad=True, device=device)
|
|
1705
|
-
v5 = wp.array(randvals(rng, (1, 5), dtype), dtype=vec5, requires_grad=True, device=device)
|
|
1706
|
-
v20 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1707
|
-
v21 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1708
|
-
v30 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1709
|
-
v31 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1710
|
-
v32 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1711
|
-
v40 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1712
|
-
v41 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1713
|
-
v42 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1714
|
-
v43 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1715
|
-
v50 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1716
|
-
v51 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1717
|
-
v52 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1718
|
-
v53 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1719
|
-
v54 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1720
|
-
tape = wp.Tape()
|
|
1721
|
-
with tape:
|
|
1722
|
-
wp.launch(
|
|
1723
|
-
kernel,
|
|
1724
|
-
dim=1,
|
|
1725
|
-
inputs=[
|
|
1726
|
-
s2,
|
|
1727
|
-
s3,
|
|
1728
|
-
s4,
|
|
1729
|
-
s5,
|
|
1730
|
-
v2,
|
|
1731
|
-
v3,
|
|
1732
|
-
v4,
|
|
1733
|
-
v5,
|
|
1734
|
-
],
|
|
1735
|
-
outputs=[v20, v21, v30, v31, v32, v40, v41, v42, v43, v50, v51, v52, v53, v54],
|
|
1736
|
-
device=device,
|
|
1737
|
-
)
|
|
1738
|
-
|
|
1739
|
-
if dtype in np_int_types:
|
|
1740
|
-
assert_np_equal(v20.numpy()[0], 2 * (v2.numpy()[0, 0] // s2.numpy()[0, 0]), tol=tol)
|
|
1741
|
-
assert_np_equal(v21.numpy()[0], 2 * (v2.numpy()[0, 1] // s2.numpy()[0, 1]), tol=tol)
|
|
1742
|
-
|
|
1743
|
-
assert_np_equal(v30.numpy()[0], 2 * (v3.numpy()[0, 0] // s3.numpy()[0, 0]), tol=tol)
|
|
1744
|
-
assert_np_equal(v31.numpy()[0], 2 * (v3.numpy()[0, 1] // s3.numpy()[0, 1]), tol=tol)
|
|
1745
|
-
assert_np_equal(v32.numpy()[0], 2 * (v3.numpy()[0, 2] // s3.numpy()[0, 2]), tol=tol)
|
|
1746
|
-
|
|
1747
|
-
assert_np_equal(v40.numpy()[0], 2 * (v4.numpy()[0, 0] // s4.numpy()[0, 0]), tol=tol)
|
|
1748
|
-
assert_np_equal(v41.numpy()[0], 2 * (v4.numpy()[0, 1] // s4.numpy()[0, 1]), tol=tol)
|
|
1749
|
-
assert_np_equal(v42.numpy()[0], 2 * (v4.numpy()[0, 2] // s4.numpy()[0, 2]), tol=tol)
|
|
1750
|
-
assert_np_equal(v43.numpy()[0], 2 * (v4.numpy()[0, 3] // s4.numpy()[0, 3]), tol=tol)
|
|
1751
|
-
|
|
1752
|
-
assert_np_equal(v50.numpy()[0], 2 * (v5.numpy()[0, 0] // s5.numpy()[0, 0]), tol=tol)
|
|
1753
|
-
assert_np_equal(v51.numpy()[0], 2 * (v5.numpy()[0, 1] // s5.numpy()[0, 1]), tol=tol)
|
|
1754
|
-
assert_np_equal(v52.numpy()[0], 2 * (v5.numpy()[0, 2] // s5.numpy()[0, 2]), tol=tol)
|
|
1755
|
-
assert_np_equal(v53.numpy()[0], 2 * (v5.numpy()[0, 3] // s5.numpy()[0, 3]), tol=tol)
|
|
1756
|
-
assert_np_equal(v54.numpy()[0], 2 * (v5.numpy()[0, 4] // s5.numpy()[0, 4]), tol=tol)
|
|
1757
|
-
else:
|
|
1758
|
-
assert_np_equal(v20.numpy()[0], 2 * v2.numpy()[0, 0] / s2.numpy()[0, 0], tol=tol)
|
|
1759
|
-
assert_np_equal(v21.numpy()[0], 2 * v2.numpy()[0, 1] / s2.numpy()[0, 1], tol=tol)
|
|
1760
|
-
|
|
1761
|
-
assert_np_equal(v30.numpy()[0], 2 * v3.numpy()[0, 0] / s3.numpy()[0, 0], tol=tol)
|
|
1762
|
-
assert_np_equal(v31.numpy()[0], 2 * v3.numpy()[0, 1] / s3.numpy()[0, 1], tol=tol)
|
|
1763
|
-
assert_np_equal(v32.numpy()[0], 2 * v3.numpy()[0, 2] / s3.numpy()[0, 2], tol=tol)
|
|
1764
|
-
|
|
1765
|
-
assert_np_equal(v40.numpy()[0], 2 * v4.numpy()[0, 0] / s4.numpy()[0, 0], tol=tol)
|
|
1766
|
-
assert_np_equal(v41.numpy()[0], 2 * v4.numpy()[0, 1] / s4.numpy()[0, 1], tol=tol)
|
|
1767
|
-
assert_np_equal(v42.numpy()[0], 2 * v4.numpy()[0, 2] / s4.numpy()[0, 2], tol=tol)
|
|
1768
|
-
assert_np_equal(v43.numpy()[0], 2 * v4.numpy()[0, 3] / s4.numpy()[0, 3], tol=tol)
|
|
1769
|
-
|
|
1770
|
-
assert_np_equal(v50.numpy()[0], 2 * v5.numpy()[0, 0] / s5.numpy()[0, 0], tol=tol)
|
|
1771
|
-
assert_np_equal(v51.numpy()[0], 2 * v5.numpy()[0, 1] / s5.numpy()[0, 1], tol=tol)
|
|
1772
|
-
assert_np_equal(v52.numpy()[0], 2 * v5.numpy()[0, 2] / s5.numpy()[0, 2], tol=tol)
|
|
1773
|
-
assert_np_equal(v53.numpy()[0], 2 * v5.numpy()[0, 3] / s5.numpy()[0, 3], tol=tol)
|
|
1774
|
-
assert_np_equal(v54.numpy()[0], 2 * v5.numpy()[0, 4] / s5.numpy()[0, 4], tol=tol)
|
|
1775
|
-
|
|
1776
|
-
if dtype in np_float_types:
|
|
1777
|
-
incmps = np.concatenate([v.numpy()[0] for v in [v2, v3, v4, v5]])
|
|
1778
|
-
scmps = np.concatenate([v.numpy()[0] for v in [s2, s3, s4, s5]])
|
|
1779
|
-
|
|
1780
|
-
for i, l in enumerate([v20, v21, v30, v31, v32, v40, v41, v42, v43, v50, v51, v52, v53, v54]):
|
|
1781
|
-
tape.backward(loss=l)
|
|
1782
|
-
sgrads = np.concatenate([tape.gradients[v].numpy()[0] for v in [s2, s3, s4, s5]])
|
|
1783
|
-
expected_grads = np.zeros_like(sgrads)
|
|
1784
|
-
|
|
1785
|
-
# d/ds v/s = -v/s^2
|
|
1786
|
-
expected_grads[i] = -incmps[i] * 2 / (scmps[i] * scmps[i])
|
|
1787
|
-
assert_np_equal(sgrads, expected_grads, tol=20 * tol)
|
|
1788
|
-
|
|
1789
|
-
allgrads = np.concatenate([tape.gradients[v].numpy()[0] for v in [v2, v3, v4, v5]])
|
|
1790
|
-
expected_grads = np.zeros_like(allgrads)
|
|
195
|
+
def test_tpl_ops_with_anon(test, device):
|
|
196
|
+
vec3i = wp.vec(3, dtype=int)
|
|
1791
197
|
|
|
1792
|
-
|
|
1793
|
-
|
|
1794
|
-
|
|
198
|
+
v = wp.vec3i(1, 2, 3)
|
|
199
|
+
v += vec3i(2, 3, 4)
|
|
200
|
+
v -= vec3i(3, 4, 5)
|
|
201
|
+
test.assertSequenceEqual(v, (0, 1, 2))
|
|
1795
202
|
|
|
1796
|
-
|
|
203
|
+
v = vec3i(1, 2, 3)
|
|
204
|
+
v += wp.vec3i(2, 3, 4)
|
|
205
|
+
v -= wp.vec3i(3, 4, 5)
|
|
206
|
+
test.assertSequenceEqual(v, (0, 1, 2))
|
|
1797
207
|
|
|
1798
208
|
|
|
1799
|
-
def
|
|
209
|
+
def test_negation(test, device, dtype, register_kernels=False):
|
|
1800
210
|
rng = np.random.default_rng(123)
|
|
1801
211
|
|
|
1802
212
|
tol = {
|
|
@@ -1811,15 +221,15 @@ def test_addition(test, device, dtype, register_kernels=False):
|
|
|
1811
221
|
vec4 = wp.types.vector(length=4, dtype=wptype)
|
|
1812
222
|
vec5 = wp.types.vector(length=5, dtype=wptype)
|
|
1813
223
|
|
|
1814
|
-
def
|
|
1815
|
-
s2: wp.array(dtype=vec2),
|
|
1816
|
-
s3: wp.array(dtype=vec3),
|
|
1817
|
-
s4: wp.array(dtype=vec4),
|
|
1818
|
-
s5: wp.array(dtype=vec5),
|
|
224
|
+
def check_negation(
|
|
1819
225
|
v2: wp.array(dtype=vec2),
|
|
1820
226
|
v3: wp.array(dtype=vec3),
|
|
1821
227
|
v4: wp.array(dtype=vec4),
|
|
1822
228
|
v5: wp.array(dtype=vec5),
|
|
229
|
+
v2out: wp.array(dtype=vec2),
|
|
230
|
+
v3out: wp.array(dtype=vec3),
|
|
231
|
+
v4out: wp.array(dtype=vec4),
|
|
232
|
+
v5out: wp.array(dtype=vec5),
|
|
1823
233
|
v20: wp.array(dtype=wptype),
|
|
1824
234
|
v21: wp.array(dtype=wptype),
|
|
1825
235
|
v30: wp.array(dtype=wptype),
|
|
@@ -1835,11 +245,17 @@ def test_addition(test, device, dtype, register_kernels=False):
|
|
|
1835
245
|
v53: wp.array(dtype=wptype),
|
|
1836
246
|
v54: wp.array(dtype=wptype),
|
|
1837
247
|
):
|
|
1838
|
-
v2result = v2[0]
|
|
1839
|
-
v3result = v3[0]
|
|
1840
|
-
v4result = v4[0]
|
|
1841
|
-
v5result = v5[0]
|
|
248
|
+
v2result = -v2[0]
|
|
249
|
+
v3result = -v3[0]
|
|
250
|
+
v4result = -v4[0]
|
|
251
|
+
v5result = -v5[0]
|
|
252
|
+
|
|
253
|
+
v2out[0] = v2result
|
|
254
|
+
v3out[0] = v3result
|
|
255
|
+
v4out[0] = v4result
|
|
256
|
+
v5out[0] = v5result
|
|
1842
257
|
|
|
258
|
+
# multiply these outputs by 2 so we've got something to backpropagate:
|
|
1843
259
|
v20[0] = wptype(2) * v2result[0]
|
|
1844
260
|
v21[0] = wptype(2) * v2result[1]
|
|
1845
261
|
|
|
@@ -1858,19 +274,21 @@ def test_addition(test, device, dtype, register_kernels=False):
|
|
|
1858
274
|
v53[0] = wptype(2) * v5result[3]
|
|
1859
275
|
v54[0] = wptype(2) * v5result[4]
|
|
1860
276
|
|
|
1861
|
-
kernel = getkernel(
|
|
277
|
+
kernel = getkernel(check_negation, suffix=dtype.__name__)
|
|
1862
278
|
|
|
1863
279
|
if register_kernels:
|
|
1864
280
|
return
|
|
1865
281
|
|
|
1866
|
-
s2 = wp.array(randvals(rng, (1, 2), dtype), dtype=vec2, requires_grad=True, device=device)
|
|
1867
|
-
s3 = wp.array(randvals(rng, (1, 3), dtype), dtype=vec3, requires_grad=True, device=device)
|
|
1868
|
-
s4 = wp.array(randvals(rng, (1, 4), dtype), dtype=vec4, requires_grad=True, device=device)
|
|
1869
|
-
s5 = wp.array(randvals(rng, (1, 5), dtype), dtype=vec5, requires_grad=True, device=device)
|
|
1870
282
|
v2 = wp.array(randvals(rng, (1, 2), dtype), dtype=vec2, requires_grad=True, device=device)
|
|
1871
283
|
v3 = wp.array(randvals(rng, (1, 3), dtype), dtype=vec3, requires_grad=True, device=device)
|
|
1872
284
|
v4 = wp.array(randvals(rng, (1, 4), dtype), dtype=vec4, requires_grad=True, device=device)
|
|
1873
|
-
|
|
285
|
+
v5_np = randvals(rng, (1, 5), dtype)
|
|
286
|
+
v5 = wp.array(v5_np, dtype=vec5, requires_grad=True, device=device)
|
|
287
|
+
|
|
288
|
+
v2out = wp.zeros(1, dtype=vec2, device=device)
|
|
289
|
+
v3out = wp.zeros(1, dtype=vec3, device=device)
|
|
290
|
+
v4out = wp.zeros(1, dtype=vec4, device=device)
|
|
291
|
+
v5out = wp.zeros(1, dtype=vec5, device=device)
|
|
1874
292
|
v20 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1875
293
|
v21 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1876
294
|
v30 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
@@ -1885,57 +303,31 @@ def test_addition(test, device, dtype, register_kernels=False):
|
|
|
1885
303
|
v52 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1886
304
|
v53 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
1887
305
|
v54 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
306
|
+
|
|
1888
307
|
tape = wp.Tape()
|
|
1889
308
|
with tape:
|
|
1890
309
|
wp.launch(
|
|
1891
310
|
kernel,
|
|
1892
311
|
dim=1,
|
|
1893
|
-
inputs=[
|
|
1894
|
-
|
|
1895
|
-
s3,
|
|
1896
|
-
s4,
|
|
1897
|
-
s5,
|
|
1898
|
-
v2,
|
|
1899
|
-
v3,
|
|
1900
|
-
v4,
|
|
1901
|
-
v5,
|
|
1902
|
-
],
|
|
1903
|
-
outputs=[v20, v21, v30, v31, v32, v40, v41, v42, v43, v50, v51, v52, v53, v54],
|
|
312
|
+
inputs=[v2, v3, v4, v5],
|
|
313
|
+
outputs=[v2out, v3out, v4out, v5out, v20, v21, v30, v31, v32, v40, v41, v42, v43, v50, v51, v52, v53, v54],
|
|
1904
314
|
device=device,
|
|
1905
315
|
)
|
|
1906
316
|
|
|
1907
|
-
assert_np_equal(v20.numpy()[0], 2 * (v2.numpy()[0, 0] + s2.numpy()[0, 0]), tol=tol)
|
|
1908
|
-
assert_np_equal(v21.numpy()[0], 2 * (v2.numpy()[0, 1] + s2.numpy()[0, 1]), tol=tol)
|
|
1909
|
-
|
|
1910
|
-
assert_np_equal(v30.numpy()[0], 2 * (v3.numpy()[0, 0] + s3.numpy()[0, 0]), tol=tol)
|
|
1911
|
-
assert_np_equal(v31.numpy()[0], 2 * (v3.numpy()[0, 1] + s3.numpy()[0, 1]), tol=tol)
|
|
1912
|
-
assert_np_equal(v32.numpy()[0], 2 * (v3.numpy()[0, 2] + s3.numpy()[0, 2]), tol=tol)
|
|
1913
|
-
|
|
1914
|
-
assert_np_equal(v40.numpy()[0], 2 * (v4.numpy()[0, 0] + s4.numpy()[0, 0]), tol=tol)
|
|
1915
|
-
assert_np_equal(v41.numpy()[0], 2 * (v4.numpy()[0, 1] + s4.numpy()[0, 1]), tol=tol)
|
|
1916
|
-
assert_np_equal(v42.numpy()[0], 2 * (v4.numpy()[0, 2] + s4.numpy()[0, 2]), tol=tol)
|
|
1917
|
-
assert_np_equal(v43.numpy()[0], 2 * (v4.numpy()[0, 3] + s4.numpy()[0, 3]), tol=tol)
|
|
1918
|
-
|
|
1919
|
-
assert_np_equal(v50.numpy()[0], 2 * (v5.numpy()[0, 0] + s5.numpy()[0, 0]), tol=tol)
|
|
1920
|
-
assert_np_equal(v51.numpy()[0], 2 * (v5.numpy()[0, 1] + s5.numpy()[0, 1]), tol=tol)
|
|
1921
|
-
assert_np_equal(v52.numpy()[0], 2 * (v5.numpy()[0, 2] + s5.numpy()[0, 2]), tol=tol)
|
|
1922
|
-
assert_np_equal(v53.numpy()[0], 2 * (v5.numpy()[0, 3] + s5.numpy()[0, 3]), tol=tol)
|
|
1923
|
-
assert_np_equal(v54.numpy()[0], 2 * (v5.numpy()[0, 4] + s5.numpy()[0, 4]), tol=2 * tol)
|
|
1924
|
-
|
|
1925
317
|
if dtype in np_float_types:
|
|
1926
318
|
for i, l in enumerate([v20, v21, v30, v31, v32, v40, v41, v42, v43, v50, v51, v52, v53, v54]):
|
|
1927
319
|
tape.backward(loss=l)
|
|
1928
|
-
sgrads = np.concatenate([tape.gradients[v].numpy()[0] for v in [s2, s3, s4, s5]])
|
|
1929
|
-
expected_grads = np.zeros_like(sgrads)
|
|
1930
|
-
|
|
1931
|
-
expected_grads[i] = 2
|
|
1932
|
-
assert_np_equal(sgrads, expected_grads, tol=10 * tol)
|
|
1933
|
-
|
|
1934
320
|
allgrads = np.concatenate([tape.gradients[v].numpy()[0] for v in [v2, v3, v4, v5]])
|
|
321
|
+
expected_grads = np.zeros_like(allgrads)
|
|
322
|
+
expected_grads[i] = -2
|
|
1935
323
|
assert_np_equal(allgrads, expected_grads, tol=tol)
|
|
1936
|
-
|
|
1937
324
|
tape.zero()
|
|
1938
325
|
|
|
326
|
+
assert_np_equal(v2out.numpy()[0], -v2.numpy()[0], tol=tol)
|
|
327
|
+
assert_np_equal(v3out.numpy()[0], -v3.numpy()[0], tol=tol)
|
|
328
|
+
assert_np_equal(v4out.numpy()[0], -v4.numpy()[0], tol=tol)
|
|
329
|
+
assert_np_equal(v5out.numpy()[0], -v5.numpy()[0], tol=tol)
|
|
330
|
+
|
|
1939
331
|
|
|
1940
332
|
def test_subtraction_unsigned(test, device, dtype, register_kernels=False):
|
|
1941
333
|
wptype = wp.types.np_dtype_to_warp_type[np.dtype(dtype)]
|
|
@@ -2131,127 +523,6 @@ def test_subtraction(test, device, dtype, register_kernels=False):
|
|
|
2131
523
|
tape.zero()
|
|
2132
524
|
|
|
2133
525
|
|
|
2134
|
-
def test_dotproduct(test, device, dtype, register_kernels=False):
|
|
2135
|
-
rng = np.random.default_rng(123)
|
|
2136
|
-
|
|
2137
|
-
tol = {
|
|
2138
|
-
np.float16: 1.0e-2,
|
|
2139
|
-
np.float32: 1.0e-6,
|
|
2140
|
-
np.float64: 1.0e-8,
|
|
2141
|
-
}.get(dtype, 0)
|
|
2142
|
-
|
|
2143
|
-
wptype = wp.types.np_dtype_to_warp_type[np.dtype(dtype)]
|
|
2144
|
-
vec2 = wp.types.vector(length=2, dtype=wptype)
|
|
2145
|
-
vec3 = wp.types.vector(length=3, dtype=wptype)
|
|
2146
|
-
vec4 = wp.types.vector(length=4, dtype=wptype)
|
|
2147
|
-
vec5 = wp.types.vector(length=5, dtype=wptype)
|
|
2148
|
-
|
|
2149
|
-
def check_dot(
|
|
2150
|
-
s2: wp.array(dtype=vec2),
|
|
2151
|
-
s3: wp.array(dtype=vec3),
|
|
2152
|
-
s4: wp.array(dtype=vec4),
|
|
2153
|
-
s5: wp.array(dtype=vec5),
|
|
2154
|
-
v2: wp.array(dtype=vec2),
|
|
2155
|
-
v3: wp.array(dtype=vec3),
|
|
2156
|
-
v4: wp.array(dtype=vec4),
|
|
2157
|
-
v5: wp.array(dtype=vec5),
|
|
2158
|
-
dot2: wp.array(dtype=wptype),
|
|
2159
|
-
dot3: wp.array(dtype=wptype),
|
|
2160
|
-
dot4: wp.array(dtype=wptype),
|
|
2161
|
-
dot5: wp.array(dtype=wptype),
|
|
2162
|
-
):
|
|
2163
|
-
dot2[0] = wptype(2) * wp.dot(v2[0], s2[0])
|
|
2164
|
-
dot3[0] = wptype(2) * wp.dot(v3[0], s3[0])
|
|
2165
|
-
dot4[0] = wptype(2) * wp.dot(v4[0], s4[0])
|
|
2166
|
-
dot5[0] = wptype(2) * wp.dot(v5[0], s5[0])
|
|
2167
|
-
|
|
2168
|
-
kernel = getkernel(check_dot, suffix=dtype.__name__)
|
|
2169
|
-
|
|
2170
|
-
if register_kernels:
|
|
2171
|
-
return
|
|
2172
|
-
|
|
2173
|
-
s2 = wp.array(randvals(rng, (1, 2), dtype), dtype=vec2, requires_grad=True, device=device)
|
|
2174
|
-
s3 = wp.array(randvals(rng, (1, 3), dtype), dtype=vec3, requires_grad=True, device=device)
|
|
2175
|
-
s4 = wp.array(randvals(rng, (1, 4), dtype), dtype=vec4, requires_grad=True, device=device)
|
|
2176
|
-
s5 = wp.array(randvals(rng, (1, 5), dtype), dtype=vec5, requires_grad=True, device=device)
|
|
2177
|
-
v2 = wp.array(randvals(rng, (1, 2), dtype), dtype=vec2, requires_grad=True, device=device)
|
|
2178
|
-
v3 = wp.array(randvals(rng, (1, 3), dtype), dtype=vec3, requires_grad=True, device=device)
|
|
2179
|
-
v4 = wp.array(randvals(rng, (1, 4), dtype), dtype=vec4, requires_grad=True, device=device)
|
|
2180
|
-
v5 = wp.array(randvals(rng, (1, 5), dtype), dtype=vec5, requires_grad=True, device=device)
|
|
2181
|
-
dot2 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
2182
|
-
dot3 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
2183
|
-
dot4 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
2184
|
-
dot5 = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
2185
|
-
tape = wp.Tape()
|
|
2186
|
-
with tape:
|
|
2187
|
-
wp.launch(
|
|
2188
|
-
kernel,
|
|
2189
|
-
dim=1,
|
|
2190
|
-
inputs=[
|
|
2191
|
-
s2,
|
|
2192
|
-
s3,
|
|
2193
|
-
s4,
|
|
2194
|
-
s5,
|
|
2195
|
-
v2,
|
|
2196
|
-
v3,
|
|
2197
|
-
v4,
|
|
2198
|
-
v5,
|
|
2199
|
-
],
|
|
2200
|
-
outputs=[dot2, dot3, dot4, dot5],
|
|
2201
|
-
device=device,
|
|
2202
|
-
)
|
|
2203
|
-
|
|
2204
|
-
assert_np_equal(dot2.numpy()[0], 2.0 * (v2.numpy() * s2.numpy()).sum(), tol=10 * tol)
|
|
2205
|
-
assert_np_equal(dot3.numpy()[0], 2.0 * (v3.numpy() * s3.numpy()).sum(), tol=10 * tol)
|
|
2206
|
-
assert_np_equal(dot4.numpy()[0], 2.0 * (v4.numpy() * s4.numpy()).sum(), tol=10 * tol)
|
|
2207
|
-
assert_np_equal(dot5.numpy()[0], 2.0 * (v5.numpy() * s5.numpy()).sum(), tol=10 * tol)
|
|
2208
|
-
|
|
2209
|
-
if dtype in np_float_types:
|
|
2210
|
-
tape.backward(loss=dot2)
|
|
2211
|
-
sgrads = tape.gradients[s2].numpy()[0]
|
|
2212
|
-
expected_grads = 2.0 * v2.numpy()[0]
|
|
2213
|
-
assert_np_equal(sgrads, expected_grads, tol=10 * tol)
|
|
2214
|
-
|
|
2215
|
-
vgrads = tape.gradients[v2].numpy()[0]
|
|
2216
|
-
expected_grads = 2.0 * s2.numpy()[0]
|
|
2217
|
-
assert_np_equal(vgrads, expected_grads, tol=tol)
|
|
2218
|
-
|
|
2219
|
-
tape.zero()
|
|
2220
|
-
|
|
2221
|
-
tape.backward(loss=dot3)
|
|
2222
|
-
sgrads = tape.gradients[s3].numpy()[0]
|
|
2223
|
-
expected_grads = 2.0 * v3.numpy()[0]
|
|
2224
|
-
assert_np_equal(sgrads, expected_grads, tol=10 * tol)
|
|
2225
|
-
|
|
2226
|
-
vgrads = tape.gradients[v3].numpy()[0]
|
|
2227
|
-
expected_grads = 2.0 * s3.numpy()[0]
|
|
2228
|
-
assert_np_equal(vgrads, expected_grads, tol=tol)
|
|
2229
|
-
|
|
2230
|
-
tape.zero()
|
|
2231
|
-
|
|
2232
|
-
tape.backward(loss=dot4)
|
|
2233
|
-
sgrads = tape.gradients[s4].numpy()[0]
|
|
2234
|
-
expected_grads = 2.0 * v4.numpy()[0]
|
|
2235
|
-
assert_np_equal(sgrads, expected_grads, tol=10 * tol)
|
|
2236
|
-
|
|
2237
|
-
vgrads = tape.gradients[v4].numpy()[0]
|
|
2238
|
-
expected_grads = 2.0 * s4.numpy()[0]
|
|
2239
|
-
assert_np_equal(vgrads, expected_grads, tol=tol)
|
|
2240
|
-
|
|
2241
|
-
tape.zero()
|
|
2242
|
-
|
|
2243
|
-
tape.backward(loss=dot5)
|
|
2244
|
-
sgrads = tape.gradients[s5].numpy()[0]
|
|
2245
|
-
expected_grads = 2.0 * v5.numpy()[0]
|
|
2246
|
-
assert_np_equal(sgrads, expected_grads, tol=10 * tol)
|
|
2247
|
-
|
|
2248
|
-
vgrads = tape.gradients[v5].numpy()[0]
|
|
2249
|
-
expected_grads = 2.0 * s5.numpy()[0]
|
|
2250
|
-
assert_np_equal(vgrads, expected_grads, tol=10 * tol)
|
|
2251
|
-
|
|
2252
|
-
tape.zero()
|
|
2253
|
-
|
|
2254
|
-
|
|
2255
526
|
def test_length(test, device, dtype, register_kernels=False):
|
|
2256
527
|
rng = np.random.default_rng(123)
|
|
2257
528
|
|
|
@@ -2713,139 +984,6 @@ def test_crossproduct(test, device, dtype, register_kernels=False):
|
|
|
2713
984
|
tape.zero()
|
|
2714
985
|
|
|
2715
986
|
|
|
2716
|
-
def test_minmax(test, device, dtype, register_kernels=False):
|
|
2717
|
-
rng = np.random.default_rng(123)
|
|
2718
|
-
|
|
2719
|
-
# \TODO: not quite sure why, but the numbers are off for 16 bit float
|
|
2720
|
-
# on the cpu (but not cuda). This is probably just the sketchy float16
|
|
2721
|
-
# arithmetic I implemented to get all this stuff working, so
|
|
2722
|
-
# hopefully that can be fixed when we do that correctly.
|
|
2723
|
-
tol = {
|
|
2724
|
-
np.float16: 1.0e-2,
|
|
2725
|
-
}.get(dtype, 0)
|
|
2726
|
-
|
|
2727
|
-
wptype = wp.types.np_dtype_to_warp_type[np.dtype(dtype)]
|
|
2728
|
-
vec2 = wp.types.vector(length=2, dtype=wptype)
|
|
2729
|
-
vec3 = wp.types.vector(length=3, dtype=wptype)
|
|
2730
|
-
vec4 = wp.types.vector(length=4, dtype=wptype)
|
|
2731
|
-
vec5 = wp.types.vector(length=5, dtype=wptype)
|
|
2732
|
-
|
|
2733
|
-
# \TODO: Also not quite sure why: this kernel compiles incredibly
|
|
2734
|
-
# slowly though...
|
|
2735
|
-
def check_vec_min_max(
|
|
2736
|
-
a: wp.array(dtype=wptype, ndim=2),
|
|
2737
|
-
b: wp.array(dtype=wptype, ndim=2),
|
|
2738
|
-
mins: wp.array(dtype=wptype, ndim=2),
|
|
2739
|
-
maxs: wp.array(dtype=wptype, ndim=2),
|
|
2740
|
-
):
|
|
2741
|
-
for i in range(10):
|
|
2742
|
-
# multiplying by 2 so we've got something to backpropagate:
|
|
2743
|
-
a2read = vec2(a[i, 0], a[i, 1])
|
|
2744
|
-
b2read = vec2(b[i, 0], b[i, 1])
|
|
2745
|
-
c2 = wptype(2) * wp.min(a2read, b2read)
|
|
2746
|
-
d2 = wptype(2) * wp.max(a2read, b2read)
|
|
2747
|
-
|
|
2748
|
-
a3read = vec3(a[i, 2], a[i, 3], a[i, 4])
|
|
2749
|
-
b3read = vec3(b[i, 2], b[i, 3], b[i, 4])
|
|
2750
|
-
c3 = wptype(2) * wp.min(a3read, b3read)
|
|
2751
|
-
d3 = wptype(2) * wp.max(a3read, b3read)
|
|
2752
|
-
|
|
2753
|
-
a4read = vec4(a[i, 5], a[i, 6], a[i, 7], a[i, 8])
|
|
2754
|
-
b4read = vec4(b[i, 5], b[i, 6], b[i, 7], b[i, 8])
|
|
2755
|
-
c4 = wptype(2) * wp.min(a4read, b4read)
|
|
2756
|
-
d4 = wptype(2) * wp.max(a4read, b4read)
|
|
2757
|
-
|
|
2758
|
-
a5read = vec5(a[i, 9], a[i, 10], a[i, 11], a[i, 12], a[i, 13])
|
|
2759
|
-
b5read = vec5(b[i, 9], b[i, 10], b[i, 11], b[i, 12], b[i, 13])
|
|
2760
|
-
c5 = wptype(2) * wp.min(a5read, b5read)
|
|
2761
|
-
d5 = wptype(2) * wp.max(a5read, b5read)
|
|
2762
|
-
|
|
2763
|
-
mins[i, 0] = c2[0]
|
|
2764
|
-
mins[i, 1] = c2[1]
|
|
2765
|
-
|
|
2766
|
-
mins[i, 2] = c3[0]
|
|
2767
|
-
mins[i, 3] = c3[1]
|
|
2768
|
-
mins[i, 4] = c3[2]
|
|
2769
|
-
|
|
2770
|
-
mins[i, 5] = c4[0]
|
|
2771
|
-
mins[i, 6] = c4[1]
|
|
2772
|
-
mins[i, 7] = c4[2]
|
|
2773
|
-
mins[i, 8] = c4[3]
|
|
2774
|
-
|
|
2775
|
-
mins[i, 9] = c5[0]
|
|
2776
|
-
mins[i, 10] = c5[1]
|
|
2777
|
-
mins[i, 11] = c5[2]
|
|
2778
|
-
mins[i, 12] = c5[3]
|
|
2779
|
-
mins[i, 13] = c5[4]
|
|
2780
|
-
|
|
2781
|
-
maxs[i, 0] = d2[0]
|
|
2782
|
-
maxs[i, 1] = d2[1]
|
|
2783
|
-
|
|
2784
|
-
maxs[i, 2] = d3[0]
|
|
2785
|
-
maxs[i, 3] = d3[1]
|
|
2786
|
-
maxs[i, 4] = d3[2]
|
|
2787
|
-
|
|
2788
|
-
maxs[i, 5] = d4[0]
|
|
2789
|
-
maxs[i, 6] = d4[1]
|
|
2790
|
-
maxs[i, 7] = d4[2]
|
|
2791
|
-
maxs[i, 8] = d4[3]
|
|
2792
|
-
|
|
2793
|
-
maxs[i, 9] = d5[0]
|
|
2794
|
-
maxs[i, 10] = d5[1]
|
|
2795
|
-
maxs[i, 11] = d5[2]
|
|
2796
|
-
maxs[i, 12] = d5[3]
|
|
2797
|
-
maxs[i, 13] = d5[4]
|
|
2798
|
-
|
|
2799
|
-
kernel = getkernel(check_vec_min_max, suffix=dtype.__name__)
|
|
2800
|
-
output_select_kernel = get_select_kernel2(wptype)
|
|
2801
|
-
|
|
2802
|
-
if register_kernels:
|
|
2803
|
-
return
|
|
2804
|
-
|
|
2805
|
-
a = wp.array(randvals(rng, (10, 14), dtype), dtype=wptype, requires_grad=True, device=device)
|
|
2806
|
-
b = wp.array(randvals(rng, (10, 14), dtype), dtype=wptype, requires_grad=True, device=device)
|
|
2807
|
-
|
|
2808
|
-
mins = wp.zeros((10, 14), dtype=wptype, requires_grad=True, device=device)
|
|
2809
|
-
maxs = wp.zeros((10, 14), dtype=wptype, requires_grad=True, device=device)
|
|
2810
|
-
|
|
2811
|
-
tape = wp.Tape()
|
|
2812
|
-
with tape:
|
|
2813
|
-
wp.launch(kernel, dim=1, inputs=[a, b], outputs=[mins, maxs], device=device)
|
|
2814
|
-
|
|
2815
|
-
assert_np_equal(mins.numpy(), 2 * np.minimum(a.numpy(), b.numpy()), tol=tol)
|
|
2816
|
-
assert_np_equal(maxs.numpy(), 2 * np.maximum(a.numpy(), b.numpy()), tol=tol)
|
|
2817
|
-
|
|
2818
|
-
out = wp.zeros(1, dtype=wptype, requires_grad=True, device=device)
|
|
2819
|
-
if dtype in np_float_types:
|
|
2820
|
-
for i in range(10):
|
|
2821
|
-
for j in range(14):
|
|
2822
|
-
tape = wp.Tape()
|
|
2823
|
-
with tape:
|
|
2824
|
-
wp.launch(kernel, dim=1, inputs=[a, b], outputs=[mins, maxs], device=device)
|
|
2825
|
-
wp.launch(output_select_kernel, dim=1, inputs=[mins, i, j], outputs=[out], device=device)
|
|
2826
|
-
|
|
2827
|
-
tape.backward(loss=out)
|
|
2828
|
-
expected = np.zeros_like(a.numpy())
|
|
2829
|
-
expected[i, j] = 2 if (a.numpy()[i, j] < b.numpy()[i, j]) else 0
|
|
2830
|
-
assert_np_equal(tape.gradients[a].numpy(), expected, tol=tol)
|
|
2831
|
-
expected[i, j] = 2 if (b.numpy()[i, j] < a.numpy()[i, j]) else 0
|
|
2832
|
-
assert_np_equal(tape.gradients[b].numpy(), expected, tol=tol)
|
|
2833
|
-
tape.zero()
|
|
2834
|
-
|
|
2835
|
-
tape = wp.Tape()
|
|
2836
|
-
with tape:
|
|
2837
|
-
wp.launch(kernel, dim=1, inputs=[a, b], outputs=[mins, maxs], device=device)
|
|
2838
|
-
wp.launch(output_select_kernel, dim=1, inputs=[maxs, i, j], outputs=[out], device=device)
|
|
2839
|
-
|
|
2840
|
-
tape.backward(loss=out)
|
|
2841
|
-
expected = np.zeros_like(a.numpy())
|
|
2842
|
-
expected[i, j] = 2 if (a.numpy()[i, j] > b.numpy()[i, j]) else 0
|
|
2843
|
-
assert_np_equal(tape.gradients[a].numpy(), expected, tol=tol)
|
|
2844
|
-
expected[i, j] = 2 if (b.numpy()[i, j] > a.numpy()[i, j]) else 0
|
|
2845
|
-
assert_np_equal(tape.gradients[b].numpy(), expected, tol=tol)
|
|
2846
|
-
tape.zero()
|
|
2847
|
-
|
|
2848
|
-
|
|
2849
987
|
def test_casting_constructors(test, device, dtype, register_kernels=False):
|
|
2850
988
|
np_type = np.dtype(dtype)
|
|
2851
989
|
wp_type = wp.types.np_dtype_to_warp_type[np_type]
|
|
@@ -2949,85 +1087,6 @@ def test_casting_constructors(test, device, dtype, register_kernels=False):
|
|
|
2949
1087
|
assert_np_equal(out, a_grad.numpy())
|
|
2950
1088
|
|
|
2951
1089
|
|
|
2952
|
-
def test_equivalent_types(test, device, dtype, register_kernels=False):
|
|
2953
|
-
wptype = wp.types.np_dtype_to_warp_type[np.dtype(dtype)]
|
|
2954
|
-
|
|
2955
|
-
# vector types
|
|
2956
|
-
vec2 = wp.types.vector(length=2, dtype=wptype)
|
|
2957
|
-
vec3 = wp.types.vector(length=3, dtype=wptype)
|
|
2958
|
-
vec4 = wp.types.vector(length=4, dtype=wptype)
|
|
2959
|
-
vec5 = wp.types.vector(length=5, dtype=wptype)
|
|
2960
|
-
|
|
2961
|
-
# vector types equivalent to the above
|
|
2962
|
-
vec2_equiv = wp.types.vector(length=2, dtype=wptype)
|
|
2963
|
-
vec3_equiv = wp.types.vector(length=3, dtype=wptype)
|
|
2964
|
-
vec4_equiv = wp.types.vector(length=4, dtype=wptype)
|
|
2965
|
-
vec5_equiv = wp.types.vector(length=5, dtype=wptype)
|
|
2966
|
-
|
|
2967
|
-
# declare kernel with original types
|
|
2968
|
-
def check_equivalence(
|
|
2969
|
-
v2: vec2,
|
|
2970
|
-
v3: vec3,
|
|
2971
|
-
v4: vec4,
|
|
2972
|
-
v5: vec5,
|
|
2973
|
-
):
|
|
2974
|
-
wp.expect_eq(v2, vec2(wptype(1), wptype(2)))
|
|
2975
|
-
wp.expect_eq(v3, vec3(wptype(1), wptype(2), wptype(3)))
|
|
2976
|
-
wp.expect_eq(v4, vec4(wptype(1), wptype(2), wptype(3), wptype(4)))
|
|
2977
|
-
wp.expect_eq(v5, vec5(wptype(1), wptype(2), wptype(3), wptype(4), wptype(5)))
|
|
2978
|
-
|
|
2979
|
-
wp.expect_eq(v2, vec2_equiv(wptype(1), wptype(2)))
|
|
2980
|
-
wp.expect_eq(v3, vec3_equiv(wptype(1), wptype(2), wptype(3)))
|
|
2981
|
-
wp.expect_eq(v4, vec4_equiv(wptype(1), wptype(2), wptype(3), wptype(4)))
|
|
2982
|
-
wp.expect_eq(v5, vec5_equiv(wptype(1), wptype(2), wptype(3), wptype(4), wptype(5)))
|
|
2983
|
-
|
|
2984
|
-
kernel = getkernel(check_equivalence, suffix=dtype.__name__)
|
|
2985
|
-
|
|
2986
|
-
if register_kernels:
|
|
2987
|
-
return
|
|
2988
|
-
|
|
2989
|
-
# call kernel with equivalent types
|
|
2990
|
-
v2 = vec2_equiv(1, 2)
|
|
2991
|
-
v3 = vec3_equiv(1, 2, 3)
|
|
2992
|
-
v4 = vec4_equiv(1, 2, 3, 4)
|
|
2993
|
-
v5 = vec5_equiv(1, 2, 3, 4, 5)
|
|
2994
|
-
|
|
2995
|
-
wp.launch(kernel, dim=1, inputs=[v2, v3, v4, v5], device=device)
|
|
2996
|
-
|
|
2997
|
-
|
|
2998
|
-
def test_conversions(test, device, dtype, register_kernels=False):
|
|
2999
|
-
def check_vectors_equal(
|
|
3000
|
-
v0: wp.vec3,
|
|
3001
|
-
v1: wp.vec3,
|
|
3002
|
-
v2: wp.vec3,
|
|
3003
|
-
v3: wp.vec3,
|
|
3004
|
-
):
|
|
3005
|
-
wp.expect_eq(v1, v0)
|
|
3006
|
-
wp.expect_eq(v2, v0)
|
|
3007
|
-
wp.expect_eq(v3, v0)
|
|
3008
|
-
|
|
3009
|
-
kernel = getkernel(check_vectors_equal, suffix=dtype.__name__)
|
|
3010
|
-
|
|
3011
|
-
if register_kernels:
|
|
3012
|
-
return
|
|
3013
|
-
|
|
3014
|
-
v0 = wp.vec3(1, 2, 3)
|
|
3015
|
-
|
|
3016
|
-
# test explicit conversions - constructing vectors from different containers
|
|
3017
|
-
v1 = wp.vec3((1, 2, 3))
|
|
3018
|
-
v2 = wp.vec3([1, 2, 3])
|
|
3019
|
-
v3 = wp.vec3(np.array([1, 2, 3], dtype=dtype))
|
|
3020
|
-
|
|
3021
|
-
wp.launch(kernel, dim=1, inputs=[v0, v1, v2, v3], device=device)
|
|
3022
|
-
|
|
3023
|
-
# test implicit conversions - passing different containers as vectors to wp.launch()
|
|
3024
|
-
v1 = (1, 2, 3)
|
|
3025
|
-
v2 = [1, 2, 3]
|
|
3026
|
-
v3 = np.array([1, 2, 3], dtype=dtype)
|
|
3027
|
-
|
|
3028
|
-
wp.launch(kernel, dim=1, inputs=[v0, v1, v2, v3], device=device)
|
|
3029
|
-
|
|
3030
|
-
|
|
3031
1090
|
@wp.kernel
|
|
3032
1091
|
def test_vector_constructor_value_func():
|
|
3033
1092
|
a = wp.vec2()
|
|
@@ -3097,172 +1156,113 @@ def test_constructors_constant_length():
|
|
|
3097
1156
|
v[i] = float(i)
|
|
3098
1157
|
|
|
3099
1158
|
|
|
3100
|
-
|
|
3101
|
-
devices = get_test_devices()
|
|
1159
|
+
devices = get_test_devices()
|
|
3102
1160
|
|
|
3103
|
-
class TestVec(parent):
|
|
3104
|
-
pass
|
|
3105
1161
|
|
|
3106
|
-
|
|
3107
|
-
|
|
3108
|
-
add_kernel_test(TestVec, test_constructors_default_precision, dim=1, devices=devices)
|
|
3109
|
-
add_kernel_test(TestVec, test_constructors_constant_length, dim=1, devices=devices)
|
|
3110
|
-
|
|
3111
|
-
vec10 = wp.types.vector(length=10, dtype=float)
|
|
3112
|
-
add_kernel_test(
|
|
3113
|
-
TestVec,
|
|
3114
|
-
test_vector_mutation,
|
|
3115
|
-
dim=1,
|
|
3116
|
-
inputs=[vec10(1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0)],
|
|
3117
|
-
devices=devices,
|
|
3118
|
-
)
|
|
1162
|
+
class TestVec(unittest.TestCase):
|
|
1163
|
+
pass
|
|
3119
1164
|
|
|
3120
|
-
for dtype in np_unsigned_int_types:
|
|
3121
|
-
add_function_test_register_kernel(
|
|
3122
|
-
TestVec,
|
|
3123
|
-
f"test_subtraction_unsigned_{dtype.__name__}",
|
|
3124
|
-
test_subtraction_unsigned,
|
|
3125
|
-
devices=devices,
|
|
3126
|
-
dtype=dtype,
|
|
3127
|
-
)
|
|
3128
1165
|
|
|
3129
|
-
|
|
3130
|
-
|
|
3131
|
-
|
|
3132
|
-
|
|
3133
|
-
add_function_test_register_kernel(
|
|
3134
|
-
TestVec, f"test_subtraction_{dtype.__name__}", test_subtraction, devices=devices, dtype=dtype
|
|
3135
|
-
)
|
|
1166
|
+
add_kernel_test(TestVec, test_vector_constructor_value_func, dim=1, devices=devices)
|
|
1167
|
+
add_kernel_test(TestVec, test_constructors_explicit_precision, dim=1, devices=devices)
|
|
1168
|
+
add_kernel_test(TestVec, test_constructors_default_precision, dim=1, devices=devices)
|
|
1169
|
+
add_kernel_test(TestVec, test_constructors_constant_length, dim=1, devices=devices)
|
|
3136
1170
|
|
|
3137
|
-
|
|
3138
|
-
|
|
3139
|
-
|
|
3140
|
-
|
|
3141
|
-
|
|
3142
|
-
|
|
3143
|
-
|
|
3144
|
-
|
|
3145
|
-
TestVec, f"test_normalize_{dtype.__name__}", test_normalize, devices=devices, dtype=dtype
|
|
3146
|
-
)
|
|
3147
|
-
add_function_test_register_kernel(
|
|
3148
|
-
TestVec,
|
|
3149
|
-
f"test_casting_constructors_{dtype.__name__}",
|
|
3150
|
-
test_casting_constructors,
|
|
3151
|
-
devices=devices,
|
|
3152
|
-
dtype=dtype,
|
|
3153
|
-
)
|
|
1171
|
+
vec10 = wp.types.vector(length=10, dtype=float)
|
|
1172
|
+
add_kernel_test(
|
|
1173
|
+
TestVec,
|
|
1174
|
+
test_vector_mutation,
|
|
1175
|
+
dim=1,
|
|
1176
|
+
inputs=[vec10(1.0, 2.0, 3.0, 4.0, 5.0, 6.0, 7.0, 8.0, 9.0, 10.0)],
|
|
1177
|
+
devices=devices,
|
|
1178
|
+
)
|
|
3154
1179
|
|
|
3155
|
-
|
|
3156
|
-
|
|
3157
|
-
"test_anon_constructor_error_dtype_keyword_missing",
|
|
3158
|
-
test_anon_constructor_error_dtype_keyword_missing,
|
|
3159
|
-
devices=devices,
|
|
3160
|
-
)
|
|
3161
|
-
add_function_test(
|
|
1180
|
+
for dtype in np_unsigned_int_types:
|
|
1181
|
+
add_function_test_register_kernel(
|
|
3162
1182
|
TestVec,
|
|
3163
|
-
"
|
|
3164
|
-
|
|
1183
|
+
f"test_subtraction_unsigned_{dtype.__name__}",
|
|
1184
|
+
test_subtraction_unsigned,
|
|
3165
1185
|
devices=devices,
|
|
1186
|
+
dtype=dtype,
|
|
3166
1187
|
)
|
|
3167
|
-
|
|
3168
|
-
|
|
3169
|
-
|
|
3170
|
-
|
|
3171
|
-
devices=devices,
|
|
1188
|
+
|
|
1189
|
+
for dtype in np_signed_int_types + np_float_types:
|
|
1190
|
+
add_function_test_register_kernel(
|
|
1191
|
+
TestVec, f"test_negation_{dtype.__name__}", test_negation, devices=devices, dtype=dtype
|
|
3172
1192
|
)
|
|
3173
|
-
|
|
3174
|
-
TestVec,
|
|
3175
|
-
"test_anon_constructor_error_numeric_arg_missing_2",
|
|
3176
|
-
test_anon_constructor_error_numeric_arg_missing_2,
|
|
3177
|
-
devices=devices,
|
|
1193
|
+
add_function_test_register_kernel(
|
|
1194
|
+
TestVec, f"test_subtraction_{dtype.__name__}", test_subtraction, devices=devices, dtype=dtype
|
|
3178
1195
|
)
|
|
3179
|
-
|
|
3180
|
-
|
|
3181
|
-
|
|
3182
|
-
|
|
3183
|
-
devices=devices,
|
|
1196
|
+
|
|
1197
|
+
for dtype in np_float_types:
|
|
1198
|
+
add_function_test_register_kernel(
|
|
1199
|
+
TestVec, f"test_crossproduct_{dtype.__name__}", test_crossproduct, devices=devices, dtype=dtype
|
|
3184
1200
|
)
|
|
3185
|
-
|
|
3186
|
-
TestVec,
|
|
3187
|
-
"test_anon_constructor_error_numeric_args_mismatch",
|
|
3188
|
-
test_anon_constructor_error_numeric_args_mismatch,
|
|
3189
|
-
devices=devices,
|
|
1201
|
+
add_function_test_register_kernel(
|
|
1202
|
+
TestVec, f"test_length_{dtype.__name__}", test_length, devices=devices, dtype=dtype
|
|
3190
1203
|
)
|
|
3191
|
-
|
|
3192
|
-
TestVec,
|
|
3193
|
-
"test_tpl_constructor_error_incompatible_sizes",
|
|
3194
|
-
test_tpl_constructor_error_incompatible_sizes,
|
|
3195
|
-
devices=devices,
|
|
1204
|
+
add_function_test_register_kernel(
|
|
1205
|
+
TestVec, f"test_normalize_{dtype.__name__}", test_normalize, devices=devices, dtype=dtype
|
|
3196
1206
|
)
|
|
3197
|
-
|
|
1207
|
+
add_function_test_register_kernel(
|
|
3198
1208
|
TestVec,
|
|
3199
|
-
"
|
|
3200
|
-
|
|
1209
|
+
f"test_casting_constructors_{dtype.__name__}",
|
|
1210
|
+
test_casting_constructors,
|
|
3201
1211
|
devices=devices,
|
|
1212
|
+
dtype=dtype,
|
|
3202
1213
|
)
|
|
3203
|
-
add_function_test(TestVec, "test_tpl_ops_with_anon", test_tpl_ops_with_anon)
|
|
3204
|
-
|
|
3205
|
-
for dtype in np_scalar_types:
|
|
3206
|
-
add_function_test(TestVec, f"test_arrays_{dtype.__name__}", test_arrays, devices=devices, dtype=dtype)
|
|
3207
|
-
add_function_test(TestVec, f"test_components_{dtype.__name__}", test_components, devices=None, dtype=dtype)
|
|
3208
|
-
add_function_test_register_kernel(
|
|
3209
|
-
TestVec, f"test_constructors_{dtype.__name__}", test_constructors, devices=devices, dtype=dtype
|
|
3210
|
-
)
|
|
3211
|
-
add_function_test_register_kernel(
|
|
3212
|
-
TestVec, f"test_anon_type_instance_{dtype.__name__}", test_anon_type_instance, devices=devices, dtype=dtype
|
|
3213
|
-
)
|
|
3214
|
-
add_function_test_register_kernel(
|
|
3215
|
-
TestVec, f"test_indexing_{dtype.__name__}", test_indexing, devices=devices, dtype=dtype
|
|
3216
|
-
)
|
|
3217
|
-
add_function_test_register_kernel(
|
|
3218
|
-
TestVec, f"test_equality_{dtype.__name__}", test_equality, devices=devices, dtype=dtype
|
|
3219
|
-
)
|
|
3220
|
-
add_function_test_register_kernel(
|
|
3221
|
-
TestVec,
|
|
3222
|
-
f"test_scalar_multiplication_{dtype.__name__}",
|
|
3223
|
-
test_scalar_multiplication,
|
|
3224
|
-
devices=devices,
|
|
3225
|
-
dtype=dtype,
|
|
3226
|
-
)
|
|
3227
|
-
add_function_test_register_kernel(
|
|
3228
|
-
TestVec,
|
|
3229
|
-
f"test_scalar_multiplication_rightmul_{dtype.__name__}",
|
|
3230
|
-
test_scalar_multiplication_rightmul,
|
|
3231
|
-
devices=devices,
|
|
3232
|
-
dtype=dtype,
|
|
3233
|
-
)
|
|
3234
|
-
add_function_test_register_kernel(
|
|
3235
|
-
TestVec, f"test_cw_multiplication_{dtype.__name__}", test_cw_multiplication, devices=devices, dtype=dtype
|
|
3236
|
-
)
|
|
3237
|
-
add_function_test_register_kernel(
|
|
3238
|
-
TestVec, f"test_scalar_division_{dtype.__name__}", test_scalar_division, devices=devices, dtype=dtype
|
|
3239
|
-
)
|
|
3240
|
-
add_function_test_register_kernel(
|
|
3241
|
-
TestVec, f"test_cw_division_{dtype.__name__}", test_cw_division, devices=devices, dtype=dtype
|
|
3242
|
-
)
|
|
3243
|
-
add_function_test_register_kernel(
|
|
3244
|
-
TestVec, f"test_addition_{dtype.__name__}", test_addition, devices=devices, dtype=dtype
|
|
3245
|
-
)
|
|
3246
|
-
add_function_test_register_kernel(
|
|
3247
|
-
TestVec, f"test_dotproduct_{dtype.__name__}", test_dotproduct, devices=devices, dtype=dtype
|
|
3248
|
-
)
|
|
3249
|
-
add_function_test_register_kernel(
|
|
3250
|
-
TestVec, f"test_equivalent_types_{dtype.__name__}", test_equivalent_types, devices=devices, dtype=dtype
|
|
3251
|
-
)
|
|
3252
|
-
add_function_test_register_kernel(
|
|
3253
|
-
TestVec, f"test_conversions_{dtype.__name__}", test_conversions, devices=devices, dtype=dtype
|
|
3254
|
-
)
|
|
3255
|
-
add_function_test_register_kernel(
|
|
3256
|
-
TestVec, f"test_constants_{dtype.__name__}", test_constants, devices=devices, dtype=dtype
|
|
3257
|
-
)
|
|
3258
|
-
|
|
3259
|
-
# the kernels in this test compile incredibly slowly...
|
|
3260
|
-
# add_function_test_register_kernel(TestVec, f"test_minmax_{dtype.__name__}", test_minmax, devices=devices, dtype=dtype)
|
|
3261
1214
|
|
|
3262
|
-
|
|
1215
|
+
add_function_test(
|
|
1216
|
+
TestVec,
|
|
1217
|
+
"test_anon_constructor_error_dtype_keyword_missing",
|
|
1218
|
+
test_anon_constructor_error_dtype_keyword_missing,
|
|
1219
|
+
devices=devices,
|
|
1220
|
+
)
|
|
1221
|
+
add_function_test(
|
|
1222
|
+
TestVec,
|
|
1223
|
+
"test_anon_constructor_error_length_mismatch",
|
|
1224
|
+
test_anon_constructor_error_length_mismatch,
|
|
1225
|
+
devices=devices,
|
|
1226
|
+
)
|
|
1227
|
+
add_function_test(
|
|
1228
|
+
TestVec,
|
|
1229
|
+
"test_anon_constructor_error_numeric_arg_missing_1",
|
|
1230
|
+
test_anon_constructor_error_numeric_arg_missing_1,
|
|
1231
|
+
devices=devices,
|
|
1232
|
+
)
|
|
1233
|
+
add_function_test(
|
|
1234
|
+
TestVec,
|
|
1235
|
+
"test_anon_constructor_error_numeric_arg_missing_2",
|
|
1236
|
+
test_anon_constructor_error_numeric_arg_missing_2,
|
|
1237
|
+
devices=devices,
|
|
1238
|
+
)
|
|
1239
|
+
add_function_test(
|
|
1240
|
+
TestVec,
|
|
1241
|
+
"test_anon_constructor_error_dtype_keyword_extraneous",
|
|
1242
|
+
test_anon_constructor_error_dtype_keyword_extraneous,
|
|
1243
|
+
devices=devices,
|
|
1244
|
+
)
|
|
1245
|
+
add_function_test(
|
|
1246
|
+
TestVec,
|
|
1247
|
+
"test_anon_constructor_error_numeric_args_mismatch",
|
|
1248
|
+
test_anon_constructor_error_numeric_args_mismatch,
|
|
1249
|
+
devices=devices,
|
|
1250
|
+
)
|
|
1251
|
+
add_function_test(
|
|
1252
|
+
TestVec,
|
|
1253
|
+
"test_tpl_constructor_error_incompatible_sizes",
|
|
1254
|
+
test_tpl_constructor_error_incompatible_sizes,
|
|
1255
|
+
devices=devices,
|
|
1256
|
+
)
|
|
1257
|
+
add_function_test(
|
|
1258
|
+
TestVec,
|
|
1259
|
+
"test_tpl_constructor_error_numeric_args_mismatch",
|
|
1260
|
+
test_tpl_constructor_error_numeric_args_mismatch,
|
|
1261
|
+
devices=devices,
|
|
1262
|
+
)
|
|
1263
|
+
add_function_test(TestVec, "test_tpl_ops_with_anon", test_tpl_ops_with_anon)
|
|
3263
1264
|
|
|
3264
1265
|
|
|
3265
1266
|
if __name__ == "__main__":
|
|
3266
1267
|
wp.build.clear_kernel_cache()
|
|
3267
|
-
_ = register(unittest.TestCase)
|
|
3268
1268
|
unittest.main(verbosity=2, failfast=True)
|