sve-intrinsics-perm-select-matmul-fp64.ll 23.5 KB
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515
; RUN: llc -mtriple=aarch64-none-linux-gnu -mattr=+sve,+f64mm -asm-verbose=0 < %s -o - | FileCheck %s

;
; TRN1Q
;

define <vscale x 16 x i8> @trn1_i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) nounwind {
; CHECK-LABEL: trn1_i8:
; CHECK-NEXT:  trn1 z0.q, z0.q, z1.q
; CHECK-NEXT:  ret
  %out = call <vscale x 16 x i8> @llvm.aarch64.sve.trn1q.nxv16i8(<vscale x 16 x i8> %a,
                                                                 <vscale x 16 x i8> %b)
  ret <vscale x 16 x i8> %out
}

define <vscale x 8 x i16> @trn1_i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) nounwind {
; CHECK-LABEL: trn1_i16:
; CHECK-NEXT:  trn1 z0.q, z0.q, z1.q
; CHECK-NEXT:  ret
  %out = call <vscale x 8 x i16> @llvm.aarch64.sve.trn1q.nxv8i16(<vscale x 8 x i16> %a,
                                                                 <vscale x 8 x i16> %b)
  ret <vscale x 8 x i16> %out
}

define <vscale x 4 x i32> @trn1_i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) nounwind {
; CHECK-LABEL: trn1_i32:
; CHECK-NEXT:  trn1 z0.q, z0.q, z1.q
; CHECK-NEXT:  ret
  %out = call <vscale x 4 x i32> @llvm.aarch64.sve.trn1q.nxv4i32(<vscale x 4 x i32> %a,
                                                                 <vscale x 4 x i32> %b)
  ret <vscale x 4 x i32> %out
}

define <vscale x 2 x i64> @trn1_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) nounwind {
; CHECK-LABEL: trn1_i64:
; CHECK-NEXT:  trn1 z0.q, z0.q, z1.q
; CHECK-NEXT:  ret
  %out = call <vscale x 2 x i64> @llvm.aarch64.sve.trn1q.nxv2i64(<vscale x 2 x i64> %a,
                                                                 <vscale x 2 x i64> %b)
  ret <vscale x 2 x i64> %out
}

define <vscale x 8 x half> @trn1_f16(<vscale x 8 x half> %a, <vscale x 8 x half> %b) nounwind {
; CHECK-LABEL: trn1_f16:
; CHECK-NEXT:  trn1 z0.q, z0.q, z1.q
; CHECK-NEXT:  ret
  %out = call <vscale x 8 x half> @llvm.aarch64.sve.trn1q.nxv8f16(<vscale x 8 x half> %a,
                                                                  <vscale x 8 x half> %b)
  ret <vscale x 8 x half> %out
}

define <vscale x 8 x bfloat> @trn1_bf16(<vscale x 8 x bfloat> %a, <vscale x 8 x bfloat> %b) nounwind #0 {
; CHECK-LABEL: trn1_bf16:
; CHECK-NEXT:  trn1 z0.q, z0.q, z1.q
; CHECK-NEXT:  ret
  %out = call <vscale x 8 x bfloat> @llvm.aarch64.sve.trn1q.nxv8bf16(<vscale x 8 x bfloat> %a,
                                                                     <vscale x 8 x bfloat> %b)
  ret <vscale x 8 x bfloat> %out
}

define <vscale x 4 x float> @trn1_f32(<vscale x 4 x float> %a, <vscale x 4 x float> %b) nounwind {
; CHECK-LABEL: trn1_f32:
; CHECK-NEXT:  trn1 z0.q, z0.q, z1.q
; CHECK-NEXT:  ret
  %out = call <vscale x 4 x float> @llvm.aarch64.sve.trn1q.nxv4f32(<vscale x 4 x float> %a,
                                                                   <vscale x 4 x float> %b)
  ret <vscale x 4 x float> %out
}

define <vscale x 2 x double> @trn1_f64(<vscale x 2 x double> %a, <vscale x 2 x double> %b) nounwind {
; CHECK-LABEL: trn1_f64:
; CHECK-NEXT:  trn1 z0.q, z0.q, z1.q
; CHECK-NEXT:  ret
  %out = call <vscale x 2 x double> @llvm.aarch64.sve.trn1q.nxv2f64(<vscale x 2 x double> %a,
                                                                    <vscale x 2 x double> %b)
  ret <vscale x 2 x double> %out
}

;
; TRN2Q
;

define <vscale x 16 x i8> @trn2_i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) nounwind {
; CHECK-LABEL: trn2_i8:
; CHECK-NEXT:  trn2 z0.q, z0.q, z1.q
; CHECK-NEXT:  ret
  %out = call <vscale x 16 x i8> @llvm.aarch64.sve.trn2q.nxv16i8(<vscale x 16 x i8> %a,
                                                                 <vscale x 16 x i8> %b)
  ret <vscale x 16 x i8> %out
}

define <vscale x 8 x i16> @trn2_i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) nounwind {
; CHECK-LABEL: trn2_i16:
; CHECK-NEXT:  trn2 z0.q, z0.q, z1.q
; CHECK-NEXT:  ret
  %out = call <vscale x 8 x i16> @llvm.aarch64.sve.trn2q.nxv8i16(<vscale x 8 x i16> %a,
                                                                 <vscale x 8 x i16> %b)
  ret <vscale x 8 x i16> %out
}

define <vscale x 4 x i32> @trn2_i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) nounwind {
; CHECK-LABEL: trn2_i32:
; CHECK-NEXT:  trn2 z0.q, z0.q, z1.q
; CHECK-NEXT:  ret
  %out = call <vscale x 4 x i32> @llvm.aarch64.sve.trn2q.nxv4i32(<vscale x 4 x i32> %a,
                                                                 <vscale x 4 x i32> %b)
  ret <vscale x 4 x i32> %out
}

define <vscale x 2 x i64> @trn2_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) nounwind {
; CHECK-LABEL: trn2_i64:
; CHECK-NEXT:  trn2 z0.q, z0.q, z1.q
; CHECK-NEXT:  ret
  %out = call <vscale x 2 x i64> @llvm.aarch64.sve.trn2q.nxv2i64(<vscale x 2 x i64> %a,
                                                                 <vscale x 2 x i64> %b)
  ret <vscale x 2 x i64> %out
}

define <vscale x 8 x half> @trn2_f16(<vscale x 8 x half> %a, <vscale x 8 x half> %b) nounwind {
; CHECK-LABEL: trn2_f16:
; CHECK-NEXT:  trn2 z0.q, z0.q, z1.q
; CHECK-NEXT:  ret
  %out = call <vscale x 8 x half> @llvm.aarch64.sve.trn2q.nxv8f16(<vscale x 8 x half> %a,
                                                                  <vscale x 8 x half> %b)
  ret <vscale x 8 x half> %out
}

define <vscale x 8 x bfloat> @trn2_bf16(<vscale x 8 x bfloat> %a, <vscale x 8 x bfloat> %b) nounwind #0 {
; CHECK-LABEL: trn2_bf16:
; CHECK-NEXT:  trn2 z0.q, z0.q, z1.q
; CHECK-NEXT:  ret
  %out = call <vscale x 8 x bfloat> @llvm.aarch64.sve.trn2q.nxv8bf16(<vscale x 8 x bfloat> %a,
                                                                     <vscale x 8 x bfloat> %b)
  ret <vscale x 8 x bfloat> %out
}

define <vscale x 4 x float> @trn2_f32(<vscale x 4 x float> %a, <vscale x 4 x float> %b) nounwind {
; CHECK-LABEL: trn2_f32:
; CHECK-NEXT:  trn2 z0.q, z0.q, z1.q
; CHECK-NEXT:  ret
  %out = call <vscale x 4 x float> @llvm.aarch64.sve.trn2q.nxv4f32(<vscale x 4 x float> %a,
                                                                   <vscale x 4 x float> %b)
  ret <vscale x 4 x float> %out
}

define <vscale x 2 x double> @trn2_f64(<vscale x 2 x double> %a, <vscale x 2 x double> %b) nounwind {
; CHECK-LABEL: trn2_f64:
; CHECK-NEXT:  trn2 z0.q, z0.q, z1.q
; CHECK-NEXT:  ret
  %out = call <vscale x 2 x double> @llvm.aarch64.sve.trn2q.nxv2f64(<vscale x 2 x double> %a,
                                                                    <vscale x 2 x double> %b)
  ret <vscale x 2 x double> %out
}

;
; UZP1Q
;

define <vscale x 16 x i8> @uzp1_i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) nounwind {
; CHECK-LABEL: uzp1_i8:
; CHECK-NEXT:  uzp1 z0.q, z0.q, z1.q
; CHECK-NEXT:  ret
  %out = call <vscale x 16 x i8> @llvm.aarch64.sve.uzp1q.nxv16i8(<vscale x 16 x i8> %a,
                                                                 <vscale x 16 x i8> %b)
  ret <vscale x 16 x i8> %out
}

define <vscale x 8 x i16> @uzp1_i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) nounwind {
; CHECK-LABEL: uzp1_i16:
; CHECK-NEXT:  uzp1 z0.q, z0.q, z1.q
; CHECK-NEXT:  ret
  %out = call <vscale x 8 x i16> @llvm.aarch64.sve.uzp1q.nxv8i16(<vscale x 8 x i16> %a,
                                                                 <vscale x 8 x i16> %b)
  ret <vscale x 8 x i16> %out
}

define <vscale x 4 x i32> @uzp1_i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) nounwind {
; CHECK-LABEL: uzp1_i32:
; CHECK-NEXT:  uzp1 z0.q, z0.q, z1.q
; CHECK-NEXT:  ret
  %out = call <vscale x 4 x i32> @llvm.aarch64.sve.uzp1q.nxv4i32(<vscale x 4 x i32> %a,
                                                                 <vscale x 4 x i32> %b)
  ret <vscale x 4 x i32> %out
}

define <vscale x 2 x i64> @uzp1_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) nounwind {
; CHECK-LABEL: uzp1_i64:
; CHECK-NEXT:  uzp1 z0.q, z0.q, z1.q
; CHECK-NEXT:  ret
  %out = call <vscale x 2 x i64> @llvm.aarch64.sve.uzp1q.nxv2i64(<vscale x 2 x i64> %a,
                                                                 <vscale x 2 x i64> %b)
  ret <vscale x 2 x i64> %out
}

define <vscale x 8 x half> @uzp1_f16(<vscale x 8 x half> %a, <vscale x 8 x half> %b) nounwind {
; CHECK-LABEL: uzp1_f16:
; CHECK-NEXT:  uzp1 z0.q, z0.q, z1.q
; CHECK-NEXT:  ret
  %out = call <vscale x 8 x half> @llvm.aarch64.sve.uzp1q.nxv8f16(<vscale x 8 x half> %a,
                                                                  <vscale x 8 x half> %b)
  ret <vscale x 8 x half> %out
}

define <vscale x 8 x bfloat> @uzp1_bf16(<vscale x 8 x bfloat> %a, <vscale x 8 x bfloat> %b) nounwind #0 {
; CHECK-LABEL: uzp1_bf16:
; CHECK-NEXT:  uzp1 z0.q, z0.q, z1.q
; CHECK-NEXT:  ret
  %out = call <vscale x 8 x bfloat> @llvm.aarch64.sve.uzp1q.nxv8bf16(<vscale x 8 x bfloat> %a,
                                                                     <vscale x 8 x bfloat> %b)
  ret <vscale x 8 x bfloat> %out
}

define <vscale x 4 x float> @uzp1_f32(<vscale x 4 x float> %a, <vscale x 4 x float> %b) nounwind {
; CHECK-LABEL: uzp1_f32:
; CHECK-NEXT:  uzp1 z0.q, z0.q, z1.q
; CHECK-NEXT:  ret
  %out = call <vscale x 4 x float> @llvm.aarch64.sve.uzp1q.nxv4f32(<vscale x 4 x float> %a,
                                                                   <vscale x 4 x float> %b)
  ret <vscale x 4 x float> %out
}

define <vscale x 2 x double> @uzp1_f64(<vscale x 2 x double> %a, <vscale x 2 x double> %b) nounwind {
; CHECK-LABEL: uzp1_f64:
; CHECK-NEXT:  uzp1 z0.q, z0.q, z1.q
; CHECK-NEXT:  ret
  %out = call <vscale x 2 x double> @llvm.aarch64.sve.uzp1q.nxv2f64(<vscale x 2 x double> %a,
                                                                    <vscale x 2 x double> %b)
  ret <vscale x 2 x double> %out
}

;
; UZP2Q
;

define <vscale x 16 x i8> @uzp2_i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) nounwind {
; CHECK-LABEL: uzp2_i8:
; CHECK-NEXT:  uzp2 z0.q, z0.q, z1.q
; CHECK-NEXT:  ret
  %out = call <vscale x 16 x i8> @llvm.aarch64.sve.uzp2q.nxv16i8(<vscale x 16 x i8> %a,
                                                                 <vscale x 16 x i8> %b)
  ret <vscale x 16 x i8> %out
}

define <vscale x 8 x i16> @uzp2_i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) nounwind {
; CHECK-LABEL: uzp2_i16:
; CHECK-NEXT:  uzp2 z0.q, z0.q, z1.q
; CHECK-NEXT:  ret
  %out = call <vscale x 8 x i16> @llvm.aarch64.sve.uzp2q.nxv8i16(<vscale x 8 x i16> %a,
                                                                 <vscale x 8 x i16> %b)
  ret <vscale x 8 x i16> %out
}

define <vscale x 4 x i32> @uzp2_i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) nounwind {
; CHECK-LABEL: uzp2_i32:
; CHECK-NEXT:  uzp2 z0.q, z0.q, z1.q
; CHECK-NEXT:  ret
  %out = call <vscale x 4 x i32> @llvm.aarch64.sve.uzp2q.nxv4i32(<vscale x 4 x i32> %a,
                                                                 <vscale x 4 x i32> %b)
  ret <vscale x 4 x i32> %out
}

define <vscale x 2 x i64> @uzp2_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) nounwind {
; CHECK-LABEL: uzp2_i64:
; CHECK-NEXT:  uzp2 z0.q, z0.q, z1.q
; CHECK-NEXT:  ret
  %out = call <vscale x 2 x i64> @llvm.aarch64.sve.uzp2q.nxv2i64(<vscale x 2 x i64> %a,
                                                                 <vscale x 2 x i64> %b)
  ret <vscale x 2 x i64> %out
}

define <vscale x 8 x half> @uzp2_f16(<vscale x 8 x half> %a, <vscale x 8 x half> %b) nounwind {
; CHECK-LABEL: uzp2_f16:
; CHECK-NEXT:  uzp2 z0.q, z0.q, z1.q
; CHECK-NEXT:  ret
  %out = call <vscale x 8 x half> @llvm.aarch64.sve.uzp2q.nxv8f16(<vscale x 8 x half> %a,
                                                                  <vscale x 8 x half> %b)
  ret <vscale x 8 x half> %out
}

define <vscale x 8 x bfloat> @uzp2_bf16(<vscale x 8 x bfloat> %a, <vscale x 8 x bfloat> %b) nounwind #0 {
; CHECK-LABEL: uzp2_bf16:
; CHECK-NEXT:  uzp2 z0.q, z0.q, z1.q
; CHECK-NEXT:  ret
  %out = call <vscale x 8 x bfloat> @llvm.aarch64.sve.uzp2q.nxv8bf16(<vscale x 8 x bfloat> %a,
                                                                     <vscale x 8 x bfloat> %b)
  ret <vscale x 8 x bfloat> %out
}

define <vscale x 4 x float> @uzp2_f32(<vscale x 4 x float> %a, <vscale x 4 x float> %b) nounwind {
; CHECK-LABEL: uzp2_f32:
; CHECK-NEXT:  uzp2 z0.q, z0.q, z1.q
; CHECK-NEXT:  ret
  %out = call <vscale x 4 x float> @llvm.aarch64.sve.uzp2q.nxv4f32(<vscale x 4 x float> %a,
                                                                   <vscale x 4 x float> %b)
  ret <vscale x 4 x float> %out
}

define <vscale x 2 x double> @uzp2_f64(<vscale x 2 x double> %a, <vscale x 2 x double> %b) nounwind {
; CHECK-LABEL: uzp2_f64:
; CHECK-NEXT:  uzp2 z0.q, z0.q, z1.q
; CHECK-NEXT:  ret
  %out = call <vscale x 2 x double> @llvm.aarch64.sve.uzp2q.nxv2f64(<vscale x 2 x double> %a,
                                                                    <vscale x 2 x double> %b)
  ret <vscale x 2 x double> %out
}

;
; ZIP1Q
;

define <vscale x 16 x i8> @zip1_i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) nounwind {
; CHECK-LABEL: zip1_i8:
; CHECK-NEXT:  zip1 z0.q, z0.q, z1.q
; CHECK-NEXT:  ret
  %out = call <vscale x 16 x i8> @llvm.aarch64.sve.zip1q.nxv16i8(<vscale x 16 x i8> %a,
                                                                <vscale x 16 x i8> %b)
  ret <vscale x 16 x i8> %out
}

define <vscale x 8 x i16> @zip1_i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) nounwind {
; CHECK-LABEL: zip1_i16:
; CHECK-NEXT:  zip1 z0.q, z0.q, z1.q
; CHECK-NEXT:  ret
  %out = call <vscale x 8 x i16> @llvm.aarch64.sve.zip1q.nxv8i16(<vscale x 8 x i16> %a,
                                                                 <vscale x 8 x i16> %b)
  ret <vscale x 8 x i16> %out
}

define <vscale x 4 x i32> @zip1_i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) nounwind {
; CHECK-LABEL: zip1_i32:
; CHECK-NEXT:  zip1 z0.q, z0.q, z1.q
; CHECK-NEXT:  ret
  %out = call <vscale x 4 x i32> @llvm.aarch64.sve.zip1q.nxv4i32(<vscale x 4 x i32> %a,
                                                                 <vscale x 4 x i32> %b)
  ret <vscale x 4 x i32> %out
}

define <vscale x 2 x i64> @zip1_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) nounwind {
; CHECK-LABEL: zip1_i64:
; CHECK-NEXT:  zip1 z0.q, z0.q, z1.q
; CHECK-NEXT:  ret
  %out = call <vscale x 2 x i64> @llvm.aarch64.sve.zip1q.nxv2i64(<vscale x 2 x i64> %a,
                                                                 <vscale x 2 x i64> %b)
  ret <vscale x 2 x i64> %out
}

define <vscale x 8 x half> @zip1_f16(<vscale x 8 x half> %a, <vscale x 8 x half> %b) nounwind {
; CHECK-LABEL: zip1_f16:
; CHECK-NEXT:  zip1 z0.q, z0.q, z1.q
; CHECK-NEXT:  ret
  %out = call <vscale x 8 x half> @llvm.aarch64.sve.zip1q.nxv8f16(<vscale x 8 x half> %a,
                                                                  <vscale x 8 x half> %b)
  ret <vscale x 8 x half> %out
}

define <vscale x 8 x bfloat> @zip1_bf16(<vscale x 8 x bfloat> %a, <vscale x 8 x bfloat> %b) nounwind #0 {
; CHECK-LABEL: zip1_bf16:
; CHECK-NEXT:  zip1 z0.q, z0.q, z1.q
; CHECK-NEXT:  ret
  %out = call <vscale x 8 x bfloat> @llvm.aarch64.sve.zip1q.nxv8bf16(<vscale x 8 x bfloat> %a,
                                                                     <vscale x 8 x bfloat> %b)
  ret <vscale x 8 x bfloat> %out
}

define <vscale x 4 x float> @zip1_f32(<vscale x 4 x float> %a, <vscale x 4 x float> %b) nounwind {
; CHECK-LABEL: zip1_f32:
; CHECK-NEXT:  zip1 z0.q, z0.q, z1.q
; CHECK-NEXT:  ret
  %out = call <vscale x 4 x float> @llvm.aarch64.sve.zip1q.nxv4f32(<vscale x 4 x float> %a,
                                                                   <vscale x 4 x float> %b)
  ret <vscale x 4 x float> %out
}

define <vscale x 2 x double> @zip1_f64(<vscale x 2 x double> %a, <vscale x 2 x double> %b) nounwind {
; CHECK-LABEL: zip1_f64:
; CHECK-NEXT:  zip1 z0.q, z0.q, z1.q
; CHECK-NEXT:  ret
  %out = call <vscale x 2 x double> @llvm.aarch64.sve.zip1q.nxv2f64(<vscale x 2 x double> %a,
                                                                    <vscale x 2 x double> %b)
  ret <vscale x 2 x double> %out
}

;
; ZIP2Q
;

define <vscale x 16 x i8> @zip2_i8(<vscale x 16 x i8> %a, <vscale x 16 x i8> %b) nounwind {
; CHECK-LABEL: zip2_i8:
; CHECK-NEXT:  zip2 z0.q, z0.q, z1.q
; CHECK-NEXT:  ret
  %out = call <vscale x 16 x i8> @llvm.aarch64.sve.zip2q.nxv16i8(<vscale x 16 x i8> %a,
                                                                 <vscale x 16 x i8> %b)
  ret <vscale x 16 x i8> %out
}

define <vscale x 8 x i16> @zip2_i16(<vscale x 8 x i16> %a, <vscale x 8 x i16> %b) nounwind {
; CHECK-LABEL: zip2_i16:
; CHECK-NEXT:  zip2 z0.q, z0.q, z1.q
; CHECK-NEXT:  ret
  %out = call <vscale x 8 x i16> @llvm.aarch64.sve.zip2q.nxv8i16(<vscale x 8 x i16> %a,
                                                                 <vscale x 8 x i16> %b)
  ret <vscale x 8 x i16> %out
}

define <vscale x 4 x i32> @zip2_i32(<vscale x 4 x i32> %a, <vscale x 4 x i32> %b) nounwind {
; CHECK-LABEL: zip2_i32:
; CHECK-NEXT:  zip2 z0.q, z0.q, z1.q
; CHECK-NEXT:  ret
  %out = call <vscale x 4 x i32> @llvm.aarch64.sve.zip2q.nxv4i32(<vscale x 4 x i32> %a,
                                                                 <vscale x 4 x i32> %b)
  ret <vscale x 4 x i32> %out
}

define <vscale x 2 x i64> @zip2_i64(<vscale x 2 x i64> %a, <vscale x 2 x i64> %b) nounwind {
; CHECK-LABEL: zip2_i64:
; CHECK-NEXT:  zip2 z0.q, z0.q, z1.q
; CHECK-NEXT:  ret
  %out = call <vscale x 2 x i64> @llvm.aarch64.sve.zip2q.nxv2i64(<vscale x 2 x i64> %a,
                                                                 <vscale x 2 x i64> %b)
  ret <vscale x 2 x i64> %out
}

define <vscale x 8 x half> @zip2_f16(<vscale x 8 x half> %a, <vscale x 8 x half> %b) nounwind {
; CHECK-LABEL: zip2_f16:
; CHECK-NEXT:  zip2 z0.q, z0.q, z1.q
; CHECK-NEXT:  ret
  %out = call <vscale x 8 x half> @llvm.aarch64.sve.zip2q.nxv8f16(<vscale x 8 x half> %a,
                                                                  <vscale x 8 x half> %b)
  ret <vscale x 8 x half> %out
}

define <vscale x 8 x bfloat> @zip2_bf16(<vscale x 8 x bfloat> %a, <vscale x 8 x bfloat> %b) nounwind #0 {
; CHECK-LABEL: zip2_bf16:
; CHECK-NEXT:  zip2 z0.q, z0.q, z1.q
; CHECK-NEXT:  ret
  %out = call <vscale x 8 x bfloat> @llvm.aarch64.sve.zip2q.nxv8bf16(<vscale x 8 x bfloat> %a,
                                                                     <vscale x 8 x bfloat> %b)
  ret <vscale x 8 x bfloat> %out
}

define <vscale x 4 x float> @zip2_f32(<vscale x 4 x float> %a, <vscale x 4 x float> %b) nounwind {
; CHECK-LABEL: zip2_f32:
; CHECK-NEXT:  zip2 z0.q, z0.q, z1.q
; CHECK-NEXT:  ret
  %out = call <vscale x 4 x float> @llvm.aarch64.sve.zip2q.nxv4f32(<vscale x 4 x float> %a,
                                                                   <vscale x 4 x float> %b)
  ret <vscale x 4 x float> %out
}

define <vscale x 2 x double> @zip2_f64(<vscale x 2 x double> %a, <vscale x 2 x double> %b) nounwind {
; CHECK-LABEL: zip2_f64:
; CHECK-NEXT:  zip2 z0.q, z0.q, z1.q
; CHECK-NEXT:  ret
  %out = call <vscale x 2 x double> @llvm.aarch64.sve.zip2q.nxv2f64(<vscale x 2 x double> %a,
                                                                    <vscale x 2 x double> %b)
  ret <vscale x 2 x double> %out
}


declare <vscale x 2 x double> @llvm.aarch64.sve.trn1q.nxv2f64(<vscale x 2 x double>, <vscale x 2 x double>)
declare <vscale x 2 x i64> @llvm.aarch64.sve.trn1q.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>)
declare <vscale x 4 x float> @llvm.aarch64.sve.trn1q.nxv4f32(<vscale x 4 x float>, <vscale x 4 x float>)
declare <vscale x 4 x i32> @llvm.aarch64.sve.trn1q.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>)
declare <vscale x 8 x bfloat> @llvm.aarch64.sve.trn1q.nxv8bf16(<vscale x 8 x bfloat>, <vscale x 8 x bfloat>)
declare <vscale x 8 x half> @llvm.aarch64.sve.trn1q.nxv8f16(<vscale x 8 x half>, <vscale x 8 x half>)
declare <vscale x 8 x i16> @llvm.aarch64.sve.trn1q.nxv8i16(<vscale x 8 x i16>, <vscale x 8 x i16>)
declare <vscale x 16 x i8> @llvm.aarch64.sve.trn1q.nxv16i8(<vscale x 16 x i8>, <vscale x 16 x i8>)

declare <vscale x 2 x double> @llvm.aarch64.sve.trn2q.nxv2f64(<vscale x 2 x double>, <vscale x 2 x double>)
declare <vscale x 2 x i64> @llvm.aarch64.sve.trn2q.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>)
declare <vscale x 4 x float> @llvm.aarch64.sve.trn2q.nxv4f32(<vscale x 4 x float>, <vscale x 4 x float>)
declare <vscale x 4 x i32> @llvm.aarch64.sve.trn2q.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>)
declare <vscale x 8 x bfloat> @llvm.aarch64.sve.trn2q.nxv8bf16(<vscale x 8 x bfloat>, <vscale x 8 x bfloat>)
declare <vscale x 8 x half> @llvm.aarch64.sve.trn2q.nxv8f16(<vscale x 8 x half>, <vscale x 8 x half>)
declare <vscale x 8 x i16> @llvm.aarch64.sve.trn2q.nxv8i16(<vscale x 8 x i16>, <vscale x 8 x i16>)
declare <vscale x 16 x i8> @llvm.aarch64.sve.trn2q.nxv16i8(<vscale x 16 x i8>, <vscale x 16 x i8>)

declare <vscale x 2 x double> @llvm.aarch64.sve.uzp1q.nxv2f64(<vscale x 2 x double>, <vscale x 2 x double>)
declare <vscale x 2 x i64> @llvm.aarch64.sve.uzp1q.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>)
declare <vscale x 4 x float> @llvm.aarch64.sve.uzp1q.nxv4f32(<vscale x 4 x float>, <vscale x 4 x float>)
declare <vscale x 4 x i32> @llvm.aarch64.sve.uzp1q.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>)
declare <vscale x 8 x bfloat> @llvm.aarch64.sve.uzp1q.nxv8bf16(<vscale x 8 x bfloat>, <vscale x 8 x bfloat>)
declare <vscale x 8 x half> @llvm.aarch64.sve.uzp1q.nxv8f16(<vscale x 8 x half>, <vscale x 8 x half>)
declare <vscale x 8 x i16> @llvm.aarch64.sve.uzp1q.nxv8i16(<vscale x 8 x i16>, <vscale x 8 x i16>)
declare <vscale x 16 x i8> @llvm.aarch64.sve.uzp1q.nxv16i8(<vscale x 16 x i8>, <vscale x 16 x i8>)

declare <vscale x 2 x double> @llvm.aarch64.sve.uzp2q.nxv2f64(<vscale x 2 x double>, <vscale x 2 x double>)
declare <vscale x 2 x i64> @llvm.aarch64.sve.uzp2q.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>)
declare <vscale x 4 x float> @llvm.aarch64.sve.uzp2q.nxv4f32(<vscale x 4 x float>, <vscale x 4 x float>)
declare <vscale x 4 x i32> @llvm.aarch64.sve.uzp2q.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>)
declare <vscale x 8 x bfloat> @llvm.aarch64.sve.uzp2q.nxv8bf16(<vscale x 8 x bfloat>, <vscale x 8 x bfloat>)
declare <vscale x 8 x half> @llvm.aarch64.sve.uzp2q.nxv8f16(<vscale x 8 x half>, <vscale x 8 x half>)
declare <vscale x 8 x i16> @llvm.aarch64.sve.uzp2q.nxv8i16(<vscale x 8 x i16>, <vscale x 8 x i16>)
declare <vscale x 16 x i8> @llvm.aarch64.sve.uzp2q.nxv16i8(<vscale x 16 x i8>, <vscale x 16 x i8>)

declare <vscale x 2 x double> @llvm.aarch64.sve.zip1q.nxv2f64(<vscale x 2 x double>, <vscale x 2 x double>)
declare <vscale x 2 x i64> @llvm.aarch64.sve.zip1q.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>)
declare <vscale x 4 x float> @llvm.aarch64.sve.zip1q.nxv4f32(<vscale x 4 x float>, <vscale x 4 x float>)
declare <vscale x 4 x i32> @llvm.aarch64.sve.zip1q.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>)
declare <vscale x 8 x bfloat> @llvm.aarch64.sve.zip1q.nxv8bf16(<vscale x 8 x bfloat>, <vscale x 8 x bfloat>)
declare <vscale x 8 x half> @llvm.aarch64.sve.zip1q.nxv8f16(<vscale x 8 x half>, <vscale x 8 x half>)
declare <vscale x 8 x i16> @llvm.aarch64.sve.zip1q.nxv8i16(<vscale x 8 x i16>, <vscale x 8 x i16>)
declare <vscale x 16 x i8> @llvm.aarch64.sve.zip1q.nxv16i8(<vscale x 16 x i8>, <vscale x 16 x i8>)

declare <vscale x 2 x double> @llvm.aarch64.sve.zip2q.nxv2f64(<vscale x 2 x double>, <vscale x 2 x double>)
declare <vscale x 2 x i64> @llvm.aarch64.sve.zip2q.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>)
declare <vscale x 4 x float> @llvm.aarch64.sve.zip2q.nxv4f32(<vscale x 4 x float>, <vscale x 4 x float>)
declare <vscale x 4 x i32> @llvm.aarch64.sve.zip2q.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>)
declare <vscale x 8 x bfloat> @llvm.aarch64.sve.zip2q.nxv8bf16(<vscale x 8 x bfloat>, <vscale x 8 x bfloat>)
declare <vscale x 8 x half> @llvm.aarch64.sve.zip2q.nxv8f16(<vscale x 8 x half>, <vscale x 8 x half>)
declare <vscale x 8 x i16> @llvm.aarch64.sve.zip2q.nxv8i16(<vscale x 8 x i16>, <vscale x 8 x i16>)
declare <vscale x 16 x i8> @llvm.aarch64.sve.zip2q.nxv16i8(<vscale x 16 x i8>, <vscale x 16 x i8>)

; +bf16 is required for the bfloat version.
attributes #0 = { "target-features"="+sve,+fp64mm,+bf16" }