Lines Matching full:arg0
68 %arg0 = bitcast <4 x i64> %a0 to <32 x i8>
70 %res = add <32 x i8> %arg0, %arg1
85 %arg0 = bitcast <4 x i64> %a0 to <16 x i16>
87 %res = add <16 x i16> %arg0, %arg1
102 %arg0 = bitcast <4 x i64> %a0 to <8 x i32>
104 %res = add <8 x i32> %arg0, %arg1
133 %arg0 = bitcast <4 x i64> %a0 to <32 x i8>
135 %res = call <32 x i8> @llvm.x86.avx2.padds.b(<32 x i8> %arg0, <32 x i8> %arg1)
151 %arg0 = bitcast <4 x i64> %a0 to <16 x i16>
153 %res = call <16 x i16> @llvm.x86.avx2.padds.w(<16 x i16> %arg0, <16 x i16> %arg1)
169 %arg0 = bitcast <4 x i64> %a0 to <32 x i8>
171 %res = call <32 x i8> @llvm.x86.avx2.paddus.b(<32 x i8> %arg0, <32 x i8> %arg1)
187 %arg0 = bitcast <4 x i64> %a0 to <16 x i16>
189 %res = call <16 x i16> @llvm.x86.avx2.paddus.w(<16 x i16> %arg0, <16 x i16> %arg1)
205 %arg0 = bitcast <4 x i64> %a0 to <32 x i8>
207 %shuf = shufflevector <32 x i8> %arg0, <32 x i8> %arg1, <32 x i32> <i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 32, i32 33, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31, i32 48, i32 49>
222 %arg0 = bitcast <4 x i64> %a0 to <32 x i8>
224 %shuf = shufflevector <32 x i8> %arg0, <32 x i8> %arg1, <32 x i32> <i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 32, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31, i32 48>
272 %arg0 = bitcast <4 x i64> %a0 to <32 x i8>
274 %res = call <32 x i8> @llvm.x86.avx2.pavg.b(<32 x i8> %arg0, <32 x i8> %arg1)
290 %arg0 = bitcast <4 x i64> %a0 to <16 x i16>
292 %res = call <16 x i16> @llvm.x86.avx2.pavg.w(<16 x i16> %arg0, <16 x i16> %arg1)
308 %arg0 = bitcast <4 x i64> %a0 to <16 x i16>
310 %shuf = shufflevector <16 x i16> %arg0, <16 x i16> %arg1, <16 x i32> <i32 0, i32 17, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 25, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
325 %arg0 = bitcast <2 x i64> %a0 to <4 x i32>
327 %shuf = shufflevector <4 x i32> %arg0, <4 x i32> %arg1, <4 x i32> <i32 4, i32 1, i32 6, i32 3>
342 %arg0 = bitcast <4 x i64> %a0 to <8 x i32>
344 %shuf = shufflevector <8 x i32> %arg0, <8 x i32> %arg1, <8 x i32> <i32 8, i32 1, i32 10, i32 3, i32 12, i32 13, i32 6, i32 7>
359 %arg0 = bitcast <4 x i64> %a0 to <32 x i8>
362 %call = call <32 x i8> @llvm.x86.avx2.pblendvb(<32 x i8> %arg0, <32 x i8> %arg1, <32 x i8> %arg2)
378 %arg0 = bitcast <2 x i64> %a0 to <16 x i8>
379 %shuf = shufflevector <16 x i8> %arg0, <16 x i8> undef, <16 x i32> zeroinitializer
394 %arg0 = bitcast <4 x i64> %a0 to <32 x i8>
395 %shuf = shufflevector <32 x i8> %arg0, <32 x i8> undef, <32 x i32> zeroinitializer
410 %arg0 = bitcast <2 x i64> %a0 to <4 x i32>
411 %shuf = shufflevector <4 x i32> %arg0, <4 x i32> undef, <4 x i32> zeroinitializer
426 %arg0 = bitcast <4 x i64> %a0 to <8 x i32>
427 %shuf = shufflevector <8 x i32> %arg0, <8 x i32> undef, <8 x i32> zeroinitializer
540 %arg0 = bitcast <2 x i64> %a0 to <8 x i16>
541 %shuf = shufflevector <8 x i16> %arg0, <8 x i16> undef, <8 x i32> zeroinitializer
556 %arg0 = bitcast <4 x i64> %a0 to <16 x i16>
557 %shuf = shufflevector <16 x i16> %arg0, <16 x i16> undef, <16 x i32> zeroinitializer
572 %arg0 = bitcast <4 x i64> %a0 to <32 x i8>
573 %shuf = shufflevector <32 x i8> zeroinitializer, <32 x i8> %arg0, <32 x i32> <i32 13, i32 14, i32 15, i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 29, i32 30, i32 31, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60>
588 %arg0 = bitcast <4 x i64> %a0 to <32 x i8>
589 %shuf = shufflevector <32 x i8> %arg0, <32 x i8> zeroinitializer, <32 x i32> <i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 32, i32 33, i32 34, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31, i32 48, i32 49, i32 50>
604 %arg0 = bitcast <4 x i64> %a0 to <32 x i8>
606 %cmp = icmp eq <32 x i8> %arg0, %arg1
622 %arg0 = bitcast <4 x i64> %a0 to <16 x i16>
624 %cmp = icmp eq <16 x i16> %arg0, %arg1
640 %arg0 = bitcast <4 x i64> %a0 to <8 x i32>
642 %cmp = icmp eq <8 x i32> %arg0, %arg1
673 %arg0 = bitcast <4 x i64> %a0 to <32 x i8>
675 %cmp = icmp sgt <32 x i8> %arg0, %arg1
691 %arg0 = bitcast <4 x i64> %a0 to <16 x i16>
693 %cmp = icmp sgt <16 x i16> %arg0, %arg1
709 %arg0 = bitcast <4 x i64> %a0 to <8 x i32>
711 %cmp = icmp sgt <8 x i32> %arg0, %arg1
742 %arg0 = bitcast <2 x i64> %a0 to <16 x i8>
743 %ext = sext <16 x i8> %arg0 to <16 x i16>
758 %arg0 = bitcast <2 x i64> %a0 to <16 x i8>
759 %shuf = shufflevector <16 x i8> %arg0, <16 x i8> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
775 %arg0 = bitcast <2 x i64> %a0 to <16 x i8>
776 %shuf = shufflevector <16 x i8> %arg0, <16 x i8> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
791 %arg0 = bitcast <2 x i64> %a0 to <8 x i16>
792 %ext = sext <8 x i16> %arg0 to <8 x i32>
807 %arg0 = bitcast <2 x i64> %a0 to <8 x i16>
808 %shuf = shufflevector <8 x i16> %arg0, <8 x i16> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
823 %arg0 = bitcast <2 x i64> %a0 to <4 x i32>
824 %ext = sext <4 x i32> %arg0 to <4 x i64>
838 %arg0 = bitcast <2 x i64> %a0 to <16 x i8>
839 %ext = zext <16 x i8> %arg0 to <16 x i16>
854 %arg0 = bitcast <2 x i64> %a0 to <16 x i8>
855 %shuf = shufflevector <16 x i8> %arg0, <16 x i8> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
871 %arg0 = bitcast <2 x i64> %a0 to <16 x i8>
872 %shuf = shufflevector <16 x i8> %arg0, <16 x i8> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
887 %arg0 = bitcast <2 x i64> %a0 to <8 x i16>
888 %ext = zext <8 x i16> %arg0 to <8 x i32>
903 %arg0 = bitcast <2 x i64> %a0 to <8 x i16>
904 %shuf = shufflevector <8 x i16> %arg0
919 %arg0 = bitcast <2 x i64> %a0 to <4 x i32>
920 %ext = zext <4 x i32> %arg0 to <4 x i64>
950 %arg0 = bitcast <4 x i64> %a0 to <16 x i16>
952 %res = call <16 x i16> @llvm.x86.avx2.phadd.w(<16 x i16> %arg0, <16 x i16> %arg1)
968 %arg0 = bitcast <4 x i64> %a0 to <8 x i32>
970 %res = call <8 x i32> @llvm.x86.avx2.phadd.d(<8 x i32> %arg0, <8 x i32> %arg1)
986 %arg0 = bitcast <4 x i64> %a0 to <16 x i16>
988 %res = call <16 x i16> @llvm.x86.avx2.phadd.sw(<16 x i16> %arg0, <16 x i16> %arg1)
1004 %arg0 = bitcast <4 x i64> %a0 to <16 x i16>
1006 %res = call <16 x i16> @llvm.x86.avx2.phsub.w(<16 x i16> %arg0, <16 x i16> %arg1)
1022 %arg0 = bitcast <4 x i64> %a0 to <8 x i32>
1024 %res = call <8 x i32> @llvm.x86.avx2.phsub.d(<8 x i32> %arg0, <8 x i32> %arg1)
1040 %arg0 = bitcast <4 x i64> %a0 to <16 x i16>
1042 %res = call <16 x i16> @llvm.x86.avx2.phsub.sw(<16 x i16> %arg0, <16 x i16> %arg1)
1063 %arg0 = bitcast i32 *%a0 to i8*
1066 %call = call <4 x i32> @llvm.x86.avx2.gather.d.d(<4 x i32> undef, i8* %arg0, <4 x i32> %arg1, <4 x i32> %mask, i8 2)
1083 %arg0 = bitcast <2 x i64> %a0 to <4 x i32>
1087 %call = call <4 x i32> @llvm.x86.avx2.gather.d.d(<4 x i32> %arg0, i8* %arg1, <4 x i32> %arg2, <4 x i32> %arg3, i8 2)
1107 %arg0 = bitcast i32 *%a0 to i8*
1110 %call = call <8 x i32> @llvm.x86.avx2.gather.d.d.256(<8 x i32> undef, i8* %arg0, <8 x i32> %arg1, <8 x i32> %mask, i8 2)
1127 %arg0 = bitcast <4 x i64> %a0 to <8 x i32>
1131 %call = call <8 x i32> @llvm.x86.avx2.gather.d.d.256(<8 x i32> %arg0, i8* %arg1, <8 x i32> %arg2, <8 x i32> %arg3, i8 2)
1151 %arg0 = bitcast i64 *%a0 to i8*
1153 %res = call <2 x i64> @llvm.x86.avx2.gather.d.q(<2 x i64> undef, i8* %arg0, <4 x i32> %arg1, <2 x i64> <i64 -1, i64 -1>, i8 2)
1190 %arg0 = bitcast i64 *%a0 to i8*
1192 %res = call <4 x i64> @llvm.x86.avx2.gather.d.q.256(<4 x i64> undef, i8* %arg0, <4 x i32> %arg1, <4 x i64> <i64 -1, i64 -1, i64 -1, i64 -1>, i8 2)
1229 %arg0 = bitcast double *%a0 to i8*
1234 %res = call <2 x double> @llvm.x86.avx2.gather.d.pd(<2 x double> undef, i8* %arg0, <4 x i32> %arg1, <2 x double> %mask, i8 2)
1273 %arg0 = bitcast double *%a0 to i8*
1276 %res = call <4 x double> @llvm.x86.avx2.gather.d.pd.256(<4 x double> undef, i8* %arg0, <4 x i32> %arg1, <4 x double> %mask, i8 2)
1313 %arg0 = bitcast float *%a0 to i8*
1318 %call = call <4 x float> @llvm.x86.avx2.gather.d.ps(<4 x float> undef, i8* %arg0, <4 x i32> %arg1, <4 x float> %mask, i8 2)
1357 %arg0 = bitcast float *%a0 to i8*
1360 %call = call <8 x float> @llvm.x86.avx2.gather.d.ps.256(<8 x float> undef, i8* %arg0, <8 x i32> %arg1, <8 x float> %mask, i8 2)
1397 %arg0 = bitcast i32 *%a0 to i8*
1399 %call = call <4 x i32> @llvm.x86.avx2.gather.q.d(<4 x i32> undef, i8* %arg0, <2 x i64> %a1, <4 x i32> %mask, i8 2)
1416 %arg0 = bitcast <2 x i64> %a0 to <4 x i32>
1419 %call = call <4 x i32> @llvm.x86.avx2.gather.q.d(<4 x i32> %arg0, i8* %arg1, <2 x i64> %a2, <4 x i32> %arg3, i8 2)
1441 %arg0 = bitcast i32 *%a0 to i8*
1443 %call = call <4 x i32> @llvm.x86.avx2.gather.q.d.256(<4 x i32> undef, i8* %arg0, <4 x i64> %a1, <4 x i32> %mask, i8 2)
1462 %arg0 = bitcast <2 x i64> %a0 to <4 x i32>
1465 %call = call <4 x i32> @llvm.x86.avx2.gather.q.d.256(<4 x i32> %arg0, i8* %arg1, <4 x i64> %a2, <4 x i32> %arg3, i8 2)
1485 %arg0 = bitcast i64 *%a0 to i8*
1486 %call = call <2 x i64> @llvm.x86.avx2.gather.q.q(<2 x i64> undef, i8* %arg0, <2 x i64> %a1, <2 x i64> <i64 -1, i64 -1>, i8 2)
1522 %arg0 = bitcast i64 *%a0 to i8*
1523 %call = call <4 x i64> @llvm.x86.avx2.gather.q.q.256(<4 x i64> undef, i8* %arg0, <4 x i64> %a1, <4 x i64> <i64 -1, i64 -1, i64 -1, i64 -1>, i8 2)
1559 %arg0 = bitcast double *%a0 to i8*
1563 %call = call <2 x double> @llvm.x86.avx2.gather.q.pd(<2 x double> undef, i8* %arg0, <2 x i64> %a1, <2 x double> %mask, i8 2)
1601 %arg0 = bitcast double *%a0 to i8*
1603 %call = call <4 x double> @llvm.x86.avx2.gather.q.pd.256(<4 x double> undef, i8* %arg0, <4 x i64> %a1, <4 x double> %mask, i8 2)
1639 %arg0 = bitcast float *%a0 to i8*
1643 %call = call <4 x float> @llvm.x86.avx2.gather.q.ps(<4 x float> undef, i8* %arg0, <2 x i64> %a1, <4 x float> %mask, i8 2)
1681 %arg0 = bitcast float *%a0 to i8*
1685 %call = call <4 x float> @llvm.x86.avx2.gather.q.ps.256(<4 x float> undef, i8* %arg0, <4 x i64> %a1, <4 x float> %mask, i8 2)
1750 %arg0 = bitcast <4 x i64> %a0 to <16 x i16>
1752 %res = call <8 x i32> @llvm.x86.avx2.pmadd.wd(<16 x i16> %arg0, <16 x i16> %arg1)
1768 %arg0 = bitcast <4 x i64> %a0 to <32 x i8>
1770 %res = call <16 x i16> @llvm.x86.avx2.pmadd.ub.sw(<32 x i8> %arg0, <32 x i8> %arg1)
1787 %arg0 = bitcast i32* %a0 to i8*
1789 %call = call <4 x i32> @llvm.x86.avx2.maskload.d(i8* %arg0, <4 x i32> %arg1)
1806 %arg0 = bitcast i32* %a0 to i8*
1808 %call = call <8 x i32> @llvm.x86.avx2.maskload.d.256(i8* %arg0, <8 x i32> %arg1)
1825 %arg0 = bitcast i64* %a0 to i8*
1826 %res = call <2 x i64> @llvm.x86.avx2.maskload.q(i8* %arg0, <2 x i64> %a1)
1842 %arg0 = bitcast i64* %a0 to i8*
1843 %res = call <4 x i64> @llvm.x86.avx2.maskload.q.256(i8* %arg0, <4 x i64> %a1)
1859 %arg0 = bitcast float* %a0 to i8*
1862 call void @llvm.x86.avx2.maskstore.d(i8* %arg0, <4 x i32> %arg1, <4 x i32> %arg2)
1880 %arg0 = bitcast float* %a0 to i8*
1883 call void @llvm.x86.avx2.maskstore.d.256(i8* %arg0, <8 x i32> %arg1, <8 x i32> %arg2)
1899 %arg0 = bitcast i64* %a0 to i8*
1900 call void @llvm.x86.avx2.maskstore.q(i8* %arg0, <2 x i64> %a1, <2 x i64> %a2)
1918 %arg0 = bitcast i64* %a0 to i8*
1919 call void @llvm.x86.avx2.maskstore.q.256(i8* %arg0, <4 x i64> %a1, <4 x i64> %a2)
1934 %arg0 = bitcast <4 x i64> %a0 to <32 x i8>
1936 %cmp = icmp sgt <32 x i8> %arg0, %arg1
1937 %sel = select <32 x i1> %cmp, <32 x i8> %arg0, <32 x i8> %arg1
1952 %arg0 = bitcast <4 x i64> %a0 to <16 x i16>
1954 %cmp = icmp sgt <16 x i16> %arg0, %arg1
1955 %sel = select <16 x i1> %cmp, <16 x i16> %arg0, <16 x i16> %arg1
1970 %arg0 = bitcast <4 x i64> %a0 to <8 x i32>
1972 %cmp = icmp sgt <8 x i32> %arg0, %arg1
1973 %sel = select <8 x i1> %cmp, <8 x i32> %arg0, <8 x i32> %arg1
1988 %arg0 = bitcast <4 x i64> %a0 to <32 x i8>
1990 %cmp = icmp ugt <32 x i8> %arg0, %arg1
1991 %sel = select <32 x i1> %cmp, <32 x i8> %arg0, <32 x i8> %arg1
2006 %arg0 = bitcast <4 x i64> %a0 to <16 x i16>
2008 %cmp = icmp ugt <16 x i16> %arg0, %arg1
2009 %sel = select <16 x i1> %cmp, <16 x i16> %arg0, <16 x i16> %arg1
2024 %arg0 = bitcast <4 x i64> %a0 to <8 x i32>
2026 %cmp = icmp ugt <8 x i32> %arg0, %arg1
2027 %sel = select <8 x i1> %cmp, <8 x i32> %arg0, <8 x i32> %arg1
2042 %arg0 = bitcast <4 x i64> %a0 to <32 x i8>
2044 %cmp = icmp slt <32 x i8> %arg0, %arg1
2045 %sel = select <32 x i1> %cmp, <32 x i8> %arg0, <32 x i8> %arg1
2060 %arg0 = bitcast <4 x i64> %a0 to <16 x i16>
2062 %cmp = icmp slt <16 x i16> %arg0, %arg1
2063 %sel = select <16 x i1> %cmp, <16 x i16> %arg0, <16 x i16> %arg1
2078 %arg0 = bitcast <4 x i64> %a0 to <8 x i32>
2080 %cmp = icmp slt <8 x i32> %arg0, %arg1
2081 %sel = select <8 x i1> %cmp, <8 x i32> %arg0, <8 x i32> %arg1
2096 %arg0 = bitcast <4 x i64> %a0 to <32 x i8>
2098 %cmp = icmp ult <32 x i8> %arg0, %arg1
2099 %sel = select <32 x i1> %cmp, <32 x i8> %arg0, <32 x i8> %arg1
2114 %arg0 = bitcast <4 x i64> %a0 to <16 x i16>
2116 %cmp = icmp ult <16 x i16> %arg0, %arg1
2117 %sel = select <16 x i1> %cmp, <16 x i16> %arg0, <16 x i16> %arg1
2132 %arg0 = bitcast <4 x i64> %a0 to <8 x i32>
2134 %cmp = icmp ult <8 x i32> %arg0, %arg1
2135 %sel = select <8 x i1> %cmp, <8 x i32> %arg0, <8 x i32> %arg1
2152 %arg0 = bitcast <4 x i64> %a0 to <32 x i8>
2153 %res = call i32 @llvm.x86.avx2.pmovmskb(<32 x i8> %arg0)
2168 %arg0 = bitcast <4 x i64> %a0 to <32 x i8>
2170 %call = call <16 x i16> @llvm.x86.avx2.mpsadbw(<32 x i8> %arg0, <32 x i8> %arg1, i8 3)
2186 %arg0 = bitcast <4 x i64> %a0 to <8 x i32>
2188 %res = call <4 x i64> @llvm.x86.avx2.pmul.dq(<8 x i32> %arg0, <8 x i32> %arg1)
2203 %arg0 = bitcast <4 x i64> %a0 to <8 x i32>
2205 %res = call <4 x i64> @llvm.x86.avx2.pmulu.dq(<8 x i32> %arg0, <8 x i32> %arg1)
2220 %arg0 = bitcast <4 x i64> %a0 to <16 x i16>
2222 arg0, <16 x i16> %arg1)
2238 %arg0 = bitcast <4 x i64> %a0 to <16 x i16>
2240 %res = call <16 x i16> @llvm.x86.avx2.pmulhu.w(<16 x i16> %arg0, <16 x i16> %arg1)
2256 %arg0 = bitcast <4 x i64> %a0 to <16 x i16>
2258 %res = call <16 x i16> @llvm.x86.avx2.pmul.hr.sw(<16 x i16> %arg0, <16 x i16> %arg1)
2274 %arg0 = bitcast <4 x i64> %a0 to <16 x i16>
2276 %res = mul <16 x i16> %arg0, %arg1
2291 %arg0 = bitcast <4 x i64> %a0 to <8 x i32>
2293 %res = mul <8 x i32> %arg0, %arg1
2322 %arg0 = bitcast <4 x i64> %a0 to <16 x i16>
2324 %call = call <32 x i8> @llvm.x86.avx2.packsswb(<16 x i16> %arg0, <16 x i16> %arg1)
2340 %arg0 = bitcast <4 x i64> %a0 to <8 x i32>
2342 %call = call <16 x i16> @llvm.x86.avx2.packssdw(<8 x i32> %arg0, <8 x i32> %arg1)
2358 %arg0 = bitcast <4 x i64> %a0 to <16 x i16>
2360 %call = call <32 x i8> @llvm.x86.avx2.packuswb(<16 x i16> %arg0, <16 x i16> %arg1)
2376 %arg0 = bitcast <4 x i64> %a0 to <8 x i32>
2378 %call = call <16 x i16> @llvm.x86.avx2.packusdw(<8 x i32> %arg0, <8 x i32> %arg1)
2437 %arg0 = bitcast <4 x i64> %a0 to <8 x i32>
2439 %call = call <8 x i32> @llvm.x86.avx2.permd(<8 x i32> %arg0, <8 x i32> %arg1)
2471 %arg0 = bitcast <4 x i64> %a0 to <32 x i8>
2473 %res = call <4 x i64> @llvm.x86.avx2.psad.bw(<32 x i8> %arg0, <32 x i8> %arg1)
2488 %arg0 = bitcast <4 x i64> %a0 to <8 x i32>
2489 %shuf = shufflevector <8 x i32> %arg0, <8 x i32> undef, <8 x i32> <i32 3, i32 3, i32 0, i32 0, i32 7, i32 7, i32 4, i32 4>
2504 %arg0 = bitcast <4 x i64> %a0 to <32 x i8>
2506 %shuf = call <32 x i8> @llvm.x86.avx2.pshuf.b(<32 x i8> %arg0, <32 x i8> %arg1)
2522 %arg0 = bitcast <4 x i64> %a0 to <16 x i16>
2523 %shuf = shufflevector <16 x i16> %arg0, <16 x i16> undef, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 7, i32 6, i32 6, i32 5, i32 8, i32 9, i32 10, i32 11, i32 15, i32 14, i32 14, i32 13>
2538 %arg0 = bitcast <4 x i64> %a0 to <16 x i16>
2539 %shuf = shufflevector <16 x i16> %arg0, <16 x i16> undef, <16 x i32> <i32 3, i32 0, i32 1, i32 1, i32 4, i32 5, i32 6, i32 7, i32 11, i32 8, i32 9, i32 9, i32 12, i32 13, i32 14, i32 15>
2554 %arg0 = bitcast <4 x i64> %a0 to <32 x i8>
2556 %call = call <32 x i8> @llvm.x86.avx2.psign.b(<32 x i8> %arg0, <32 x i8> %arg1)
2572 %arg0 = bitcast <4 x i64> %a0 to <16 x i16>
2574 %call = call <16 x i16> @llvm.x86.avx2.psign.w(<16 x i16> %arg0, <16 x i16> %arg1)
2590 %arg0 = bitcast <4 x i64> %a0 to <8 x i32>
2592 %call = call <8 x i32> @llvm.x86.avx2.psign.d(<8 x i32> %arg0, <8 x i32> %arg1)
2608 %arg0 = bitcast <4 x i64> %a0 to <16 x i16>
2610 %res = call <16 x i16> @llvm.x86.avx2.psll.w(<16 x i16> %arg0, <8 x i16> %arg1)
2626 %arg0 = bitcast <4 x i64> %a0 to <8 x i32>
2628 %res = call <8 x i32> @llvm.x86.avx2.psll.d(<8 x i32> %arg0, <4 x i32> %arg1)
2659 %arg0 = bitcast <4 x i64> %a0 to <16 x i16>
2660 %res = call <16 x i16> @llvm.x86.avx2.pslli.w(<16 x i16> %arg0, i32 3)
2676 %arg0 = bitcast <4 x i64> %a0 to <8 x i32>
2677 %res = call <8 x i32> @llvm.x86.avx2.pslli.d(<8 x i32> %arg0, i32 3)
2708 %arg0 = bitcast <4 x i64> %a0 to <32 x i8>
2709 %shuf = shufflevector <32 x i8> zeroinitializer, <32 x i8> %arg0, <32 x i32> <i32 13, i32 14, i32 15, i32 32, i32 33, i32 34, i32 35, i32 36, i32 37, i32 38, i32 39, i32 40, i32 41, i32 42, i32 43, i32 44, i32 29, i32 30, i32 31, i32 48, i32 49, i32 50, i32 51, i32 52, i32 53, i32 54, i32 55, i32 56, i32 57, i32 58, i32 59, i32 60>
2724 %arg0 = bitcast <2 x i64> %a0 to <4 x i32>
2726 %res = call <4 x i32> @llvm.x86.avx2.psllv.d(<4 x i32> %arg0, <4 x i32> %arg1)
2742 %arg0 = bitcast <4 x i64> %a0 to <8 x i32>
2744 %res = call <8 x i32> @llvm.x86.avx2.psllv.d.256(<8 x i32> %arg0, <8 x i32> %arg1)
2790 %arg0 = bitcast <4 x i64> %a0 to <16 x i16>
2792 %res = call <16 x i16> @llvm.x86.avx2.psra.w(<16 x i16> %arg0, <8 x i16> %arg1)
2808 %arg0 = bitcast <4 x i64> %a0 to <8 x i32>
2810 %res = call <8 x i32> @llvm.x86.avx2.psra.d(<8 x i32> %arg0, <4 x i32> %arg1)
2826 %arg0 = bitcast <4 x i64> %a0 to <16 x i16>
2827 %res = call <16 x i16> @llvm.x86.avx2.psrai.w(<16 x i16> %arg0, i32 3)
2843 %arg0 = bitcast <4 x i64> %a0 to <8 x i32>
2844 %res = call <8 x i32> @llvm.x86.avx2.psrai.d(<8 x i32> %arg0, i32 3)
2860 %arg0 = bitcast <2 x i64> %a0 to <4 x i32>
2862 %res = call <4 x i32> @llvm.x86.avx2.psrav.d(<4 x i32> %arg0, <4 x i32> %arg1)
2878 %arg0 = bitcast <4 x i64> %a0 to <8 x i32>
2880 %res = call <8 x i32> @llvm.x86.avx2.psrav.d.256(<8 x i32> %arg0, <8 x i32> %arg1)
2896 %arg0 = bitcast <4 x i64> %a0 to <16 x i16>
2898 %res = call <16 x i16> @llvm.x86.avx2.psrl.w(<16 x i16> %arg0, <8 x i16> %arg1)
2914 %arg0 = bitcast <4 x i64> %a0 to <8 x i32>
2916 %res = call <8 x i32> @llvm.x86.avx2.psrl.d(<8 x i32> %arg0, <4 x i32> %arg1)
2947 %arg0 = bitcast <4 x i64> %a0 to <16 x i16>
2948 %res = call <16 x i16> @llvm.x86.avx2.psrli.w(<16 x i16> %arg0, i32 3)
2964 %arg0 = bitcast <4 x i64> %a0 to <8 x i32>
2965 %res = call <8 x i32> @llvm.x86.avx2.psrli.d(<8 x i32> %arg0, i32 3)
2996 %arg0 = bitcast <4 x i64> %a0 to <32 x i8>
2997 %shuf = shufflevector <32 x i8> %arg0, <32 x i8> zeroinitializer, <32 x i32> <i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 32, i32 33, i32 34, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31, i32 48, i32 49, i32 50>
3012 %arg0 = bitcast <2 x i64> %a0 to <4 x i32>
3014 %res = call <4 x i32> @llvm.x86.avx2.psrlv.d(<4 x i32> %arg0, <4 x i32> %arg1)
3030 %arg0 = bitcast <4 x i64> %a0 to <8 x i32>
3032 %res = call <8 x i32> @llvm.x86.avx2.psrlv.d.256(<8 x i32> %arg0, <8 x i32> %arg1)
3079 %arg0 = bitcast <4 x i64> *%a0 to i8*
3080 %res = call <4 x i64> @llvm.x86.avx2.movntdqa(i8* %arg0)
3095 %arg0 = bitcast <4 x i64> %a0 to <32 x i8>
3097 %res = sub <32 x i8> %arg0, %arg1
3112 %arg0 = bitcast <4 x i64> %a0 to <16 x i16>
3114 %res = sub <16 x i16> %arg0, %arg1
3129 %arg0 = bitcast <4 x i64> %a0 to <8 x i32>
3131 %res = sub <8 x i32> %arg0, %arg1
3160 %arg0 = bitcast <4 x i64> %a0 to <32 x i8>
3162 %res = call <32 x i8> @llvm.x86.avx2.psubs.b(<32 x i8> %arg0, <32 x i8> %arg1)
3178 %arg0 = bitcast <4 x i64> %a0 to <16 x i16>
3180 %res = call <16 x i16> @llvm.x86.avx2.psubs.w(<16 x i16> %arg0, <16 x i16> %arg1)
3196 %arg0 = bitcast <4 x i64> %a0 to <32 x i8>
3198 %res = call <32 x i8> @llvm.x86.avx2.psubus.b(<32 x i8> %arg0, <32 x i8> %arg1)
3214 %arg0 = bitcast <4 x i64> %a0 to <16 x i16>
3216 %res = call <16 x i16> @llvm.x86.avx2.psubus.w(<16 x i16> %arg0, <16 x i16> %arg1)
3232 %arg0 = bitcast <4 x i64> %a0 to <32 x i8>
3234 %res = shufflevector <32 x i8> %arg0, <32 x i8> %arg1, <32 x i32> <i32 8, i32 40, i32 9, i32 41, i32 10, i32 42, i32 11, i32 43, i32 12, i32 44, i32 13, i32 45, i32 14, i32 46, i32 15, i32 47, i32 24, i32 56, i32 25, i32 57, i32 26, i32 58, i32 27, i32 59, i32 28, i32 60, i32 29, i32 61, i32 30, i32 62, i32 31, i32 63>
3249 %arg0 = bitcast <4 x i64> %a0 to <16 x i16>
3251 %res = shufflevector <16 x i16> %arg0, <16 x i16> %arg1, <16 x i32> <i32 4, i32 20, i32 5, i32 21, i32 6, i32 22, i32 7, i32 23, i32 12, i32 28, i32 13, i32 29, i32 14, i32 30, i32 15, i32 31>
3266 %arg0 = bitcast <4 x i64> %a0 to <8 x i32>
3268 %res = shufflevector <8 x i32> %arg0, <8 x i32> %arg1, <8 x i32> <i32 2, i32 10, i32 3, i32 11, i32 6, i32 14, i32 7, i32 15>
3297 %arg0 = bitcast <4 x i64> %a0 to <32 x i8>
3299 %res = shufflevector <32 x i8> %arg0, <32 x i8> %arg1, <32 x i32> <i32 0, i32 32, i32 1, i32 33, i32 2, i32 34, i32 3, i32 35, i32 4, i32 36, i32 5, i32 37, i32 6, i32 38, i32 7, i32 39, i32 16, i32 48, i32 17, i32 49, i32 18, i32 50, i32 19, i32 51, i32 20, i32 52, i32 21, i32 53, i32 22, i32 54, i32 23, i32 55>
3314 %arg0 = bitcast <4 x i64> %a0 to <16 x i16>
3316 %res = shufflevector <16 x i16> %arg0, <16 x i16> %arg1, <16 x i32> <i32 0, i32 16, i32 1, i32 17, i32 2, i32 18, i32 3, i32 19, i32 8, i32 24, i32 9, i32 25, i32 10, i32 26, i32 11, i32 27>
3331 %arg0 = bitcast <4 x i64> %a0 to <8 x i32>
3333 %res = shufflevector <8 x i32> %arg0, <8 x i32> %arg1, <8 x i32> <i32 0, i32 8, i32 1, i32 9, i32 4, i32 12, i32 5, i32 13>
