Lines Matching full:tmp1
7 %tmp1 = load <8 x i8>, <8 x i8>* %A
9 %tmp3 = call <8 x i8> @llvm.aarch64.neon.sabd.v8i8(<8 x i8> %tmp1, <8 x i8> %tmp2)
17 %tmp1 = load <4 x i16>, <4 x i16>* %A
19 %tmp3 = call <4 x i16> @llvm.aarch64.neon.sabd.v4i16(<4 x i16> %tmp1, <4 x i16> %tmp2)
27 %tmp1 = load <2 x i32>, <2 x i32>* %A
29 %tmp3 = call <2 x i32> @llvm.aarch64.neon.sabd.v2i32(<2 x i32> %tmp1, <2 x i32> %tmp2)
39 %tmp1 = shufflevector <16 x i8> %load1, <16 x i8> undef, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
41 %tmp3 = call <8 x i8> @llvm.aarch64.neon.sabd.v8i8(<8 x i8> %tmp1, <8 x i8> %tmp2)
51 %tmp1 = shufflevector <8 x i16> %load1, <8 x i16> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
53 %tmp3 = call <4 x i16> @llvm.aarch64.neon.sabd.v4i16(<4 x i16> %tmp1, <4 x i16> %tmp2)
63 %tmp1 = shufflevector <4 x i32> %load1, <4 x i32> undef, <2 x i32> <i32 2, i32 3>
65 %tmp3 = call <2 x i32> @llvm.aarch64.neon.sabd.v2i32(<2 x i32> %tmp1, <2 x i32> %tmp2)
73 %tmp1 = load <8 x i8>, <8 x i8>* %A
75 %tmp3 = call <8 x i8> @llvm.aarch64.neon.uabd.v8i8(<8 x i8> %tmp1, <8 x i8> %tmp2)
83 %tmp1 = load <4 x i16>, <4 x i16>* %A
85 %tmp3 = call <4 x i16> @llvm.aarch64.neon.uabd.v4i16(<4 x i16> %tmp1, <4 x i16> %tmp2)
93 %tmp1 = load <2 x i32>, <2 x i32>* %A
95 %tmp3 = call <2 x i32> @llvm.aarch64.neon.uabd.v2i32(<2 x i32> %tmp1, <2 x i32> %tmp2)
105 %tmp1 = shufflevector <16 x i8> %load1, <16 x i8> undef, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
108 %tmp3 = call <8 x i8> @llvm.aarch64.neon.uabd.v8i8(<8 x i8> %tmp1, <8 x i8> %tmp2)
118 %tmp1 = shufflevector <8 x i16> %load1, <8 x i16> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
120 %tmp3 = call <4 x i16> @llvm.aarch64.neon.uabd.v4i16(<4 x i16> %tmp1, <4 x i16> %tmp2)
130 %tmp1 = shufflevector <4 x i32> %load1, <4 x i32> undef, <2 x i32> <i32 2, i32 3>
132 %tmp3 = call <2 x i32> @llvm.aarch64.neon.uabd.v2i32(<2 x i32> %tmp1, <2 x i32> %tmp2)
206 %tmp1 = load <2 x float>, <2 x float>* %A
208 %tmp3 = call <2 x float> @llvm.aarch64.neon.fabd.v2f32(<2 x float> %tmp1, <2 x float> %tmp2)
215 %tmp1 = load <4 x float>, <4 x float>* %A
217 %tmp3 = call <4 x float> @llvm.aarch64.neon.fabd.v4f32(<4 x float> %tmp1, <4 x float> %tmp2)
224 %tmp1 = load <2 x double>, <2 x double>* %A
226 %tmp3 = call <2 x double> @llvm.aarch64.neon.fabd.v2f64(<2 x double> %tmp1, <2 x double> %tmp2)
237 %tmp1 = load <8 x i8>, <8 x i8>* %A
239 %tmp3 = call <8 x i8> @llvm.aarch64.neon.sabd.v8i8(<8 x i8> %tmp1, <8 x i8> %tmp2)
246 %tmp1 = load <16 x i8>, <16 x i8>* %A
248 %tmp3 = call <16 x i8> @llvm.aarch64.neon.sabd.v16i8(<16 x i8> %tmp1, <16 x i8> %tmp2)
255 %tmp1 = load <4 x i16>, <4 x i16>* %A
257 %tmp3 = call <4 x i16> @llvm.aarch64.neon.sabd.v4i16(<4 x i16> %tmp1, <4 x i16> %tmp2)
264 %tmp1 = load <8 x i16>, <8 x i16>* %A
266 %tmp3 = call <8 x i16> @llvm.aarch64.neon.sabd.v8i16(<8 x i16> %tmp1, <8 x i16> %tmp2)
273 %tmp1 = load <2 x i32>, <2 x i32>* %A
275 %tmp3 = call <2 x i32> @llvm.aarch64.neon.sabd.v2i32(<2 x i32> %tmp1, <2 x i32> %tmp2)
282 %tmp1 = load <4 x i32>, <4 x i32>* %A
284 %tmp3 = call <4 x i32> @llvm.aarch64.neon.sabd.v4i32(<4 x i32> %tmp1, <4 x i32> %tmp2)
298 %tmp1 = load <8 x i8>, <8 x i8>* %A
300 %tmp3 = call <8 x i8> @llvm.aarch64.neon.uabd.v8i8(<8 x i8> %tmp1, <8 x i8> %tmp2)
307 %tmp1 = load <16 x i8>, <16 x i8>* %A
309 %tmp3 = call <16 x i8> @llvm.aarch64.neon.uabd.v16i8(<16 x i8> %tmp1, <16 x i8> %tmp2)
316 %tmp1 = load <4 x i16>, <4 x i16>* %A
318 %tmp3 = call <4 x i16> @llvm.aarch64.neon.uabd.v4i16(<4 x i16> %tmp1, <4 x i16> %tmp2)
325 %tmp1 = load <8 x i16>, <8 x i16>* %A
327 %tmp3 = call <8 x i16> @llvm.aarch64.neon.uabd.v8i16(<8 x i16> %tmp1, <8 x i16> %tmp2)
334 %tmp1 = load <2 x i32>, <2 x i32>* %A
336 %tmp3 = call <2 x i32> @llvm.aarch64.neon.uabd.v2i32(<2 x i32> %tmp1, <2 x i32> %tmp2)
343 %tmp1 = load <4 x i32>, <4 x i32>* %A
345 %tmp3 = call <4 x i32> @llvm.aarch64.neon.uabd.v4i32(<4 x i32> %tmp1, <4 x i32> %tmp2)
359 %tmp1 = load <8 x i8>, <8 x i8>* %A
360 %tmp3 = call <8 x i8> @llvm.aarch64.neon.sqabs.v8i8(<8 x i8> %tmp1)
367 %tmp1
368 %tmp3 = call <16 x i8> @llvm.aarch64.neon.sqabs.v16i8(<16 x i8> %tmp1)
375 %tmp1 = load <4 x i16>, <4 x i16>* %A
376 %tmp3 = call <4 x i16> @llvm.aarch64.neon.sqabs.v4i16(<4 x i16> %tmp1)
383 %tmp1 = load <8 x i16>, <8 x i16>* %A
384 %tmp3 = call <8 x i16> @llvm.aarch64.neon.sqabs.v8i16(<8 x i16> %tmp1)
391 %tmp1 = load <2 x i32>, <2 x i32>* %A
392 %tmp3 = call <2 x i32> @llvm.aarch64.neon.sqabs.v2i32(<2 x i32> %tmp1)
399 %tmp1 = load <4 x i32>, <4 x i32>* %A
400 %tmp3 = call <4 x i32> @llvm.aarch64.neon.sqabs.v4i32(<4 x i32> %tmp1)
414 %tmp1 = load <8 x i8>, <8 x i8>* %A
415 %tmp3 = call <8 x i8> @llvm.aarch64.neon.sqneg.v8i8(<8 x i8> %tmp1)
422 %tmp1 = load <16 x i8>, <16 x i8>* %A
423 %tmp3 = call <16 x i8> @llvm.aarch64.neon.sqneg.v16i8(<16 x i8> %tmp1)
430 %tmp1 = load <4 x i16>, <4 x i16>* %A
431 %tmp3 = call <4 x i16> @llvm.aarch64.neon.sqneg.v4i16(<4 x i16> %tmp1)
438 %tmp1 = load <8 x i16>, <8 x i16>* %A
439 %tmp3 = call <8 x i16> @llvm.aarch64.neon.sqneg.v8i16(<8 x i16> %tmp1)
446 %tmp1 = load <2 x i32>, <2 x i32>* %A
447 %tmp3 = call <2 x i32> @llvm.aarch64.neon.sqneg.v2i32(<2 x i32> %tmp1)
454 %tmp1 = load <4 x i32>, <4 x i32>* %A
455 %tmp3 = call <4 x i32> @llvm.aarch64.neon.sqneg.v4i32(<4 x i32> %tmp1)
469 %tmp1 = load <8 x i8>, <8 x i8>* %A
470 %tmp3 = call <8 x i8> @llvm.aarch64.neon.abs.v8i8(<8 x i8> %tmp1)
477 %tmp1 = load <16 x i8>, <16 x i8>* %A
478 %tmp3 = call <16 x i8> @llvm.aarch64.neon.abs.v16i8(<16 x i8> %tmp1)
485 %tmp1 = load <4 x i16>, <4 x i16>* %A
486 %tmp3 = call <4 x i16> @llvm.aarch64.neon.abs.v4i16(<4 x i16> %tmp1)
493 %tmp1 = load <8 x i16>, <8 x i16>* %A
494 %tmp3 = call <8 x i16> @llvm.aarch64.neon.abs.v8i16(<8 x i16> %tmp1)
501 %tmp1 = load <2 x i32>, <2 x i32>* %A
502 %tmp3 = call <2 x i32> @llvm.aarch64.neon.abs.v2i32(<2 x i32> %tmp1)
509 %tmp1 = load <4 x i32>, <4 x i32>* %A
510 %tmp3 = call <4 x i32> @llvm.aarch64.neon.abs.v4i32(<4 x i32> %tmp1)
540 %tmp1 = load <8 x i8>, <8 x i8>* %A
543 %tmp4 = call <8 x i8> @llvm.aarch64.neon.sabd.v8i8(<8 x i8> %tmp1, <8 x i8> %tmp2)
552 %tmp1 = load <4 x i16>, <4 x i16>* %A
555 %tmp4 = call <4 x i16> @llvm.aarch64.neon.sabd.v4i16(<4 x i16> %tmp1, <4 x i16> %tmp2)
564 %tmp1 = load <2 x i32>, <2 x i32>* %A
567 %tmp4 = call <2 x i32> @llvm.aarch64.neon.sabd.v2i32(<2 x i32> %tmp1, <2 x i32> %tmp2)
580 %tmp1 = shufflevector <16 x i8> %load1, <16 x i8> undef, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
582 %tmp4 = call <8 x i8> @llvm.aarch64.neon.sabd.v8i8(<8 x i8> %tmp1, <8 x i8> %tmp2)
594 %tmp1 = shufflevector <8 x i16> %load1, <8 x i16> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
596 %tmp4 = call <4 x i16> @llvm.aarch64.neon.sabd.v4i16(<4 x i16> %tmp1, <4 x i16> %tmp2)
608 %tmp1 = shufflevector <4 x i32> %load1, <4 x i32> undef, <2 x i32> <i32 2, i32 3>
610 %tmp4 = call <2 x i32> @llvm.aarch64.neon.sabd.v2i32(<2 x i32> %tmp1, <2 x i32> %tmp2)
619 %tmp1 = load <8 x i8>, <8 x i8>* %A
622 %tmp4 = call <8 x i8> @llvm.aarch64.neon.uabd.v8i8(<8 x i8> %tmp1, <8 x i8> %tmp2)
631 %tmp1 = load <4 x i16>, <4 x i16>* %A
634 %tmp4 = call <4 x i16> @llvm.aarch64.neon.uabd.v4i16(<4 x i16> %tmp1, <4 x i16> %tmp2)
643 %tmp1 = load <2 x i32>, <2 x i32>* %A
646 %tmp4 = call <2 x i32> @llvm.aarch64.neon.uabd.v2i32(<2 x i32> %tmp1, <2 x i32> %tmp2)
658 %tmp1 = shufflevector <16 x i8> %load1, <16 x i8> undef, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
660 %tmp4 = call <8 x i8> @llvm.aarch64.neon.uabd.v8i8(<8 x i8> %tmp1, <8 x i8> %tmp2)
672 %tmp1 = shufflevector <8 x i16> %load1, <8 x i16> undef, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
674 %tmp4 = call <4 x i16> @llvm.aarch64.neon.uabd.v4i16(<4 x i16> %tmp1, <4 x i16> %tmp2)
686 %tmp1 = shufflevector <4 x i32> %load1, <4 x i32> undef, <2 x i32> <i32 2, i32 3>
688 %tmp4 = call <2 x i32> @llvm.aarch64.neon.uabd.v2i32(<2 x i32> %tmp1, <2 x i32> %tmp2)
697 %tmp1 = load <8 x i8>, <8 x i8>* %A
699 %tmp3 = call <8 x i8> @llvm.aarch64.neon.sabd.v8i8(<8 x i8> %tmp1, <8 x i8> %tmp2)
708 %tmp1 = load <16 x i8>, <16 x i8>* %A
710 %tmp3 = call <16 x i8> @llvm.aarch64.neon.sabd.v16i8(<16 x i8> %tmp1, <16 x i8> %tmp2)
719 %tmp1 = load <4 x i16>, <4 x i16>* %A
721 %tmp3 = call <4 x i16> @llvm.aarch64.neon.sabd.v4i16(<4 x i16> %tmp1, <4 x i16> %tmp2)
730 %tmp1 = load <8 x i16>, <8 x i16>* %A
732 %tmp3 = call <8 x i16> @llvm.aarch64.neon.sabd.v8i16(<8 x i16> %tmp1, <8 x i16> %tmp2)
741 %tmp1 = load <2 x i32>, <2 x i32>* %A
743 %tmp3 = call <2 x i32> @llvm.aarch64.neon.sabd.v2i32(<2 x i32> %tmp1, <2 x i32> %tmp2)
752 %tmp1 = load <4 x i32>, <4 x i32>* %A
754 %tmp3 = call <4 x i32> @llvm.aarch64.neon.sabd.v4i32(<4 x i32> %tmp1, <4 x i32> %tmp2)
763 %tmp1 = load <8 x i8>, <8 x i8>* %A
765 %tmp3 = call <8 x i8> @llvm.aarch64.neon.uabd.v8i8(<8 x i8> %tmp1, <8 x i8> %tmp2)
774 %tmp1 = load <16 x i8>, <16 x i8>* %A
776 tmp1, <16 x i8> %tmp2)
785 %tmp1 = load <4 x i16>, <4 x i16>* %A
787 %tmp3 = call <4 x i16> @llvm.aarch64.neon.uabd.v4i16(<4 x i16> %tmp1, <4 x i16> %tmp2)
796 %tmp1 = load <8 x i16>, <8 x i16>* %A
798 %tmp3 = call <8 x i16> @llvm.aarch64.neon.uabd.v8i16(<8 x i16> %tmp1, <8 x i16> %tmp2)
807 %tmp1 = load <2 x i32>, <2 x i32>* %A
809 %tmp3 = call <2 x i32> @llvm.aarch64.neon.uabd.v2i32(<2 x i32> %tmp1, <2 x i32> %tmp2)
818 %tmp1 = load <4 x i32>, <4 x i32>* %A
820 %tmp3 = call <4 x i32> @llvm.aarch64.neon.uabd.v4i32(<4 x i32> %tmp1, <4 x i32> %tmp2)
