mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-01 00:12:50 +01:00
bcf2d46d8a
have their low bits set to zero. This allows us to optimize out explicit stack alignment code like in stack-align.ll:test4 when it is redundant. Doing this causes the code generator to start turning FI+cst into FI|cst all over the place, which is general goodness (that is the canonical form) except that various pieces of the code generator don't handle OR aggressively. Fix this by introducing a new SelectionDAG::isBaseWithConstantOffset predicate, and using it in places that are looking for ADD(X,CST). The ARM backend in particular was missing a lot of addressing mode folding opportunities around OR. llvm-svn: 125470
52 lines
1.6 KiB
LLVM
52 lines
1.6 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 ) ; <double> [#uses=1]
|
|
volatile store double %tmp4, double* %P
|
|
%tmp = getelementptr { double, double }* %z, i32 0, i32 0 ; <double*> [#uses=1]
|
|
%tmp1 = volatile load double* %tmp, align 8 ; <double> [#uses=1]
|
|
%tmp2 = tail call double @fabs( double %tmp1 ) ; <double> [#uses=1]
|
|
; CHECK: andpd{{.*}}4(%esp), %xmm
|
|
%tmp6 = fadd double %tmp4, %tmp2 ; <double> [#uses=1]
|
|
volatile store 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
|
|
}
|