rjw | 1f88458 | 2022-01-06 17:20:42 +0800 | [diff] [blame^] | 1 | #if defined(__arm__) |
| 2 | #define __ARM_MAX_ARCH__ 8 |
| 3 | |
| 4 | .text |
| 5 | .code 32 |
| 6 | |
| 7 | #if __ARM_MAX_ARCH__>=7 |
| 8 | .align 5 |
| 9 | .LOPENSSL_armcap: |
| 10 | .word OPENSSL_armcap_P-.Lbn_mul_mont |
| 11 | #endif |
| 12 | |
| 13 | .globl bn_mul_mont |
| 14 | .hidden bn_mul_mont |
| 15 | .type bn_mul_mont,%function |
| 16 | |
| 17 | .align 5 |
| 18 | bn_mul_mont: |
| 19 | .Lbn_mul_mont: |
| 20 | ldr ip,[sp,#4] @ load num |
| 21 | stmdb sp!,{r0,r2} @ sp points at argument block |
| 22 | #if __ARM_MAX_ARCH__>=7 |
| 23 | tst ip,#7 |
| 24 | bne .Lialu |
| 25 | adr r0,bn_mul_mont |
| 26 | ldr r2,.LOPENSSL_armcap |
| 27 | ldr r0,[r0,r2] |
| 28 | #ifdef __APPLE__ |
| 29 | ldr r0,[r0] |
| 30 | #endif |
| 31 | tst r0,#1 @ NEON available? |
| 32 | ldmia sp, {r0,r2} |
| 33 | beq .Lialu |
| 34 | add sp,sp,#8 |
| 35 | b bn_mul8x_mont_neon |
| 36 | .align 4 |
| 37 | .Lialu: |
| 38 | #endif |
| 39 | cmp ip,#2 |
| 40 | mov r0,ip @ load num |
| 41 | movlt r0,#0 |
| 42 | addlt sp,sp,#2*4 |
| 43 | blt .Labrt |
| 44 | |
| 45 | stmdb sp!,{r4,r5,r6,r7,r8,r9,r10,r11,r12,lr} @ save 10 registers |
| 46 | |
| 47 | mov r0,r0,lsl#2 @ rescale r0 for byte count |
| 48 | sub sp,sp,r0 @ alloca(4*num) |
| 49 | sub sp,sp,#4 @ +extra dword |
| 50 | sub r0,r0,#4 @ "num=num-1" |
| 51 | add r4,r2,r0 @ &bp[num-1] |
| 52 | |
| 53 | add r0,sp,r0 @ r0 to point at &tp[num-1] |
| 54 | ldr r8,[r0,#14*4] @ &n0 |
| 55 | ldr r2,[r2] @ bp[0] |
| 56 | ldr r5,[r1],#4 @ ap[0],ap++ |
| 57 | ldr r6,[r3],#4 @ np[0],np++ |
| 58 | ldr r8,[r8] @ *n0 |
| 59 | str r4,[r0,#15*4] @ save &bp[num] |
| 60 | |
| 61 | umull r10,r11,r5,r2 @ ap[0]*bp[0] |
| 62 | str r8,[r0,#14*4] @ save n0 value |
| 63 | mul r8,r10,r8 @ "tp[0]"*n0 |
| 64 | mov r12,#0 |
| 65 | umlal r10,r12,r6,r8 @ np[0]*n0+"t[0]" |
| 66 | mov r4,sp |
| 67 | |
| 68 | .L1st: |
| 69 | ldr r5,[r1],#4 @ ap[j],ap++ |
| 70 | mov r10,r11 |
| 71 | ldr r6,[r3],#4 @ np[j],np++ |
| 72 | mov r11,#0 |
| 73 | umlal r10,r11,r5,r2 @ ap[j]*bp[0] |
| 74 | mov r14,#0 |
| 75 | umlal r12,r14,r6,r8 @ np[j]*n0 |
| 76 | adds r12,r12,r10 |
| 77 | str r12,[r4],#4 @ tp[j-1]=,tp++ |
| 78 | adc r12,r14,#0 |
| 79 | cmp r4,r0 |
| 80 | bne .L1st |
| 81 | |
| 82 | adds r12,r12,r11 |
| 83 | ldr r4,[r0,#13*4] @ restore bp |
| 84 | mov r14,#0 |
| 85 | ldr r8,[r0,#14*4] @ restore n0 |
| 86 | adc r14,r14,#0 |
| 87 | str r12,[r0] @ tp[num-1]= |
| 88 | str r14,[r0,#4] @ tp[num]= |
| 89 | |
| 90 | .Louter: |
| 91 | sub r7,r0,sp @ "original" r0-1 value |
| 92 | sub r1,r1,r7 @ "rewind" ap to &ap[1] |
| 93 | ldr r2,[r4,#4]! @ *(++bp) |
| 94 | sub r3,r3,r7 @ "rewind" np to &np[1] |
| 95 | ldr r5,[r1,#-4] @ ap[0] |
| 96 | ldr r10,[sp] @ tp[0] |
| 97 | ldr r6,[r3,#-4] @ np[0] |
| 98 | ldr r7,[sp,#4] @ tp[1] |
| 99 | |
| 100 | mov r11,#0 |
| 101 | umlal r10,r11,r5,r2 @ ap[0]*bp[i]+tp[0] |
| 102 | str r4,[r0,#13*4] @ save bp |
| 103 | mul r8,r10,r8 |
| 104 | mov r12,#0 |
| 105 | umlal r10,r12,r6,r8 @ np[0]*n0+"tp[0]" |
| 106 | mov r4,sp |
| 107 | |
| 108 | .Linner: |
| 109 | ldr r5,[r1],#4 @ ap[j],ap++ |
| 110 | adds r10,r11,r7 @ +=tp[j] |
| 111 | ldr r6,[r3],#4 @ np[j],np++ |
| 112 | mov r11,#0 |
| 113 | umlal r10,r11,r5,r2 @ ap[j]*bp[i] |
| 114 | mov r14,#0 |
| 115 | umlal r12,r14,r6,r8 @ np[j]*n0 |
| 116 | adc r11,r11,#0 |
| 117 | ldr r7,[r4,#8] @ tp[j+1] |
| 118 | adds r12,r12,r10 |
| 119 | str r12,[r4],#4 @ tp[j-1]=,tp++ |
| 120 | adc r12,r14,#0 |
| 121 | cmp r4,r0 |
| 122 | bne .Linner |
| 123 | |
| 124 | adds r12,r12,r11 |
| 125 | mov r14,#0 |
| 126 | ldr r4,[r0,#13*4] @ restore bp |
| 127 | adc r14,r14,#0 |
| 128 | ldr r8,[r0,#14*4] @ restore n0 |
| 129 | adds r12,r12,r7 |
| 130 | ldr r7,[r0,#15*4] @ restore &bp[num] |
| 131 | adc r14,r14,#0 |
| 132 | str r12,[r0] @ tp[num-1]= |
| 133 | str r14,[r0,#4] @ tp[num]= |
| 134 | |
| 135 | cmp r4,r7 |
| 136 | bne .Louter |
| 137 | |
| 138 | ldr r2,[r0,#12*4] @ pull rp |
| 139 | add r0,r0,#4 @ r0 to point at &tp[num] |
| 140 | sub r5,r0,sp @ "original" num value |
| 141 | mov r4,sp @ "rewind" r4 |
| 142 | mov r1,r4 @ "borrow" r1 |
| 143 | sub r3,r3,r5 @ "rewind" r3 to &np[0] |
| 144 | |
| 145 | subs r7,r7,r7 @ "clear" carry flag |
| 146 | .Lsub: ldr r7,[r4],#4 |
| 147 | ldr r6,[r3],#4 |
| 148 | sbcs r7,r7,r6 @ tp[j]-np[j] |
| 149 | str r7,[r2],#4 @ rp[j]= |
| 150 | teq r4,r0 @ preserve carry |
| 151 | bne .Lsub |
| 152 | sbcs r14,r14,#0 @ upmost carry |
| 153 | mov r4,sp @ "rewind" r4 |
| 154 | sub r2,r2,r5 @ "rewind" r2 |
| 155 | |
| 156 | and r1,r4,r14 |
| 157 | bic r3,r2,r14 |
| 158 | orr r1,r1,r3 @ ap=borrow?tp:rp |
| 159 | |
| 160 | .Lcopy: ldr r7,[r1],#4 @ copy or in-place refresh |
| 161 | str sp,[r4],#4 @ zap tp |
| 162 | str r7,[r2],#4 |
| 163 | cmp r4,r0 |
| 164 | bne .Lcopy |
| 165 | |
| 166 | add sp,r0,#4 @ skip over tp[num+1] |
| 167 | ldmia sp!,{r4,r5,r6,r7,r8,r9,r10,r11,r12,lr} @ restore registers |
| 168 | add sp,sp,#2*4 @ skip over {r0,r2} |
| 169 | mov r0,#1 |
| 170 | .Labrt: |
| 171 | #if __ARM_ARCH__>=5 |
| 172 | bx lr @ .word 0xe12fff1e |
| 173 | #else |
| 174 | tst lr,#1 |
| 175 | moveq pc,lr @ be binary compatible with V4, yet |
| 176 | .word 0xe12fff1e @ interoperable with Thumb ISA:-) |
| 177 | #endif |
| 178 | .size bn_mul_mont,.-bn_mul_mont |
| 179 | #if __ARM_MAX_ARCH__>=7 |
| 180 | .arch armv7-a |
| 181 | .fpu neon |
| 182 | |
| 183 | .type bn_mul8x_mont_neon,%function |
| 184 | .align 5 |
| 185 | bn_mul8x_mont_neon: |
| 186 | mov ip,sp |
| 187 | stmdb sp!,{r4,r5,r6,r7,r8,r9,r10,r11} |
| 188 | vstmdb sp!,{d8,d9,d10,d11,d12,d13,d14,d15} @ ABI specification says so |
| 189 | ldmia ip,{r4,r5} @ load rest of parameter block |
| 190 | |
| 191 | sub r7,sp,#16 |
| 192 | vld1.32 {d28[0]}, [r2,:32]! |
| 193 | sub r7,r7,r5,lsl#4 |
| 194 | vld1.32 {d0,d1,d2,d3}, [r1]! @ can't specify :32 :-( |
| 195 | and r7,r7,#-64 |
| 196 | vld1.32 {d30[0]}, [r4,:32] |
| 197 | mov sp,r7 @ alloca |
| 198 | veor d8,d8,d8 |
| 199 | subs r8,r5,#8 |
| 200 | vzip.16 d28,d8 |
| 201 | |
| 202 | vmull.u32 q6,d28,d0[0] |
| 203 | vmull.u32 q7,d28,d0[1] |
| 204 | vmull.u32 q8,d28,d1[0] |
| 205 | vshl.i64 d10,d13,#16 |
| 206 | vmull.u32 q9,d28,d1[1] |
| 207 | |
| 208 | vadd.u64 d10,d10,d12 |
| 209 | veor d8,d8,d8 |
| 210 | vmul.u32 d29,d10,d30 |
| 211 | |
| 212 | vmull.u32 q10,d28,d2[0] |
| 213 | vld1.32 {d4,d5,d6,d7}, [r3]! |
| 214 | vmull.u32 q11,d28,d2[1] |
| 215 | vmull.u32 q12,d28,d3[0] |
| 216 | vzip.16 d29,d8 |
| 217 | vmull.u32 q13,d28,d3[1] |
| 218 | |
| 219 | bne .LNEON_1st |
| 220 | |
| 221 | @ special case for num=8, everything is in register bank... |
| 222 | |
| 223 | vmlal.u32 q6,d29,d4[0] |
| 224 | sub r9,r5,#1 |
| 225 | vmlal.u32 q7,d29,d4[1] |
| 226 | vmlal.u32 q8,d29,d5[0] |
| 227 | vmlal.u32 q9,d29,d5[1] |
| 228 | |
| 229 | vmlal.u32 q10,d29,d6[0] |
| 230 | vmov q5,q6 |
| 231 | vmlal.u32 q11,d29,d6[1] |
| 232 | vmov q6,q7 |
| 233 | vmlal.u32 q12,d29,d7[0] |
| 234 | vmov q7,q8 |
| 235 | vmlal.u32 q13,d29,d7[1] |
| 236 | vmov q8,q9 |
| 237 | vmov q9,q10 |
| 238 | vshr.u64 d10,d10,#16 |
| 239 | vmov q10,q11 |
| 240 | vmov q11,q12 |
| 241 | vadd.u64 d10,d10,d11 |
| 242 | vmov q12,q13 |
| 243 | veor q13,q13 |
| 244 | vshr.u64 d10,d10,#16 |
| 245 | |
| 246 | b .LNEON_outer8 |
| 247 | |
| 248 | .align 4 |
| 249 | .LNEON_outer8: |
| 250 | vld1.32 {d28[0]}, [r2,:32]! |
| 251 | veor d8,d8,d8 |
| 252 | vzip.16 d28,d8 |
| 253 | vadd.u64 d12,d12,d10 |
| 254 | |
| 255 | vmlal.u32 q6,d28,d0[0] |
| 256 | vmlal.u32 q7,d28,d0[1] |
| 257 | vmlal.u32 q8,d28,d1[0] |
| 258 | vshl.i64 d10,d13,#16 |
| 259 | vmlal.u32 q9,d28,d1[1] |
| 260 | |
| 261 | vadd.u64 d10,d10,d12 |
| 262 | veor d8,d8,d8 |
| 263 | subs r9,r9,#1 |
| 264 | vmul.u32 d29,d10,d30 |
| 265 | |
| 266 | vmlal.u32 q10,d28,d2[0] |
| 267 | vmlal.u32 q11,d28,d2[1] |
| 268 | vmlal.u32 q12,d28,d3[0] |
| 269 | vzip.16 d29,d8 |
| 270 | vmlal.u32 q13,d28,d3[1] |
| 271 | |
| 272 | vmlal.u32 q6,d29,d4[0] |
| 273 | vmlal.u32 q7,d29,d4[1] |
| 274 | vmlal.u32 q8,d29,d5[0] |
| 275 | vmlal.u32 q9,d29,d5[1] |
| 276 | |
| 277 | vmlal.u32 q10,d29,d6[0] |
| 278 | vmov q5,q6 |
| 279 | vmlal.u32 q11,d29,d6[1] |
| 280 | vmov q6,q7 |
| 281 | vmlal.u32 q12,d29,d7[0] |
| 282 | vmov q7,q8 |
| 283 | vmlal.u32 q13,d29,d7[1] |
| 284 | vmov q8,q9 |
| 285 | vmov q9,q10 |
| 286 | vshr.u64 d10,d10,#16 |
| 287 | vmov q10,q11 |
| 288 | vmov q11,q12 |
| 289 | vadd.u64 d10,d10,d11 |
| 290 | vmov q12,q13 |
| 291 | veor q13,q13 |
| 292 | vshr.u64 d10,d10,#16 |
| 293 | |
| 294 | bne .LNEON_outer8 |
| 295 | |
| 296 | vadd.u64 d12,d12,d10 |
| 297 | mov r7,sp |
| 298 | vshr.u64 d10,d12,#16 |
| 299 | mov r8,r5 |
| 300 | vadd.u64 d13,d13,d10 |
| 301 | add r6,sp,#16 |
| 302 | vshr.u64 d10,d13,#16 |
| 303 | vzip.16 d12,d13 |
| 304 | |
| 305 | b .LNEON_tail2 |
| 306 | |
| 307 | .align 4 |
| 308 | .LNEON_1st: |
| 309 | vmlal.u32 q6,d29,d4[0] |
| 310 | vld1.32 {d0,d1,d2,d3}, [r1]! |
| 311 | vmlal.u32 q7,d29,d4[1] |
| 312 | subs r8,r8,#8 |
| 313 | vmlal.u32 q8,d29,d5[0] |
| 314 | vmlal.u32 q9,d29,d5[1] |
| 315 | |
| 316 | vmlal.u32 q10,d29,d6[0] |
| 317 | vld1.32 {d4,d5}, [r3]! |
| 318 | vmlal.u32 q11,d29,d6[1] |
| 319 | vst1.64 {q6,q7}, [r7,:256]! |
| 320 | vmlal.u32 q12,d29,d7[0] |
| 321 | vmlal.u32 q13,d29,d7[1] |
| 322 | vst1.64 {q8,q9}, [r7,:256]! |
| 323 | |
| 324 | vmull.u32 q6,d28,d0[0] |
| 325 | vld1.32 {d6,d7}, [r3]! |
| 326 | vmull.u32 q7,d28,d0[1] |
| 327 | vst1.64 {q10,q11}, [r7,:256]! |
| 328 | vmull.u32 q8,d28,d1[0] |
| 329 | vmull.u32 q9,d28,d1[1] |
| 330 | vst1.64 {q12,q13}, [r7,:256]! |
| 331 | |
| 332 | vmull.u32 q10,d28,d2[0] |
| 333 | vmull.u32 q11,d28,d2[1] |
| 334 | vmull.u32 q12,d28,d3[0] |
| 335 | vmull.u32 q13,d28,d3[1] |
| 336 | |
| 337 | bne .LNEON_1st |
| 338 | |
| 339 | vmlal.u32 q6,d29,d4[0] |
| 340 | add r6,sp,#16 |
| 341 | vmlal.u32 q7,d29,d4[1] |
| 342 | sub r1,r1,r5,lsl#2 @ rewind r1 |
| 343 | vmlal.u32 q8,d29,d5[0] |
| 344 | vld1.64 {q5}, [sp,:128] |
| 345 | vmlal.u32 q9,d29,d5[1] |
| 346 | sub r9,r5,#1 |
| 347 | |
| 348 | vmlal.u32 q10,d29,d6[0] |
| 349 | vst1.64 {q6,q7}, [r7,:256]! |
| 350 | vmlal.u32 q11,d29,d6[1] |
| 351 | vshr.u64 d10,d10,#16 |
| 352 | vld1.64 {q6}, [r6, :128]! |
| 353 | vmlal.u32 q12,d29,d7[0] |
| 354 | vst1.64 {q8,q9}, [r7,:256]! |
| 355 | vmlal.u32 q13,d29,d7[1] |
| 356 | |
| 357 | vst1.64 {q10,q11}, [r7,:256]! |
| 358 | vadd.u64 d10,d10,d11 |
| 359 | veor q4,q4,q4 |
| 360 | vst1.64 {q12,q13}, [r7,:256]! |
| 361 | vld1.64 {q7,q8}, [r6, :256]! |
| 362 | vst1.64 {q4}, [r7,:128] |
| 363 | vshr.u64 d10,d10,#16 |
| 364 | |
| 365 | b .LNEON_outer |
| 366 | |
| 367 | .align 4 |
| 368 | .LNEON_outer: |
| 369 | vld1.32 {d28[0]}, [r2,:32]! |
| 370 | sub r3,r3,r5,lsl#2 @ rewind r3 |
| 371 | vld1.32 {d0,d1,d2,d3}, [r1]! |
| 372 | veor d8,d8,d8 |
| 373 | mov r7,sp |
| 374 | vzip.16 d28,d8 |
| 375 | sub r8,r5,#8 |
| 376 | vadd.u64 d12,d12,d10 |
| 377 | |
| 378 | vmlal.u32 q6,d28,d0[0] |
| 379 | vld1.64 {q9,q10},[r6,:256]! |
| 380 | vmlal.u32 q7,d28,d0[1] |
| 381 | vmlal.u32 q8,d28,d1[0] |
| 382 | vld1.64 {q11,q12},[r6,:256]! |
| 383 | vmlal.u32 q9,d28,d1[1] |
| 384 | |
| 385 | vshl.i64 d10,d13,#16 |
| 386 | veor d8,d8,d8 |
| 387 | vadd.u64 d10,d10,d12 |
| 388 | vld1.64 {q13},[r6,:128]! |
| 389 | vmul.u32 d29,d10,d30 |
| 390 | |
| 391 | vmlal.u32 q10,d28,d2[0] |
| 392 | vld1.32 {d4,d5,d6,d7}, [r3]! |
| 393 | vmlal.u32 q11,d28,d2[1] |
| 394 | vmlal.u32 q12,d28,d3[0] |
| 395 | vzip.16 d29,d8 |
| 396 | vmlal.u32 q13,d28,d3[1] |
| 397 | |
| 398 | .LNEON_inner: |
| 399 | vmlal.u32 q6,d29,d4[0] |
| 400 | vld1.32 {d0,d1,d2,d3}, [r1]! |
| 401 | vmlal.u32 q7,d29,d4[1] |
| 402 | subs r8,r8,#8 |
| 403 | vmlal.u32 q8,d29,d5[0] |
| 404 | vmlal.u32 q9,d29,d5[1] |
| 405 | vst1.64 {q6,q7}, [r7,:256]! |
| 406 | |
| 407 | vmlal.u32 q10,d29,d6[0] |
| 408 | vld1.64 {q6}, [r6, :128]! |
| 409 | vmlal.u32 q11,d29,d6[1] |
| 410 | vst1.64 {q8,q9}, [r7,:256]! |
| 411 | vmlal.u32 q12,d29,d7[0] |
| 412 | vld1.64 {q7,q8}, [r6, :256]! |
| 413 | vmlal.u32 q13,d29,d7[1] |
| 414 | vst1.64 {q10,q11}, [r7,:256]! |
| 415 | |
| 416 | vmlal.u32 q6,d28,d0[0] |
| 417 | vld1.64 {q9,q10}, [r6, :256]! |
| 418 | vmlal.u32 q7,d28,d0[1] |
| 419 | vst1.64 {q12,q13}, [r7,:256]! |
| 420 | vmlal.u32 q8,d28,d1[0] |
| 421 | vld1.64 {q11,q12}, [r6, :256]! |
| 422 | vmlal.u32 q9,d28,d1[1] |
| 423 | vld1.32 {d4,d5,d6,d7}, [r3]! |
| 424 | |
| 425 | vmlal.u32 q10,d28,d2[0] |
| 426 | vld1.64 {q13}, [r6, :128]! |
| 427 | vmlal.u32 q11,d28,d2[1] |
| 428 | vmlal.u32 q12,d28,d3[0] |
| 429 | vmlal.u32 q13,d28,d3[1] |
| 430 | |
| 431 | bne .LNEON_inner |
| 432 | |
| 433 | vmlal.u32 q6,d29,d4[0] |
| 434 | add r6,sp,#16 |
| 435 | vmlal.u32 q7,d29,d4[1] |
| 436 | sub r1,r1,r5,lsl#2 @ rewind r1 |
| 437 | vmlal.u32 q8,d29,d5[0] |
| 438 | vld1.64 {q5}, [sp,:128] |
| 439 | vmlal.u32 q9,d29,d5[1] |
| 440 | subs r9,r9,#1 |
| 441 | |
| 442 | vmlal.u32 q10,d29,d6[0] |
| 443 | vst1.64 {q6,q7}, [r7,:256]! |
| 444 | vmlal.u32 q11,d29,d6[1] |
| 445 | vld1.64 {q6}, [r6, :128]! |
| 446 | vshr.u64 d10,d10,#16 |
| 447 | vst1.64 {q8,q9}, [r7,:256]! |
| 448 | vmlal.u32 q12,d29,d7[0] |
| 449 | vld1.64 {q7,q8}, [r6, :256]! |
| 450 | vmlal.u32 q13,d29,d7[1] |
| 451 | |
| 452 | vst1.64 {q10,q11}, [r7,:256]! |
| 453 | vadd.u64 d10,d10,d11 |
| 454 | vst1.64 {q12,q13}, [r7,:256]! |
| 455 | vshr.u64 d10,d10,#16 |
| 456 | |
| 457 | bne .LNEON_outer |
| 458 | |
| 459 | mov r7,sp |
| 460 | mov r8,r5 |
| 461 | |
| 462 | .LNEON_tail: |
| 463 | vadd.u64 d12,d12,d10 |
| 464 | vld1.64 {q9,q10}, [r6, :256]! |
| 465 | vshr.u64 d10,d12,#16 |
| 466 | vadd.u64 d13,d13,d10 |
| 467 | vld1.64 {q11,q12}, [r6, :256]! |
| 468 | vshr.u64 d10,d13,#16 |
| 469 | vld1.64 {q13}, [r6, :128]! |
| 470 | vzip.16 d12,d13 |
| 471 | |
| 472 | .LNEON_tail2: |
| 473 | vadd.u64 d14,d14,d10 |
| 474 | vst1.32 {d12[0]}, [r7, :32]! |
| 475 | vshr.u64 d10,d14,#16 |
| 476 | vadd.u64 d15,d15,d10 |
| 477 | vshr.u64 d10,d15,#16 |
| 478 | vzip.16 d14,d15 |
| 479 | |
| 480 | vadd.u64 d16,d16,d10 |
| 481 | vst1.32 {d14[0]}, [r7, :32]! |
| 482 | vshr.u64 d10,d16,#16 |
| 483 | vadd.u64 d17,d17,d10 |
| 484 | vshr.u64 d10,d17,#16 |
| 485 | vzip.16 d16,d17 |
| 486 | |
| 487 | vadd.u64 d18,d18,d10 |
| 488 | vst1.32 {d16[0]}, [r7, :32]! |
| 489 | vshr.u64 d10,d18,#16 |
| 490 | vadd.u64 d19,d19,d10 |
| 491 | vshr.u64 d10,d19,#16 |
| 492 | vzip.16 d18,d19 |
| 493 | |
| 494 | vadd.u64 d20,d20,d10 |
| 495 | vst1.32 {d18[0]}, [r7, :32]! |
| 496 | vshr.u64 d10,d20,#16 |
| 497 | vadd.u64 d21,d21,d10 |
| 498 | vshr.u64 d10,d21,#16 |
| 499 | vzip.16 d20,d21 |
| 500 | |
| 501 | vadd.u64 d22,d22,d10 |
| 502 | vst1.32 {d20[0]}, [r7, :32]! |
| 503 | vshr.u64 d10,d22,#16 |
| 504 | vadd.u64 d23,d23,d10 |
| 505 | vshr.u64 d10,d23,#16 |
| 506 | vzip.16 d22,d23 |
| 507 | |
| 508 | vadd.u64 d24,d24,d10 |
| 509 | vst1.32 {d22[0]}, [r7, :32]! |
| 510 | vshr.u64 d10,d24,#16 |
| 511 | vadd.u64 d25,d25,d10 |
| 512 | vld1.64 {q6}, [r6, :128]! |
| 513 | vshr.u64 d10,d25,#16 |
| 514 | vzip.16 d24,d25 |
| 515 | |
| 516 | vadd.u64 d26,d26,d10 |
| 517 | vst1.32 {d24[0]}, [r7, :32]! |
| 518 | vshr.u64 d10,d26,#16 |
| 519 | vadd.u64 d27,d27,d10 |
| 520 | vld1.64 {q7,q8}, [r6, :256]! |
| 521 | vshr.u64 d10,d27,#16 |
| 522 | vzip.16 d26,d27 |
| 523 | subs r8,r8,#8 |
| 524 | vst1.32 {d26[0]}, [r7, :32]! |
| 525 | |
| 526 | bne .LNEON_tail |
| 527 | |
| 528 | vst1.32 {d10[0]}, [r7, :32] @ top-most bit |
| 529 | sub r3,r3,r5,lsl#2 @ rewind r3 |
| 530 | subs r1,sp,#0 @ clear carry flag |
| 531 | add r2,sp,r5,lsl#2 |
| 532 | |
| 533 | .LNEON_sub: |
| 534 | ldmia r1!, {r4,r5,r6,r7} |
| 535 | ldmia r3!, {r8,r9,r10,r11} |
| 536 | sbcs r8, r4,r8 |
| 537 | sbcs r9, r5,r9 |
| 538 | sbcs r10,r6,r10 |
| 539 | sbcs r11,r7,r11 |
| 540 | teq r1,r2 @ preserves carry |
| 541 | stmia r0!, {r8,r9,r10,r11} |
| 542 | bne .LNEON_sub |
| 543 | |
| 544 | ldr r10, [r1] @ load top-most bit |
| 545 | veor q0,q0,q0 |
| 546 | sub r11,r2,sp @ this is num*4 |
| 547 | veor q1,q1,q1 |
| 548 | mov r1,sp |
| 549 | sub r0,r0,r11 @ rewind r0 |
| 550 | mov r3,r2 @ second 3/4th of frame |
| 551 | sbcs r10,r10,#0 @ result is carry flag |
| 552 | |
| 553 | .LNEON_copy_n_zap: |
| 554 | ldmia r1!, {r4,r5,r6,r7} |
| 555 | ldmia r0, {r8,r9,r10,r11} |
| 556 | movcc r8, r4 |
| 557 | vst1.64 {q0,q1}, [r3,:256]! @ wipe |
| 558 | movcc r9, r5 |
| 559 | movcc r10,r6 |
| 560 | vst1.64 {q0,q1}, [r3,:256]! @ wipe |
| 561 | movcc r11,r7 |
| 562 | ldmia r1, {r4,r5,r6,r7} |
| 563 | stmia r0!, {r8,r9,r10,r11} |
| 564 | sub r1,r1,#16 |
| 565 | ldmia r0, {r8,r9,r10,r11} |
| 566 | movcc r8, r4 |
| 567 | vst1.64 {q0,q1}, [r1,:256]! @ wipe |
| 568 | movcc r9, r5 |
| 569 | movcc r10,r6 |
| 570 | vst1.64 {q0,q1}, [r3,:256]! @ wipe |
| 571 | movcc r11,r7 |
| 572 | teq r1,r2 @ preserves carry |
| 573 | stmia r0!, {r8,r9,r10,r11} |
| 574 | bne .LNEON_copy_n_zap |
| 575 | |
| 576 | sub sp,ip,#96 |
| 577 | vldmia sp!,{d8,d9,d10,d11,d12,d13,d14,d15} |
| 578 | ldmia sp!,{r4,r5,r6,r7,r8,r9,r10,r11} |
| 579 | bx lr @ .word 0xe12fff1e |
| 580 | .size bn_mul8x_mont_neon,.-bn_mul8x_mont_neon |
| 581 | #endif |
| 582 | .byte 77,111,110,116,103,111,109,101,114,121,32,109,117,108,116,105,112,108,105,99,97,116,105,111,110,32,102,111,114,32,65,82,77,118,52,47,78,69,79,78,44,32,67,82,89,80,84,79,71,65,77,83,32,98,121,32,60,97,112,112,114,111,64,111,112,101,110,115,115,108,46,111,114,103,62,0 |
| 583 | .align 2 |
| 584 | .align 2 |
| 585 | #if __ARM_MAX_ARCH__>=7 |
| 586 | .comm OPENSSL_armcap_P,4,4 |
| 587 | .hidden OPENSSL_armcap_P |
| 588 | #endif |
| 589 | #endif |