-; RUN: llvm-as < %s | llc -relocation-model=static -mcpu=yonah | grep {andpd.*4(%esp), %xmm}
+; RUN: llc < %s -relocation-model=static -mcpu=yonah | FileCheck %s
; The double argument is at 4(esp) which is 16-byte aligned, allowing us to
; fold the load into the andpd.
target triple = "i686-apple-darwin8"
@G = external global double
-define void @test({ double, double }* byval %z, double* %P) {
+define void @test({ double, double }* byval %z, double* %P) nounwind {
entry:
- %tmp = getelementptr { double, double }* %z, i32 0, i32 0 ; <double*> [#uses=1]
- %tmp1 = load double* %tmp, align 8 ; <double> [#uses=1]
- %tmp2 = tail call double @fabs( double %tmp1 ) ; <double> [#uses=1]
%tmp3 = load double* @G, align 16 ; <double> [#uses=1]
- %tmp4 = tail call double @fabs( double %tmp3 ) ; <double> [#uses=1]
+ %tmp4 = tail call double @fabs( double %tmp3 ) readnone ; <double> [#uses=1]
+ store volatile double %tmp4, double* %P
+ %tmp = getelementptr { double, double }* %z, i32 0, i32 0 ; <double*> [#uses=1]
+ %tmp1 = load volatile double* %tmp, align 8 ; <double> [#uses=1]
+ %tmp2 = tail call double @fabs( double %tmp1 ) readnone ; <double> [#uses=1]
+ ; CHECK: andpd{{.*}}4(%esp), %xmm
%tmp6 = fadd double %tmp4, %tmp2 ; <double> [#uses=1]
- store double %tmp6, double* %P, align 8
+ store volatile double %tmp6, double* %P, align 8
ret void
}
+define void @test2() alignstack(16) nounwind {
+entry:
+ ; CHECK: andl{{.*}}$-16, %esp
+ ret void
+}
+
+; Use a call to force a spill.
+define <2 x double> @test3(<2 x double> %x, <2 x double> %y) alignstack(32) nounwind {
+entry:
+ ; CHECK: andl{{.*}}$-32, %esp
+ call void @test2()
+ %A = fmul <2 x double> %x, %y
+ ret <2 x double> %A
+}
+
declare double @fabs(double)
+
+; The pointer is already known aligned, so and x,-16 is eliminable.
+define i32 @test4() nounwind {
+entry:
+ %buffer = alloca [2048 x i8], align 16
+ %0 = ptrtoint [2048 x i8]* %buffer to i32
+ %and = and i32 %0, -16
+ ret i32 %and
+; CHECK-LABEL: test4:
+; CHECK-NOT: and
+; CHECK: ret
+}