%quux = type { i32 (...)**, %baz*, i32 }
%quuz = type { %quux, i32, %bar, [128 x i8], [16 x %foo], %foo, %foo, %foo }
-declare <4 x float> @llvm.arm.neon.vld1.v4f32(i8*) nounwind readonly
+declare <4 x float> @llvm.arm.neon.vld1.v4f32(i8*, i32) nounwind readonly
-define arm_apcscc void @aaa(%quuz* %this, i8* %block) {
+define void @aaa(%quuz* %this, i8* %block) {
; CHECK: aaa:
-; CHECK: vstmia sp
-; CHECK: vldmia sp
+; CHECK: bic {{.*}}, #15
+; CHECK: vst1.64 {{.*}}sp, :128
+; CHECK: vld1.64 {{.*}}sp, :128
entry:
- %0 = call <4 x float> @llvm.arm.neon.vld1.v4f32(i8* undef) nounwind ; <<4 x float>> [#uses=1]
+ %aligned_vec = alloca <4 x float>, align 16
+ %"alloca point" = bitcast i32 0 to i32
+ %vecptr = bitcast <4 x float>* %aligned_vec to i8*
+ %0 = call <4 x float> @llvm.arm.neon.vld1.v4f32(i8* %vecptr, i32 1) nounwind ; <<4 x float>> [#uses=1]
store float 6.300000e+01, float* undef, align 4
- %1 = call <4 x float> @llvm.arm.neon.vld1.v4f32(i8* undef) nounwind ; <<4 x float>> [#uses=1]
+ %1 = call <4 x float> @llvm.arm.neon.vld1.v4f32(i8* undef, i32 1) nounwind ; <<4 x float>> [#uses=1]
+ store float 0.000000e+00, float* undef, align 4
+ %2 = call <4 x float> @llvm.arm.neon.vld1.v4f32(i8* undef, i32 1) nounwind ; <<4 x float>> [#uses=1]
+ %ld3 = call <4 x float> @llvm.arm.neon.vld1.v4f32(i8* undef, i32 1) nounwind
+ store float 0.000000e+00, float* undef, align 4
+ %ld4 = call <4 x float> @llvm.arm.neon.vld1.v4f32(i8* undef, i32 1) nounwind
+ store float 0.000000e+00, float* undef, align 4
+ %ld5 = call <4 x float> @llvm.arm.neon.vld1.v4f32(i8* undef, i32 1) nounwind
+ store float 0.000000e+00, float* undef, align 4
+ %ld6 = call <4 x float> @llvm.arm.neon.vld1.v4f32(i8* undef, i32 1) nounwind
+ store float 0.000000e+00, float* undef, align 4
+ %ld7 = call <4 x float> @llvm.arm.neon.vld1.v4f32(i8* undef, i32 1) nounwind
+ store float 0.000000e+00, float* undef, align 4
+ %ld8 = call <4 x float> @llvm.arm.neon.vld1.v4f32(i8* undef, i32 1) nounwind
+ store float 0.000000e+00, float* undef, align 4
+ %ld9 = call <4 x float> @llvm.arm.neon.vld1.v4f32(i8* undef, i32 1) nounwind
+ store float 0.000000e+00, float* undef, align 4
+ %ld10 = call <4 x float> @llvm.arm.neon.vld1.v4f32(i8* undef, i32 1) nounwind
+ store float 0.000000e+00, float* undef, align 4
+ %ld11 = call <4 x float> @llvm.arm.neon.vld1.v4f32(i8* undef, i32 1) nounwind
+ store float 0.000000e+00, float* undef, align 4
+ %ld12 = call <4 x float> @llvm.arm.neon.vld1.v4f32(i8* undef, i32 1) nounwind
store float 0.000000e+00, float* undef, align 4
- %2 = call <4 x float> @llvm.arm.neon.vld1.v4f32(i8* undef) nounwind ; <<4 x float>> [#uses=1]
%val173 = load <4 x float>* undef ; <<4 x float>> [#uses=1]
br label %bb4
%18 = fmul <4 x float> %17, %val173 ; <<4 x float>> [#uses=1]
%19 = shufflevector <4 x float> %18, <4 x float> undef, <2 x i32> <i32 2, i32 3> ; <<2 x float>> [#uses=1]
%20 = shufflevector <2 x float> %19, <2 x float> undef, <4 x i32> zeroinitializer ; <<4 x float>> [#uses=1]
- %21 = fadd <4 x float> zeroinitializer, %20 ; <<4 x float>> [#uses=2]
+ %tmp1 = fadd <4 x float> %20, %ld3
+ %tmp2 = fadd <4 x float> %tmp1, %ld4
+ %tmp3 = fadd <4 x float> %tmp2, %ld5
+ %tmp4 = fadd <4 x float> %tmp3, %ld6
+ %tmp5 = fadd <4 x float> %tmp4, %ld7
+ %tmp6 = fadd <4 x float> %tmp5, %ld8
+ %tmp7 = fadd <4 x float> %tmp6, %ld9
+ %tmp8 = fadd <4 x float> %tmp7, %ld10
+ %tmp9 = fadd <4 x float> %tmp8, %ld11
+ %21 = fadd <4 x float> %tmp9, %ld12
%22 = fcmp ogt <4 x float> %besterror.0.2264, %21 ; <<4 x i1>> [#uses=0]
- br i1 undef, label %bb193, label %bb186
+ %tmp = extractelement <4 x i1> %22, i32 0
+ br i1 %tmp, label %bb193, label %bb186
bb186: ; preds = %bb4
br label %bb193