1 ; RUN: llc < %s -march=x86 -mattr=+sse2 -stats -realign-stack=0 |&\
2 ; RUN: grep {asm-printer} | grep 34
4 target datalayout = "e-p:32:32"
5 define void @foo(i32* %mc, i32* %bp, i32* %ms, i32* %xmb, i32* %mpp, i32* %tpmm, i32* %ip, i32* %tpim, i32* %dpp, i32* %tpdm, i32* %bpi, i32 %M) nounwind {
7 %tmp9 = icmp slt i32 %M, 5 ; <i1> [#uses=1]
8 br i1 %tmp9, label %return, label %cond_true
10 cond_true: ; preds = %cond_true, %entry
11 %indvar = phi i32 [ 0, %entry ], [ %indvar.next, %cond_true ] ; <i32> [#uses=2]
12 %tmp. = shl i32 %indvar, 2 ; <i32> [#uses=1]
13 %tmp.10 = add nsw i32 %tmp., 1 ; <i32> [#uses=2]
14 %tmp31 = add nsw i32 %tmp.10, -1 ; <i32> [#uses=4]
15 %tmp32 = getelementptr i32* %mpp, i32 %tmp31 ; <i32*> [#uses=1]
16 %tmp34 = bitcast i32* %tmp32 to <16 x i8>* ; <i8*> [#uses=1]
17 %tmp = load <16 x i8>* %tmp34, align 1
18 %tmp42 = getelementptr i32* %tpmm, i32 %tmp31 ; <i32*> [#uses=1]
19 %tmp42.upgrd.1 = bitcast i32* %tmp42 to <4 x i32>* ; <<4 x i32>*> [#uses=1]
20 %tmp46 = load <4 x i32>* %tmp42.upgrd.1 ; <<4 x i32>> [#uses=1]
21 %tmp54 = bitcast <16 x i8> %tmp to <4 x i32> ; <<4 x i32>> [#uses=1]
22 %tmp55 = add <4 x i32> %tmp54, %tmp46 ; <<4 x i32>> [#uses=2]
23 %tmp55.upgrd.2 = bitcast <4 x i32> %tmp55 to <2 x i64> ; <<2 x i64>> [#uses=1]
24 %tmp62 = getelementptr i32* %ip, i32 %tmp31 ; <i32*> [#uses=1]
25 %tmp65 = bitcast i32* %tmp62 to <16 x i8>* ; <i8*> [#uses=1]
26 %tmp66 = load <16 x i8>* %tmp65, align 1
27 %tmp73 = getelementptr i32* %tpim, i32 %tmp31 ; <i32*> [#uses=1]
28 %tmp73.upgrd.3 = bitcast i32* %tmp73 to <4 x i32>* ; <<4 x i32>*> [#uses=1]
29 %tmp77 = load <4 x i32>* %tmp73.upgrd.3 ; <<4 x i32>> [#uses=1]
30 %tmp87 = bitcast <16 x i8> %tmp66 to <4 x i32> ; <<4 x i32>> [#uses=1]
31 %tmp88 = add <4 x i32> %tmp87, %tmp77 ; <<4 x i32>> [#uses=2]
32 %tmp88.upgrd.4 = bitcast <4 x i32> %tmp88 to <2 x i64> ; <<2 x i64>> [#uses=1]
33 %tmp99 = tail call <4 x i32> @llvm.x86.sse2.pcmpgt.d( <4 x i32> %tmp88, <4 x i32> %tmp55 ) ; <<4 x i32>> [#uses=1]
34 %tmp99.upgrd.5 = bitcast <4 x i32> %tmp99 to <2 x i64> ; <<2 x i64>> [#uses=2]
35 %tmp110 = xor <2 x i64> %tmp99.upgrd.5, < i64 -1, i64 -1 > ; <<2 x i64>> [#uses=1]
36 %tmp111 = and <2 x i64> %tmp110, %tmp55.upgrd.2 ; <<2 x i64>> [#uses=1]
37 %tmp121 = and <2 x i64> %tmp99.upgrd.5, %tmp88.upgrd.4 ; <<2 x i64>> [#uses=1]
38 %tmp131 = or <2 x i64> %tmp121, %tmp111 ; <<2 x i64>> [#uses=1]
39 %tmp137 = getelementptr i32* %mc, i32 %tmp.10 ; <i32*> [#uses=1]
40 %tmp137.upgrd.7 = bitcast i32* %tmp137 to <2 x i64>* ; <<2 x i64>*> [#uses=1]
41 store <2 x i64> %tmp131, <2 x i64>* %tmp137.upgrd.7
42 %tmp147 = add nsw i32 %tmp.10, 8 ; <i32> [#uses=1]
43 %tmp.upgrd.8 = icmp ne i32 %tmp147, %M ; <i1> [#uses=1]
44 %indvar.next = add i32 %indvar, 1 ; <i32> [#uses=1]
45 br i1 %tmp.upgrd.8, label %cond_true, label %return
47 return: ; preds = %cond_true, %entry
51 declare <4 x i32> @llvm.x86.sse2.pcmpgt.d(<4 x i32>, <4 x i32>)