[EABI] Add LLVM support for -meabi flag

"GCC requires the freestanding environment provide memcpy, memmove, memset
and memcmp": https://gcc.gnu.org/onlinedocs/gcc-5.2.0/gcc/Standards.html

Hence in GNUEABI targets LLVM should not convert 'memops' to their equivalent
'__aeabi_memops'. This convertion violates GCC contract.

The -meabi flag controls whether or not LLVM will modify 'memops' in GNUEABI
targets.

Without -meabi: use the triple default EABI.
With -meabi=default: use the triple default EABI.
With -meabi=gnu: use 'memops'.
With -meabi=4 or -meabi=5: use '__aeabi_memops'.
With -meabi set to an unknown value: same as -meabi=default.

Patch by Vinicius Tinti.

llvm-svn: 252462

2 files changed, 214 insertions, 104 deletions

diff --git a/llvm/test/CodeGen/ARM/arm-eabi.ll b/llvm/test/CodeGen/ARM/arm-eabi.ll
new file mode 100644
index 00000000000..d1e7a947553
--- /dev/null
+++ b/llvm/test/CodeGen/ARM/arm-eabi.ll
@@ -0,0 +1,63 @@
+; RUN: llc < %s -mtriple=arm-none-eabi -disable-post-ra -o - | FileCheck %s --check-prefix=CHECK-EABI
+; RUN: llc < %s -mtriple=arm-none-eabihf -disable-post-ra -o - | FileCheck %s --check-prefix=CHECK-EABI
+; RUN: llc < %s -mtriple=arm-none-androideabi -disable-post-ra -o - | FileCheck %s --check-prefix=CHECK-EABI
+; RUN: llc < %s -mtriple=arm-none-gnueabi -disable-post-ra -o - | FileCheck %s --check-prefix=CHECK-GNUEABI
+; RUN: llc < %s -mtriple=arm-none-gnueabihf -disable-post-ra -o - | FileCheck %s --check-prefix=CHECK-GNUEABI
+; RUN: llc < %s -mtriple=arm-none-eabi -meabi=gnu -disable-post-ra -o - | FileCheck %s --check-prefix=CHECK-GNUEABI
+; RUN: llc < %s -mtriple=arm-none-eabihf -meabi=gnu -disable-post-ra -o - | FileCheck %s --check-prefix=CHECK-GNUEABI
+; RUN: llc < %s -mtriple=arm-none-androideabi -meabi=gnu -disable-post-ra -o - | FileCheck %s --check-prefix=CHECK-GNUEABI
+; RUN: llc < %s -mtriple=arm-none-gnueabi -meabi=gnu -disable-post-ra -o - | FileCheck %s --check-prefix=CHECK-GNUEABI
+; RUN: llc < %s -mtriple=arm-none-gnueabihf -meabi=gnu -disable-post-ra -o - | FileCheck %s --check-prefix=CHECK-GNUEABI
+; RUN: llc < %s -mtriple=arm-none-eabi -meabi=4 -disable-post-ra -o - | FileCheck %s --check-prefix=CHECK-EABI
+; RUN: llc < %s -mtriple=arm-none-eabihf -meabi=4 -disable-post-ra -o - | FileCheck %s --check-prefix=CHECK-EABI
+; RUN: llc < %s -mtriple=arm-none-androideabi -meabi=4 -disable-post-ra -o - | FileCheck %s --check-prefix=CHECK-EABI
+; RUN: llc < %s -mtriple=arm-none-gnueabi -meabi=4 -disable-post-ra -o - | FileCheck %s --check-prefix=CHECK-EABI
+; RUN: llc < %s -mtriple=arm-none-gnueabihf -meabi=4 -disable-post-ra -o - | FileCheck %s --check-prefix=CHECK-EABI
+; RUN: llc < %s -mtriple=arm-none-eabi -meabi=5 -disable-post-ra -o - | FileCheck %s --check-prefix=CHECK-EABI
+; RUN: llc < %s -mtriple=arm-none-eabihf -meabi=5 -disable-post-ra -o - | FileCheck %s --check-prefix=CHECK-EABI
+; RUN: llc < %s -mtriple=arm-none-androideabi -meabi=5 -disable-post-ra -o - | FileCheck %s --check-prefix=CHECK-EABI
+; RUN: llc < %s -mtriple=arm-none-gnueabi -meabi=5 -disable-post-ra -o - | FileCheck %s --check-prefix=CHECK-EABI
+; RUN: llc < %s -mtriple=arm-none-gnueabihf -meabi=5 -disable-post-ra -o - | FileCheck %s --check-prefix=CHECK-EABI
+
+%struct.my_s = type { [18 x i32] }
+
+define void @foo(i32* %t) {
+  ; CHECK-LABEL: foo
+
+  %1 = alloca i32*, align 4
+  store i32* %t, i32** %1, align 4
+  %2 = load i32*, i32** %1, align 4
+  %3 = bitcast i32* %2 to %struct.my_s*
+  %4 = bitcast %struct.my_s* %3 to i8*
+  ; CHECK-EABI: bl __aeabi_memcpy
+  ; CHECK-GNUEABI: bl memcpy
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %4, i8* inttoptr (i32 1 to i8*), i32 72, i32 4, i1 false)
+  ret void
+}
+
+define void @f1(i8* %dest, i8* %src) {
+entry:
+  ; CHECK-LABEL: f1
+
+  ; memmove
+  ; CHECK-EABI: bl __aeabi_memmove
+  ; CHECK-GNUEABI: bl memmove
+  call void @llvm.memmove.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 500, i32 0, i1 false)
+
+  ; memcpy
+  ; CHECK-EABI: bl __aeabi_memcpy
+  ; CHECK-GNUEABI: bl memcpy
+  call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 500, i32 0, i1 false)
+
+  ; memset
+  ; CHECK-EABI: mov r2, #1
+  ; CHECK-EABI: bl __aeabi_memset
+  ; CHECK-GNUEABI: mov r1, #1
+  ; CHECK-GNUEABI: bl memset
+  call void @llvm.memset.p0i8.i32(i8* %dest, i8 1, i32 500, i32 0, i1 false)
+  ret void
+}
+
+declare void @llvm.memmove.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i32, i1) nounwind
+declare void @llvm.memcpy.p0i8.p0i8.i32(i8* nocapture, i8* nocapture, i32, i32, i1) nounwind
+declare void @llvm.memset.p0i8.i32(i8* nocapture, i8, i32, i32, i1) nounwind
diff --git a/llvm/test/CodeGen/ARM/memfunc.ll b/llvm/test/CodeGen/ARM/memfunc.ll
index 5223983a7f3..66743f3e9d5 100644
--- a/llvm/test/CodeGen/ARM/memfunc.ll
+++ b/llvm/test/CodeGen/ARM/memfunc.ll
@@ -1,79 +1,95 @@
-; RUN: llc < %s -mtriple=armv7-apple-ios -disable-post-ra -o - | FileCheck %s --check-prefix=CHECK-IOS --check-prefix=CHECK
-; RUN: llc < %s -mtriple=thumbv7m-none-macho -disable-post-ra -o - | FileCheck %s --check-prefix=CHECK-DARWIN --check-prefix=CHECK
-; RUN: llc < %s -mtriple=arm-none-eabi -disable-post-ra -o - | FileCheck %s --check-prefix=CHECK-EABI --check-prefix=CHECK
-; RUN: llc < %s -mtriple=arm-none-eabihf -disable-post-ra -o - | FileCheck %s --check-prefix=CHECK-EABI --check-prefix=CHECK
+; RUN: llc < %s -mtriple=armv7-apple-ios -disable-post-ra -o - | FileCheck %s --check-prefix=CHECK-IOS
+; RUN: llc < %s -mtriple=thumbv7m-none-macho -disable-post-ra -o - | FileCheck %s --check-prefix=CHECK-DARWIN
+; RUN: llc < %s -mtriple=arm-none-eabi -disable-post-ra -o - | FileCheck %s --check-prefix=CHECK-EABI
+; RUN: llc < %s -mtriple=arm-none-eabihf -disable-post-ra -o - | FileCheck %s --check-prefix=CHECK-EABI
+; RUN: llc < %s -mtriple=arm-none-androideabi -disable-post-ra -o - | FileCheck %s --check-prefix=CHECK-EABI
+; RUN: llc < %s -mtriple=arm-none-gnueabi -disable-post-ra -o - | FileCheck %s --check-prefix=CHECK-GNUEABI
+; RUN: llc < %s -mtriple=arm-none-gnueabihf -disable-post-ra -o - | FileCheck %s --check-prefix=CHECK-GNUEABI
 
 define void @f1(i8* %dest, i8* %src) {
 entry:
   ; CHECK-LABEL: f1
 
-  ; CHECK-IOS: memmove
-  ; CHECK-DARWIN: memmove
-  ; CHECK-EABI: __aeabi_memmove
+  ; CHECK-IOS: bl _memmove
+  ; CHECK-DARWIN: bl _memmove
+  ; CHECK-EABI: bl __aeabi_memmove
+  ; CHECK-GNUEABI: bl memmove
   call void @llvm.memmove.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 500, i32 0, i1 false)
 
-  ; CHECK-IOS: memcpy
-  ; CHECK-DARWIN: memcpy
-  ; CHECK-EABI: __aeabi_memcpy
+  ; CHECK-IOS: bl _memcpy
+  ; CHECK-DARWIN: bl _memcpy
+  ; CHECK-EABI: bl __aeabi_memcpy
+  ; CHECK-GNUEABI: bl memcpy
   call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 500, i32 0, i1 false)
 
   ; EABI memset swaps arguments
   ; CHECK-IOS: mov r1, #1
-  ; CHECK-IOS: memset
+  ; CHECK-IOS: bl _memset
   ; CHECK-DARWIN: movs r1, #1
-  ; CHECK-DARWIN: memset
+  ; CHECK-DARWIN: bl _memset
   ; CHECK-EABI: mov r2, #1
-  ; CHECK-EABI: __aeabi_memset
+  ; CHECK-EABI: bl __aeabi_memset
+  ; CHECK-GNUEABI: mov r1, #1
+  ; CHECK-GNUEABI: bl memset
   call void @llvm.memset.p0i8.i32(i8* %dest, i8 1, i32 500, i32 0, i1 false)
 
   ; EABI uses memclr if value set to 0
   ; CHECK-IOS: mov r1, #0
-  ; CHECK-IOS: memset
+  ; CHECK-IOS: bl _memset
   ; CHECK-DARWIN: movs r1, #0
-  ; CHECK-DARWIN: memset
-  ; CHECK-EABI: __aeabi_memclr
+  ; CHECK-DARWIN: bl _memset
+  ; CHECK-EABI: bl __aeabi_memclr
+  ; CHECK-GNUEABI: bl memset
   call void @llvm.memset.p0i8.i32(i8* %dest, i8 0, i32 500, i32 0, i1 false)
-  
+
   ; EABI uses aligned function variants if possible
 
-  ; CHECK-IOS: memmove
-  ; CHECK-DARWIN: memmove
-  ; CHECK-EABI: __aeabi_memmove4
+  ; CHECK-IOS: bl _memmove
+  ; CHECK-DARWIN: bl _memmove
+  ; CHECK-EABI: bl __aeabi_memmove4
+  ; CHECK-GNUEABI: bl memmove
   call void @llvm.memmove.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 500, i32 4, i1 false)
 
-  ; CHECK-IOS: memcpy
-  ; CHECK-DARWIN: memcpy
-  ; CHECK-EABI: __aeabi_memcpy4
+  ; CHECK-IOS: bl _memcpy
+  ; CHECK-DARWIN: bl _memcpy
+  ; CHECK-EABI: bl __aeabi_memcpy4
+  ; CHECK-GNUEABI: bl memcpy
   call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 500, i32 4, i1 false)
 
-  ; CHECK-IOS: memset
-  ; CHECK-DARWIN: memset
-  ; CHECK-EABI: __aeabi_memset4
+  ; CHECK-IOS: bl _memset
+  ; CHECK-DARWIN: bl _memset
+  ; CHECK-EABI: bl __aeabi_memset4
+  ; CHECK-GNUEABI: bl memset
   call void @llvm.memset.p0i8.i32(i8* %dest, i8 1, i32 500, i32 4, i1 false)
 
-  ; CHECK-IOS: memset
-  ; CHECK-DARWIN: memset
-  ; CHECK-EABI: __aeabi_memclr4
+  ; CHECK-IOS: bl _memset
+  ; CHECK-DARWIN: bl _memset
+  ; CHECK-EABI: bl __aeabi_memclr4
+  ; CHECK-GNUEABI: bl memset
   call void @llvm.memset.p0i8.i32(i8* %dest, i8 0, i32 500, i32 4, i1 false)
 
-  ; CHECK-IOS: memmove
-  ; CHECK-DARWIN: memmove
-  ; CHECK-EABI: __aeabi_memmove8
+  ; CHECK-IOS: bl _memmove
+  ; CHECK-DARWIN: bl _memmove
+  ; CHECK-EABI: bl __aeabi_memmove8
+  ; CHECK-GNUEABI: bl memmove
   call void @llvm.memmove.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 500, i32 8, i1 false)
 
-  ; CHECK-IOS: memcpy
-  ; CHECK-DARWIN: memcpy
-  ; CHECK-EABI: __aeabi_memcpy8
+  ; CHECK-IOS: bl _memcpy
+  ; CHECK-DARWIN: bl _memcpy
+  ; CHECK-EABI: bl __aeabi_memcpy8
+  ; CHECK-GNUEABI: bl memcpy
   call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %src, i32 500, i32 8, i1 false)
 
-  ; CHECK-IOS: memset
-  ; CHECK-DARWIN: memset
-  ; CHECK-EABI: __aeabi_memset8
+  ; CHECK-IOS: bl _memset
+  ; CHECK-DARWIN: bl _memset
+  ; CHECK-EABI: bl __aeabi_memset8
+  ; CHECK-GNUEABI: bl memset
   call void @llvm.memset.p0i8.i32(i8* %dest, i8 1, i32 500, i32 8, i1 false)
 
-  ; CHECK-IOS: memset
-  ; CHECK-DARWIN: memset
-  ; CHECK-EABI: __aeabi_memclr8
+  ; CHECK-IOS: bl _memset
+  ; CHECK-DARWIN: bl _memset
+  ; CHECK-EABI: bl __aeabi_memclr8
+  ; CHECK-GNUEABI: bl memset
   call void @llvm.memset.p0i8.i32(i8* %dest, i8 0, i32 500, i32 8, i1 false)
 
   unreachable
@@ -86,32 +102,38 @@ entry:
 
   ; IOS (ARMv7) should 8-byte align, others should 4-byte align
   ; CHECK-IOS: add r1, sp, #32
-  ; CHECK-IOS: memmove
+  ; CHECK-IOS: bl _memmove
   ; CHECK-DARWIN: add r1, sp, #28
-  ; CHECK-DARWIN: memmove
+  ; CHECK-DARWIN: bl _memmove
   ; CHECK-EABI: add r1, sp, #28
-  ; CHECK-EABI: __aeabi_memmove
+  ; CHECK-EABI: bl __aeabi_memmove
+  ; CHECK-GNUEABI: add r1, sp, #28
+  ; CHECK-GNUEABI: bl memmove
   %arr0 = alloca [9 x i8], align 1
   %0 = bitcast [9 x i8]* %arr0 to i8*
   call void @llvm.memmove.p0i8.p0i8.i32(i8* %dest, i8* %0, i32 %n, i32 0, i1 false)
 
   ; CHECK: add r1, sp, #16
-  ; CHECK-IOS: memcpy
-  ; CHECK-DARWIN: memcpy
-  ; CHECK-EABI: __aeabi_memcpy
+  ; CHECK-IOS: bl _memcpy
+  ; CHECK-DARWIN: bl _memcpy
+  ; CHECK-EABI: bl __aeabi_memcpy
+  ; CHECK-GNUEABI: bl memcpy
   %arr1 = alloca [9 x i8], align 1
   %1 = bitcast [9 x i8]* %arr1 to i8*
   call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %1, i32 %n, i32 0, i1 false)
 
   ; CHECK-IOS: mov r0, sp
   ; CHECK-IOS: mov r1, #1
-  ; CHECK-IOS: memset
+  ; CHECK-IOS: bl _memset
   ; CHECK-DARWIN: add r0, sp, #4
   ; CHECK-DARWIN: movs r1, #1
-  ; CHECK-DARWIN: memset
+  ; CHECK-DARWIN: bl _memset
   ; CHECK-EABI: add r0, sp, #4
   ; CHECK-EABI: mov r2, #1
-  ; CHECK-EABI: __aeabi_memset
+  ; CHECK-EABI: bl __aeabi_memset
+  ; CHECK-GNUEABI: add r0, sp, #4
+  ; CHECK-GNUEABI: mov r1, #1
+  ; CHECK-GNUEABI: bl memset
   %arr2 = alloca [9 x i8], align 1
   %2 = bitcast [9 x i8]* %arr2 to i8*
   call void @llvm.memset.p0i8.i32(i8* %2, i8 1, i32 %n, i32 0, i1 false)
@@ -125,28 +147,32 @@ entry:
   ; CHECK-LABEL: f3
 
   ; CHECK: {{add(.w)? r1, sp, #17|sub(.w)? r1, r7, #15}}
-  ; CHECK-IOS: memmove
-  ; CHECK-DARWIN: memmove
-  ; CHECK-EABI: __aeabi_memmove
+  ; CHECK-IOS: bl _memmove
+  ; CHECK-DARWIN: bl _memmove
+  ; CHECK-EABI: bl __aeabi_memmove
+  ; CHECK-GNUEABI: bl memmove
   %arr0 = alloca [7 x i8], align 1
   %0 = bitcast [7 x i8]* %arr0 to i8*
   call void @llvm.memmove.p0i8.p0i8.i32(i8* %dest, i8* %0, i32 %n, i32 0, i1 false)
 
   ; CHECK: {{add(.w)? r1, sp, #10}}
-  ; CHECK-IOS: memcpy
-  ; CHECK-DARWIN: memcpy
-  ; CHECK-EABI: __aeabi_memcpy
+  ; CHECK-IOS: bl _memcpy
+  ; CHECK-DARWIN: bl _memcpy
+  ; CHECK-EABI: bl __aeabi_memcpy
+  ; CHECK-GNUEABI: bl memcpy
   %arr1 = alloca [7 x i8], align 1
   %1 = bitcast [7 x i8]* %arr1 to i8*
   call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %1, i32 %n, i32 0, i1 false)
 
   ; CHECK: {{add(.w)? r0, sp, #3}}
   ; CHECK-IOS: mov r1, #1
-  ; CHECK-IOS: memset
+  ; CHECK-IOS: bl _memset
   ; CHECK-DARWIN: movs r1, #1
-  ; CHECK-DARWIN: memset
+  ; CHECK-DARWIN: bl _memset
   ; CHECK-EABI: mov r2, #1
-  ; CHECK-EABI: __aeabi_memset
+  ; CHECK-EABI: bl __aeabi_memset
+  ; CHECK-GNUEABI: mov r1, #1
+  ; CHECK-GNUEABI: bl memset
   %arr2 = alloca [7 x i8], align 1
   %2 = bitcast [7 x i8]* %arr2 to i8*
   call void @llvm.memset.p0i8.i32(i8* %2, i8 1, i32 %n, i32 0, i1 false)
@@ -160,28 +186,32 @@ entry:
   ; CHECK-LABEL: f4
 
   ; CHECK: {{add(.w)? r., sp, #23|sub(.w)? r., r7, #17}}
-  ; CHECK-IOS: memmove
-  ; CHECK-DARWIN: memmove
-  ; CHECK-EABI: __aeabi_memmove
+  ; CHECK-IOS: bl _memmove
+  ; CHECK-DARWIN: bl _memmove
+  ; CHECK-EABI: bl __aeabi_memmove
+  ; CHECK-GNUEABI: bl memmove
   %arr0 = alloca [9 x i8], align 1
   %0 = getelementptr inbounds [9 x i8], [9 x i8]* %arr0, i32 0, i32 4
   call void @llvm.memmove.p0i8.p0i8.i32(i8* %dest, i8* %0, i32 %n, i32 0, i1 false)
 
   ; CHECK: {{add(.w)? r., sp, #(10|14)}}
-  ; CHECK-IOS: memcpy
-  ; CHECK-DARWIN: memcpy
-  ; CHECK-EABI: __aeabi_memcpy
+  ; CHECK-IOS: bl _memcpy
+  ; CHECK-DARWIN: bl _memcpy
+  ; CHECK-EABI: bl __aeabi_memcpy
+  ; CHECK-GNUEABI: bl memcpy
   %arr1 = alloca [9 x i8], align 1
   %1 = getelementptr inbounds [9 x i8], [9 x i8]* %arr1, i32 0, i32 4
   call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %1, i32 %n, i32 0, i1 false)
 
   ; CHECK: {{add(.w)? r., sp, #(1|5)}}
   ; CHECK-IOS: mov r1, #1
-  ; CHECK-IOS: memset
+  ; CHECK-IOS: bl _memset
   ; CHECK-DARWIN: movs r1, #1
-  ; CHECK-DARWIN: memset
+  ; CHECK-DARWIN: bl _memset
   ; CHECK-EABI: mov r2, #1
-  ; CHECK-EABI: __aeabi_memset
+  ; CHECK-EABI: bl __aeabi_memset
+  ; CHECK-GNUEABI: mov r1, #1
+  ; CHECK-GNUEABI: bl memset
   %arr2 = alloca [9 x i8], align 1
   %2 = getelementptr inbounds [9 x i8], [9 x i8]* %arr2, i32 0, i32 4
   call void @llvm.memset.p0i8.i32(i8* %2, i8 1, i32 %n, i32 0, i1 false)
@@ -195,28 +225,32 @@ entry:
   ; CHECK-LABEL: f5
 
   ; CHECK: {{add(.w)? r., sp, #27|sub(.w)? r., r7, #21}}
-  ; CHECK-IOS: memmove
-  ; CHECK-DARWIN: memmove
-  ; CHECK-EABI: __aeabi_memmove
+  ; CHECK-IOS: bl _memmove
+  ; CHECK-DARWIN: bl _memmove
+  ; CHECK-EABI: bl __aeabi_memmove
+  ; CHECK-GNUEABI: bl memmove
   %arr0 = alloca [13 x i8], align 1
   %0 = getelementptr inbounds [13 x i8], [13 x i8]* %arr0, i32 0, i32 1
   call void @llvm.memmove.p0i8.p0i8.i32(i8* %dest, i8* %0, i32 %n, i32 0, i1 false)
 
   ; CHECK: {{add(.w)? r., sp, #(10|14)}}
-  ; CHECK-IOS: memcpy
-  ; CHECK-DARWIN: memcpy
-  ; CHECK-EABI: __aeabi_memcpy
+  ; CHECK-IOS: bl _memcpy
+  ; CHECK-DARWIN: bl _memcpy
+  ; CHECK-EABI: bl __aeabi_memcpy
+  ; CHECK-GNUEABI: bl memcpy
   %arr1 = alloca [13 x i8], align 1
   %1 = getelementptr inbounds [13 x i8], [13 x i8]* %arr1, i32 0, i32 1
   call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %1, i32 %n, i32 0, i1 false)
 
   ; CHECK: {{add(.w)? r., sp, #(1|5)}}
   ; CHECK-IOS: mov r1, #1
-  ; CHECK-IOS: memset
+  ; CHECK-IOS: bl _memset
   ; CHECK-DARWIN: movs r1, #1
-  ; CHECK-DARWIN: memset
+  ; CHECK-DARWIN: bl _memset
   ; CHECK-EABI: mov r2, #1
-  ; CHECK-EABI: __aeabi_memset
+  ; CHECK-EABI: bl __aeabi_memset
+  ; CHECK-GNUEABI: mov r1, #1
+  ; CHECK-GNUEABI: bl memset
   %arr2 = alloca [13 x i8], align 1
   %2 = getelementptr inbounds [13 x i8], [13 x i8]* %arr2, i32 0, i32 1
   call void @llvm.memset.p0i8.i32(i8* %2, i8 1, i32 %n, i32 0, i1 false)
@@ -230,28 +264,32 @@ entry:
   ; CHECK-LABEL: f6
 
   ; CHECK: {{add(.w)? r., sp, #27|sub(.w)? r., r7, #25}}
-  ; CHECK-IOS: memmove
-  ; CHECK-DARWIN: memmove
-  ; CHECK-EABI: __aeabi_memmove
+  ; CHECK-IOS: bl _memmove
+  ; CHECK-DARWIN: bl _memmove
+  ; CHECK-EABI: bl __aeabi_memmove
+  ; CHECK-GNUEABI: bl memmove
   %arr0 = alloca [13 x i8], align 1
   %0 = getelementptr inbounds [13 x i8], [13 x i8]* %arr0, i32 0, i32 %i
   call void @llvm.memmove.p0i8.p0i8.i32(i8* %dest, i8* %0, i32 %n, i32 0, i1 false)
 
   ; CHECK: {{add(.w)? r., sp, #(10|14)}}
-  ; CHECK-IOS: memcpy
-  ; CHECK-DARWIN: memcpy
-  ; CHECK-EABI: __aeabi_memcpy
+  ; CHECK-IOS: bl _memcpy
+  ; CHECK-DARWIN: bl _memcpy
+  ; CHECK-EABI: bl __aeabi_memcpy
+  ; CHECK-GNUEABI: bl memcpy
   %arr1 = alloca [13 x i8], align 1
   %1 = getelementptr inbounds [13 x i8], [13 x i8]* %arr1, i32 0, i32 %i
   call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %1, i32 %n, i32 0, i1 false)
 
   ; CHECK: {{add(.w)? r., sp, #(1|5)}}
   ; CHECK-IOS: mov r1, #1
-  ; CHECK-IOS: memset
+  ; CHECK-IOS: bl _memset
   ; CHECK-DARWIN: movs r1, #1
-  ; CHECK-DARWIN: memset
+  ; CHECK-DARWIN: bl _memset
   ; CHECK-EABI: mov r2, #1
-  ; CHECK-EABI: __aeabi_memset
+  ; CHECK-EABI: bl __aeabi_memset
+  ; CHECK-GNUEABI: mov r1, #1
+  ; CHECK-GNUEABI: bl memset
   %arr2 = alloca [13 x i8], align 1
   %2 = getelementptr inbounds [13 x i8], [13 x i8]* %arr2, i32 0, i32 %i
   call void @llvm.memset.p0i8.i32(i8* %2, i8 1, i32 %n, i32 0, i1 false)
@@ -265,28 +303,32 @@ entry:
   ; CHECK-LABEL: f7
 
   ; CHECK: {{add(.w)? r., sp, #27|sub(.w)? r., r7, #21}}
-  ; CHECK-IOS: memmove
-  ; CHECK-DARWIN: memmove
-  ; CHECK-EABI: __aeabi_memmove
+  ; CHECK-IOS: bl _memmove
+  ; CHECK-DARWIN: bl _memmove
+  ; CHECK-EABI: bl __aeabi_memmove
+  ; CHECK-GNUEABI: bl memmove
   %arr0 = alloca [13 x i8], align 1
   %0 = getelementptr [13 x i8], [13 x i8]* %arr0, i32 0, i32 4
   call void @llvm.memmove.p0i8.p0i8.i32(i8* %dest, i8* %0, i32 %n, i32 0, i1 false)
 
   ; CHECK: {{add(.w)? r., sp, #(10|14)}}
-  ; CHECK-IOS: memcpy
-  ; CHECK-DARWIN: memcpy
-  ; CHECK-EABI: __aeabi_memcpy
+  ; CHECK-IOS: bl _memcpy
+  ; CHECK-DARWIN: bl _memcpy
+  ; CHECK-EABI: bl __aeabi_memcpy
+  ; CHECK-GNUEABI: bl memcpy
   %arr1 = alloca [13 x i8], align 1
   %1 = getelementptr [13 x i8], [13 x i8]* %arr1, i32 0, i32 4
   call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %1, i32 %n, i32 0, i1 false)
 
   ; CHECK: {{add(.w)? r., sp, #(1|5)}}
   ; CHECK-IOS: mov r1, #1
-  ; CHECK-IOS: memset
+  ; CHECK-IOS: bl _memset
   ; CHECK-DARWIN: movs r1, #1
-  ; CHECK-DARWIN: memset
+  ; CHECK-DARWIN: bl _memset
   ; CHECK-EABI: mov r2, #1
-  ; CHECK-EABI: __aeabi_memset
+  ; CHECK-EABI: bl __aeabi_memset
+  ; CHECK-GNUEABI: mov r1, #1
+  ; CHECK-GNUEABI: bl memset
   %arr2 = alloca [13 x i8], align 1
   %2 = getelementptr [13 x i8], [13 x i8]* %arr2, i32 0, i32 4
   call void @llvm.memset.p0i8.i32(i8* %2, i8 1, i32 %n, i32 0, i1 false)
@@ -300,28 +342,32 @@ entry:
   ; CHECK-LABEL: f8
 
   ; CHECK: {{add(.w)? r., sp, #27|sub(.w)? r., r7, #21}}
-  ; CHECK-IOS: memmove
-  ; CHECK-DARWIN: memmove
-  ; CHECK-EABI: __aeabi_memmove
+  ; CHECK-IOS: bl _memmove
+  ; CHECK-DARWIN: bl _memmove
+  ; CHECK-EABI: bl __aeabi_memmove
+  ; CHECK-GNUEABI: bl memmove
   %arr0 = alloca [13 x i8], align 1
   %0 = getelementptr inbounds [13 x i8], [13 x i8]* %arr0, i32 0, i32 16
   call void @llvm.memmove.p0i8.p0i8.i32(i8* %dest, i8* %0, i32 %n, i32 0, i1 false)
 
   ; CHECK: {{add(.w)? r., sp, #(10|14)}}
-  ; CHECK-IOS: memcpy
-  ; CHECK-DARWIN: memcpy
-  ; CHECK-EABI: __aeabi_memcpy
+  ; CHECK-IOS: bl _memcpy
+  ; CHECK-DARWIN: bl _memcpy
+  ; CHECK-EABI: bl __aeabi_memcpy
+  ; CHECK-GNUEABI: bl memcpy
   %arr1 = alloca [13 x i8], align 1
   %1 = getelementptr inbounds [13 x i8], [13 x i8]* %arr1, i32 0, i32 16
   call void @llvm.memcpy.p0i8.p0i8.i32(i8* %dest, i8* %1, i32 %n, i32 0, i1 false)
 
   ; CHECK: {{add(.w)? r., sp, #(1|5)}}
   ; CHECK-IOS: mov r1, #1
-  ; CHECK-IOS: memset
+  ; CHECK-IOS: bl _memset
   ; CHECK-DARWIN: movs r1, #1
-  ; CHECK-DARWIN: memset
+  ; CHECK-DARWIN: bl _memset
   ; CHECK-EABI: mov r2, #1
-  ; CHECK-EABI: __aeabi_memset
+  ; CHECK-EABI: bl __aeabi_memset
+  ; CHECK-GNUEABI: mov r1, #1
+  ; CHECK-GNUEABI: bl memset
   %arr2 = alloca [13 x i8], align 1
   %2 = getelementptr inbounds [13 x i8], [13 x i8]* %arr2, i32 0, i32 16
   call void @llvm.memset.p0i8.i32(i8* %2, i8 1, i32 %n, i32 0, i1 false)
@@ -357,6 +403,7 @@ entry:
 ; CHECK-IOS: .align 3
 ; CHECK-DARWIN: .align 2
 ; CHECK-EABI: .align 2
+; CHECK-GNUEABI: .align 2
 ; CHECK: arr2:
 ; CHECK: {{\.section.+foo,bar}}
 ; CHECK-NOT: .align