| /external/llvm/test/CodeGen/X86/ |
| D | avx512-intrinsics-upgrade.ll | 4 declare <16 x float> @llvm.x86.avx512.mask.broadcast.ss.ps.512(<4 x float>, <16 x float>, i16) noun…
17 …%res = call <16 x float> @llvm.x86.avx512.mask.broadcast.ss.ps.512(<4 x float> %a0, <16 x float> z…
18 …%res1 = call <16 x float> @llvm.x86.avx512.mask.broadcast.ss.ps.512(<4 x float> %a0, <16 x float> …
19 …%res2 = call <16 x float> @llvm.x86.avx512.mask.broadcast.ss.ps.512(<4 x float> %a0, <16 x float> …
25 declare <8 x double> @llvm.x86.avx512.mask.broadcast.sd.pd.512(<2 x double>, <8 x double>, i8) noun…
38 …%res = call <8 x double> @llvm.x86.avx512.mask.broadcast.sd.pd.512(<2 x double> %a0, <8 x double> …
39 …%res1 = call <8 x double> @llvm.x86.avx512.mask.broadcast.sd.pd.512(<2 x double> %a0, <8 x double>…
40 …%res2 = call <8 x double> @llvm.x86.avx512.mask.broadcast.sd.pd.512(<2 x double> %a0, <8 x double>…
46 declare <16 x i32> @llvm.x86.avx512.pbroadcastd.512(<4 x i32>, <16 x i32>, i16)
58 %res = call <16 x i32> @llvm.x86.avx512.pbroadcastd.512(<4 x i32> %x0, <16 x i32> %x1, i16 -1)
[all …]
|
| D | avx512dq-intrinsics.ll | 4 declare <8 x i64> @llvm.x86.avx512.mask.cvtpd2qq.512(<8 x double>, <8 x i64>, i8, i32)
14 …%res = call <8 x i64> @llvm.x86.avx512.mask.cvtpd2qq.512(<8 x double> %x0, <8 x i64> %x1, i8 %x2, …
15 …%res1 = call <8 x i64> @llvm.x86.avx512.mask.cvtpd2qq.512(<8 x double> %x0, <8 x i64> %x1, i8 -1, …
20 declare <8 x i64> @llvm.x86.avx512.mask.cvtpd2uqq.512(<8 x double>, <8 x i64>, i8, i32)
30 …%res = call <8 x i64> @llvm.x86.avx512.mask.cvtpd2uqq.512(<8 x double> %x0, <8 x i64> %x1, i8 %x2,…
31 …%res1 = call <8 x i64> @llvm.x86.avx512.mask.cvtpd2uqq.512(<8 x double> %x0, <8 x i64> %x1, i8 -1,…
36 declare <8 x i64> @llvm.x86.avx512.mask.cvtps2qq.512(<8 x float>, <8 x i64>, i8, i32)
46 …%res = call <8 x i64> @llvm.x86.avx512.mask.cvtps2qq.512(<8 x float> %x0, <8 x i64> %x1, i8 %x2, i…
47 …%res1 = call <8 x i64> @llvm.x86.avx512.mask.cvtps2qq.512(<8 x float> %x0, <8 x i64> %x1, i8 -1, i…
52 declare <8 x i64> @llvm.x86.avx512.mask.cvtps2uqq.512(<8 x float>, <8 x i64>, i8, i32)
[all …]
|
| D | avx512cdvl-intrinsics.ll | 6 declare <4 x i32> @llvm.x86.avx512.mask.lzcnt.d.128(<4 x i32>, <4 x i32>, i8)
18 %res = call <4 x i32> @llvm.x86.avx512.mask.lzcnt.d.128(<4 x i32> %x0, <4 x i32> %x1, i8 %x2)
19 %res1 = call <4 x i32> @llvm.x86.avx512.mask.lzcnt.d.128(<4 x i32> %x0, <4 x i32> %x1, i8 -1)
20 …%res3 = call <4 x i32> @llvm.x86.avx512.mask.lzcnt.d.128(<4 x i32> %x0, <4 x i32> zeroinitializer,…
26 declare <8 x i32> @llvm.x86.avx512.mask.lzcnt.d.256(<8 x i32>, <8 x i32>, i8)
36 %res = call <8 x i32> @llvm.x86.avx512.mask.lzcnt.d.256(<8 x i32> %x0, <8 x i32> %x1, i8 %x2)
37 %res1 = call <8 x i32> @llvm.x86.avx512.mask.lzcnt.d.256(<8 x i32> %x0, <8 x i32> %x1, i8 -1)
42 declare <2 x i64> @llvm.x86.avx512.mask.lzcnt.q.128(<2 x i64>, <2 x i64>, i8)
52 %res = call <2 x i64> @llvm.x86.avx512.mask.lzcnt.q.128(<2 x i64> %x0, <2 x i64> %x1, i8 %x2)
53 %res1 = call <2 x i64> @llvm.x86.avx512.mask.lzcnt.q.128(<2 x i64> %x0, <2 x i64> %x1, i8 -1)
[all …]
|
| D | avx512-gather-scatter-intrin.ll | 4 declare <16 x float> @llvm.x86.avx512.gather.dps.512 (<16 x float>, i8*, <16 x i32>, i16, i32)
5 declare void @llvm.x86.avx512.scatter.dps.512 (i8*, i16, <16 x i32>, <16 x float>, i32)
6 declare <8 x double> @llvm.x86.avx512.gather.dpd.512 (<8 x double>, i8*, <8 x i32>, i8, i32)
7 declare void @llvm.x86.avx512.scatter.dpd.512 (i8*, i8, <8 x i32>, <8 x double>, i32)
9 declare <8 x float> @llvm.x86.avx512.gather.qps.512 (<8 x float>, i8*, <8 x i64>, i8, i32)
10 declare void @llvm.x86.avx512.scatter.qps.512 (i8*, i8, <8 x i64>, <8 x float>, i32)
11 declare <8 x double> @llvm.x86.avx512.gather.qpd.512 (<8 x double>, i8*, <8 x i64>, i8, i32)
12 declare void @llvm.x86.avx512.scatter.qpd.512 (i8*, i8, <8 x i64>, <8 x double>, i32)
23 …%x = call <16 x float> @llvm.x86.avx512.gather.dps.512 (<16 x float> %src, i8* %base, <16 x i32>%i…
25 …call void @llvm.x86.avx512.scatter.dps.512 (i8* %stbuf, i16 %mask, <16 x i32>%ind2, <16 x float> %…
[all …]
|
| D | avx512-intrinsics.ll | 4 declare i32 @llvm.x86.avx512.kortestz.w(i16, i16) nounwind readnone
14 %res = call i32 @llvm.x86.avx512.kortestz.w(i16 %a0, i16 %a1)
18 declare i32 @llvm.x86.avx512.kortestc.w(i16, i16) nounwind readnone
28 %res = call i32 @llvm.x86.avx512.kortestc.w(i16 %a0, i16 %a1)
32 declare i16 @llvm.x86.avx512.kand.w(i16, i16) nounwind readnone
44 %t1 = call i16 @llvm.x86.avx512.kand.w(i16 %a0, i16 8)
45 %t2 = call i16 @llvm.x86.avx512.kand.w(i16 %t1, i16 %a1)
49 declare i16 @llvm.x86.avx512.knot.w(i16) nounwind readnone
57 %res = call i16 @llvm.x86.avx512.knot.w(i16 %a0)
61 declare i16 @llvm.x86.avx512.kunpck.bw(i16, i16) nounwind readnone
[all …]
|
| D | avx512er-intrinsics.ll | 5 …%res = call <16 x float> @llvm.x86.avx512.rsqrt28.ps(<16 x float> %a0, <16 x float> zeroinitialize…
12 …%res = call <16 x float> @llvm.x86.avx512.rsqrt28.ps(<16 x float> %a0, <16 x float> %a1, i16 6, i3…
18 …%res = call <16 x float> @llvm.x86.avx512.rsqrt28.ps(<16 x float> %a0, <16 x float> undef, i16 6, …
25 …%res = call <16 x float> @llvm.x86.avx512.rsqrt28.ps(<16 x float> %a0, <16 x float> zeroinitialize…
31 …%res = call <16 x float> @llvm.x86.avx512.rsqrt28.ps(<16 x float> %a0, <16 x float> undef, i16 6, …
36 declare <16 x float> @llvm.x86.avx512.rsqrt28.ps(<16 x float>, <16 x float>, i16, i32) nounwind rea…
40 …%res = call <16 x float> @llvm.x86.avx512.rcp28.ps(<16 x float> %a0, <16 x float> zeroinitializer,…
43 declare <16 x float> @llvm.x86.avx512.rcp28.ps(<16 x float>, <16 x float>, i16, i32) nounwind readn…
47 …%res = call <8 x double> @llvm.x86.avx512.rcp28.pd(<8 x double> %a0, <8 x double> zeroinitializer,…
50 declare <8 x double> @llvm.x86.avx512.rcp28.pd(<8 x double>, <8 x double>, i8, i32) nounwind readno…
[all …]
|
| D | avx512bwvl-intrinsics-upgrade.ll | 4 declare <32 x i8> @llvm.x86.avx512.pbroadcastb.256(<16 x i8>, <32 x i8>, i32)
16 %res = call <32 x i8> @llvm.x86.avx512.pbroadcastb.256(<16 x i8> %x0, <32 x i8> %x1, i32 -1)
17 %res1 = call <32 x i8> @llvm.x86.avx512.pbroadcastb.256(<16 x i8> %x0, <32 x i8> %x1, i32 %mask)
18 …%res2 = call <32 x i8> @llvm.x86.avx512.pbroadcastb.256(<16 x i8> %x0, <32 x i8> zeroinitializer, …
24 declare <16 x i8> @llvm.x86.avx512.pbroadcastb.128(<16 x i8>, <16 x i8>, i16)
36 %res = call <16 x i8> @llvm.x86.avx512.pbroadcastb.128(<16 x i8> %x0, <16 x i8> %x1, i16 -1)
37 %res1 = call <16 x i8> @llvm.x86.avx512.pbroadcastb.128(<16 x i8> %x0, <16 x i8> %x1, i16 %mask)
38 …%res2 = call <16 x i8> @llvm.x86.avx512.pbroadcastb.128(<16 x i8> %x0, <16 x i8> zeroinitializer, …
44 declare <16 x i16> @llvm.x86.avx512.pbroadcastw.256(<8 x i16>, <16 x i16>, i16)
56 %res = call <16 x i16> @llvm.x86.avx512.pbroadcastw.256(<8 x i16> %x0, <16 x i16> %x1, i16 -1)
[all …]
|
| D | avx512ifmavl-intrinsics.ll | 4 declare <2 x i64> @llvm.x86.avx512.mask.vpmadd52h.uq.128(<2 x i64>, <2 x i64>, <2 x i64>, i8)
22 …%res = call <2 x i64> @llvm.x86.avx512.mask.vpmadd52h.uq.128(<2 x i64> %x0, <2 x i64> %x1, <2 x i6…
23 …%res1 = call <2 x i64> @llvm.x86.avx512.mask.vpmadd52h.uq.128(<2 x i64> %x0, <2 x i64> %x1, <2 x i…
24 …%res2 = call <2 x i64> @llvm.x86.avx512.mask.vpmadd52h.uq.128(<2 x i64> zeroinitializer, <2 x i64>…
25 …%res3 = call <2 x i64> @llvm.x86.avx512.mask.vpmadd52h.uq.128(<2 x i64> %x0, <2 x i64> %x1, <2 x i…
32 declare <4 x i64> @llvm.x86.avx512.mask.vpmadd52h.uq.256(<4 x i64>, <4 x i64>, <4 x i64>, i8)
50 …%res = call <4 x i64> @llvm.x86.avx512.mask.vpmadd52h.uq.256(<4 x i64> %x0, <4 x i64> %x1, <4 x i6…
51 …%res1 = call <4 x i64> @llvm.x86.avx512.mask.vpmadd52h.uq.256(<4 x i64> %x0, <4 x i64> %x1, <4 x i…
52 …%res2 = call <4 x i64> @llvm.x86.avx512.mask.vpmadd52h.uq.256(<4 x i64> zeroinitializer, <4 x i64>…
53 …%res3 = call <4 x i64> @llvm.x86.avx512.mask.vpmadd52h.uq.256(<4 x i64> %x0, <4 x i64> %x1, <4 x i…
[all …]
|
| D | avx512vl-intrinsics.ll | 34 %res0 = call i8 @llvm.x86.avx512.mask.cmp.d.256(<8 x i32> %a0, <8 x i32> %a1, i32 0, i8 -1)
36 %res1 = call i8 @llvm.x86.avx512.mask.cmp.d.256(<8 x i32> %a0, <8 x i32> %a1, i32 1, i8 -1)
38 %res2 = call i8 @llvm.x86.avx512.mask.cmp.d.256(<8 x i32> %a0, <8 x i32> %a1, i32 2, i8 -1)
40 %res3 = call i8 @llvm.x86.avx512.mask.cmp.d.256(<8 x i32> %a0, <8 x i32> %a1, i32 3, i8 -1)
42 %res4 = call i8 @llvm.x86.avx512.mask.cmp.d.256(<8 x i32> %a0, <8 x i32> %a1, i32 4, i8 -1)
44 %res5 = call i8 @llvm.x86.avx512.mask.cmp.d.256(<8 x i32> %a0, <8 x i32> %a1, i32 5, i8 -1)
46 %res6 = call i8 @llvm.x86.avx512.mask.cmp.d.256(<8 x i32> %a0, <8 x i32> %a1, i32 6, i8 -1)
48 %res7 = call i8 @llvm.x86.avx512.mask.cmp.d.256(<8 x i32> %a0, <8 x i32> %a1, i32 7, i8 -1)
82 %res0 = call i8 @llvm.x86.avx512.mask.cmp.d.256(<8 x i32> %a0, <8 x i32> %a1, i32 0, i8 %mask)
84 %res1 = call i8 @llvm.x86.avx512.mask.cmp.d.256(<8 x i32> %a0, <8 x i32> %a1, i32 1, i8 %mask)
[all …]
|
| D | avx512-fma-intrinsics.ll | 4 declare <16 x float> @llvm.x86.avx512.mask.vfmadd.ps.512(<16 x float>, <16 x float>, <16 x float>, …
5 declare <8 x double> @llvm.x86.avx512.mask.vfmadd.pd.512(<8 x double>, <8 x double>, <8 x double>, …
12 …%res = call <16 x float> @llvm.x86.avx512.mask.vfnmadd.ps.512(<16 x float> %a0, <16 x float> %a1, …
15 declare <16 x float> @llvm.x86.avx512.mask.vfnmadd.ps.512(<16 x float>, <16 x float>, <16 x float>,…
23 …%res = call <16 x float> @llvm.x86.avx512.mask.vfnmadd.ps.512(<16 x float> %a0, <16 x float> %a1, …
32 …%res = call <8 x double> @llvm.x86.avx512.mask.vfnmadd.pd.512(<8 x double> %a0, <8 x double> %a1, …
35 declare <8 x double> @llvm.x86.avx512.mask.vfnmadd.pd.512(<8 x double>, <8 x double>, <8 x double>,…
43 …%res = call <8 x double> @llvm.x86.avx512.mask.vfnmadd.pd.512(<8 x double> %a0, <8 x double> %a1, …
52 …%res = call <16 x float> @llvm.x86.avx512.mask.vfnmsub.ps.512(<16 x float> %a0, <16 x float> %a1, …
55 declare <16 x float> @llvm.x86.avx512.mask.vfnmsub.ps.512(<16 x float>, <16 x float>, <16 x float>,…
[all …]
|
| D | avx512-scalarIntrinsics.ll | 10 …%res = call <4 x float> @llvm.x86.avx512.rsqrt14.ss(<4 x float> %a0, <4 x float> %a0, <4 x float> …
13 declare <4 x float> @llvm.x86.avx512.rsqrt14.ss(<4 x float>, <4 x float>, <4 x float>, i8) nounwind…
20 …%res = call <4 x float> @llvm.x86.avx512.rcp14.ss(<4 x float> %a0, <4 x float> %a0, <4 x float> ze…
23 declare <4 x float> @llvm.x86.avx512.rcp14.ss(<4 x float>, <4 x float>, <4 x float>, i8) nounwind r…
30 …%res = call <2 x double> @llvm.x86.avx512.rsqrt14.sd(<2 x double> %a0, <2 x double> %a0, <2 x doub…
33 declare <2 x double> @llvm.x86.avx512.rsqrt14.sd(<2 x double>, <2 x double>, <2 x double>, i8) noun…
40 …%res = call <2 x double> @llvm.x86.avx512.rcp14.sd(<2 x double> %a0, <2 x double> %a0, <2 x double…
44 declare <2 x double> @llvm.x86.avx512.rcp14.sd(<2 x double>, <2 x double>, <2 x double>, i8) nounwi…
46 declare <4 x float> @llvm.x86.avx512.mask.scalef.ss(<4 x float>, <4 x float>,<4 x float>, i8, i32)
51 …%res = call <4 x float> @llvm.x86.avx512.mask.scalef.ss(<4 x float> %x0, <4 x float> %x1, <4 x flo…
[all …]
|
| D | avx512vl-intrinsics-upgrade.ll | 4 declare <8 x i32> @llvm.x86.avx512.pbroadcastd.256(<4 x i32>, <8 x i32>, i8)
17 %res = call <8 x i32> @llvm.x86.avx512.pbroadcastd.256(<4 x i32> %y, <8 x i32> %x1, i8 -1)
18 %res1 = call <8 x i32> @llvm.x86.avx512.pbroadcastd.256(<4 x i32> %x0, <8 x i32> %x1, i8 %mask)
19 …%res2 = call <8 x i32> @llvm.x86.avx512.pbroadcastd.256(<4 x i32> %x0, <8 x i32> zeroinitializer, …
25 declare <4 x i32> @llvm.x86.avx512.pbroadcastd.128(<4 x i32>, <4 x i32>, i8)
37 %res = call <4 x i32> @llvm.x86.avx512.pbroadcastd.128(<4 x i32> %x0, <4 x i32> %x1, i8 -1)
38 %res1 = call <4 x i32> @llvm.x86.avx512.pbroadcastd.128(<4 x i32> %x0, <4 x i32> %x1, i8 %mask)
39 …%res2 = call <4 x i32> @llvm.x86.avx512.pbroadcastd.128(<4 x i32> %x0, <4 x i32> zeroinitializer, …
45 declare <4 x i64> @llvm.x86.avx512.pbroadcastq.256(<2 x i64>, <4 x i64>, i8)
57 %res = call <4 x i64> @llvm.x86.avx512.pbroadcastq.256(<2 x i64> %x0, <4 x i64> %x1,i8 -1)
[all …]
|
| D | avx512ifma-intrinsics.ll | 3 declare <8 x i64> @llvm.x86.avx512.mask.vpmadd52h.uq.512(<8 x i64>, <8 x i64>, <8 x i64>, i8)
19 …%res = call <8 x i64> @llvm.x86.avx512.mask.vpmadd52h.uq.512(<8 x i64> %x0, <8 x i64> %x1, <8 x i6…
20 …%res1 = call <8 x i64> @llvm.x86.avx512.mask.vpmadd52h.uq.512(<8 x i64> %x0, <8 x i64> %x1, <8 x i…
21 …%res2 = call <8 x i64> @llvm.x86.avx512.mask.vpmadd52h.uq.512(<8 x i64> zeroinitializer, <8 x i64>…
22 …%res3 = call <8 x i64> @llvm.x86.avx512.mask.vpmadd52h.uq.512(<8 x i64> %x0, <8 x i64> %x1, <8 x i…
29 declare <8 x i64> @llvm.x86.avx512.maskz.vpmadd52h.uq.512(<8 x i64>, <8 x i64>, <8 x i64>, i8)
45 …%res = call <8 x i64> @llvm.x86.avx512.maskz.vpmadd52h.uq.512(<8 x i64> %x0, <8 x i64> %x1, <8 x i…
46 …%res1 = call <8 x i64> @llvm.x86.avx512.maskz.vpmadd52h.uq.512(<8 x i64> %x0, <8 x i64> %x1, <8 x …
47 …%res2 = call <8 x i64> @llvm.x86.avx512.maskz.vpmadd52h.uq.512(<8 x i64> zeroinitializer, <8 x i64…
48 …%res3 = call <8 x i64> @llvm.x86.avx512.maskz.vpmadd52h.uq.512(<8 x i64> %x0, <8 x i64> %x1, <8 x …
[all …]
|
| D | avx512dqvl-intrinsics.ll | 9 …%res = call <8 x i64> @llvm.x86.avx512.mask.pmull.q.512(<8 x i64> %a, <8 x i64> %b, <8 x i64> zero…
20 …%res = call <8 x i64> @llvm.x86.avx512.mask.pmull.q.512(<8 x i64> %a, <8 x i64> %b, <8 x i64> %pas…
30 …%res = call <8 x i64> @llvm.x86.avx512.mask.pmull.q.512(<8 x i64> %a, <8 x i64> %b, <8 x i64> zero…
40 …%res = call <8 x i64> @llvm.x86.avx512.mask.pmull.q.512(<8 x i64> %a, <8 x i64> %b, <8 x i64> zero…
52 …%res = call <8 x i64> @llvm.x86.avx512.mask.pmull.q.512(<8 x i64> %a, <8 x i64> %b, <8 x i64> %pas…
63 …%res = call <8 x i64> @llvm.x86.avx512.mask.pmull.q.512(<8 x i64> %a, <8 x i64> %b, <8 x i64> zero…
75 …%res = call <8 x i64> @llvm.x86.avx512.mask.pmull.q.512(<8 x i64> %a, <8 x i64> %b, <8 x i64> zero…
89 …%res = call <8 x i64> @llvm.x86.avx512.mask.pmull.q.512(<8 x i64> %a, <8 x i64> %b, <8 x i64> %pas…
102 …%res = call <8 x i64> @llvm.x86.avx512.mask.pmull.q.512(<8 x i64> %a, <8 x i64> %b, <8 x i64> zero…
105 declare <8 x i64> @llvm.x86.avx512.mask.pmull.q.512(<8 x i64>, <8 x i64>, <8 x i64>, i8)
[all …]
|
| D | avx512vbmi-intrinsics.ll | 3 declare <64 x i8> @llvm.x86.avx512.mask.permvar.qi.512(<64 x i8>, <64 x i8>, <64 x i8>, i64)
15 …%res = call <64 x i8> @llvm.x86.avx512.mask.permvar.qi.512(<64 x i8> %x0, <64 x i8> %x1, <64 x i8>…
16 …%res1 = call <64 x i8> @llvm.x86.avx512.mask.permvar.qi.512(<64 x i8> %x0, <64 x i8> %x1, <64 x i8…
17 …%res2 = call <64 x i8> @llvm.x86.avx512.mask.permvar.qi.512(<64 x i8> %x0, <64 x i8> %x1, <64 x i8…
23 declare <64 x i8> @llvm.x86.avx512.mask.pmultishift.qb.512(<64 x i8>, <64 x i8>, <64 x i8>, i64)
32 …%res = call <64 x i8> @llvm.x86.avx512.mask.pmultishift.qb.512(<64 x i8> %x0, <64 x i8> %x1, <64 x…
33 …%res1 = call <64 x i8> @llvm.x86.avx512.mask.pmultishift.qb.512(<64 x i8> %x0, <64 x i8> %x1, <64 …
34 …%res2 = call <64 x i8> @llvm.x86.avx512.mask.pmultishift.qb.512(<64 x i8> %x0, <64 x i8> %x1, <64 …
40 declare <64 x i8> @llvm.x86.avx512.mask.vpermi2var.qi.512(<64 x i8>, <64 x i8>, <64 x i8>, i64)
54 …%res = call <64 x i8> @llvm.x86.avx512.mask.vpermi2var.qi.512(<64 x i8> %x0, <64 x i8> %x1, <64 x …
[all …]
|
| D | avx512bw-intrinsics.ll | 72 %res0 = call i64 @llvm.x86.avx512.mask.cmp.b.512(<64 x i8> %a0, <64 x i8> %a1, i32 0, i64 -1)
73 %res1 = call i64 @llvm.x86.avx512.mask.cmp.b.512(<64 x i8> %a0, <64 x i8> %a1, i32 1, i64 -1)
75 %res2 = call i64 @llvm.x86.avx512.mask.cmp.b.512(<64 x i8> %a0, <64 x i8> %a1, i32 2, i64 -1)
77 %res3 = call i64 @llvm.x86.avx512.mask.cmp.b.512(<64 x i8> %a0, <64 x i8> %a1, i32 3, i64 -1)
79 %res4 = call i64 @llvm.x86.avx512.mask.cmp.b.512(<64 x i8> %a0, <64 x i8> %a1, i32 4, i64 -1)
81 %res5 = call i64 @llvm.x86.avx512.mask.cmp.b.512(<64 x i8> %a0, <64 x i8> %a1, i32 5, i64 -1)
83 %res6 = call i64 @llvm.x86.avx512.mask.cmp.b.512(<64 x i8> %a0, <64 x i8> %a1, i32 6, i64 -1)
85 %res7 = call i64 @llvm.x86.avx512.mask.cmp.b.512(<64 x i8> %a0, <64 x i8> %a1, i32 7, i64 -1)
161 %res0 = call i64 @llvm.x86.avx512.mask.cmp.b.512(<64 x i8> %a0, <64 x i8> %a1, i32 0, i64 %mask)
162 %res1 = call i64 @llvm.x86.avx512.mask.cmp.b.512(<64 x i8> %a0, <64 x i8> %a1, i32 1, i64 %mask)
[all …]
|
| D | avx512bwvl-intrinsics.ll | 35 %res0 = call i32 @llvm.x86.avx512.mask.cmp.b.256(<32 x i8> %a0, <32 x i8> %a1, i32 0, i32 -1)
37 %res1 = call i32 @llvm.x86.avx512.mask.cmp.b.256(<32 x i8> %a0, <32 x i8> %a1, i32 1, i32 -1)
39 %res2 = call i32 @llvm.x86.avx512.mask.cmp.b.256(<32 x i8> %a0, <32 x i8> %a1, i32 2, i32 -1)
41 %res3 = call i32 @llvm.x86.avx512.mask.cmp.b.256(<32 x i8> %a0, <32 x i8> %a1, i32 3, i32 -1)
43 %res4 = call i32 @llvm.x86.avx512.mask.cmp.b.256(<32 x i8> %a0, <32 x i8> %a1, i32 4, i32 -1)
45 %res5 = call i32 @llvm.x86.avx512.mask.cmp.b.256(<32 x i8> %a0, <32 x i8> %a1, i32 5, i32 -1)
47 %res6 = call i32 @llvm.x86.avx512.mask.cmp.b.256(<32 x i8> %a0, <32 x i8> %a1, i32 6, i32 -1)
49 %res7 = call i32 @llvm.x86.avx512.mask.cmp.b.256(<32 x i8> %a0, <32 x i8> %a1, i32 7, i32 -1)
84 %res0 = call i32 @llvm.x86.avx512.mask.cmp.b.256(<32 x i8> %a0, <32 x i8> %a1, i32 0, i32 %mask)
86 %res1 = call i32 @llvm.x86.avx512.mask.cmp.b.256(<32 x i8> %a0, <32 x i8> %a1, i32 1, i32 %mask)
[all …]
|
| D | vector-shuffle-combining-avx512bw.ll | 4 declare <64 x i8> @llvm.x86.avx512.mask.pshuf.b.512(<64 x i8>, <64 x i8>, <64 x i8>, i64)
6 declare <16 x float> @llvm.x86.avx512.mask.vpermilvar.ps.512(<16 x float>, <16 x i32>, <16 x float>…
8 declare <8 x double> @llvm.x86.avx512.mask.permvar.df.512(<8 x double>, <8 x i64>, <8 x double>, i8)
9 declare <8 x i64> @llvm.x86.avx512.mask.permvar.di.512(<8 x i64>, <8 x i64>, <8 x i64>, i8)
10 declare <16 x i32> @llvm.x86.avx512.mask.permvar.si.512(<16 x i32>, <16 x i32>, <16 x i32>, i16)
11 declare <32 x i16> @llvm.x86.avx512.mask.permvar.hi.512(<32 x i16>, <32 x i16>, <32 x i16>, i32)
13 declare <8 x double> @llvm.x86.avx512.maskz.vpermt2var.pd.512(<8 x i64>, <8 x double>, <8 x double>…
14 declare <16 x float> @llvm.x86.avx512.maskz.vpermt2var.ps.512(<16 x i32>, <16 x float>, <16 x float…
16 declare <8 x i64> @llvm.x86.avx512.maskz.vpermt2var.q.512(<8 x i64>, <8 x i64>, <8 x i64>, i8)
17 declare <16 x i32> @llvm.x86.avx512.maskz.vpermt2var.d.512(<16 x i32>, <16 x i32>, <16 x i32>, i16)
[all …]
|
| D | avx512vbmivl-intrinsics.ll | 3 declare <16 x i8> @llvm.x86.avx512.mask.permvar.qi.128(<16 x i8>, <16 x i8>, <16 x i8>, i16)
15 …%res = call <16 x i8> @llvm.x86.avx512.mask.permvar.qi.128(<16 x i8> %x0, <16 x i8> %x1, <16 x i8>…
16 …%res1 = call <16 x i8> @llvm.x86.avx512.mask.permvar.qi.128(<16 x i8> %x0, <16 x i8> %x1, <16 x i8…
17 …%res2 = call <16 x i8> @llvm.x86.avx512.mask.permvar.qi.128(<16 x i8> %x0, <16 x i8> %x1, <16 x i8…
23 declare <32 x i8> @llvm.x86.avx512.mask.permvar.qi.256(<32 x i8>, <32 x i8>, <32 x i8>, i32)
35 …%res = call <32 x i8> @llvm.x86.avx512.mask.permvar.qi.256(<32 x i8> %x0, <32 x i8> %x1, <32 x i8>…
36 …%res1 = call <32 x i8> @llvm.x86.avx512.mask.permvar.qi.256(<32 x i8> %x0, <32 x i8> %x1, <32 x i8…
37 …%res2 = call <32 x i8> @llvm.x86.avx512.mask.permvar.qi.256(<32 x i8> %x0, <32 x i8> %x1, <32 x i8…
43 declare <16 x i8> @llvm.x86.avx512.mask.pmultishift.qb.128(<16 x i8>, <16 x i8>, <16 x i8>, i16)
55 …%res = call <16 x i8> @llvm.x86.avx512.mask.pmultishift.qb.128(<16 x i8> %x0, <16 x i8> %x1, <16 x…
[all …]
|
| /external/XNNPACK/src/qs8-vaddc/gen/ |
| D | minmax-avx512skx-mul32-ld128-x16.c | 25 const __m512i va_multiplier = _mm512_load_si512(params->avx512.a_multiplier); in xnn_qs8_vaddc_minmax_ukernel__avx512skx_mul32_ld128_x16()
26 const __m128i vshift = _mm_load_si128((const __m128i*) params->avx512.shift); in xnn_qs8_vaddc_minmax_ukernel__avx512skx_mul32_ld128_x16()
27 …const __m256i voutput_zero_point = _mm256_load_si256((const __m256i*) params->avx512.output_zero_p… in xnn_qs8_vaddc_minmax_ukernel__avx512skx_mul32_ld128_x16()
28 const __m128i voutput_min = _mm_load_si128((const __m128i*) params->avx512.output_min); in xnn_qs8_vaddc_minmax_ukernel__avx512skx_mul32_ld128_x16()
29 const __m128i voutput_max = _mm_load_si128((const __m128i*) params->avx512.output_max); in xnn_qs8_vaddc_minmax_ukernel__avx512skx_mul32_ld128_x16()
32 _mm512_broadcastd_epi32(_mm_cvtsi32_si128(params->avx512.b_multiplier[0] * (int32_t) *input_b)), in xnn_qs8_vaddc_minmax_ukernel__avx512skx_mul32_ld128_x16()
33 _mm512_load_si512(params->avx512.bias)); in xnn_qs8_vaddc_minmax_ukernel__avx512skx_mul32_ld128_x16()
|
| D | minmax-avx512skx-mul32-ld128-x32.c | 25 const __m512i va_multiplier = _mm512_load_si512(params->avx512.a_multiplier); in xnn_qs8_vaddc_minmax_ukernel__avx512skx_mul32_ld128_x32()
26 const __m128i vshift = _mm_load_si128((const __m128i*) params->avx512.shift); in xnn_qs8_vaddc_minmax_ukernel__avx512skx_mul32_ld128_x32()
27 const __m512i voutput_zero_point = _mm512_load_si512(params->avx512.output_zero_point); in xnn_qs8_vaddc_minmax_ukernel__avx512skx_mul32_ld128_x32()
28 const __m256i voutput_min = _mm256_load_si256((const __m256i*) params->avx512.output_min); in xnn_qs8_vaddc_minmax_ukernel__avx512skx_mul32_ld128_x32()
29 const __m256i voutput_max = _mm256_load_si256((const __m256i*) params->avx512.output_max); in xnn_qs8_vaddc_minmax_ukernel__avx512skx_mul32_ld128_x32()
32 _mm512_broadcastd_epi32(_mm_cvtsi32_si128(params->avx512.b_multiplier[0] * (int32_t) *input_b)), in xnn_qs8_vaddc_minmax_ukernel__avx512skx_mul32_ld128_x32()
33 _mm512_load_si512(params->avx512.bias)); in xnn_qs8_vaddc_minmax_ukernel__avx512skx_mul32_ld128_x32()
|
| /external/XNNPACK/src/qu8-vaddc/gen/ |
| D | minmax-avx512skx-mul32-ld128-x16.c | 25 const __m512i va_multiplier = _mm512_load_si512(params->avx512.a_multiplier); in xnn_qu8_vaddc_minmax_ukernel__avx512skx_mul32_ld128_x16()
26 const __m128i vshift = _mm_load_si128((const __m128i*) params->avx512.shift); in xnn_qu8_vaddc_minmax_ukernel__avx512skx_mul32_ld128_x16()
27 …const __m256i voutput_zero_point = _mm256_load_si256((const __m256i*) params->avx512.output_zero_p… in xnn_qu8_vaddc_minmax_ukernel__avx512skx_mul32_ld128_x16()
28 const __m128i voutput_min = _mm_load_si128((const __m128i*) params->avx512.output_min); in xnn_qu8_vaddc_minmax_ukernel__avx512skx_mul32_ld128_x16()
29 const __m128i voutput_max = _mm_load_si128((const __m128i*) params->avx512.output_max); in xnn_qu8_vaddc_minmax_ukernel__avx512skx_mul32_ld128_x16()
32 _mm512_broadcastd_epi32(_mm_cvtsi32_si128(params->avx512.b_multiplier[0] * (int32_t) *input_b)), in xnn_qu8_vaddc_minmax_ukernel__avx512skx_mul32_ld128_x16()
33 _mm512_load_si512(params->avx512.bias)); in xnn_qu8_vaddc_minmax_ukernel__avx512skx_mul32_ld128_x16()
|
| D | minmax-avx512skx-mul32-ld128-x32.c | 25 const __m512i va_multiplier = _mm512_load_si512(params->avx512.a_multiplier); in xnn_qu8_vaddc_minmax_ukernel__avx512skx_mul32_ld128_x32()
26 const __m128i vshift = _mm_load_si128((const __m128i*) params->avx512.shift); in xnn_qu8_vaddc_minmax_ukernel__avx512skx_mul32_ld128_x32()
27 const __m512i voutput_zero_point = _mm512_load_si512(params->avx512.output_zero_point); in xnn_qu8_vaddc_minmax_ukernel__avx512skx_mul32_ld128_x32()
28 const __m256i voutput_min = _mm256_load_si256((const __m256i*) params->avx512.output_min); in xnn_qu8_vaddc_minmax_ukernel__avx512skx_mul32_ld128_x32()
29 const __m256i voutput_max = _mm256_load_si256((const __m256i*) params->avx512.output_max); in xnn_qu8_vaddc_minmax_ukernel__avx512skx_mul32_ld128_x32()
32 _mm512_broadcastd_epi32(_mm_cvtsi32_si128(params->avx512.b_multiplier[0] * (int32_t) *input_b)), in xnn_qu8_vaddc_minmax_ukernel__avx512skx_mul32_ld128_x32()
33 _mm512_load_si512(params->avx512.bias)); in xnn_qu8_vaddc_minmax_ukernel__avx512skx_mul32_ld128_x32()
|
| /external/XNNPACK/src/qu8-vadd/gen/ |
| D | minmax-avx512skx-mul32-ld128-x16.c | 25 const __m512i vbias = _mm512_load_si512(params->avx512.bias); in xnn_qu8_vadd_minmax_ukernel__avx512skx_mul32_ld128_x16()
26 const __m512i va_multiplier = _mm512_load_si512(params->avx512.a_multiplier); in xnn_qu8_vadd_minmax_ukernel__avx512skx_mul32_ld128_x16()
27 const __m512i vb_multiplier = _mm512_load_si512(params->avx512.b_multiplier); in xnn_qu8_vadd_minmax_ukernel__avx512skx_mul32_ld128_x16()
28 const __m128i vshift = _mm_load_si128((const __m128i*) params->avx512.shift); in xnn_qu8_vadd_minmax_ukernel__avx512skx_mul32_ld128_x16()
29 …const __m256i voutput_zero_point = _mm256_load_si256((const __m256i*) params->avx512.output_zero_p… in xnn_qu8_vadd_minmax_ukernel__avx512skx_mul32_ld128_x16()
30 const __m128i voutput_min = _mm_load_si128((const __m128i*) params->avx512.output_min); in xnn_qu8_vadd_minmax_ukernel__avx512skx_mul32_ld128_x16()
31 const __m128i voutput_max = _mm_load_si128((const __m128i*) params->avx512.output_max); in xnn_qu8_vadd_minmax_ukernel__avx512skx_mul32_ld128_x16()
|
| /external/XNNPACK/src/qs8-vadd/gen/ |
| D | minmax-avx512skx-mul32-ld128-x16.c | 25 const __m512i vbias = _mm512_load_si512(params->avx512.bias); in xnn_qs8_vadd_minmax_ukernel__avx512skx_mul32_ld128_x16()
26 const __m512i va_multiplier = _mm512_load_si512(params->avx512.a_multiplier); in xnn_qs8_vadd_minmax_ukernel__avx512skx_mul32_ld128_x16()
27 const __m512i vb_multiplier = _mm512_load_si512(params->avx512.b_multiplier); in xnn_qs8_vadd_minmax_ukernel__avx512skx_mul32_ld128_x16()
28 const __m128i vshift = _mm_load_si128((const __m128i*) params->avx512.shift); in xnn_qs8_vadd_minmax_ukernel__avx512skx_mul32_ld128_x16()
29 …const __m256i voutput_zero_point = _mm256_load_si256((const __m256i*) params->avx512.output_zero_p… in xnn_qs8_vadd_minmax_ukernel__avx512skx_mul32_ld128_x16()
30 const __m128i voutput_min = _mm_load_si128((const __m128i*) params->avx512.output_min); in xnn_qs8_vadd_minmax_ukernel__avx512skx_mul32_ld128_x16()
31 const __m128i voutput_max = _mm_load_si128((const __m128i*) params->avx512.output_max); in xnn_qs8_vadd_minmax_ukernel__avx512skx_mul32_ld128_x16()
|