1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
|
--- contrib/python/numpy/py3/numpy/core/src/_simd/_simd.dispatch.h (index)
+++ contrib/python/numpy/py3/numpy/core/src/_simd/_simd.dispatch.h (working tree)
@@ -10,8 +10,13 @@
#undef NPY__CPU_DISPATCH_CALL
#define NPY__CPU_DISPATCH_BASELINE_CALL(CB, ...) \
NPY__CPU_DISPATCH_EXPAND_(CB(__VA_ARGS__))
+#if defined(__x86_64__) || defined(_M_X64)
#define NPY__CPU_DISPATCH_CALL(CHK, CB, ...) \
NPY__CPU_DISPATCH_EXPAND_(CB((CHK(AVX512_SKX)), AVX512_SKX, __VA_ARGS__)) \
NPY__CPU_DISPATCH_EXPAND_(CB((CHK(AVX512F)), AVX512F, __VA_ARGS__)) \
NPY__CPU_DISPATCH_EXPAND_(CB((CHK(AVX)&&CHK(F16C)&&CHK(FMA3)&&CHK(AVX2)), FMA3__AVX2, __VA_ARGS__)) \
NPY__CPU_DISPATCH_EXPAND_(CB((CHK(SSE)&&CHK(SSE2)&&CHK(SSE3)&&CHK(SSSE3)&&CHK(SSE41)&&CHK(POPCNT)&&CHK(SSE42)), SSE42, __VA_ARGS__))
+#elif defined(__aarch64__)
+#define NPY__CPU_DISPATCH_CALL(CHK, CB, ...) \
+
+#endif
--- contrib/python/numpy/py3/numpy/core/src/umath/_umath_tests.dispatch.h (index)
+++ contrib/python/numpy/py3/numpy/core/src/umath/_umath_tests.dispatch.h (working tree)
@@ -10,6 +10,11 @@
#undef NPY__CPU_DISPATCH_CALL
#define NPY__CPU_DISPATCH_BASELINE_CALL(CB, ...) \
NPY__CPU_DISPATCH_EXPAND_(CB(__VA_ARGS__))
+#if defined(__x86_64__) || defined(_M_X64)
#define NPY__CPU_DISPATCH_CALL(CHK, CB, ...) \
NPY__CPU_DISPATCH_EXPAND_(CB((CHK(AVX)&&CHK(F16C)&&CHK(AVX2)), AVX2, __VA_ARGS__)) \
NPY__CPU_DISPATCH_EXPAND_(CB((CHK(SSE)&&CHK(SSE2)&&CHK(SSE3)&&CHK(SSSE3)&&CHK(SSE41)), SSE41, __VA_ARGS__))
+#elif defined(__aarch64__)
+#define NPY__CPU_DISPATCH_CALL(CHK, CB, ...) \
+ NPY__CPU_DISPATCH_EXPAND_(CB((CHK(ASIMD)&&CHK(ASIMDHP)), ASIMDHP, __VA_ARGS__))
+#endif
--- contrib/python/numpy/py3/numpy/core/src/umath/loops_arithm_fp.dispatch.h (index)
+++ contrib/python/numpy/py3/numpy/core/src/umath/loops_arithm_fp.dispatch.h (working tree)
@@ -10,5 +10,10 @@
#undef NPY__CPU_DISPATCH_CALL
#define NPY__CPU_DISPATCH_BASELINE_CALL(CB, ...) \
NPY__CPU_DISPATCH_EXPAND_(CB(__VA_ARGS__))
+#if defined(__x86_64__) || defined(_M_X64)
#define NPY__CPU_DISPATCH_CALL(CHK, CB, ...) \
NPY__CPU_DISPATCH_EXPAND_(CB((CHK(AVX)&&CHK(F16C)&&CHK(FMA3)&&CHK(AVX2)), FMA3__AVX2, __VA_ARGS__))
+#elif defined(__aarch64__)
+#define NPY__CPU_DISPATCH_CALL(CHK, CB, ...) \
+
+#endif
--- contrib/python/numpy/py3/numpy/core/src/umath/loops_arithmetic.dispatch.h (index)
+++ contrib/python/numpy/py3/numpy/core/src/umath/loops_arithmetic.dispatch.h (working tree)
@@ -10,8 +10,13 @@
#undef NPY__CPU_DISPATCH_CALL
#define NPY__CPU_DISPATCH_BASELINE_CALL(CB, ...) \
NPY__CPU_DISPATCH_EXPAND_(CB(__VA_ARGS__))
+#if defined(__x86_64__) || defined(_M_X64)
#define NPY__CPU_DISPATCH_CALL(CHK, CB, ...) \
NPY__CPU_DISPATCH_EXPAND_(CB((CHK(AVX512_SKX)), AVX512_SKX, __VA_ARGS__)) \
NPY__CPU_DISPATCH_EXPAND_(CB((CHK(AVX512F)), AVX512F, __VA_ARGS__)) \
NPY__CPU_DISPATCH_EXPAND_(CB((CHK(AVX)&&CHK(F16C)&&CHK(AVX2)), AVX2, __VA_ARGS__)) \
NPY__CPU_DISPATCH_EXPAND_(CB((CHK(SSE)&&CHK(SSE2)&&CHK(SSE3)&&CHK(SSSE3)&&CHK(SSE41)), SSE41, __VA_ARGS__))
+#elif defined(__aarch64__)
+#define NPY__CPU_DISPATCH_CALL(CHK, CB, ...) \
+
+#endif
--- contrib/python/numpy/py3/numpy/core/src/umath/loops_exponent_log.dispatch.h (index)
+++ contrib/python/numpy/py3/numpy/core/src/umath/loops_exponent_log.dispatch.h (working tree)
@@ -10,7 +10,12 @@
#undef NPY__CPU_DISPATCH_CALL
#define NPY__CPU_DISPATCH_BASELINE_CALL(CB, ...) \
NPY__CPU_DISPATCH_EXPAND_(CB(__VA_ARGS__))
+#if defined(__x86_64__) || defined(_M_X64)
#define NPY__CPU_DISPATCH_CALL(CHK, CB, ...) \
NPY__CPU_DISPATCH_EXPAND_(CB((CHK(AVX512_SKX)), AVX512_SKX, __VA_ARGS__)) \
NPY__CPU_DISPATCH_EXPAND_(CB((CHK(AVX512F)), AVX512F, __VA_ARGS__)) \
NPY__CPU_DISPATCH_EXPAND_(CB((CHK(AVX)&&CHK(F16C)&&CHK(FMA3)&&CHK(AVX2)), FMA3__AVX2, __VA_ARGS__))
+#elif defined(__aarch64__)
+#define NPY__CPU_DISPATCH_CALL(CHK, CB, ...) \
+
+#endif
--- contrib/python/numpy/py3/numpy/core/src/umath/loops_trigonometric.dispatch.h (index)
+++ contrib/python/numpy/py3/numpy/core/src/umath/loops_trigonometric.dispatch.h (working tree)
@@ -10,6 +10,11 @@
#undef NPY__CPU_DISPATCH_CALL
#define NPY__CPU_DISPATCH_BASELINE_CALL(CB, ...) \
NPY__CPU_DISPATCH_EXPAND_(CB(__VA_ARGS__))
+#if defined(__x86_64__) || defined(_M_X64)
#define NPY__CPU_DISPATCH_CALL(CHK, CB, ...) \
NPY__CPU_DISPATCH_EXPAND_(CB((CHK(AVX512F)), AVX512F, __VA_ARGS__)) \
NPY__CPU_DISPATCH_EXPAND_(CB((CHK(AVX)&&CHK(F16C)&&CHK(FMA3)&&CHK(AVX2)), FMA3__AVX2, __VA_ARGS__))
+#elif defined(__aarch64__)
+#define NPY__CPU_DISPATCH_CALL(CHK, CB, ...) \
+
+#endif
--- contrib/python/numpy/py3/numpy/core/src/umath/loops_umath_fp.dispatch.h (index)
+++ contrib/python/numpy/py3/numpy/core/src/umath/loops_umath_fp.dispatch.h (working tree)
@@ -10,5 +10,10 @@
#undef NPY__CPU_DISPATCH_CALL
#define NPY__CPU_DISPATCH_BASELINE_CALL(CB, ...) \
NPY__CPU_DISPATCH_EXPAND_(CB(__VA_ARGS__))
+#if defined(__x86_64__) || defined(_M_X64)
#define NPY__CPU_DISPATCH_CALL(CHK, CB, ...) \
NPY__CPU_DISPATCH_EXPAND_(CB((CHK(AVX512_SKX)), AVX512_SKX, __VA_ARGS__))
+#elif defined(__aarch64__)
+#define NPY__CPU_DISPATCH_CALL(CHK, CB, ...) \
+
+#endif
--- contrib/python/numpy/py3/numpy/core/src/umath/loops_unary_fp.dispatch.h (index)
+++ contrib/python/numpy/py3/numpy/core/src/umath/loops_unary_fp.dispatch.h (working tree)
@@ -10,5 +10,10 @@
#undef NPY__CPU_DISPATCH_CALL
#define NPY__CPU_DISPATCH_BASELINE_CALL(CB, ...) \
NPY__CPU_DISPATCH_EXPAND_(CB(__VA_ARGS__))
+#if defined(__x86_64__) || defined(_M_X64)
#define NPY__CPU_DISPATCH_CALL(CHK, CB, ...) \
NPY__CPU_DISPATCH_EXPAND_(CB((CHK(SSE)&&CHK(SSE2)&&CHK(SSE3)&&CHK(SSSE3)&&CHK(SSE41)), SSE41, __VA_ARGS__))
+#elif defined(__aarch64__)
+#define NPY__CPU_DISPATCH_CALL(CHK, CB, ...) \
+
+#endif
--- contrib/python/numpy/py3/numpy/core/src/multiarray/argfunc.dispatch.h (index)
+++ contrib/python/numpy/py3/numpy/core/src/multiarray/argfunc.dispatch.h (working tree)
@@ -10,7 +10,12 @@
#undef NPY__CPU_DISPATCH_CALL
#define NPY__CPU_DISPATCH_BASELINE_CALL(CB, ...) \
NPY__CPU_DISPATCH_EXPAND_(CB(__VA_ARGS__))
+#if defined(__x86_64__) || defined(_M_X64)
#define NPY__CPU_DISPATCH_CALL(CHK, CB, ...) \
NPY__CPU_DISPATCH_EXPAND_(CB((CHK(AVX512_SKX)), AVX512_SKX, __VA_ARGS__)) \
NPY__CPU_DISPATCH_EXPAND_(CB((CHK(AVX)&&CHK(F16C)&&CHK(AVX2)), AVX2, __VA_ARGS__)) \
NPY__CPU_DISPATCH_EXPAND_(CB((CHK(SSE)&&CHK(SSE2)&&CHK(SSE3)&&CHK(SSSE3)&&CHK(SSE41)&&CHK(POPCNT)&&CHK(SSE42)), SSE42, __VA_ARGS__))
+#elif defined(__aarch64__)
+#define NPY__CPU_DISPATCH_CALL(CHK, CB, ...) \
+
+#endif
--- contrib/python/numpy/py3/numpy/core/src/umath/loops_hyperbolic.dispatch.h (index)
+++ contrib/python/numpy/py3/numpy/core/src/umath/loops_hyperbolic.dispatch.h (working tree)
@@ -10,6 +10,11 @@
#undef NPY__CPU_DISPATCH_CALL
#define NPY__CPU_DISPATCH_BASELINE_CALL(CB, ...) \
NPY__CPU_DISPATCH_EXPAND_(CB(__VA_ARGS__))
+#if defined(__x86_64__) || defined(_M_X64)
#define NPY__CPU_DISPATCH_CALL(CHK, CB, ...) \
NPY__CPU_DISPATCH_EXPAND_(CB((CHK(AVX512_SKX)), AVX512_SKX, __VA_ARGS__)) \
NPY__CPU_DISPATCH_EXPAND_(CB((CHK(AVX)&&CHK(F16C)&&CHK(FMA3)&&CHK(AVX2)), FMA3__AVX2, __VA_ARGS__))
+#elif defined(__aarch64__)
+#define NPY__CPU_DISPATCH_CALL(CHK, CB, ...) \
+
+#endif
--- contrib/python/numpy/py3/numpy/core/src/umath/loops_minmax.dispatch.h (index)
+++ contrib/python/numpy/py3/numpy/core/src/umath/loops_minmax.dispatch.h (working tree)
@@ -10,6 +10,11 @@
#undef NPY__CPU_DISPATCH_CALL
#define NPY__CPU_DISPATCH_BASELINE_CALL(CB, ...) \
NPY__CPU_DISPATCH_EXPAND_(CB(__VA_ARGS__))
+#if defined(__x86_64__) || defined(_M_X64)
#define NPY__CPU_DISPATCH_CALL(CHK, CB, ...) \
NPY__CPU_DISPATCH_EXPAND_(CB((CHK(AVX512_SKX)), AVX512_SKX, __VA_ARGS__)) \
NPY__CPU_DISPATCH_EXPAND_(CB((CHK(AVX)&&CHK(F16C)&&CHK(AVX2)), AVX2, __VA_ARGS__))
+#elif defined(__aarch64__)
+#define NPY__CPU_DISPATCH_CALL(CHK, CB, ...) \
+
+#endif
--- contrib/python/numpy/py3/numpy/core/src/umath/loops_comparison.dispatch.h (index)
+++ contrib/python/numpy/py3/numpy/core/src/umath/loops_comparison.dispatch.h (working tree)
@@ -10,8 +10,13 @@
#undef NPY__CPU_DISPATCH_CALL
#define NPY__CPU_DISPATCH_BASELINE_CALL(CB, ...) \
NPY__CPU_DISPATCH_EXPAND_(CB(__VA_ARGS__))
+#if defined(__x86_64__) || defined(_M_X64)
#define NPY__CPU_DISPATCH_CALL(CHK, CB, ...) \
NPY__CPU_DISPATCH_EXPAND_(CB((CHK(AVX512_SKX)), AVX512_SKX, __VA_ARGS__)) \
NPY__CPU_DISPATCH_EXPAND_(CB((CHK(AVX512F)), AVX512F, __VA_ARGS__)) \
NPY__CPU_DISPATCH_EXPAND_(CB((CHK(AVX)&&CHK(F16C)&&CHK(AVX2)), AVX2, __VA_ARGS__)) \
NPY__CPU_DISPATCH_EXPAND_(CB((CHK(SSE)&&CHK(SSE2)&&CHK(SSE3)&&CHK(SSSE3)&&CHK(SSE41)&&CHK(POPCNT)&&CHK(SSE42)), SSE42, __VA_ARGS__))
+#elif defined(__aarch64__)
+#define NPY__CPU_DISPATCH_CALL(CHK, CB, ...) \
+
+#endif
--- contrib/python/numpy/py3/numpy/core/src/umath/_umath_tests.dispatch.asimdhp.c (index)
+++ contrib/python/numpy/py3/numpy/core/src/umath/_umath_tests.dispatch.asimdhp.c (working tree)
@@ -0,0 +1,12 @@
+/**
+ * AUTOGENERATED DON'T EDIT
+ * Please make changes to the code generator (distutils/ccompiler_opt.py)
+ */
+#define NPY__CPU_TARGET_MODE
+#define NPY__CPU_TARGET_CURRENT ASIMDHP
+#define NPY__CPU_TARGET_NEON
+#define NPY__CPU_TARGET_NEON_FP16
+#define NPY__CPU_TARGET_NEON_VFPV4
+#define NPY__CPU_TARGET_ASIMD
+#define NPY__CPU_TARGET_ASIMDHP
+#include "_umath_tests.dispatch.c"
--- contrib/python/numpy/py3/numpy/distutils/include/npy_cpu_dispatch_config.aarch64.h (index)
+++ contrib/python/numpy/py3/numpy/distutils/include/npy_cpu_dispatch_config.aarch64.h (working tree)
@@ -0,0 +1,42 @@
+/*
+ * AUTOGENERATED DON'T EDIT
+ * Please make changes to the code generator (distutils/ccompiler_opt.py)
+*/
+#define NPY_WITH_CPU_BASELINE "NEON NEON_FP16 NEON_VFPV4 ASIMD"
+#define NPY_WITH_CPU_DISPATCH "ASIMDHP ASIMDDP ASIMDFHM"
+#define NPY_WITH_CPU_BASELINE_N 4
+#define NPY_WITH_CPU_DISPATCH_N 3
+#define NPY_WITH_CPU_EXPAND_(X) X
+#define NPY_WITH_CPU_BASELINE_CALL(MACRO_TO_CALL, ...) \
+ NPY_WITH_CPU_EXPAND_(MACRO_TO_CALL(NEON, __VA_ARGS__)) \
+ NPY_WITH_CPU_EXPAND_(MACRO_TO_CALL(NEON_FP16, __VA_ARGS__)) \
+ NPY_WITH_CPU_EXPAND_(MACRO_TO_CALL(NEON_VFPV4, __VA_ARGS__)) \
+ NPY_WITH_CPU_EXPAND_(MACRO_TO_CALL(ASIMD, __VA_ARGS__))
+#define NPY_WITH_CPU_DISPATCH_CALL(MACRO_TO_CALL, ...) \
+ NPY_WITH_CPU_EXPAND_(MACRO_TO_CALL(ASIMDHP, __VA_ARGS__)) \
+ NPY_WITH_CPU_EXPAND_(MACRO_TO_CALL(ASIMDDP, __VA_ARGS__)) \
+ NPY_WITH_CPU_EXPAND_(MACRO_TO_CALL(ASIMDFHM, __VA_ARGS__))
+/******* baseline features *******/
+ /** NEON **/
+ #define NPY_HAVE_NEON 1
+ #include <arm_neon.h>
+ /** NEON_FP16 **/
+ #define NPY_HAVE_NEON_FP16 1
+ /** NEON_VFPV4 **/
+ #define NPY_HAVE_NEON_VFPV4 1
+ /** ASIMD **/
+ #define NPY_HAVE_ASIMD 1
+
+/******* dispatch features *******/
+#ifdef NPY__CPU_TARGET_ASIMDHP
+ /** ASIMDHP **/
+ #define NPY_HAVE_ASIMDHP 1
+#endif /*NPY__CPU_TARGET_ASIMDHP*/
+#ifdef NPY__CPU_TARGET_ASIMDDP
+ /** ASIMDDP **/
+ #define NPY_HAVE_ASIMDDP 1
+#endif /*NPY__CPU_TARGET_ASIMDDP*/
+#ifdef NPY__CPU_TARGET_ASIMDFHM
+ /** ASIMDFHM **/
+ #define NPY_HAVE_ASIMDFHM 1
+#endif /*NPY__CPU_TARGET_ASIMDFHM*/
--- contrib/python/numpy/py3/numpy/core/src/npysort/simd_qsort.dispatch.h (index)
+++ contrib/python/numpy/py3/numpy/core/src/npysort/simd_qsort.dispatch.h (working tree)
@@ -10,5 +10,10 @@
#undef NPY__CPU_DISPATCH_CALL
#define NPY__CPU_DISPATCH_BASELINE_CALL(CB, ...) \
+#if defined(__x86_64__) || defined(_M_X64)
#define NPY__CPU_DISPATCH_CALL(CHK, CB, ...) \
NPY__CPU_DISPATCH_EXPAND_(CB((CHK(AVX512_SKX)), AVX512_SKX, __VA_ARGS__))
+#elif defined(__aarch64__)
+#define NPY__CPU_DISPATCH_CALL(CHK, CB, ...) \
+
+#endif
--- contrib/python/numpy/py3/numpy/core/src/npysort/simd_qsort_16bit.dispatch.h (index)
+++ contrib/python/numpy/py3/numpy/core/src/npysort/simd_qsort_16bit.dispatch.h (working tree)
@@ -10,5 +10,10 @@
#undef NPY__CPU_DISPATCH_CALL
#define NPY__CPU_DISPATCH_BASELINE_CALL(CB, ...) \
+#if defined(__x86_64__) || defined(_M_X64)
#define NPY__CPU_DISPATCH_CALL(CHK, CB, ...) \
NPY__CPU_DISPATCH_EXPAND_(CB((CHK(AVX512_ICL)), AVX512_ICL, __VA_ARGS__))
+#elif defined(__aarch64__)
+#define NPY__CPU_DISPATCH_CALL(CHK, CB, ...) \
+
+#endif
--- contrib/python/numpy/py3/numpy/core/src/umath/loops_autovec.dispatch.h (index)
+++ contrib/python/numpy/py3/numpy/core/src/umath/loops_autovec.dispatch.h (working tree)
@@ -10,5 +10,10 @@
#undef NPY__CPU_DISPATCH_CALL
#define NPY__CPU_DISPATCH_BASELINE_CALL(CB, ...) \
NPY__CPU_DISPATCH_EXPAND_(CB(__VA_ARGS__))
+#if defined(__x86_64__) || defined(_M_X64)
#define NPY__CPU_DISPATCH_CALL(CHK, CB, ...) \
NPY__CPU_DISPATCH_EXPAND_(CB((CHK(AVX)&&CHK(F16C)&&CHK(AVX2)), AVX2, __VA_ARGS__))
+#elif defined(__aarch64__)
+#define NPY__CPU_DISPATCH_CALL(CHK, CB, ...) \
+
+#endif
--- contrib/python/numpy/py3/numpy/core/src/umath/loops_logical.dispatch.h (index)
+++ contrib/python/numpy/py3/numpy/core/src/umath/loops_logical.dispatch.h (working tree)
@@ -10,6 +10,11 @@
#undef NPY__CPU_DISPATCH_CALL
#define NPY__CPU_DISPATCH_BASELINE_CALL(CB, ...) \
NPY__CPU_DISPATCH_EXPAND_(CB(__VA_ARGS__))
+#if defined(__x86_64__) || defined(_M_X64)
#define NPY__CPU_DISPATCH_CALL(CHK, CB, ...) \
NPY__CPU_DISPATCH_EXPAND_(CB((CHK(AVX512_SKX)), AVX512_SKX, __VA_ARGS__)) \
NPY__CPU_DISPATCH_EXPAND_(CB((CHK(AVX)&&CHK(F16C)&&CHK(AVX2)), AVX2, __VA_ARGS__))
+#elif defined(__aarch64__)
+#define NPY__CPU_DISPATCH_CALL(CHK, CB, ...) \
+
+#endif
--- contrib/python/numpy/py3/numpy/core/src/umath/loops_unary.dispatch.h (index)
+++ contrib/python/numpy/py3/numpy/core/src/umath/loops_unary.dispatch.h (working tree)
@@ -10,6 +10,11 @@
#undef NPY__CPU_DISPATCH_CALL
#define NPY__CPU_DISPATCH_BASELINE_CALL(CB, ...) \
NPY__CPU_DISPATCH_EXPAND_(CB(__VA_ARGS__))
+#if defined(__x86_64__) || defined(_M_X64)
#define NPY__CPU_DISPATCH_CALL(CHK, CB, ...) \
NPY__CPU_DISPATCH_EXPAND_(CB((CHK(AVX512_SKX)), AVX512_SKX, __VA_ARGS__)) \
NPY__CPU_DISPATCH_EXPAND_(CB((CHK(AVX)&&CHK(F16C)&&CHK(AVX2)), AVX2, __VA_ARGS__))
+#elif defined(__aarch64__)
+#define NPY__CPU_DISPATCH_CALL(CHK, CB, ...) \
+
+#endif
--- contrib/python/numpy/py3/numpy/core/src/umath/loops_unary_complex.dispatch.h (index)
+++ contrib/python/numpy/py3/numpy/core/src/umath/loops_unary_complex.dispatch.h (working tree)
@@ -10,6 +10,11 @@
#undef NPY__CPU_DISPATCH_CALL
#define NPY__CPU_DISPATCH_BASELINE_CALL(CB, ...) \
NPY__CPU_DISPATCH_EXPAND_(CB(__VA_ARGS__))
+#if defined(__x86_64__) || defined(_M_X64)
#define NPY__CPU_DISPATCH_CALL(CHK, CB, ...) \
NPY__CPU_DISPATCH_EXPAND_(CB((CHK(AVX512F)), AVX512F, __VA_ARGS__)) \
NPY__CPU_DISPATCH_EXPAND_(CB((CHK(AVX)&&CHK(F16C)&&CHK(FMA3)&&CHK(AVX2)), FMA3__AVX2, __VA_ARGS__))
+#elif defined(__aarch64__)
+#define NPY__CPU_DISPATCH_CALL(CHK, CB, ...) \
+
+#endif
--- contrib/python/numpy/py3/numpy/core/src/umath/loops_unary_fp_le.dispatch.h (index)
+++ contrib/python/numpy/py3/numpy/core/src/umath/loops_unary_fp_le.dispatch.h (working tree)
@@ -10,5 +10,10 @@
#undef NPY__CPU_DISPATCH_CALL
#define NPY__CPU_DISPATCH_BASELINE_CALL(CB, ...) \
NPY__CPU_DISPATCH_EXPAND_(CB(__VA_ARGS__))
+#if defined(__x86_64__) || defined(_M_X64)
#define NPY__CPU_DISPATCH_CALL(CHK, CB, ...) \
NPY__CPU_DISPATCH_EXPAND_(CB((CHK(SSE)&&CHK(SSE2)&&CHK(SSE3)&&CHK(SSSE3)&&CHK(SSE41)), SSE41, __VA_ARGS__))
+#elif defined(__aarch64__)
+#define NPY__CPU_DISPATCH_CALL(CHK, CB, ...) \
+
+#endif
|
