[InstCombine] Fix bug in pointer replacement

[jprice]

Summary

This optimisation was crashing when there was a chain of more than one bitcast instruction to replace, as a result of the changes in D27283.

[yaxunl]

LGTM. Thanks!

[jprice]

Thanks for the speedy review!

I don't have commit access, so could someone please commit this on my behalf?

[yaxunl]

I will help you commit this patch. Thanks for the quick fix.

lib/Transforms/InstCombine/InstCombineLoadStoreAlloca.cpp

void PointerReplacer::replace(Instruction *I) {
   } else if (auto *BC = dyn_cast<BitCastInst>(I)) {
     auto *V = getReplacement(BC->getOperand(0));
     assert(V && "Operand not replaced");
     auto *NewT = PointerType::get(BC->getType()->getPointerElementType(),
                                   V->getType()->getPointerAddressSpace());
     auto *NewI = new BitCastInst(V, NewT);
     IC.InsertNewInstWith(NewI, *BC);
     NewI->takeName(BC);
-    WorkMap[GEP] = NewI;
+    WorkMap[BC] = NewI;
   } else {
     llvm_unreachable("should never reach here");
   }
 }
 
 void PointerReplacer::replacePointer(Instruction &I, Value *V) {
 #ifndef NDEBUG
   auto *PT = cast<PointerType>(I.getType());

test/Transforms/InstCombine/memcpy-addrspace.ll

entry:
   call void @llvm.memcpy.p0i8.p2i8.i64(i8* %0, i8 addrspace(2)* bitcast ([8 x i32] addrspace(2)* @test.data to i8 addrspace(2)*), i64 32, i32 4, i1 false)
   %arrayidx = getelementptr inbounds [8 x i32], [8 x i32]* %data, i64 0, i64 %x
   %1 = load i32, i32* %arrayidx, align 4
   %arrayidx1 = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 %x
   store i32 %1, i32 addrspace(1)* %arrayidx1, align 4
   ret void
 }
 
+; CHECK-LABEL: test_load_bitcast_chain
+; CHECK: %[[GEP:.*]] = getelementptr [8 x i32], [8 x i32] addrspace(2)* @test.data, i64 0, i64 %x
+; CHECK: %{{.*}} = load i32, i32 addrspace(2)* %[[GEP]]
+; CHECK-NOT: alloca
+; CHECK-NOT: call void @llvm.memcpy.p0i8.p2i8.i64
+; CHECK-NOT: addrspacecast
+; CHECK-NOT: load i32, i32*
+define void @test_load_bitcast_chain(i32 addrspace(1)* %out, i64 %x) {
+entry:
+  %data = alloca [8 x i32], align 4
+  %0 = bitcast [8 x i32]* %data to i8*
+  call void @llvm.memcpy.p0i8.p2i8.i64(i8* %0, i8 addrspace(2)* bitcast ([8 x i32] addrspace(2)* @test.data to i8 addrspace(2)*), i64 32, i32 4, i1 false)
+  %1 = bitcast i8* %0 to i32*
+  %arrayidx = getelementptr inbounds i32, i32* %1, i64 %x
+  %2 = load i32, i32* %arrayidx, align 4
+  %arrayidx1 = getelementptr inbounds i32, i32 addrspace(1)* %out, i64 %x
+  store i32 %2, i32 addrspace(1)* %arrayidx1, align 4
+  ret void
+}
+
 ; CHECK-LABEL: test_call
 ; CHECK: alloca
 ; CHECK: call void @llvm.memcpy.p0i8.p2i8.i64
 ; CHECK-NOT: addrspacecast
 ; CHECK: call i32 @foo(i32* %{{.*}})
 define void @test_call(i32 addrspace(1)* %out, i64 %x) {
 entry:
   %data = alloca [8 x i32], align 4