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
328
329
330
331
332
333
334
335
|
/* Function atanhf vectorized with AVX2.
Copyright (C) 2021 Free Software Foundation, Inc.
This file is part of the GNU C Library.
The GNU C Library is free software; you can redistribute it and/or
modify it under the terms of the GNU Lesser General Public
License as published by the Free Software Foundation; either
version 2.1 of the License, or (at your option) any later version.
The GNU C Library is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
Lesser General Public License for more details.
You should have received a copy of the GNU Lesser General Public
License along with the GNU C Library; if not, see
https://www.gnu.org/licenses/. */
/*
* ALGORITHM DESCRIPTION:
*
* Compute atanh(x) as 0.5 * log((1 + x)/(1 - x))
*
* Special cases:
*
* atanh(0) = 0
* atanh(+1) = +INF
* atanh(-1) = -INF
* atanh(x) = NaN if |x| > 1, or if x is a NaN or INF
*
*/
/* Offsets for data table __svml_satanh_data_internal
*/
#define SgnMask 0
#define sOne 32
#define sPoly 64
#define iBrkValue 320
#define iOffExpoMask 352
#define sHalf 384
#define sSign 416
#define sTopMask12 448
#define TinyRange 480
#define sLn2 512
#include <sysdep.h>
.text
.section .text.avx2,"ax",@progbits
ENTRY(_ZGVdN8v_atanhf_avx2)
pushq %rbp
cfi_def_cfa_offset(16)
movq %rsp, %rbp
cfi_def_cfa(6, 16)
cfi_offset(6, -16)
andq $-32, %rsp
subq $96, %rsp
/* Load constants including One = 1 */
vmovups sOne+__svml_satanh_data_internal(%rip), %ymm5
vmovups sTopMask12+__svml_satanh_data_internal(%rip), %ymm13
vmovaps %ymm0, %ymm6
/* Strip off the sign, so treat X as positive until right at the end */
vandps SgnMask+__svml_satanh_data_internal(%rip), %ymm6, %ymm10
vsubps %ymm10, %ymm5, %ymm1
/*
* Compute V = 2 * X trivially, and UHi + U_lo = 1 - X in two pieces,
* the upper part UHi being <= 12 bits long. Then we have
* atanh(X) = 1/2 * log((1 + X) / (1 - X)) = 1/2 * log1p(V / (UHi + ULo)).
*/
vaddps %ymm10, %ymm10, %ymm14
/*
* Check whether |X| < 1, in which case we use the main function.
* Otherwise set the rangemask so that the callout will get used.
* Note that this will also use the callout for NaNs since not(NaN < 1).
*/
vcmpnlt_uqps %ymm5, %ymm10, %ymm7
vsubps %ymm1, %ymm5, %ymm9
vcmplt_oqps TinyRange+__svml_satanh_data_internal(%rip), %ymm10, %ymm4
vrcpps %ymm1, %ymm11
vsubps %ymm10, %ymm9, %ymm12
vandps %ymm13, %ymm11, %ymm0
/* No need to split sU when FMA is available */
vfnmadd213ps %ymm5, %ymm0, %ymm1
vmovaps %ymm6, %ymm8
vfmadd213ps %ymm6, %ymm6, %ymm8
vfnmadd231ps %ymm0, %ymm12, %ymm1
/*
* Split V as well into upper 12 bits and lower part, so that we can get
* a preliminary quotient estimate without rounding error.
*/
vandps %ymm13, %ymm14, %ymm15
vmovmskps %ymm7, %edx
vsubps %ymm15, %ymm14, %ymm7
/* Hence get initial quotient estimate QHi + QLo = R * VHi + R * VLo */
vmulps %ymm15, %ymm0, %ymm10
/* Compute D = E + E^2 */
vfmadd213ps %ymm1, %ymm1, %ymm1
/* Record the sign for eventual reincorporation. */
vandps sSign+__svml_satanh_data_internal(%rip), %ymm6, %ymm3
/* Or the sign bit in with the tiny result to handle atanh(-0) correctly */
vorps %ymm3, %ymm8, %ymm2
vmulps %ymm7, %ymm0, %ymm8
/*
* Compute R * (VHi + VLo) * (1 + E + E^2)
* = R * (VHi + VLo) * (1 + D)
* = QHi + (QHi * D + QLo + QLo * D)
*/
vmulps %ymm1, %ymm10, %ymm9
vfmadd213ps %ymm8, %ymm8, %ymm1
vaddps %ymm1, %ymm9, %ymm1
/* reduction: compute r,n */
vmovups iBrkValue+__svml_satanh_data_internal(%rip), %ymm9
/*
* Now finally accumulate the high and low parts of the
* argument to log1p, H + L, with a final compensated summation.
*/
vaddps %ymm1, %ymm10, %ymm12
vsubps %ymm12, %ymm10, %ymm11
/*
* Now we feed into the log1p code, using H in place of _VARG1 and
* later incorporating L into the reduced argument.
* compute 1+x as high, low parts
*/
vmaxps %ymm12, %ymm5, %ymm13
vminps %ymm12, %ymm5, %ymm14
vaddps %ymm11, %ymm1, %ymm0
vaddps %ymm14, %ymm13, %ymm1
vpsubd %ymm9, %ymm1, %ymm7
vsubps %ymm1, %ymm13, %ymm15
vpsrad $23, %ymm7, %ymm10
vpand iOffExpoMask+__svml_satanh_data_internal(%rip), %ymm7, %ymm8
vaddps %ymm15, %ymm14, %ymm13
vpslld $23, %ymm10, %ymm11
vpaddd %ymm9, %ymm8, %ymm15
vaddps %ymm13, %ymm0, %ymm14
vcvtdq2ps %ymm10, %ymm0
vpsubd %ymm11, %ymm5, %ymm12
/* polynomial evaluation */
vsubps %ymm5, %ymm15, %ymm5
vmulps %ymm14, %ymm12, %ymm1
vaddps %ymm5, %ymm1, %ymm5
vmovups sPoly+224+__svml_satanh_data_internal(%rip), %ymm1
vfmadd213ps sPoly+192+__svml_satanh_data_internal(%rip), %ymm5, %ymm1
vfmadd213ps sPoly+160+__svml_satanh_data_internal(%rip), %ymm5, %ymm1
vfmadd213ps sPoly+128+__svml_satanh_data_internal(%rip), %ymm5, %ymm1
vfmadd213ps sPoly+96+__svml_satanh_data_internal(%rip), %ymm5, %ymm1
vfmadd213ps sPoly+64+__svml_satanh_data_internal(%rip), %ymm5, %ymm1
vfmadd213ps sPoly+32+__svml_satanh_data_internal(%rip), %ymm5, %ymm1
vfmadd213ps sPoly+__svml_satanh_data_internal(%rip), %ymm5, %ymm1
vmulps %ymm1, %ymm5, %ymm7
vfmadd213ps %ymm5, %ymm5, %ymm7
/* final reconstruction */
vfmadd132ps sLn2+__svml_satanh_data_internal(%rip), %ymm7, %ymm0
/* Finally, halve the result and reincorporate the sign */
vxorps sHalf+__svml_satanh_data_internal(%rip), %ymm3, %ymm3
vmulps %ymm0, %ymm3, %ymm0
vblendvps %ymm4, %ymm2, %ymm0, %ymm0
testl %edx, %edx
/* Go to special inputs processing branch */
jne L(SPECIAL_VALUES_BRANCH)
# LOE rbx r12 r13 r14 r15 edx ymm0 ymm6
/* Restore registers
* and exit the function
*/
L(EXIT):
movq %rbp, %rsp
popq %rbp
cfi_def_cfa(7, 8)
cfi_restore(6)
ret
cfi_def_cfa(6, 16)
cfi_offset(6, -16)
/* Branch to process
* special inputs
*/
L(SPECIAL_VALUES_BRANCH):
vmovups %ymm6, 32(%rsp)
vmovups %ymm0, 64(%rsp)
# LOE rbx r12 r13 r14 r15 edx ymm0
xorl %eax, %eax
# LOE rbx r12 r13 r14 r15 eax edx
vzeroupper
movq %r12, 16(%rsp)
/* DW_CFA_expression: r12 (r12) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -32; DW_OP_and; DW_OP_const4s: -80; DW_OP_plus) */
.cfi_escape 0x10, 0x0c, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0xb0, 0xff, 0xff, 0xff, 0x22
movl %eax, %r12d
movq %r13, 8(%rsp)
/* DW_CFA_expression: r13 (r13) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -32; DW_OP_and; DW_OP_const4s: -88; DW_OP_plus) */
.cfi_escape 0x10, 0x0d, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0xa8, 0xff, 0xff, 0xff, 0x22
movl %edx, %r13d
movq %r14, (%rsp)
/* DW_CFA_expression: r14 (r14) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -32; DW_OP_and; DW_OP_const4s: -96; DW_OP_plus) */
.cfi_escape 0x10, 0x0e, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0xa0, 0xff, 0xff, 0xff, 0x22
# LOE rbx r15 r12d r13d
/* Range mask
* bits check
*/
L(RANGEMASK_CHECK):
btl %r12d, %r13d
/* Call scalar math function */
jc L(SCALAR_MATH_CALL)
# LOE rbx r15 r12d r13d
/* Special inputs
* processing loop
*/
L(SPECIAL_VALUES_LOOP):
incl %r12d
cmpl $8, %r12d
/* Check bits in range mask */
jl L(RANGEMASK_CHECK)
# LOE rbx r15 r12d r13d
movq 16(%rsp), %r12
cfi_restore(12)
movq 8(%rsp), %r13
cfi_restore(13)
movq (%rsp), %r14
cfi_restore(14)
vmovups 64(%rsp), %ymm0
/* Go to exit */
jmp L(EXIT)
/* DW_CFA_expression: r12 (r12) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -32; DW_OP_and; DW_OP_const4s: -80; DW_OP_plus) */
.cfi_escape 0x10, 0x0c, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0xb0, 0xff, 0xff, 0xff, 0x22
/* DW_CFA_expression: r13 (r13) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -32; DW_OP_and; DW_OP_const4s: -88; DW_OP_plus) */
.cfi_escape 0x10, 0x0d, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0xa8, 0xff, 0xff, 0xff, 0x22
/* DW_CFA_expression: r14 (r14) (DW_OP_lit8; DW_OP_minus; DW_OP_const4s: -32; DW_OP_and; DW_OP_const4s: -96; DW_OP_plus) */
.cfi_escape 0x10, 0x0e, 0x0e, 0x38, 0x1c, 0x0d, 0xe0, 0xff, 0xff, 0xff, 0x1a, 0x0d, 0xa0, 0xff, 0xff, 0xff, 0x22
# LOE rbx r12 r13 r14 r15 ymm0
/* Scalar math fucntion call
* to process special input
*/
L(SCALAR_MATH_CALL):
movl %r12d, %r14d
movss 32(%rsp,%r14,4), %xmm0
call atanhf@PLT
# LOE rbx r14 r15 r12d r13d xmm0
movss %xmm0, 64(%rsp,%r14,4)
/* Process special inputs in loop */
jmp L(SPECIAL_VALUES_LOOP)
# LOE rbx r15 r12d r13d
END(_ZGVdN8v_atanhf_avx2)
.section .rodata, "a"
.align 32
#ifdef __svml_satanh_data_internal_typedef
typedef unsigned int VUINT32;
typedef struct {
__declspec(align(32)) VUINT32 SgnMask[8][1];
__declspec(align(32)) VUINT32 sOne[8][1];
__declspec(align(32)) VUINT32 sPoly[8][8][1];
__declspec(align(32)) VUINT32 iBrkValue[8][1];
__declspec(align(32)) VUINT32 iOffExpoMask[8][1];
__declspec(align(32)) VUINT32 sHalf[8][1];
__declspec(align(32)) VUINT32 sSign[8][1];
__declspec(align(32)) VUINT32 sTopMask12[8][1];
__declspec(align(32)) VUINT32 TinyRange[8][1];
__declspec(align(32)) VUINT32 sLn2[8][1];
} __svml_satanh_data_internal;
#endif
__svml_satanh_data_internal:
/*== SgnMask ==*/
.long 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff
/*== sOne = SP 1.0 ==*/
.align 32
.long 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000
/*== sPoly[] = SP polynomial ==*/
.align 32
.long 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000 /* -5.0000000000000000000000000e-01 P0 */
.long 0x3eaaaa94, 0x3eaaaa94, 0x3eaaaa94, 0x3eaaaa94, 0x3eaaaa94, 0x3eaaaa94, 0x3eaaaa94, 0x3eaaaa94 /* 3.3333265781402587890625000e-01 P1 */
.long 0xbe80058e, 0xbe80058e, 0xbe80058e, 0xbe80058e, 0xbe80058e, 0xbe80058e, 0xbe80058e, 0xbe80058e /* -2.5004237890243530273437500e-01 P2 */
.long 0x3e4ce190, 0x3e4ce190, 0x3e4ce190, 0x3e4ce190, 0x3e4ce190, 0x3e4ce190, 0x3e4ce190, 0x3e4ce190 /* 2.0007920265197753906250000e-01 P3 */
.long 0xbe28ad37, 0xbe28ad37, 0xbe28ad37, 0xbe28ad37, 0xbe28ad37, 0xbe28ad37, 0xbe28ad37, 0xbe28ad37 /* -1.6472326219081878662109375e-01 P4 */
.long 0x3e0fcb12, 0x3e0fcb12, 0x3e0fcb12, 0x3e0fcb12, 0x3e0fcb12, 0x3e0fcb12, 0x3e0fcb12, 0x3e0fcb12 /* 1.4042308926582336425781250e-01 P5 */
.long 0xbe1ad9e3, 0xbe1ad9e3, 0xbe1ad9e3, 0xbe1ad9e3, 0xbe1ad9e3, 0xbe1ad9e3, 0xbe1ad9e3, 0xbe1ad9e3 /* -1.5122179687023162841796875e-01 P6 */
.long 0x3e0d84ed, 0x3e0d84ed, 0x3e0d84ed, 0x3e0d84ed, 0x3e0d84ed, 0x3e0d84ed, 0x3e0d84ed, 0x3e0d84ed /* 1.3820238411426544189453125e-01 P7 */
/*== iBrkValue = SP 2/3 ==*/
.align 32
.long 0x3f2aaaab, 0x3f2aaaab, 0x3f2aaaab, 0x3f2aaaab, 0x3f2aaaab, 0x3f2aaaab, 0x3f2aaaab, 0x3f2aaaab
/*== iOffExpoMask = SP significand mask ==*/
.align 32
.long 0x007fffff, 0x007fffff, 0x007fffff, 0x007fffff, 0x007fffff, 0x007fffff, 0x007fffff, 0x007fffff
/*== sHalf ==*/
.align 32
.long 0x3F000000, 0x3F000000, 0x3F000000, 0x3F000000, 0x3F000000, 0x3F000000, 0x3F000000, 0x3F000000
/*== sSign ==*/
.align 32
.long 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000, 0x80000000
/*== sTopMask12 ==*/
.align 32
.long 0xFFFFF000, 0xFFFFF000, 0xFFFFF000, 0xFFFFF000, 0xFFFFF000, 0xFFFFF000, 0xFFFFF000, 0xFFFFF000
/*== TinyRange ==*/
.align 32
.long 0x0C000000, 0x0C000000, 0x0C000000, 0x0C000000, 0x0C000000, 0x0C000000, 0x0C000000, 0x0C000000
/*== sLn2 = SP ln(2) ==*/
.align 32
.long 0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218, 0x3f317218
.align 32
.type __svml_satanh_data_internal,@object
.size __svml_satanh_data_internal,.-__svml_satanh_data_internal
|