aesni-x86[_64].pl: optimize for Sandy Bridge and add XTS mode.
[openssl.git] / crypto / aes / asm / aes-parisc.pl
1 #!/usr/bin/env perl
2
3 # ====================================================================
4 # Written by Andy Polyakov <appro@fy.chalmers.se> for the OpenSSL
5 # project. The module is, however, dual licensed under OpenSSL and
6 # CRYPTOGAMS licenses depending on where you obtain it. For further
7 # details see http://www.openssl.org/~appro/cryptogams/.
8 # ====================================================================
9
10 # AES for PA-RISC.
11 #
12 # June 2009.
13 #
14 # The module is mechanical transliteration of aes-sparcv9.pl, but with
15 # a twist: S-boxes are compressed even further down to 1K+256B. On
16 # PA-7100LC performance is ~40% better than gcc 3.2 generated code and
17 # is about 33 cycles per byte processed with 128-bit key. Newer CPUs
18 # perform at 16 cycles per byte. It's not faster than code generated
19 # by vendor compiler, but recall that it has compressed S-boxes, which
20 # requires extra processing.
21 #
22 # Special thanks to polarhome.com for providing HP-UX account.
23
24 $flavour = shift;
25 $output = shift;
26 open STDOUT,">$output";
27
28 if ($flavour =~ /64/) {
29         $LEVEL          ="2.0W";
30         $SIZE_T         =8;
31         $FRAME_MARKER   =80;
32         $SAVED_RP       =16;
33         $PUSH           ="std";
34         $PUSHMA         ="std,ma";
35         $POP            ="ldd";
36         $POPMB          ="ldd,mb";
37 } else {
38         $LEVEL          ="1.0";
39         $SIZE_T         =4;
40         $FRAME_MARKER   =48;
41         $SAVED_RP       =20;
42         $PUSH           ="stw";
43         $PUSHMA         ="stwm";
44         $POP            ="ldw";
45         $POPMB          ="ldwm";
46 }
47
48 $FRAME=16*$SIZE_T+$FRAME_MARKER;# 16 saved regs + frame marker
49                                 #                 [+ argument transfer]
50 $inp="%r26";    # arg0
51 $out="%r25";    # arg1
52 $key="%r24";    # arg2
53
54 ($s0,$s1,$s2,$s3) = ("%r1","%r2","%r3","%r4");
55 ($t0,$t1,$t2,$t3) = ("%r5","%r6","%r7","%r8");
56
57 ($acc0, $acc1, $acc2, $acc3, $acc4, $acc5, $acc6, $acc7,
58  $acc8, $acc9,$acc10,$acc11,$acc12,$acc13,$acc14,$acc15) =
59 ("%r9","%r10","%r11","%r12","%r13","%r14","%r15","%r16",
60 "%r17","%r18","%r19","%r20","%r21","%r22","%r23","%r26");
61
62 $tbl="%r28";
63 $rounds="%r29";
64
65 $code=<<___;
66         .LEVEL  $LEVEL
67         .SPACE  \$TEXT\$
68         .SUBSPA \$CODE\$,QUAD=0,ALIGN=8,ACCESS=0x2C,CODE_ONLY
69
70         .EXPORT AES_encrypt,ENTRY,ARGW0=GR,ARGW1=GR,ARGW2=GR
71         .ALIGN  64
72 AES_encrypt
73         .PROC
74         .CALLINFO       FRAME=`$FRAME-16*$SIZE_T`,NO_CALLS,SAVE_RP,ENTRY_GR=18
75         .ENTRY
76         $PUSH   %r2,-$SAVED_RP(%sp)     ; standard prologue
77         $PUSHMA %r3,$FRAME(%sp)
78         $PUSH   %r4,`-$FRAME+1*$SIZE_T`(%sp)
79         $PUSH   %r5,`-$FRAME+2*$SIZE_T`(%sp)
80         $PUSH   %r6,`-$FRAME+3*$SIZE_T`(%sp)
81         $PUSH   %r7,`-$FRAME+4*$SIZE_T`(%sp)
82         $PUSH   %r8,`-$FRAME+5*$SIZE_T`(%sp)
83         $PUSH   %r9,`-$FRAME+6*$SIZE_T`(%sp)
84         $PUSH   %r10,`-$FRAME+7*$SIZE_T`(%sp)
85         $PUSH   %r11,`-$FRAME+8*$SIZE_T`(%sp)
86         $PUSH   %r12,`-$FRAME+9*$SIZE_T`(%sp)
87         $PUSH   %r13,`-$FRAME+10*$SIZE_T`(%sp)
88         $PUSH   %r14,`-$FRAME+11*$SIZE_T`(%sp)
89         $PUSH   %r15,`-$FRAME+12*$SIZE_T`(%sp)
90         $PUSH   %r16,`-$FRAME+13*$SIZE_T`(%sp)
91         $PUSH   %r17,`-$FRAME+14*$SIZE_T`(%sp)
92         $PUSH   %r18,`-$FRAME+15*$SIZE_T`(%sp)
93
94         blr     %r0,$tbl
95         ldi     3,$t0
96 L\$enc_pic
97         andcm   $tbl,$t0,$tbl
98         ldo     L\$AES_Te-L\$enc_pic($tbl),$tbl
99
100         and     $inp,$t0,$t0
101         sub     $inp,$t0,$inp
102         ldw     0($inp),$s0
103         ldw     4($inp),$s1
104         ldw     8($inp),$s2
105         comib,= 0,$t0,L\$enc_inp_aligned
106         ldw     12($inp),$s3
107
108         sh3addl $t0,%r0,$t0
109         subi    32,$t0,$t0
110         mtctl   $t0,%cr11
111         ldw     16($inp),$t1
112         vshd    $s0,$s1,$s0
113         vshd    $s1,$s2,$s1
114         vshd    $s2,$s3,$s2
115         vshd    $s3,$t1,$s3
116
117 L\$enc_inp_aligned
118         bl      _parisc_AES_encrypt,%r31
119         nop
120
121         extru,<> $out,31,2,%r0
122         b       L\$enc_out_aligned
123         nop
124
125         _srm    $s0,24,$acc0
126         _srm    $s0,16,$acc1
127         stb     $acc0,0($out)
128         _srm    $s0,8,$acc2
129         stb     $acc1,1($out)
130         _srm    $s1,24,$acc4
131         stb     $acc2,2($out)
132         _srm    $s1,16,$acc5
133         stb     $s0,3($out)
134         _srm    $s1,8,$acc6
135         stb     $acc4,4($out)
136         _srm    $s2,24,$acc0
137         stb     $acc5,5($out)
138         _srm    $s2,16,$acc1
139         stb     $acc6,6($out)
140         _srm    $s2,8,$acc2
141         stb     $s1,7($out)
142         _srm    $s3,24,$acc4
143         stb     $acc0,8($out)
144         _srm    $s3,16,$acc5
145         stb     $acc1,9($out)
146         _srm    $s3,8,$acc6
147         stb     $acc2,10($out)
148         stb     $s2,11($out)
149         stb     $acc4,12($out)
150         stb     $acc5,13($out)
151         stb     $acc6,14($out)
152         b       L\$enc_done
153         stb     $s3,15($out)
154
155 L\$enc_out_aligned
156         stw     $s0,0($out)
157         stw     $s1,4($out)
158         stw     $s2,8($out)
159         stw     $s3,12($out)
160
161 L\$enc_done
162         $POP    `-$FRAME-$SAVED_RP`(%sp),%r2    ; standard epilogue
163         $POP    `-$FRAME+1*$SIZE_T`(%sp),%r4
164         $POP    `-$FRAME+2*$SIZE_T`(%sp),%r5
165         $POP    `-$FRAME+3*$SIZE_T`(%sp),%r6
166         $POP    `-$FRAME+4*$SIZE_T`(%sp),%r7
167         $POP    `-$FRAME+5*$SIZE_T`(%sp),%r8
168         $POP    `-$FRAME+6*$SIZE_T`(%sp),%r9
169         $POP    `-$FRAME+7*$SIZE_T`(%sp),%r10
170         $POP    `-$FRAME+8*$SIZE_T`(%sp),%r11
171         $POP    `-$FRAME+9*$SIZE_T`(%sp),%r12
172         $POP    `-$FRAME+10*$SIZE_T`(%sp),%r13
173         $POP    `-$FRAME+11*$SIZE_T`(%sp),%r14
174         $POP    `-$FRAME+12*$SIZE_T`(%sp),%r15
175         $POP    `-$FRAME+13*$SIZE_T`(%sp),%r16
176         $POP    `-$FRAME+14*$SIZE_T`(%sp),%r17
177         $POP    `-$FRAME+15*$SIZE_T`(%sp),%r18
178         bv      (%r2)
179         .EXIT
180         $POPMB  -$FRAME(%sp),%r3
181         .PROCEND
182
183         .ALIGN  16
184 _parisc_AES_encrypt
185         .PROC
186         .CALLINFO       MILLICODE
187         .ENTRY
188         ldw     240($key),$rounds
189         ldw     0($key),$t0
190         ldw     4($key),$t1
191         ldw     8($key),$t2
192         _srm    $rounds,1,$rounds
193         xor     $t0,$s0,$s0
194         ldw     12($key),$t3
195         _srm    $s0,24,$acc0
196         xor     $t1,$s1,$s1
197         ldw     16($key),$t0
198         _srm    $s1,16,$acc1
199         xor     $t2,$s2,$s2
200         ldw     20($key),$t1
201         xor     $t3,$s3,$s3
202         ldw     24($key),$t2
203         ldw     28($key),$t3
204 L\$enc_loop
205         _srm    $s2,8,$acc2
206         ldwx,s  $acc0($tbl),$acc0
207         _srm    $s3,0,$acc3
208         ldwx,s  $acc1($tbl),$acc1
209         _srm    $s1,24,$acc4
210         ldwx,s  $acc2($tbl),$acc2
211         _srm    $s2,16,$acc5
212         ldwx,s  $acc3($tbl),$acc3
213         _srm    $s3,8,$acc6
214         ldwx,s  $acc4($tbl),$acc4
215         _srm    $s0,0,$acc7
216         ldwx,s  $acc5($tbl),$acc5
217         _srm    $s2,24,$acc8
218         ldwx,s  $acc6($tbl),$acc6
219         _srm    $s3,16,$acc9
220         ldwx,s  $acc7($tbl),$acc7
221         _srm    $s0,8,$acc10
222         ldwx,s  $acc8($tbl),$acc8
223         _srm    $s1,0,$acc11
224         ldwx,s  $acc9($tbl),$acc9
225         _srm    $s3,24,$acc12
226         ldwx,s  $acc10($tbl),$acc10
227         _srm    $s0,16,$acc13
228         ldwx,s  $acc11($tbl),$acc11
229         _srm    $s1,8,$acc14
230         ldwx,s  $acc12($tbl),$acc12
231         _srm    $s2,0,$acc15
232         ldwx,s  $acc13($tbl),$acc13
233         ldwx,s  $acc14($tbl),$acc14
234         ldwx,s  $acc15($tbl),$acc15
235         addib,= -1,$rounds,L\$enc_last
236         ldo     32($key),$key
237
238                 _ror    $acc1,8,$acc1
239                 xor     $acc0,$t0,$t0
240         ldw     0($key),$s0
241                 _ror    $acc2,16,$acc2
242                 xor     $acc1,$t0,$t0
243         ldw     4($key),$s1
244                 _ror    $acc3,24,$acc3
245                 xor     $acc2,$t0,$t0
246         ldw     8($key),$s2
247                 _ror    $acc5,8,$acc5
248                 xor     $acc3,$t0,$t0
249         ldw     12($key),$s3
250                 _ror    $acc6,16,$acc6
251                 xor     $acc4,$t1,$t1
252                 _ror    $acc7,24,$acc7
253                 xor     $acc5,$t1,$t1
254                 _ror    $acc9,8,$acc9
255                 xor     $acc6,$t1,$t1
256                 _ror    $acc10,16,$acc10
257                 xor     $acc7,$t1,$t1
258                 _ror    $acc11,24,$acc11
259                 xor     $acc8,$t2,$t2
260                 _ror    $acc13,8,$acc13
261                 xor     $acc9,$t2,$t2
262                 _ror    $acc14,16,$acc14
263                 xor     $acc10,$t2,$t2
264                 _ror    $acc15,24,$acc15
265                 xor     $acc11,$t2,$t2
266                 xor     $acc12,$acc14,$acc14
267                 xor     $acc13,$t3,$t3
268         _srm    $t0,24,$acc0
269                 xor     $acc14,$t3,$t3
270         _srm    $t1,16,$acc1
271                 xor     $acc15,$t3,$t3
272
273         _srm    $t2,8,$acc2
274         ldwx,s  $acc0($tbl),$acc0
275         _srm    $t3,0,$acc3
276         ldwx,s  $acc1($tbl),$acc1
277         _srm    $t1,24,$acc4
278         ldwx,s  $acc2($tbl),$acc2
279         _srm    $t2,16,$acc5
280         ldwx,s  $acc3($tbl),$acc3
281         _srm    $t3,8,$acc6
282         ldwx,s  $acc4($tbl),$acc4
283         _srm    $t0,0,$acc7
284         ldwx,s  $acc5($tbl),$acc5
285         _srm    $t2,24,$acc8
286         ldwx,s  $acc6($tbl),$acc6
287         _srm    $t3,16,$acc9
288         ldwx,s  $acc7($tbl),$acc7
289         _srm    $t0,8,$acc10
290         ldwx,s  $acc8($tbl),$acc8
291         _srm    $t1,0,$acc11
292         ldwx,s  $acc9($tbl),$acc9
293         _srm    $t3,24,$acc12
294         ldwx,s  $acc10($tbl),$acc10
295         _srm    $t0,16,$acc13
296         ldwx,s  $acc11($tbl),$acc11
297         _srm    $t1,8,$acc14
298         ldwx,s  $acc12($tbl),$acc12
299         _srm    $t2,0,$acc15
300         ldwx,s  $acc13($tbl),$acc13
301                 _ror    $acc1,8,$acc1
302         ldwx,s  $acc14($tbl),$acc14
303
304                 _ror    $acc2,16,$acc2
305                 xor     $acc0,$s0,$s0
306         ldwx,s  $acc15($tbl),$acc15
307                 _ror    $acc3,24,$acc3
308                 xor     $acc1,$s0,$s0
309         ldw     16($key),$t0
310                 _ror    $acc5,8,$acc5
311                 xor     $acc2,$s0,$s0
312         ldw     20($key),$t1
313                 _ror    $acc6,16,$acc6
314                 xor     $acc3,$s0,$s0
315         ldw     24($key),$t2
316                 _ror    $acc7,24,$acc7
317                 xor     $acc4,$s1,$s1
318         ldw     28($key),$t3
319                 _ror    $acc9,8,$acc9
320                 xor     $acc5,$s1,$s1
321         ldw     1024+0($tbl),%r0                ; prefetch te4
322                 _ror    $acc10,16,$acc10
323                 xor     $acc6,$s1,$s1
324         ldw     1024+32($tbl),%r0               ; prefetch te4
325                 _ror    $acc11,24,$acc11
326                 xor     $acc7,$s1,$s1
327         ldw     1024+64($tbl),%r0               ; prefetch te4
328                 _ror    $acc13,8,$acc13
329                 xor     $acc8,$s2,$s2
330         ldw     1024+96($tbl),%r0               ; prefetch te4
331                 _ror    $acc14,16,$acc14
332                 xor     $acc9,$s2,$s2
333         ldw     1024+128($tbl),%r0              ; prefetch te4
334                 _ror    $acc15,24,$acc15
335                 xor     $acc10,$s2,$s2
336         ldw     1024+160($tbl),%r0              ; prefetch te4
337         _srm    $s0,24,$acc0
338                 xor     $acc11,$s2,$s2
339         ldw     1024+192($tbl),%r0              ; prefetch te4
340                 xor     $acc12,$acc14,$acc14
341                 xor     $acc13,$s3,$s3
342         ldw     1024+224($tbl),%r0              ; prefetch te4
343         _srm    $s1,16,$acc1
344                 xor     $acc14,$s3,$s3
345         b       L\$enc_loop
346                 xor     $acc15,$s3,$s3
347
348         .ALIGN  16
349 L\$enc_last
350         ldo     1024($tbl),$rounds
351                 _ror    $acc1,8,$acc1
352                 xor     $acc0,$t0,$t0
353         ldw     0($key),$s0
354                 _ror    $acc2,16,$acc2
355                 xor     $acc1,$t0,$t0
356         ldw     4($key),$s1
357                 _ror    $acc3,24,$acc3
358                 xor     $acc2,$t0,$t0
359         ldw     8($key),$s2
360                 _ror    $acc5,8,$acc5
361                 xor     $acc3,$t0,$t0
362         ldw     12($key),$s3
363                 _ror    $acc6,16,$acc6
364                 xor     $acc4,$t1,$t1
365                 _ror    $acc7,24,$acc7
366                 xor     $acc5,$t1,$t1
367                 _ror    $acc9,8,$acc9
368                 xor     $acc6,$t1,$t1
369                 _ror    $acc10,16,$acc10
370                 xor     $acc7,$t1,$t1
371                 _ror    $acc11,24,$acc11
372                 xor     $acc8,$t2,$t2
373                 _ror    $acc13,8,$acc13
374                 xor     $acc9,$t2,$t2
375                 _ror    $acc14,16,$acc14
376                 xor     $acc10,$t2,$t2
377                 _ror    $acc15,24,$acc15
378                 xor     $acc11,$t2,$t2
379                 xor     $acc12,$acc14,$acc14
380                 xor     $acc13,$t3,$t3
381         _srm    $t0,24,$acc0
382                 xor     $acc14,$t3,$t3
383         _srm    $t1,16,$acc1
384                 xor     $acc15,$t3,$t3
385
386         _srm    $t2,8,$acc2
387         ldbx    $acc0($rounds),$acc0
388         _srm    $t1,24,$acc4
389         ldbx    $acc1($rounds),$acc1
390         _srm    $t2,16,$acc5
391         _srm    $t3,0,$acc3
392         ldbx    $acc2($rounds),$acc2
393         ldbx    $acc3($rounds),$acc3
394         _srm    $t3,8,$acc6
395         ldbx    $acc4($rounds),$acc4
396         _srm    $t2,24,$acc8
397         ldbx    $acc5($rounds),$acc5
398         _srm    $t3,16,$acc9
399         _srm    $t0,0,$acc7
400         ldbx    $acc6($rounds),$acc6
401         ldbx    $acc7($rounds),$acc7
402         _srm    $t0,8,$acc10
403         ldbx    $acc8($rounds),$acc8
404         _srm    $t3,24,$acc12
405         ldbx    $acc9($rounds),$acc9
406         _srm    $t0,16,$acc13
407         _srm    $t1,0,$acc11
408         ldbx    $acc10($rounds),$acc10
409         _srm    $t1,8,$acc14
410         ldbx    $acc11($rounds),$acc11
411         ldbx    $acc12($rounds),$acc12
412         ldbx    $acc13($rounds),$acc13
413         _srm    $t2,0,$acc15
414         ldbx    $acc14($rounds),$acc14
415
416                 dep     $acc0,7,8,$acc3
417         ldbx    $acc15($rounds),$acc15
418                 dep     $acc4,7,8,$acc7
419                 dep     $acc1,15,8,$acc3
420                 dep     $acc5,15,8,$acc7
421                 dep     $acc2,23,8,$acc3
422                 dep     $acc6,23,8,$acc7
423                 xor     $acc3,$s0,$s0
424                 xor     $acc7,$s1,$s1
425                 dep     $acc8,7,8,$acc11
426                 dep     $acc12,7,8,$acc15
427                 dep     $acc9,15,8,$acc11
428                 dep     $acc13,15,8,$acc15
429                 dep     $acc10,23,8,$acc11
430                 dep     $acc14,23,8,$acc15
431                 xor     $acc11,$s2,$s2
432
433         bv      (%r31)
434         .EXIT
435                 xor     $acc15,$s3,$s3
436         .PROCEND
437
438         .ALIGN  64
439 L\$AES_Te
440         .WORD   0xc66363a5, 0xf87c7c84, 0xee777799, 0xf67b7b8d
441         .WORD   0xfff2f20d, 0xd66b6bbd, 0xde6f6fb1, 0x91c5c554
442         .WORD   0x60303050, 0x02010103, 0xce6767a9, 0x562b2b7d
443         .WORD   0xe7fefe19, 0xb5d7d762, 0x4dababe6, 0xec76769a
444         .WORD   0x8fcaca45, 0x1f82829d, 0x89c9c940, 0xfa7d7d87
445         .WORD   0xeffafa15, 0xb25959eb, 0x8e4747c9, 0xfbf0f00b
446         .WORD   0x41adadec, 0xb3d4d467, 0x5fa2a2fd, 0x45afafea
447         .WORD   0x239c9cbf, 0x53a4a4f7, 0xe4727296, 0x9bc0c05b
448         .WORD   0x75b7b7c2, 0xe1fdfd1c, 0x3d9393ae, 0x4c26266a
449         .WORD   0x6c36365a, 0x7e3f3f41, 0xf5f7f702, 0x83cccc4f
450         .WORD   0x6834345c, 0x51a5a5f4, 0xd1e5e534, 0xf9f1f108
451         .WORD   0xe2717193, 0xabd8d873, 0x62313153, 0x2a15153f
452         .WORD   0x0804040c, 0x95c7c752, 0x46232365, 0x9dc3c35e
453         .WORD   0x30181828, 0x379696a1, 0x0a05050f, 0x2f9a9ab5
454         .WORD   0x0e070709, 0x24121236, 0x1b80809b, 0xdfe2e23d
455         .WORD   0xcdebeb26, 0x4e272769, 0x7fb2b2cd, 0xea75759f
456         .WORD   0x1209091b, 0x1d83839e, 0x582c2c74, 0x341a1a2e
457         .WORD   0x361b1b2d, 0xdc6e6eb2, 0xb45a5aee, 0x5ba0a0fb
458         .WORD   0xa45252f6, 0x763b3b4d, 0xb7d6d661, 0x7db3b3ce
459         .WORD   0x5229297b, 0xdde3e33e, 0x5e2f2f71, 0x13848497
460         .WORD   0xa65353f5, 0xb9d1d168, 0x00000000, 0xc1eded2c
461         .WORD   0x40202060, 0xe3fcfc1f, 0x79b1b1c8, 0xb65b5bed
462         .WORD   0xd46a6abe, 0x8dcbcb46, 0x67bebed9, 0x7239394b
463         .WORD   0x944a4ade, 0x984c4cd4, 0xb05858e8, 0x85cfcf4a
464         .WORD   0xbbd0d06b, 0xc5efef2a, 0x4faaaae5, 0xedfbfb16
465         .WORD   0x864343c5, 0x9a4d4dd7, 0x66333355, 0x11858594
466         .WORD   0x8a4545cf, 0xe9f9f910, 0x04020206, 0xfe7f7f81
467         .WORD   0xa05050f0, 0x783c3c44, 0x259f9fba, 0x4ba8a8e3
468         .WORD   0xa25151f3, 0x5da3a3fe, 0x804040c0, 0x058f8f8a
469         .WORD   0x3f9292ad, 0x219d9dbc, 0x70383848, 0xf1f5f504
470         .WORD   0x63bcbcdf, 0x77b6b6c1, 0xafdada75, 0x42212163
471         .WORD   0x20101030, 0xe5ffff1a, 0xfdf3f30e, 0xbfd2d26d
472         .WORD   0x81cdcd4c, 0x180c0c14, 0x26131335, 0xc3ecec2f
473         .WORD   0xbe5f5fe1, 0x359797a2, 0x884444cc, 0x2e171739
474         .WORD   0x93c4c457, 0x55a7a7f2, 0xfc7e7e82, 0x7a3d3d47
475         .WORD   0xc86464ac, 0xba5d5de7, 0x3219192b, 0xe6737395
476         .WORD   0xc06060a0, 0x19818198, 0x9e4f4fd1, 0xa3dcdc7f
477         .WORD   0x44222266, 0x542a2a7e, 0x3b9090ab, 0x0b888883
478         .WORD   0x8c4646ca, 0xc7eeee29, 0x6bb8b8d3, 0x2814143c
479         .WORD   0xa7dede79, 0xbc5e5ee2, 0x160b0b1d, 0xaddbdb76
480         .WORD   0xdbe0e03b, 0x64323256, 0x743a3a4e, 0x140a0a1e
481         .WORD   0x924949db, 0x0c06060a, 0x4824246c, 0xb85c5ce4
482         .WORD   0x9fc2c25d, 0xbdd3d36e, 0x43acacef, 0xc46262a6
483         .WORD   0x399191a8, 0x319595a4, 0xd3e4e437, 0xf279798b
484         .WORD   0xd5e7e732, 0x8bc8c843, 0x6e373759, 0xda6d6db7
485         .WORD   0x018d8d8c, 0xb1d5d564, 0x9c4e4ed2, 0x49a9a9e0
486         .WORD   0xd86c6cb4, 0xac5656fa, 0xf3f4f407, 0xcfeaea25
487         .WORD   0xca6565af, 0xf47a7a8e, 0x47aeaee9, 0x10080818
488         .WORD   0x6fbabad5, 0xf0787888, 0x4a25256f, 0x5c2e2e72
489         .WORD   0x381c1c24, 0x57a6a6f1, 0x73b4b4c7, 0x97c6c651
490         .WORD   0xcbe8e823, 0xa1dddd7c, 0xe874749c, 0x3e1f1f21
491         .WORD   0x964b4bdd, 0x61bdbddc, 0x0d8b8b86, 0x0f8a8a85
492         .WORD   0xe0707090, 0x7c3e3e42, 0x71b5b5c4, 0xcc6666aa
493         .WORD   0x904848d8, 0x06030305, 0xf7f6f601, 0x1c0e0e12
494         .WORD   0xc26161a3, 0x6a35355f, 0xae5757f9, 0x69b9b9d0
495         .WORD   0x17868691, 0x99c1c158, 0x3a1d1d27, 0x279e9eb9
496         .WORD   0xd9e1e138, 0xebf8f813, 0x2b9898b3, 0x22111133
497         .WORD   0xd26969bb, 0xa9d9d970, 0x078e8e89, 0x339494a7
498         .WORD   0x2d9b9bb6, 0x3c1e1e22, 0x15878792, 0xc9e9e920
499         .WORD   0x87cece49, 0xaa5555ff, 0x50282878, 0xa5dfdf7a
500         .WORD   0x038c8c8f, 0x59a1a1f8, 0x09898980, 0x1a0d0d17
501         .WORD   0x65bfbfda, 0xd7e6e631, 0x844242c6, 0xd06868b8
502         .WORD   0x824141c3, 0x299999b0, 0x5a2d2d77, 0x1e0f0f11
503         .WORD   0x7bb0b0cb, 0xa85454fc, 0x6dbbbbd6, 0x2c16163a
504         .BYTE   0x63, 0x7c, 0x77, 0x7b, 0xf2, 0x6b, 0x6f, 0xc5
505         .BYTE   0x30, 0x01, 0x67, 0x2b, 0xfe, 0xd7, 0xab, 0x76
506         .BYTE   0xca, 0x82, 0xc9, 0x7d, 0xfa, 0x59, 0x47, 0xf0
507         .BYTE   0xad, 0xd4, 0xa2, 0xaf, 0x9c, 0xa4, 0x72, 0xc0
508         .BYTE   0xb7, 0xfd, 0x93, 0x26, 0x36, 0x3f, 0xf7, 0xcc
509         .BYTE   0x34, 0xa5, 0xe5, 0xf1, 0x71, 0xd8, 0x31, 0x15
510         .BYTE   0x04, 0xc7, 0x23, 0xc3, 0x18, 0x96, 0x05, 0x9a
511         .BYTE   0x07, 0x12, 0x80, 0xe2, 0xeb, 0x27, 0xb2, 0x75
512         .BYTE   0x09, 0x83, 0x2c, 0x1a, 0x1b, 0x6e, 0x5a, 0xa0
513         .BYTE   0x52, 0x3b, 0xd6, 0xb3, 0x29, 0xe3, 0x2f, 0x84
514         .BYTE   0x53, 0xd1, 0x00, 0xed, 0x20, 0xfc, 0xb1, 0x5b
515         .BYTE   0x6a, 0xcb, 0xbe, 0x39, 0x4a, 0x4c, 0x58, 0xcf
516         .BYTE   0xd0, 0xef, 0xaa, 0xfb, 0x43, 0x4d, 0x33, 0x85
517         .BYTE   0x45, 0xf9, 0x02, 0x7f, 0x50, 0x3c, 0x9f, 0xa8
518         .BYTE   0x51, 0xa3, 0x40, 0x8f, 0x92, 0x9d, 0x38, 0xf5
519         .BYTE   0xbc, 0xb6, 0xda, 0x21, 0x10, 0xff, 0xf3, 0xd2
520         .BYTE   0xcd, 0x0c, 0x13, 0xec, 0x5f, 0x97, 0x44, 0x17
521         .BYTE   0xc4, 0xa7, 0x7e, 0x3d, 0x64, 0x5d, 0x19, 0x73
522         .BYTE   0x60, 0x81, 0x4f, 0xdc, 0x22, 0x2a, 0x90, 0x88
523         .BYTE   0x46, 0xee, 0xb8, 0x14, 0xde, 0x5e, 0x0b, 0xdb
524         .BYTE   0xe0, 0x32, 0x3a, 0x0a, 0x49, 0x06, 0x24, 0x5c
525         .BYTE   0xc2, 0xd3, 0xac, 0x62, 0x91, 0x95, 0xe4, 0x79
526         .BYTE   0xe7, 0xc8, 0x37, 0x6d, 0x8d, 0xd5, 0x4e, 0xa9
527         .BYTE   0x6c, 0x56, 0xf4, 0xea, 0x65, 0x7a, 0xae, 0x08
528         .BYTE   0xba, 0x78, 0x25, 0x2e, 0x1c, 0xa6, 0xb4, 0xc6
529         .BYTE   0xe8, 0xdd, 0x74, 0x1f, 0x4b, 0xbd, 0x8b, 0x8a
530         .BYTE   0x70, 0x3e, 0xb5, 0x66, 0x48, 0x03, 0xf6, 0x0e
531         .BYTE   0x61, 0x35, 0x57, 0xb9, 0x86, 0xc1, 0x1d, 0x9e
532         .BYTE   0xe1, 0xf8, 0x98, 0x11, 0x69, 0xd9, 0x8e, 0x94
533         .BYTE   0x9b, 0x1e, 0x87, 0xe9, 0xce, 0x55, 0x28, 0xdf
534         .BYTE   0x8c, 0xa1, 0x89, 0x0d, 0xbf, 0xe6, 0x42, 0x68
535         .BYTE   0x41, 0x99, 0x2d, 0x0f, 0xb0, 0x54, 0xbb, 0x16
536 ___
537
538 $code.=<<___;
539         .EXPORT AES_decrypt,ENTRY,ARGW0=GR,ARGW1=GR,ARGW2=GR
540         .ALIGN  16
541 AES_decrypt
542         .PROC
543         .CALLINFO       FRAME=`$FRAME-16*$SIZE_T`,NO_CALLS,SAVE_RP,ENTRY_GR=18
544         .ENTRY
545         $PUSH   %r2,-$SAVED_RP(%sp)     ; standard prologue
546         $PUSHMA %r3,$FRAME(%sp)
547         $PUSH   %r4,`-$FRAME+1*$SIZE_T`(%sp)
548         $PUSH   %r5,`-$FRAME+2*$SIZE_T`(%sp)
549         $PUSH   %r6,`-$FRAME+3*$SIZE_T`(%sp)
550         $PUSH   %r7,`-$FRAME+4*$SIZE_T`(%sp)
551         $PUSH   %r8,`-$FRAME+5*$SIZE_T`(%sp)
552         $PUSH   %r9,`-$FRAME+6*$SIZE_T`(%sp)
553         $PUSH   %r10,`-$FRAME+7*$SIZE_T`(%sp)
554         $PUSH   %r11,`-$FRAME+8*$SIZE_T`(%sp)
555         $PUSH   %r12,`-$FRAME+9*$SIZE_T`(%sp)
556         $PUSH   %r13,`-$FRAME+10*$SIZE_T`(%sp)
557         $PUSH   %r14,`-$FRAME+11*$SIZE_T`(%sp)
558         $PUSH   %r15,`-$FRAME+12*$SIZE_T`(%sp)
559         $PUSH   %r16,`-$FRAME+13*$SIZE_T`(%sp)
560         $PUSH   %r17,`-$FRAME+14*$SIZE_T`(%sp)
561         $PUSH   %r18,`-$FRAME+15*$SIZE_T`(%sp)
562
563         blr     %r0,$tbl
564         ldi     3,$t0
565 L\$dec_pic
566         andcm   $tbl,$t0,$tbl
567         ldo     L\$AES_Td-L\$dec_pic($tbl),$tbl
568
569         and     $inp,$t0,$t0
570         sub     $inp,$t0,$inp
571         ldw     0($inp),$s0
572         ldw     4($inp),$s1
573         ldw     8($inp),$s2
574         comib,= 0,$t0,L\$dec_inp_aligned
575         ldw     12($inp),$s3
576
577         sh3addl $t0,%r0,$t0
578         subi    32,$t0,$t0
579         mtctl   $t0,%cr11
580         ldw     16($inp),$t1
581         vshd    $s0,$s1,$s0
582         vshd    $s1,$s2,$s1
583         vshd    $s2,$s3,$s2
584         vshd    $s3,$t1,$s3
585
586 L\$dec_inp_aligned
587         bl      _parisc_AES_decrypt,%r31
588         nop
589
590         extru,<> $out,31,2,%r0
591         b       L\$dec_out_aligned
592         nop
593
594         _srm    $s0,24,$acc0
595         _srm    $s0,16,$acc1
596         stb     $acc0,0($out)
597         _srm    $s0,8,$acc2
598         stb     $acc1,1($out)
599         _srm    $s1,24,$acc4
600         stb     $acc2,2($out)
601         _srm    $s1,16,$acc5
602         stb     $s0,3($out)
603         _srm    $s1,8,$acc6
604         stb     $acc4,4($out)
605         _srm    $s2,24,$acc0
606         stb     $acc5,5($out)
607         _srm    $s2,16,$acc1
608         stb     $acc6,6($out)
609         _srm    $s2,8,$acc2
610         stb     $s1,7($out)
611         _srm    $s3,24,$acc4
612         stb     $acc0,8($out)
613         _srm    $s3,16,$acc5
614         stb     $acc1,9($out)
615         _srm    $s3,8,$acc6
616         stb     $acc2,10($out)
617         stb     $s2,11($out)
618         stb     $acc4,12($out)
619         stb     $acc5,13($out)
620         stb     $acc6,14($out)
621         b       L\$dec_done
622         stb     $s3,15($out)
623
624 L\$dec_out_aligned
625         stw     $s0,0($out)
626         stw     $s1,4($out)
627         stw     $s2,8($out)
628         stw     $s3,12($out)
629
630 L\$dec_done
631         $POP    `-$FRAME-$SAVED_RP`(%sp),%r2    ; standard epilogue
632         $POP    `-$FRAME+1*$SIZE_T`(%sp),%r4
633         $POP    `-$FRAME+2*$SIZE_T`(%sp),%r5
634         $POP    `-$FRAME+3*$SIZE_T`(%sp),%r6
635         $POP    `-$FRAME+4*$SIZE_T`(%sp),%r7
636         $POP    `-$FRAME+5*$SIZE_T`(%sp),%r8
637         $POP    `-$FRAME+6*$SIZE_T`(%sp),%r9
638         $POP    `-$FRAME+7*$SIZE_T`(%sp),%r10
639         $POP    `-$FRAME+8*$SIZE_T`(%sp),%r11
640         $POP    `-$FRAME+9*$SIZE_T`(%sp),%r12
641         $POP    `-$FRAME+10*$SIZE_T`(%sp),%r13
642         $POP    `-$FRAME+11*$SIZE_T`(%sp),%r14
643         $POP    `-$FRAME+12*$SIZE_T`(%sp),%r15
644         $POP    `-$FRAME+13*$SIZE_T`(%sp),%r16
645         $POP    `-$FRAME+14*$SIZE_T`(%sp),%r17
646         $POP    `-$FRAME+15*$SIZE_T`(%sp),%r18
647         bv      (%r2)
648         .EXIT
649         $POPMB  -$FRAME(%sp),%r3
650         .PROCEND
651
652         .ALIGN  16
653 _parisc_AES_decrypt
654         .PROC
655         .CALLINFO       MILLICODE
656         .ENTRY
657         ldw     240($key),$rounds
658         ldw     0($key),$t0
659         ldw     4($key),$t1
660         ldw     8($key),$t2
661         ldw     12($key),$t3
662         _srm    $rounds,1,$rounds
663         xor     $t0,$s0,$s0
664         ldw     16($key),$t0
665         xor     $t1,$s1,$s1
666         ldw     20($key),$t1
667         _srm    $s0,24,$acc0
668         xor     $t2,$s2,$s2
669         ldw     24($key),$t2
670         xor     $t3,$s3,$s3
671         ldw     28($key),$t3
672         _srm    $s3,16,$acc1
673 L\$dec_loop
674         _srm    $s2,8,$acc2
675         ldwx,s  $acc0($tbl),$acc0
676         _srm    $s1,0,$acc3
677         ldwx,s  $acc1($tbl),$acc1
678         _srm    $s1,24,$acc4
679         ldwx,s  $acc2($tbl),$acc2
680         _srm    $s0,16,$acc5
681         ldwx,s  $acc3($tbl),$acc3
682         _srm    $s3,8,$acc6
683         ldwx,s  $acc4($tbl),$acc4
684         _srm    $s2,0,$acc7
685         ldwx,s  $acc5($tbl),$acc5
686         _srm    $s2,24,$acc8
687         ldwx,s  $acc6($tbl),$acc6
688         _srm    $s1,16,$acc9
689         ldwx,s  $acc7($tbl),$acc7
690         _srm    $s0,8,$acc10
691         ldwx,s  $acc8($tbl),$acc8
692         _srm    $s3,0,$acc11
693         ldwx,s  $acc9($tbl),$acc9
694         _srm    $s3,24,$acc12
695         ldwx,s  $acc10($tbl),$acc10
696         _srm    $s2,16,$acc13
697         ldwx,s  $acc11($tbl),$acc11
698         _srm    $s1,8,$acc14
699         ldwx,s  $acc12($tbl),$acc12
700         _srm    $s0,0,$acc15
701         ldwx,s  $acc13($tbl),$acc13
702         ldwx,s  $acc14($tbl),$acc14
703         ldwx,s  $acc15($tbl),$acc15
704         addib,= -1,$rounds,L\$dec_last
705         ldo     32($key),$key
706
707                 _ror    $acc1,8,$acc1
708                 xor     $acc0,$t0,$t0
709         ldw     0($key),$s0
710                 _ror    $acc2,16,$acc2
711                 xor     $acc1,$t0,$t0
712         ldw     4($key),$s1
713                 _ror    $acc3,24,$acc3
714                 xor     $acc2,$t0,$t0
715         ldw     8($key),$s2
716                 _ror    $acc5,8,$acc5
717                 xor     $acc3,$t0,$t0
718         ldw     12($key),$s3
719                 _ror    $acc6,16,$acc6
720                 xor     $acc4,$t1,$t1
721                 _ror    $acc7,24,$acc7
722                 xor     $acc5,$t1,$t1
723                 _ror    $acc9,8,$acc9
724                 xor     $acc6,$t1,$t1
725                 _ror    $acc10,16,$acc10
726                 xor     $acc7,$t1,$t1
727                 _ror    $acc11,24,$acc11
728                 xor     $acc8,$t2,$t2
729                 _ror    $acc13,8,$acc13
730                 xor     $acc9,$t2,$t2
731                 _ror    $acc14,16,$acc14
732                 xor     $acc10,$t2,$t2
733                 _ror    $acc15,24,$acc15
734                 xor     $acc11,$t2,$t2
735                 xor     $acc12,$acc14,$acc14
736                 xor     $acc13,$t3,$t3
737         _srm    $t0,24,$acc0
738                 xor     $acc14,$t3,$t3
739                 xor     $acc15,$t3,$t3
740         _srm    $t3,16,$acc1
741
742         _srm    $t2,8,$acc2
743         ldwx,s  $acc0($tbl),$acc0
744         _srm    $t1,0,$acc3
745         ldwx,s  $acc1($tbl),$acc1
746         _srm    $t1,24,$acc4
747         ldwx,s  $acc2($tbl),$acc2
748         _srm    $t0,16,$acc5
749         ldwx,s  $acc3($tbl),$acc3
750         _srm    $t3,8,$acc6
751         ldwx,s  $acc4($tbl),$acc4
752         _srm    $t2,0,$acc7
753         ldwx,s  $acc5($tbl),$acc5
754         _srm    $t2,24,$acc8
755         ldwx,s  $acc6($tbl),$acc6
756         _srm    $t1,16,$acc9
757         ldwx,s  $acc7($tbl),$acc7
758         _srm    $t0,8,$acc10
759         ldwx,s  $acc8($tbl),$acc8
760         _srm    $t3,0,$acc11
761         ldwx,s  $acc9($tbl),$acc9
762         _srm    $t3,24,$acc12
763         ldwx,s  $acc10($tbl),$acc10
764         _srm    $t2,16,$acc13
765         ldwx,s  $acc11($tbl),$acc11
766         _srm    $t1,8,$acc14
767         ldwx,s  $acc12($tbl),$acc12
768         _srm    $t0,0,$acc15
769         ldwx,s  $acc13($tbl),$acc13
770                 _ror    $acc1,8,$acc1
771         ldwx,s  $acc14($tbl),$acc14
772
773                 _ror    $acc2,16,$acc2
774                 xor     $acc0,$s0,$s0
775         ldwx,s  $acc15($tbl),$acc15
776                 _ror    $acc3,24,$acc3
777                 xor     $acc1,$s0,$s0
778         ldw     16($key),$t0
779                 _ror    $acc5,8,$acc5
780                 xor     $acc2,$s0,$s0
781         ldw     20($key),$t1
782                 _ror    $acc6,16,$acc6
783                 xor     $acc3,$s0,$s0
784         ldw     24($key),$t2
785                 _ror    $acc7,24,$acc7
786                 xor     $acc4,$s1,$s1
787         ldw     28($key),$t3
788                 _ror    $acc9,8,$acc9
789                 xor     $acc5,$s1,$s1
790         ldw     1024+0($tbl),%r0                ; prefetch td4
791                 _ror    $acc10,16,$acc10
792                 xor     $acc6,$s1,$s1
793         ldw     1024+32($tbl),%r0               ; prefetch td4
794                 _ror    $acc11,24,$acc11
795                 xor     $acc7,$s1,$s1
796         ldw     1024+64($tbl),%r0               ; prefetch td4
797                 _ror    $acc13,8,$acc13
798                 xor     $acc8,$s2,$s2
799         ldw     1024+96($tbl),%r0               ; prefetch td4
800                 _ror    $acc14,16,$acc14
801                 xor     $acc9,$s2,$s2
802         ldw     1024+128($tbl),%r0              ; prefetch td4
803                 _ror    $acc15,24,$acc15
804                 xor     $acc10,$s2,$s2
805         ldw     1024+160($tbl),%r0              ; prefetch td4
806         _srm    $s0,24,$acc0
807                 xor     $acc11,$s2,$s2
808         ldw     1024+192($tbl),%r0              ; prefetch td4
809                 xor     $acc12,$acc14,$acc14
810                 xor     $acc13,$s3,$s3
811         ldw     1024+224($tbl),%r0              ; prefetch td4
812                 xor     $acc14,$s3,$s3
813                 xor     $acc15,$s3,$s3
814         b       L\$dec_loop
815         _srm    $s3,16,$acc1
816
817         .ALIGN  16
818 L\$dec_last
819         ldo     1024($tbl),$rounds
820                 _ror    $acc1,8,$acc1
821                 xor     $acc0,$t0,$t0
822         ldw     0($key),$s0
823                 _ror    $acc2,16,$acc2
824                 xor     $acc1,$t0,$t0
825         ldw     4($key),$s1
826                 _ror    $acc3,24,$acc3
827                 xor     $acc2,$t0,$t0
828         ldw     8($key),$s2
829                 _ror    $acc5,8,$acc5
830                 xor     $acc3,$t0,$t0
831         ldw     12($key),$s3
832                 _ror    $acc6,16,$acc6
833                 xor     $acc4,$t1,$t1
834                 _ror    $acc7,24,$acc7
835                 xor     $acc5,$t1,$t1
836                 _ror    $acc9,8,$acc9
837                 xor     $acc6,$t1,$t1
838                 _ror    $acc10,16,$acc10
839                 xor     $acc7,$t1,$t1
840                 _ror    $acc11,24,$acc11
841                 xor     $acc8,$t2,$t2
842                 _ror    $acc13,8,$acc13
843                 xor     $acc9,$t2,$t2
844                 _ror    $acc14,16,$acc14
845                 xor     $acc10,$t2,$t2
846                 _ror    $acc15,24,$acc15
847                 xor     $acc11,$t2,$t2
848                 xor     $acc12,$acc14,$acc14
849                 xor     $acc13,$t3,$t3
850         _srm    $t0,24,$acc0
851                 xor     $acc14,$t3,$t3
852                 xor     $acc15,$t3,$t3
853         _srm    $t3,16,$acc1
854
855         _srm    $t2,8,$acc2
856         ldbx    $acc0($rounds),$acc0
857         _srm    $t1,24,$acc4
858         ldbx    $acc1($rounds),$acc1
859         _srm    $t0,16,$acc5
860         _srm    $t1,0,$acc3
861         ldbx    $acc2($rounds),$acc2
862         ldbx    $acc3($rounds),$acc3
863         _srm    $t3,8,$acc6
864         ldbx    $acc4($rounds),$acc4
865         _srm    $t2,24,$acc8
866         ldbx    $acc5($rounds),$acc5
867         _srm    $t1,16,$acc9
868         _srm    $t2,0,$acc7
869         ldbx    $acc6($rounds),$acc6
870         ldbx    $acc7($rounds),$acc7
871         _srm    $t0,8,$acc10
872         ldbx    $acc8($rounds),$acc8
873         _srm    $t3,24,$acc12
874         ldbx    $acc9($rounds),$acc9
875         _srm    $t2,16,$acc13
876         _srm    $t3,0,$acc11
877         ldbx    $acc10($rounds),$acc10
878         _srm    $t1,8,$acc14
879         ldbx    $acc11($rounds),$acc11
880         ldbx    $acc12($rounds),$acc12
881         ldbx    $acc13($rounds),$acc13
882         _srm    $t0,0,$acc15
883         ldbx    $acc14($rounds),$acc14
884
885                 dep     $acc0,7,8,$acc3
886         ldbx    $acc15($rounds),$acc15
887                 dep     $acc4,7,8,$acc7
888                 dep     $acc1,15,8,$acc3
889                 dep     $acc5,15,8,$acc7
890                 dep     $acc2,23,8,$acc3
891                 dep     $acc6,23,8,$acc7
892                 xor     $acc3,$s0,$s0
893                 xor     $acc7,$s1,$s1
894                 dep     $acc8,7,8,$acc11
895                 dep     $acc12,7,8,$acc15
896                 dep     $acc9,15,8,$acc11
897                 dep     $acc13,15,8,$acc15
898                 dep     $acc10,23,8,$acc11
899                 dep     $acc14,23,8,$acc15
900                 xor     $acc11,$s2,$s2
901
902         bv      (%r31)
903         .EXIT
904                 xor     $acc15,$s3,$s3
905         .PROCEND
906
907         .ALIGN  64
908 L\$AES_Td
909         .WORD   0x51f4a750, 0x7e416553, 0x1a17a4c3, 0x3a275e96
910         .WORD   0x3bab6bcb, 0x1f9d45f1, 0xacfa58ab, 0x4be30393
911         .WORD   0x2030fa55, 0xad766df6, 0x88cc7691, 0xf5024c25
912         .WORD   0x4fe5d7fc, 0xc52acbd7, 0x26354480, 0xb562a38f
913         .WORD   0xdeb15a49, 0x25ba1b67, 0x45ea0e98, 0x5dfec0e1
914         .WORD   0xc32f7502, 0x814cf012, 0x8d4697a3, 0x6bd3f9c6
915         .WORD   0x038f5fe7, 0x15929c95, 0xbf6d7aeb, 0x955259da
916         .WORD   0xd4be832d, 0x587421d3, 0x49e06929, 0x8ec9c844
917         .WORD   0x75c2896a, 0xf48e7978, 0x99583e6b, 0x27b971dd
918         .WORD   0xbee14fb6, 0xf088ad17, 0xc920ac66, 0x7dce3ab4
919         .WORD   0x63df4a18, 0xe51a3182, 0x97513360, 0x62537f45
920         .WORD   0xb16477e0, 0xbb6bae84, 0xfe81a01c, 0xf9082b94
921         .WORD   0x70486858, 0x8f45fd19, 0x94de6c87, 0x527bf8b7
922         .WORD   0xab73d323, 0x724b02e2, 0xe31f8f57, 0x6655ab2a
923         .WORD   0xb2eb2807, 0x2fb5c203, 0x86c57b9a, 0xd33708a5
924         .WORD   0x302887f2, 0x23bfa5b2, 0x02036aba, 0xed16825c
925         .WORD   0x8acf1c2b, 0xa779b492, 0xf307f2f0, 0x4e69e2a1
926         .WORD   0x65daf4cd, 0x0605bed5, 0xd134621f, 0xc4a6fe8a
927         .WORD   0x342e539d, 0xa2f355a0, 0x058ae132, 0xa4f6eb75
928         .WORD   0x0b83ec39, 0x4060efaa, 0x5e719f06, 0xbd6e1051
929         .WORD   0x3e218af9, 0x96dd063d, 0xdd3e05ae, 0x4de6bd46
930         .WORD   0x91548db5, 0x71c45d05, 0x0406d46f, 0x605015ff
931         .WORD   0x1998fb24, 0xd6bde997, 0x894043cc, 0x67d99e77
932         .WORD   0xb0e842bd, 0x07898b88, 0xe7195b38, 0x79c8eedb
933         .WORD   0xa17c0a47, 0x7c420fe9, 0xf8841ec9, 0x00000000
934         .WORD   0x09808683, 0x322bed48, 0x1e1170ac, 0x6c5a724e
935         .WORD   0xfd0efffb, 0x0f853856, 0x3daed51e, 0x362d3927
936         .WORD   0x0a0fd964, 0x685ca621, 0x9b5b54d1, 0x24362e3a
937         .WORD   0x0c0a67b1, 0x9357e70f, 0xb4ee96d2, 0x1b9b919e
938         .WORD   0x80c0c54f, 0x61dc20a2, 0x5a774b69, 0x1c121a16
939         .WORD   0xe293ba0a, 0xc0a02ae5, 0x3c22e043, 0x121b171d
940         .WORD   0x0e090d0b, 0xf28bc7ad, 0x2db6a8b9, 0x141ea9c8
941         .WORD   0x57f11985, 0xaf75074c, 0xee99ddbb, 0xa37f60fd
942         .WORD   0xf701269f, 0x5c72f5bc, 0x44663bc5, 0x5bfb7e34
943         .WORD   0x8b432976, 0xcb23c6dc, 0xb6edfc68, 0xb8e4f163
944         .WORD   0xd731dcca, 0x42638510, 0x13972240, 0x84c61120
945         .WORD   0x854a247d, 0xd2bb3df8, 0xaef93211, 0xc729a16d
946         .WORD   0x1d9e2f4b, 0xdcb230f3, 0x0d8652ec, 0x77c1e3d0
947         .WORD   0x2bb3166c, 0xa970b999, 0x119448fa, 0x47e96422
948         .WORD   0xa8fc8cc4, 0xa0f03f1a, 0x567d2cd8, 0x223390ef
949         .WORD   0x87494ec7, 0xd938d1c1, 0x8ccaa2fe, 0x98d40b36
950         .WORD   0xa6f581cf, 0xa57ade28, 0xdab78e26, 0x3fadbfa4
951         .WORD   0x2c3a9de4, 0x5078920d, 0x6a5fcc9b, 0x547e4662
952         .WORD   0xf68d13c2, 0x90d8b8e8, 0x2e39f75e, 0x82c3aff5
953         .WORD   0x9f5d80be, 0x69d0937c, 0x6fd52da9, 0xcf2512b3
954         .WORD   0xc8ac993b, 0x10187da7, 0xe89c636e, 0xdb3bbb7b
955         .WORD   0xcd267809, 0x6e5918f4, 0xec9ab701, 0x834f9aa8
956         .WORD   0xe6956e65, 0xaaffe67e, 0x21bccf08, 0xef15e8e6
957         .WORD   0xbae79bd9, 0x4a6f36ce, 0xea9f09d4, 0x29b07cd6
958         .WORD   0x31a4b2af, 0x2a3f2331, 0xc6a59430, 0x35a266c0
959         .WORD   0x744ebc37, 0xfc82caa6, 0xe090d0b0, 0x33a7d815
960         .WORD   0xf104984a, 0x41ecdaf7, 0x7fcd500e, 0x1791f62f
961         .WORD   0x764dd68d, 0x43efb04d, 0xccaa4d54, 0xe49604df
962         .WORD   0x9ed1b5e3, 0x4c6a881b, 0xc12c1fb8, 0x4665517f
963         .WORD   0x9d5eea04, 0x018c355d, 0xfa877473, 0xfb0b412e
964         .WORD   0xb3671d5a, 0x92dbd252, 0xe9105633, 0x6dd64713
965         .WORD   0x9ad7618c, 0x37a10c7a, 0x59f8148e, 0xeb133c89
966         .WORD   0xcea927ee, 0xb761c935, 0xe11ce5ed, 0x7a47b13c
967         .WORD   0x9cd2df59, 0x55f2733f, 0x1814ce79, 0x73c737bf
968         .WORD   0x53f7cdea, 0x5ffdaa5b, 0xdf3d6f14, 0x7844db86
969         .WORD   0xcaaff381, 0xb968c43e, 0x3824342c, 0xc2a3405f
970         .WORD   0x161dc372, 0xbce2250c, 0x283c498b, 0xff0d9541
971         .WORD   0x39a80171, 0x080cb3de, 0xd8b4e49c, 0x6456c190
972         .WORD   0x7bcb8461, 0xd532b670, 0x486c5c74, 0xd0b85742
973         .BYTE   0x52, 0x09, 0x6a, 0xd5, 0x30, 0x36, 0xa5, 0x38
974         .BYTE   0xbf, 0x40, 0xa3, 0x9e, 0x81, 0xf3, 0xd7, 0xfb
975         .BYTE   0x7c, 0xe3, 0x39, 0x82, 0x9b, 0x2f, 0xff, 0x87
976         .BYTE   0x34, 0x8e, 0x43, 0x44, 0xc4, 0xde, 0xe9, 0xcb
977         .BYTE   0x54, 0x7b, 0x94, 0x32, 0xa6, 0xc2, 0x23, 0x3d
978         .BYTE   0xee, 0x4c, 0x95, 0x0b, 0x42, 0xfa, 0xc3, 0x4e
979         .BYTE   0x08, 0x2e, 0xa1, 0x66, 0x28, 0xd9, 0x24, 0xb2
980         .BYTE   0x76, 0x5b, 0xa2, 0x49, 0x6d, 0x8b, 0xd1, 0x25
981         .BYTE   0x72, 0xf8, 0xf6, 0x64, 0x86, 0x68, 0x98, 0x16
982         .BYTE   0xd4, 0xa4, 0x5c, 0xcc, 0x5d, 0x65, 0xb6, 0x92
983         .BYTE   0x6c, 0x70, 0x48, 0x50, 0xfd, 0xed, 0xb9, 0xda
984         .BYTE   0x5e, 0x15, 0x46, 0x57, 0xa7, 0x8d, 0x9d, 0x84
985         .BYTE   0x90, 0xd8, 0xab, 0x00, 0x8c, 0xbc, 0xd3, 0x0a
986         .BYTE   0xf7, 0xe4, 0x58, 0x05, 0xb8, 0xb3, 0x45, 0x06
987         .BYTE   0xd0, 0x2c, 0x1e, 0x8f, 0xca, 0x3f, 0x0f, 0x02
988         .BYTE   0xc1, 0xaf, 0xbd, 0x03, 0x01, 0x13, 0x8a, 0x6b
989         .BYTE   0x3a, 0x91, 0x11, 0x41, 0x4f, 0x67, 0xdc, 0xea
990         .BYTE   0x97, 0xf2, 0xcf, 0xce, 0xf0, 0xb4, 0xe6, 0x73
991         .BYTE   0x96, 0xac, 0x74, 0x22, 0xe7, 0xad, 0x35, 0x85
992         .BYTE   0xe2, 0xf9, 0x37, 0xe8, 0x1c, 0x75, 0xdf, 0x6e
993         .BYTE   0x47, 0xf1, 0x1a, 0x71, 0x1d, 0x29, 0xc5, 0x89
994         .BYTE   0x6f, 0xb7, 0x62, 0x0e, 0xaa, 0x18, 0xbe, 0x1b
995         .BYTE   0xfc, 0x56, 0x3e, 0x4b, 0xc6, 0xd2, 0x79, 0x20
996         .BYTE   0x9a, 0xdb, 0xc0, 0xfe, 0x78, 0xcd, 0x5a, 0xf4
997         .BYTE   0x1f, 0xdd, 0xa8, 0x33, 0x88, 0x07, 0xc7, 0x31
998         .BYTE   0xb1, 0x12, 0x10, 0x59, 0x27, 0x80, 0xec, 0x5f
999         .BYTE   0x60, 0x51, 0x7f, 0xa9, 0x19, 0xb5, 0x4a, 0x0d
1000         .BYTE   0x2d, 0xe5, 0x7a, 0x9f, 0x93, 0xc9, 0x9c, 0xef
1001         .BYTE   0xa0, 0xe0, 0x3b, 0x4d, 0xae, 0x2a, 0xf5, 0xb0
1002         .BYTE   0xc8, 0xeb, 0xbb, 0x3c, 0x83, 0x53, 0x99, 0x61
1003         .BYTE   0x17, 0x2b, 0x04, 0x7e, 0xba, 0x77, 0xd6, 0x26
1004         .BYTE   0xe1, 0x69, 0x14, 0x63, 0x55, 0x21, 0x0c, 0x7d
1005         .STRINGZ "AES for PA-RISC, CRYPTOGAMS by <appro\@openssl.org>"
1006 ___
1007
1008 foreach (split("\n",$code)) {
1009         s/\`([^\`]*)\`/eval $1/ge;
1010
1011         # translate made up instructons: _ror, _srm
1012         s/_ror(\s+)(%r[0-9]+),/shd$1$2,$2,/                             or
1013
1014         s/_srm(\s+%r[0-9]+),([0-9]+),/
1015                 $SIZE_T==4 ? sprintf("extru%s,%d,8,",$1,31-$2)
1016                 :            sprintf("extrd,u%s,%d,8,",$1,63-$2)/e;
1017
1018         s/,\*/,/ if ($SIZE_T==4);
1019         print $_,"\n";
1020 }
1021 close STDOUT;