llvm/test/CodeGen/X86/stack-align.ll
Bob Wilson 53624a2df5 Refactor and check "onlyReadsMemory" before optimizing builtins.
This patch is mostly just refactoring a bunch of copy-and-pasted code, but
it also adds a check that the call instructions are readnone or readonly.
That check was already present for sin, cos, sqrt, log2, and exp2 calls, but
it was missing for the rest of the builtins being handled in this code.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@161282 91177308-0d34-0410-b5e6-96231b3b80d8
2012-08-03 23:29:17 +00:00

52 lines
1.7 KiB
LLVM

; RUN: llc < %s -relocation-model=static -realign-stack=1 -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 datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:64:64-v128:128:128-a0:0:64-f80:128:128"
target triple = "i686-apple-darwin8"
@G = external global double
define void @test({ double, double }* byval %z, double* %P) nounwind {
entry:
%tmp3 = load double* @G, align 16 ; <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 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: test4:
; CHECK-NOT: and
; CHECK: ret
}