From cab5680f6c75867afa51dddc8dc8f4e3188e4d37 Mon Sep 17 00:00:00 2001
From: Jonathan Roelofs <jonathan@codesourcery.com>
Date: Wed, 21 Jan 2015 22:39:43 +0000
Subject: [PATCH] Fix load-store optimizer on thumbv4t

Thumbv4t does not have lo->lo copies other than MOVS,
and that can't be predicated. So emit MOVS when needed
and bail if there's a predicate.

http://reviews.llvm.org/D6592


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@226711 91177308-0d34-0410-b5e6-96231b3b80d8
---
 lib/Target/ARM/ARMLoadStoreOptimizer.cpp      | 17 +++++-
 .../ARM/2015-01-21-thumbv4t-ldstr-opt.ll      | 55 +++++++++++++++++++
 2 files changed, 69 insertions(+), 3 deletions(-)
 create mode 100644 test/CodeGen/ARM/2015-01-21-thumbv4t-ldstr-opt.ll

diff --git a/lib/Target/ARM/ARMLoadStoreOptimizer.cpp b/lib/Target/ARM/ARMLoadStoreOptimizer.cpp
index c429ac18521..fda3e815624 100644
--- a/lib/Target/ARM/ARMLoadStoreOptimizer.cpp
+++ b/lib/Target/ARM/ARMLoadStoreOptimizer.cpp
@@ -567,10 +567,21 @@ ARMLoadStoreOpt::MergeOps(MachineBasicBlock &MBB,
       //   MOV  NewBase, Base
       //   ADDS NewBase, #imm8.
       if (Base != NewBase && Offset >= 8) {
+        const ARMSubtarget &Subtarget = MBB.getParent()->getTarget()
+                       .getSubtarget<ARMSubtarget>();
         // Need to insert a MOV to the new base first.
-        BuildMI(MBB, MBBI, dl, TII->get(ARM::tMOVr), NewBase)
-          .addReg(Base, getKillRegState(BaseKill))
-          .addImm(Pred).addReg(PredReg);
+        if (isARMLowRegister(NewBase) && isARMLowRegister(Base) &&
+            !Subtarget.hasV6Ops()) {
+          // thumbv4t doesn't have lo->lo copies, and we can't predicate tMOVSr
+          if (Pred != ARMCC::AL)
+            return false;
+          BuildMI(MBB, MBBI, dl, TII->get(ARM::tMOVSr), NewBase)
+            .addReg(Base, getKillRegState(BaseKill));
+        } else
+          BuildMI(MBB, MBBI, dl, TII->get(ARM::tMOVr), NewBase)
+            .addReg(Base, getKillRegState(BaseKill))
+            .addImm(Pred).addReg(PredReg);
+
         // Set up BaseKill and Base correctly to insert the ADDS/SUBS below.
         Base = NewBase;
         BaseKill = false;
diff --git a/test/CodeGen/ARM/2015-01-21-thumbv4t-ldstr-opt.ll b/test/CodeGen/ARM/2015-01-21-thumbv4t-ldstr-opt.ll
new file mode 100644
index 00000000000..f3cc3d82121
--- /dev/null
+++ b/test/CodeGen/ARM/2015-01-21-thumbv4t-ldstr-opt.ll
@@ -0,0 +1,55 @@
+; RUN: llc -mtriple=thumbv4t-none--eabi < %s | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK-V4T
+; RUN: llc -mtriple=thumbv6m-none--eabi < %s | FileCheck %s --check-prefix=CHECK --check-prefix=CHECK-V6M
+
+; CHECK-LABEL: foo
+define i32 @foo(i32 %z, ...) #0 {
+entry:
+  %a = alloca i32, align 4
+  %b = alloca i32, align 4
+  %c = alloca i32, align 4
+  %d = alloca i32, align 4
+  %e = alloca i32, align 4
+  %f = alloca i32, align 4
+  %g = alloca i32, align 4
+  %h = alloca i32, align 4
+
+  store i32 1, i32* %a, align 4
+  store i32 2, i32* %b, align 4
+  store i32 3, i32* %c, align 4
+  store i32 4, i32* %d, align 4
+  store i32 5, i32* %e, align 4
+  store i32 6, i32* %f, align 4
+  store i32 7, i32* %g, align 4
+  store i32 8, i32* %h, align 4
+
+  %0 = load i32* %a, align 4
+  %1 = load i32* %b, align 4
+  %2 = load i32* %c, align 4
+  %3 = load i32* %d, align 4
+  %4 = load i32* %e, align 4
+  %5 = load i32* %f, align 4
+  %6 = load i32* %g, align 4
+  %7 = load i32* %h, align 4
+
+  %add  = add nsw i32 %0, %1
+  %add4 = add nsw i32 %add, %2
+  %add5 = add nsw i32 %add4, %3
+  %add6 = add nsw i32 %add5, %4
+  %add7 = add nsw i32 %add6, %5
+  %add8 = add nsw i32 %add7, %6
+  %add9 = add nsw i32 %add8, %7
+
+  %addz = add nsw i32 %add9, %z
+  call void @llvm.va_start(i8* null)
+  ret i32 %addz
+
+; CHECK:      sub sp, #40
+; CHECK-NEXT: add [[BASE:r[0-9]]], sp, #8
+
+; CHECK-V4T:  movs [[NEWBASE:r[0-9]]], [[BASE]]
+; CHECK-V6M:  mov [[NEWBASE:r[0-9]]], [[BASE]]
+; CHECK-NEXT: adds [[NEWBASE]], #8
+; CHECK-NEXT: ldm [[NEWBASE]],
+}
+
+declare void @llvm.va_start(i8*) nounwind
-- 
2.34.1