mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-10-23 04:52:54 +02:00
4291d4247a
This commit is to improve global merge pass and support global symbol merge. The global symbol merge is not enabled by default. For aarch64, we need some more back-end fix to make it really benifit ADRP CSE. llvm-svn: 210640
86 lines
4.9 KiB
LLVM
86 lines
4.9 KiB
LLVM
; RUN: llc %s -O0 -o - | FileCheck -check-prefix=NO-MERGE %s
|
|
; RUN: llc %s -O0 -o - -enable-global-merge=false | FileCheck -check-prefix=NO-MERGE %s
|
|
; RUN: llc %s -O0 -o - -enable-global-merge=true | FileCheck -check-prefix=NO-MERGE %s
|
|
; RUN: llc %s -O1 -o - | FileCheck -check-prefix=MERGE %s
|
|
; RUN: llc %s -O1 -o - -enable-global-merge=false | FileCheck -check-prefix=NO-MERGE %s
|
|
; RUN: llc %s -O1 -o - -enable-global-merge=true | FileCheck -check-prefix=MERGE %s
|
|
|
|
; MERGE-NOT: .zerofill __DATA,__bss,_bar,20,2
|
|
; MERGE-NOT: .zerofill __DATA,__bss,_baz,20,2
|
|
; MERGE-NOT: .zerofill __DATA,__bss,_foo,20,2
|
|
; MERGE: .zerofill __DATA,__bss,__MergedGlobals,60,4
|
|
; MERGE-NOT: .zerofill __DATA,__bss,_bar,20,2
|
|
; MERGE-NOT: .zerofill __DATA,__bss,_baz,20,2
|
|
; MERGE-NOT: .zerofill __DATA,__bss,_foo,20,2
|
|
|
|
; NO-MERGE-NOT: .zerofill __DATA,__bss,__MergedGlobals,60,4
|
|
; NO-MERGE: .zerofill __DATA,__bss,_bar,20,2
|
|
; NO-MERGE: .zerofill __DATA,__bss,_baz,20,2
|
|
; NO-MERGE: .zerofill __DATA,__bss,_foo,20,2
|
|
; NO-MERGE-NOT: .zerofill __DATA,__bss,__MergedGlobals,60,4
|
|
|
|
target datalayout = "e-p:32:32:32-i1:8:32-i8:8:32-i16:16:32-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:32:64-v128:32:128-a0:0:32-n32-S32"
|
|
target triple = "thumbv7-apple-ios3.0.0"
|
|
|
|
@bar = internal global [5 x i32] zeroinitializer, align 4
|
|
@baz = internal global [5 x i32] zeroinitializer, align 4
|
|
@foo = internal global [5 x i32] zeroinitializer, align 4
|
|
|
|
; Function Attrs: nounwind ssp
|
|
define internal void @initialize() #0 {
|
|
%1 = tail call i32 bitcast (i32 (...)* @calc to i32 ()*)() #3
|
|
store i32 %1, i32* getelementptr inbounds ([5 x i32]* @bar, i32 0, i32 0), align 4, !tbaa !1
|
|
%2 = tail call i32 bitcast (i32 (...)* @calc to i32 ()*)() #3
|
|
store i32 %2, i32* getelementptr inbounds ([5 x i32]* @baz, i32 0, i32 0), align 4, !tbaa !1
|
|
%3 = tail call i32 bitcast (i32 (...)* @calc to i32 ()*)() #3
|
|
store i32 %3, i32* getelementptr inbounds ([5 x i32]* @bar, i32 0, i32 1), align 4, !tbaa !1
|
|
%4 = tail call i32 bitcast (i32 (...)* @calc to i32 ()*)() #3
|
|
store i32 %4, i32* getelementptr inbounds ([5 x i32]* @baz, i32 0, i32 1), align 4, !tbaa !1
|
|
%5 = tail call i32 bitcast (i32 (...)* @calc to i32 ()*)() #3
|
|
store i32 %5, i32* getelementptr inbounds ([5 x i32]* @bar, i32 0, i32 2), align 4, !tbaa !1
|
|
%6 = tail call i32 bitcast (i32 (...)* @calc to i32 ()*)() #3
|
|
store i32 %6, i32* getelementptr inbounds ([5 x i32]* @baz, i32 0, i32 2), align 4, !tbaa !1
|
|
%7 = tail call i32 bitcast (i32 (...)* @calc to i32 ()*)() #3
|
|
store i32 %7, i32* getelementptr inbounds ([5 x i32]* @bar, i32 0, i32 3), align 4, !tbaa !1
|
|
%8 = tail call i32 bitcast (i32 (...)* @calc to i32 ()*)() #3
|
|
store i32 %8, i32* getelementptr inbounds ([5 x i32]* @baz, i32 0, i32 3), align 4, !tbaa !1
|
|
%9 = tail call i32 bitcast (i32 (...)* @calc to i32 ()*)() #3
|
|
store i32 %9, i32* getelementptr inbounds ([5 x i32]* @bar, i32 0, i32 4), align 4, !tbaa !1
|
|
%10 = tail call i32 bitcast (i32 (...)* @calc to i32 ()*)() #3
|
|
store i32 %10, i32* getelementptr inbounds ([5 x i32]* @baz, i32 0, i32 4), align 4, !tbaa !1
|
|
ret void
|
|
}
|
|
|
|
declare i32 @calc(...) #1
|
|
|
|
; Function Attrs: nounwind ssp
|
|
define internal void @calculate() #0 {
|
|
%1 = load <4 x i32>* bitcast ([5 x i32]* @bar to <4 x i32>*), align 4
|
|
%2 = load <4 x i32>* bitcast ([5 x i32]* @baz to <4 x i32>*), align 4
|
|
%3 = mul <4 x i32> %2, %1
|
|
store <4 x i32> %3, <4 x i32>* bitcast ([5 x i32]* @foo to <4 x i32>*), align 4
|
|
%4 = load i32* getelementptr inbounds ([5 x i32]* @bar, i32 0, i32 4), align 4, !tbaa !1
|
|
%5 = load i32* getelementptr inbounds ([5 x i32]* @baz, i32 0, i32 4), align 4, !tbaa !1
|
|
%6 = mul nsw i32 %5, %4
|
|
store i32 %6, i32* getelementptr inbounds ([5 x i32]* @foo, i32 0, i32 4), align 4, !tbaa !1
|
|
ret void
|
|
}
|
|
|
|
; Function Attrs: nounwind readnone ssp
|
|
define internal i32* @returnFoo() #2 {
|
|
ret i32* getelementptr inbounds ([5 x i32]* @foo, i32 0, i32 0)
|
|
}
|
|
|
|
attributes #0 = { nounwind ssp "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "stack-protector-buffer-size"="8" "unsafe-fp-math"="false" "use-soft-float"="false" }
|
|
attributes #1 = { "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "stack-protector-buffer-size"="8" "unsafe-fp-math"="false" "use-soft-float"="false" }
|
|
attributes #2 = { nounwind readnone ssp "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "stack-protector-buffer-size"="8" "unsafe-fp-math"="false" "use-soft-float"="false" }
|
|
attributes #3 = { nounwind }
|
|
|
|
!llvm.ident = !{!0}
|
|
|
|
!0 = metadata !{metadata !"LLVM version 3.4 "}
|
|
!1 = metadata !{metadata !2, metadata !2, i64 0}
|
|
!2 = metadata !{metadata !"int", metadata !3, i64 0}
|
|
!3 = metadata !{metadata !"omnipotent char", metadata !4, i64 0}
|
|
!4 = metadata !{metadata !"Simple C/C++ TBAA"}
|