3 files changed, 167 insertions, 5 deletions
diff --git a/llvm/lib/Transforms/InstCombine/InstCombineLoadStoreAlloca.cpp b/llvm/lib/Transforms/InstCombine/InstCombineLoadStoreAlloca.cpp
index 5aa59c69f39..e7a45330d95 100644
--- a/llvm/lib/Transforms/InstCombine/InstCombineLoadStoreAlloca.cpp
+++ b/llvm/lib/Transforms/InstCombine/InstCombineLoadStoreAlloca.cpp
@@ -483,12 +483,17 @@ static Instruction *combineLoadToOperationType(InstCombiner &IC, LoadInst &LI) {
   }
 
   // Fold away bit casts of the loaded value by loading the desired type.
+  // We can do this for BitCastInsts as well as casts from and to pointer types,
+  // as long as those are noops (i.e., the source or dest type have the same
+  // bitwidth as the target's pointers).
   if (LI.hasOneUse())
-    if (auto *BC = dyn_cast<BitCastInst>(LI.user_back())) {
-      LoadInst *NewLoad = combineLoadToNewType(IC, LI, BC->getDestTy());
-      BC->replaceAllUsesWith(NewLoad);
-      IC.EraseInstFromFunction(*BC);
-      return &LI;
+    if (auto* CI = dyn_cast<CastInst>(LI.user_back())) {
+      if (CI->isNoopCast(DL)) {
+        LoadInst *NewLoad = combineLoadToNewType(IC, LI, CI->getDestTy());
+        CI->replaceAllUsesWith(NewLoad);
+        IC.EraseInstFromFunction(*CI);
+        return &LI;
+      }
     }
 
   // FIXME: We should also canonicalize loads of vectors when their elements are
diff --git a/llvm/test/Transforms/InstCombine/load-bitcast32.ll b/llvm/test/Transforms/InstCombine/load-bitcast32.ll
new file mode 100644
index 00000000000..b1c78a8a314
--- /dev/null
+++ b/llvm/test/Transforms/InstCombine/load-bitcast32.ll
@@ -0,0 +1,79 @@
+; RUN: opt -instcombine -S < %s | FileCheck %s
+
+target datalayout = "p:32:32:32"
+
+
+define i64* @test1(i8* %x) {
+entry:
+; CHECK-LABEL: @test1(
+; CHECK: load i64, i64*
+; CHECK: ret
+  %a = bitcast i8* %x to i64*
+  %b = load i64, i64* %a
+  %c = inttoptr i64 %b to i64*
+
+  ret i64* %c
+}
+
+define i32* @test2(i8* %x) {
+entry:
+; CHECK-LABEL: @test2(
+; CHECK: load i32*, i32**
+; CHECK: ret
+  %a = bitcast i8* %x to i32*
+  %b = load i32, i32* %a
+  %c = inttoptr i32 %b to i32*
+
+  ret i32* %c
+}
+
+define i64* @test3(i8* %x) {
+entry:
+; CHECK-LABEL: @test3(
+; CHECK: load i64*, i64**
+; CHECK: ret
+  %a = bitcast i8* %x to i32*
+  %b = load i32, i32* %a
+  %c = inttoptr i32 %b to i64*
+
+  ret i64* %c
+}
+
+define i64 @test4(i8* %x) {
+entry:
+; CHECK-LABEL: @test4(
+; CHECK: load i32, i32*
+; CHECK: zext
+; CHECK: ret
+  %a = bitcast i8* %x to i64**
+  %b = load i64*, i64** %a
+  %c = ptrtoint i64* %b to i64
+
+  ret i64 %c
+}
+
+define i32 @test5(i8* %x) {
+entry:
+; CHECK-LABEL: @test5(
+; CHECK: load i32, i32*
+; CHECK: ret
+  %a = bitcast i8* %x to i32**
+  %b = load i32*, i32** %a
+  %c = ptrtoint i32* %b to i32
+
+  ret i32 %c
+}
+
+define i64 @test6(i8* %x) {
+entry:
+; CHECK-LABEL: @test6(
+; CHECK: load i32, i32*
+; CHECK: zext
+; CHECK: ret
+  %a = bitcast i8* %x to i32**
+  %b = load i32*, i32** %a
+  %c = ptrtoint i32* %b to i64
+
+  ret i64 %c
+}
+
diff --git a/llvm/test/Transforms/InstCombine/load-bitcast64.ll b/llvm/test/Transforms/InstCombine/load-bitcast64.ll
new file mode 100644
index 00000000000..d14c686d83e
--- /dev/null
+++ b/llvm/test/Transforms/InstCombine/load-bitcast64.ll
@@ -0,0 +1,78 @@
+; RUN: opt -instcombine -S < %s | FileCheck %s
+
+target datalayout = "p:64:64:64"
+
+
+define i64* @test1(i8* %x) {
+entry:
+; CHECK-LABEL: @test1(
+; CHECK: load i64*, i64**
+; CHECK: ret
+  %a = bitcast i8* %x to i64*
+  %b = load i64, i64* %a
+  %c = inttoptr i64 %b to i64*
+
+  ret i64* %c
+}
+
+define i32* @test2(i8* %x) {
+entry:
+; CHECK-LABEL: @test2(
+; CHECK: load i32, i32*
+; CHECK: ret
+  %a = bitcast i8* %x to i32*
+  %b = load i32, i32* %a
+  %c = inttoptr i32 %b to i32*
+
+  ret i32* %c
+}
+
+define i64* @test3(i8* %x) {
+entry:
+; CHECK-LABEL: @test3(
+; CHECK: load i32, i32*
+; CHECK: ret
+  %a = bitcast i8* %x to i32*
+  %b = load i32, i32* %a
+  %c = inttoptr i32 %b to i64*
+
+  ret i64* %c
+}
+
+define i64 @test4(i8* %x) {
+entry:
+; CHECK-LABEL: @test4(
+; CHECK: load i64, i64*
+; CHECK: ret
+  %a = bitcast i8* %x to i64**
+  %b = load i64*, i64** %a
+  %c = ptrtoint i64* %b to i64
+
+  ret i64 %c
+}
+
+define i32 @test5(i8* %x) {
+entry:
+; CHECK-LABEL: @test5(
+; CHECK: load i64, i64*
+; CHECK: trunc
+; CHECK: ret
+  %a = bitcast i8* %x to i32**
+  %b = load i32*, i32** %a
+  %c = ptrtoint i32* %b to i32
+
+  ret i32 %c
+}
+
+define i64 @test6(i8* %x) {
+entry:
+; CHECK-LABEL: @test6(
+; CHECK: load i64, i64*
+; CHECK: ret
+  %a = bitcast i8* %x to i32**
+  %b = load i32*, i32** %a
+  %c = ptrtoint i32* %b to i64
+
+  ret i64 %c
+}
+