Merge pull request #123 from cramertj/aarch64-fix

aarch64 fix

lib/CodeGen/GlobalISel/IRTranslator.cpp

@@ -11,6 +11,7 @@
 //===----------------------------------------------------------------------===//
 
 #include "llvm/CodeGen/GlobalISel/IRTranslator.h"
+#include "llvm/ADT/PostOrderIterator.h"
 #include "llvm/ADT/STLExtras.h"
 #include "llvm/ADT/ScopeExit.h"
 #include "llvm/ADT/SmallSet.h"
@@ -32,6 +33,7 @@
 #include "llvm/CodeGen/TargetRegisterInfo.h"
 #include "llvm/CodeGen/TargetSubtargetInfo.h"
 #include "llvm/IR/BasicBlock.h"
+#include "llvm/IR/CFG.h"
 #include "llvm/IR/Constant.h"
 #include "llvm/IR/Constants.h"
 #include "llvm/IR/DataLayout.h"
@@ -1593,19 +1595,20 @@ bool IRTranslator::runOnMachineFunction(MachineFunction &CurMF) {
     ArgIt++;
   }
 
-  // And translate the function!
-  for (const BasicBlock &BB : F) {
-    MachineBasicBlock &MBB = getMBB(BB);
+  // Need to visit defs before uses when translating instructions.
+  ReversePostOrderTraversal<const Function *> RPOT(&F);
+  for (const BasicBlock *BB : RPOT) {
+    MachineBasicBlock &MBB = getMBB(*BB);
     // Set the insertion point of all the following translations to
     // the end of this basic block.
     CurBuilder.setMBB(MBB);
 
-    for (const Instruction &Inst : BB) {
+    for (const Instruction &Inst : *BB) {
       if (translate(Inst))
         continue;
 
       OptimizationRemarkMissed R("gisel-irtranslator", "GISelFailure",
-                                 Inst.getDebugLoc(), &BB);
+                                 Inst.getDebugLoc(), BB);
       R << "unable to translate instruction: " << ore::NV("Opcode", &Inst);
 
       if (ORE->allowExtraAnalysis("gisel-irtranslator")) {

test/CodeGen/AArch64/GlobalISel/arm64-fallback.ll

@@ -141,7 +141,7 @@ define fp128 @test_quad_dump() {
   ret fp128 0xL00000000000000004000000000000000
 }
 
-; FALLBACK-WITH-REPORT-ERR: remark: <unknown>:0:0: unable to legalize instruction: %0:_(p0) = G_EXTRACT_VECTOR_ELT %1:_(<2 x p0>), %2:_(s32) (in function: vector_of_pointers_extractelement)
+; FALLBACK-WITH-REPORT-ERR: remark: <unknown>:0:0: unable to legalize instruction: %2:_(p0) = G_EXTRACT_VECTOR_ELT %0:_(<2 x p0>), %3:_(s32) (in function: vector_of_pointers_extractelement)
 ; FALLBACK-WITH-REPORT-ERR: warning: Instruction selection used fallback path for vector_of_pointers_extractelement
 ; FALLBACK-WITH-REPORT-OUT-LABEL: vector_of_pointers_extractelement:
 @var = global <2 x i16*> zeroinitializer
@@ -158,7 +158,7 @@ end:
   br label %block
 }
 
-; FALLBACK-WITH-REPORT-ERR: remark: <unknown>:0:0: unable to legalize instruction: G_STORE %0:_(<2 x p0>), %5:_(p0) :: (store 16 into `<2 x i16*>* undef`) (in function: vector_of_pointers_insertelement)
+; FALLBACK-WITH-REPORT-ERR: remark: <unknown>:0:0: unable to legalize instruction: G_STORE %2:_(<2 x p0>), %1:_(p0) :: (store 16 into `<2 x i16*>* undef`) (in function: vector_of_pointers_insertelement)
 ; FALLBACK-WITH-REPORT-ERR: warning: Instruction selection used fallback path for vector_of_pointers_insertelement
 ; FALLBACK-WITH-REPORT-OUT-LABEL: vector_of_pointers_insertelement:
 define void @vector_of_pointers_insertelement() {

test/CodeGen/AArch64/GlobalISel/arm64-irtranslator.ll

@@ -138,9 +138,9 @@ false:
 ; CHECK: %0:_(s32) = COPY $w0
 ; CHECK: %[[reg100:[0-9]+]]:_(s32) = G_CONSTANT i32 100
 ; CHECK: %[[reg200:[0-9]+]]:_(s32) = G_CONSTANT i32 200
-; CHECK: %[[reg0:[0-9]+]]:_(s32) = G_CONSTANT i32 0
-; CHECK: %[[reg1:[0-9]+]]:_(s32) = G_CONSTANT i32 1
 ; CHECK: %[[reg2:[0-9]+]]:_(s32) = G_CONSTANT i32 2
+; CHECK: %[[reg1:[0-9]+]]:_(s32) = G_CONSTANT i32 1
+; CHECK: %[[reg0:[0-9]+]]:_(s32) = G_CONSTANT i32 0
 ; CHECK: %[[regicmp100:[0-9]+]]:_(s1) = G_ICMP intpred(eq), %[[reg100]](s32), %0
 ; CHECK: G_BRCOND %[[regicmp100]](s1), %[[BB_CASE100]]
 ; CHECK: G_BR %[[BB_NOTCASE100_CHECKNEXT]]
@@ -413,9 +413,9 @@ define i64* @trivial_bitcast(i8* %a) {
 ; CHECK:     G_BR %[[CAST:bb\.[0-9]+]]
 
 ; CHECK: [[END:bb\.[0-9]+]].{{[a-zA-Z0-9.]+}}:
+; CHECK:     $x0 = COPY [[A]]
 
 ; CHECK: [[CAST]].{{[a-zA-Z0-9.]+}}:
-; CHECK:     {{%[0-9]+}}:_(p0) = COPY [[A]]
 ; CHECK:     G_BR %[[END]]
 define i64* @trivial_bitcast_with_copy(i8* %a) {
   br label %cast

test/CodeGen/AArch64/GlobalISel/irtranslator-block-order.ll

@@ -0,0 +1,19 @@
+; RUN: llc -O0 -o - %s | FileCheck %s
+target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
+target triple = "aarch64-unknown-linux-gnu"
+
+; CHECK-LABEL: testfn
+; CHECK: ret
+define void @testfn() {
+start:
+  br label %bb2
+
+bb1:
+  store i8 %0, i8* undef, align 4
+  ret void
+
+bb2:
+  %0 = extractvalue { i32, i8 } undef, 1
+  br label %bb1
+}
+