ARM64: initial backend import

This adds a second implementation of the AArch64 architecture to LLVM,
accessible in parallel via the "arm64" triple. The plan over the
coming weeks & months is to merge the two into a single backend,
during which time thorough code review should naturally occur.

Everything will be easier with the target in-tree though, hence this
commit.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@205090 91177308-0d34-0410-b5e6-96231b3b80d8

4 files changed, 181 insertions, 0 deletions

diff --git a/test/Transforms/GlobalMerge/ARM/arm.ll b/test/Transforms/GlobalMerge/ARM/arm.ll
new file mode 100644
index 0000000000..8c77de62ec
--- /dev/null
+++ b/test/Transforms/GlobalMerge/ARM/arm.ll
@@ -0,0 +1,85 @@
+; RUN: llc %s -O0 -o - | FileCheck -check-prefix=NO-MERGE %s
+; RUN: llc %s -O0 -o - -global-merge=false | FileCheck -check-prefix=NO-MERGE %s
+; RUN: llc %s -O0 -o - -global-merge=true | FileCheck -check-prefix=NO-MERGE %s
+; RUN: llc %s -O1 -o - | FileCheck -check-prefix=MERGE %s
+; RUN: llc %s -O1 -o - -global-merge=false | FileCheck -check-prefix=NO-MERGE %s
+; RUN: llc %s -O1 -o - -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"}
diff --git a/test/Transforms/GlobalMerge/ARM/lit.local.cfg b/test/Transforms/GlobalMerge/ARM/lit.local.cfg
new file mode 100644
index 0000000000..8a3ba96497
--- /dev/null
+++ b/test/Transforms/GlobalMerge/ARM/lit.local.cfg
@@ -0,0 +1,4 @@
+targets = set(config.root.targets_to_build.split())
+if not 'ARM' in targets:
+    config.unsupported = True
+
diff --git a/test/Transforms/GlobalMerge/ARM64/arm64.ll b/test/Transforms/GlobalMerge/ARM64/arm64.ll
new file mode 100644
index 0000000000..eea474a74f
--- /dev/null
+++ b/test/Transforms/GlobalMerge/ARM64/arm64.ll
@@ -0,0 +1,88 @@
+; RUN: llc %s -O0 -o - | FileCheck -check-prefix=NO-MERGE %s
+; RUN: llc %s -O0 -o - -global-merge=false | FileCheck -check-prefix=NO-MERGE %s
+; RUN: llc %s -O0 -o - -global-merge=true | FileCheck -check-prefix=NO-MERGE %s
+; RUN: llc %s -O1 -o - | FileCheck -check-prefix=MERGE %s
+; RUN: llc %s -O1 -o - -global-merge=false | FileCheck -check-prefix=NO-MERGE %s
+; RUN: llc %s -O1 -o - -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:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-n32:64-S128"
+target triple = "arm64-apple-ios7.0.0"
+
+@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 ()*)() #2
+  store i32 %1, i32* getelementptr inbounds ([5 x i32]* @bar, i64 0, i64 0), align 4
+  %2 = tail call i32 bitcast (i32 (...)* @calc to i32 ()*)() #2
+  store i32 %2, i32* getelementptr inbounds ([5 x i32]* @baz, i64 0, i64 0), align 4
+  %3 = tail call i32 bitcast (i32 (...)* @calc to i32 ()*)() #2
+  store i32 %3, i32* getelementptr inbounds ([5 x i32]* @bar, i64 0, i64 1), align 4
+  %4 = tail call i32 bitcast (i32 (...)* @calc to i32 ()*)() #2
+  store i32 %4, i32* getelementptr inbounds ([5 x i32]* @baz, i64 0, i64 1), align 4
+  %5 = tail call i32 bitcast (i32 (...)* @calc to i32 ()*)() #2
+  store i32 %5, i32* getelementptr inbounds ([5 x i32]* @bar, i64 0, i64 2), align 4
+  %6 = tail call i32 bitcast (i32 (...)* @calc to i32 ()*)() #2
+  store i32 %6, i32* getelementptr inbounds ([5 x i32]* @baz, i64 0, i64 2), align 4
+  %7 = tail call i32 bitcast (i32 (...)* @calc to i32 ()*)() #2
+  store i32 %7, i32* getelementptr inbounds ([5 x i32]* @bar, i64 0, i64 3), align 4
+  %8 = tail call i32 bitcast (i32 (...)* @calc to i32 ()*)() #2
+  store i32 %8, i32* getelementptr inbounds ([5 x i32]* @baz, i64 0, i64 3), align 4
+  %9 = tail call i32 bitcast (i32 (...)* @calc to i32 ()*)() #2
+  store i32 %9, i32* getelementptr inbounds ([5 x i32]* @bar, i64 0, i64 4), align 4
+  %10 = tail call i32 bitcast (i32 (...)* @calc to i32 ()*)() #2
+  store i32 %10, i32* getelementptr inbounds ([5 x i32]* @baz, i64 0, i64 4), align 4
+  ret void
+}
+
+declare i32 @calc(...)
+
+; Function Attrs: nounwind ssp
+define internal void @calculate() #0 {
+  %1 = load i32* getelementptr inbounds ([5 x i32]* @bar, i64 0, i64 0), align 4
+  %2 = load i32* getelementptr inbounds ([5 x i32]* @baz, i64 0, i64 0), align 4
+  %3 = mul nsw i32 %2, %1
+  store i32 %3, i32* getelementptr inbounds ([5 x i32]* @foo, i64 0, i64 0), align 4
+  %4 = load i32* getelementptr inbounds ([5 x i32]* @bar, i64 0, i64 1), align 4
+  %5 = load i32* getelementptr inbounds ([5 x i32]* @baz, i64 0, i64 1), align 4
+  %6 = mul nsw i32 %5, %4
+  store i32 %6, i32* getelementptr inbounds ([5 x i32]* @foo, i64 0, i64 1), align 4
+  %7 = load i32* getelementptr inbounds ([5 x i32]* @bar, i64 0, i64 2), align 4
+  %8 = load i32* getelementptr inbounds ([5 x i32]* @baz, i64 0, i64 2), align 4
+  %9 = mul nsw i32 %8, %7
+  store i32 %9, i32* getelementptr inbounds ([5 x i32]* @foo, i64 0, i64 2), align 4
+  %10 = load i32* getelementptr inbounds ([5 x i32]* @bar, i64 0, i64 3), align 4
+  %11 = load i32* getelementptr inbounds ([5 x i32]* @baz, i64 0, i64 3), align 4
+  %12 = mul nsw i32 %11, %10
+  store i32 %12, i32* getelementptr inbounds ([5 x i32]* @foo, i64 0, i64 3), align 4
+  %13 = load i32* getelementptr inbounds ([5 x i32]* @bar, i64 0, i64 4), align 4
+  %14 = load i32* getelementptr inbounds ([5 x i32]* @baz, i64 0, i64 4), align 4
+  %15 = mul nsw i32 %14, %13
+  store i32 %15, i32* getelementptr inbounds ([5 x i32]* @foo, i64 0, i64 4), align 4
+  ret void
+}
+
+; Function Attrs: nounwind readnone ssp
+define internal i32* @returnFoo() #1 {
+  ret i32* getelementptr inbounds ([5 x i32]* @foo, i64 0, i64 0)
+}
+
+attributes #0 = { nounwind ssp }
+attributes #1 = { nounwind readnone ssp }
+attributes #2 = { nounwind }
diff --git a/test/Transforms/GlobalMerge/ARM64/lit.local.cfg b/test/Transforms/GlobalMerge/ARM64/lit.local.cfg
new file mode 100644
index 0000000000..a75a42b6f7
--- /dev/null
+++ b/test/Transforms/GlobalMerge/ARM64/lit.local.cfg
@@ -0,0 +1,4 @@
+targets = set(config.root.targets_to_build.split())
+if not 'ARM64' in targets:
+    config.unsupported = True
+