diff --git a/llvm/lib/Transforms/InstCombine/InstCombineLoadStoreAlloca.cpp b/llvm/lib/Transforms/InstCombine/InstCombineLoadStoreAlloca.cpp
--- a/llvm/lib/Transforms/InstCombine/InstCombineLoadStoreAlloca.cpp
+++ b/llvm/lib/Transforms/InstCombine/InstCombineLoadStoreAlloca.cpp
@@ -18,6 +18,7 @@
 #include "llvm/Analysis/Loads.h"
 #include "llvm/IR/DataLayout.h"
 #include "llvm/IR/DebugInfoMetadata.h"
+#include "llvm/IR/Instructions.h"
 #include "llvm/IR/IntrinsicInst.h"
 #include "llvm/IR/LLVMContext.h"
 #include "llvm/IR/PatternMatch.h"
@@ -1601,6 +1602,21 @@
   if (!OtherBr || BBI == OtherBB->begin())
     return false;
 
+  auto OtherStoreIsMergeable = [&](StoreInst *OtherStore) -> StoreInst * {
+    if (!OtherStore ||
+        OtherStore->getPointerOperand() != SI.getPointerOperand())
+      return nullptr;
+    if (SI.isSameOperationAs(OtherStore))
+      return OtherStore;
+
+    auto *SIVTy = SI.getValueOperand()->getType();
+    auto *OSVTy = OtherStore->getValueOperand()->getType();
+    if (!CastInst::isBitOrNoopPointerCastable(OSVTy, SIVTy, DL) ||
+        !SI.hasSameSpecialState(OtherStore))
+      return nullptr;
+    return OtherStore;
+  };
+
   // If the other block ends in an unconditional branch, check for the 'if then
   // else' case. There is an instruction before the branch.
   StoreInst *OtherStore = nullptr;
@@ -1615,10 +1631,11 @@
     }
     // If this isn't a store, isn't a store to the same location, or is not the
     // right kind of store, bail out.
-    OtherStore = dyn_cast<StoreInst>(BBI);
-    if (!OtherStore || OtherStore->getOperand(1) != SI.getOperand(1) ||
-        !SI.isSameOperationAs(OtherStore))
-      return false;
+    if (auto *S = dyn_cast<StoreInst>(BBI)) {
+      OtherStore = OtherStoreIsMergeable(S);
+      if (!OtherStore)
+        return false;
+    }
   } else {
     // Otherwise, the other block ended with a conditional branch. If one of the
     // destinations is StoreBB, then we have the if/then case.
@@ -1631,12 +1648,12 @@
     // lives in OtherBB.
     for (;; --BBI) {
       // Check to see if we find the matching store.
-      if ((OtherStore = dyn_cast<StoreInst>(BBI))) {
-        if (OtherStore->getOperand(1) != SI.getOperand(1) ||
-            !SI.isSameOperationAs(OtherStore))
+      if (auto *S = dyn_cast<StoreInst>(BBI)) {
+        OtherStore = OtherStoreIsMergeable(S);
+        if (!OtherStore)
           return false;
-        break;
       }
+
       // If we find something that may be using or overwriting the stored
       // value, or if we run out of instructions, we can't do the transform.
       if (BBI->mayReadFromMemory() || BBI->mayThrow() ||
@@ -1654,14 +1671,17 @@
   }
 
   // Insert a PHI node now if we need it.
-  Value *MergedVal = OtherStore->getOperand(0);
+  Value *MergedVal = OtherStore->getValueOperand();
   // The debug locations of the original instructions might differ. Merge them.
   DebugLoc MergedLoc = DILocation::getMergedLocation(SI.getDebugLoc(),
                                                      OtherStore->getDebugLoc());
-  if (MergedVal != SI.getOperand(0)) {
-    PHINode *PN = PHINode::Create(MergedVal->getType(), 2, "storemerge");
-    PN->addIncoming(SI.getOperand(0), SI.getParent());
-    PN->addIncoming(OtherStore->getOperand(0), OtherBB);
+  if (MergedVal != SI.getValueOperand()) {
+    PHINode *PN =
+        PHINode::Create(SI.getValueOperand()->getType(), 2, "storemerge");
+    PN->addIncoming(SI.getValueOperand(), SI.getParent());
+    Builder.SetInsertPoint(OtherStore);
+    PN->addIncoming(Builder.CreateBitOrPointerCast(MergedVal, PN->getType()),
+                    OtherBB);
     MergedVal = InsertNewInstBefore(PN, DestBB->front());
     PN->setDebugLoc(MergedLoc);
   }
diff --git a/llvm/test/Transforms/InstCombine/AMDGPU/merging-stores-into-successor.ll b/llvm/test/Transforms/InstCombine/AMDGPU/merging-stores-into-successor.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/Transforms/InstCombine/AMDGPU/merging-stores-into-successor.ll
@@ -0,0 +1,33 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 2
+; RUN: opt -S -passes=instcombine -o - %s | FileCheck %s
+
+target datalayout = "e-p:64:64-p1:64:64-p2:32:32-p3:32:32-p4:64:64-p5:32:32-p6:32:32-p7:160:256:256:32-p8:128:128-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128-v192:256-v256:256-v512:512-v1024:1024-v2048:2048-n32:64-S32-A5"
+target triple = "amdgcn-amd-amdhsa"
+
+define ptr @inttoptr_merge(i1 %cond, i64 %a, ptr %b) {
+; CHECK-LABEL: define ptr @inttoptr_merge
+; CHECK-SAME: (i1 [[COND:%.*]], i64 [[A:%.*]], ptr [[B:%.*]]) {
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    br i1 [[COND]], label [[BB0:%.*]], label [[BB1:%.*]]
+; CHECK:       BB0:
+; CHECK-NEXT:    [[TMP0:%.*]] = inttoptr i64 [[A]] to ptr
+; CHECK-NEXT:    br label [[SINK:%.*]]
+; CHECK:       BB1:
+; CHECK-NEXT:    br label [[SINK]]
+; CHECK:       sink:
+; CHECK-NEXT:    [[STOREMERGE:%.*]] = phi ptr [ [[B]], [[BB1]] ], [ [[TMP0]], [[BB0]] ]
+; CHECK-NEXT:    ret ptr [[STOREMERGE]]
+;
+entry:
+  %alloca = alloca ptr
+  br i1 %cond, label %BB0, label %BB1
+BB0:
+  store i64 %a, ptr %alloca
+  br label %sink
+BB1:
+  store ptr %b, ptr %alloca
+  br label %sink
+sink:
+  %val = load ptr, ptr %alloca
+  ret ptr %val
+}
diff --git a/llvm/test/Transforms/InstCombine/merging-multiple-stores-into-successor.ll b/llvm/test/Transforms/InstCombine/merging-multiple-stores-into-successor.ll
--- a/llvm/test/Transforms/InstCombine/merging-multiple-stores-into-successor.ll
+++ b/llvm/test/Transforms/InstCombine/merging-multiple-stores-into-successor.ll
@@ -71,3 +71,205 @@
 bb12:                                             ; preds = %bb10, %bb9
   ret void
 }
+
+define half @diff_types_same_width_merge(i1 %cond, half %a, i16 %b) {
+; CHECK-LABEL: @diff_types_same_width_merge(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    br i1 [[COND:%.*]], label [[BB0:%.*]], label [[BB1:%.*]]
+; CHECK:       BB0:
+; CHECK-NEXT:    br label [[SINK:%.*]]
+; CHECK:       BB1:
+; CHECK-NEXT:    [[TMP0:%.*]] = bitcast i16 [[B:%.*]] to half
+; CHECK-NEXT:    br label [[SINK]]
+; CHECK:       sink:
+; CHECK-NEXT:    [[STOREMERGE:%.*]] = phi half [ [[TMP0]], [[BB1]] ], [ [[A:%.*]], [[BB0]] ]
+; CHECK-NEXT:    ret half [[STOREMERGE]]
+;
+entry:
+  %alloca = alloca half
+  br i1 %cond, label %BB0, label %BB1
+BB0:
+  store half %a, ptr %alloca
+  br label %sink
+BB1:
+  store i16 %b, ptr %alloca
+  br label %sink
+sink:
+  %val = load half, ptr %alloca
+  ret half %val
+}
+
+define i32 @diff_types_diff_width_no_merge(i1 %cond, i32 %a, i64 %b) {
+; CHECK-LABEL: @diff_types_diff_width_no_merge(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[ALLOCA:%.*]] = alloca i64, align 8
+; CHECK-NEXT:    br i1 [[COND:%.*]], label [[A:%.*]], label [[B:%.*]]
+; CHECK:       A:
+; CHECK-NEXT:    store i32 [[A:%.*]], ptr [[ALLOCA]], align 8
+; CHECK-NEXT:    br label [[SINK:%.*]]
+; CHECK:       B:
+; CHECK-NEXT:    store i64 [[B:%.*]], ptr [[ALLOCA]], align 8
+; CHECK-NEXT:    br label [[SINK]]
+; CHECK:       sink:
+; CHECK-NEXT:    [[VAL:%.*]] = load i32, ptr [[ALLOCA]], align 8
+; CHECK-NEXT:    ret i32 [[VAL]]
+;
+entry:
+  %alloca = alloca i64
+  br i1 %cond, label %A, label %B
+A:
+  store i32 %a, ptr %alloca
+  br label %sink
+B:
+  store i64 %b, ptr %alloca
+  br label %sink
+sink:
+  %val = load i32, ptr %alloca
+  ret i32 %val
+}
+
+define <4 x i32> @vec_no_merge(i1 %cond, <2 x i32> %a, <4 x i32> %b) {
+; CHECK-LABEL: @vec_no_merge(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[ALLOCA:%.*]] = alloca i64, align 16
+; CHECK-NEXT:    br i1 [[COND:%.*]], label [[A:%.*]], label [[B:%.*]]
+; CHECK:       A:
+; CHECK-NEXT:    store <2 x i32> [[A:%.*]], ptr [[ALLOCA]], align 16
+; CHECK-NEXT:    br label [[SINK:%.*]]
+; CHECK:       B:
+; CHECK-NEXT:    store <4 x i32> [[B:%.*]], ptr [[ALLOCA]], align 16
+; CHECK-NEXT:    br label [[SINK]]
+; CHECK:       sink:
+; CHECK-NEXT:    [[VAL:%.*]] = load <4 x i32>, ptr [[ALLOCA]], align 16
+; CHECK-NEXT:    ret <4 x i32> [[VAL]]
+;
+entry:
+  %alloca = alloca i64
+  br i1 %cond, label %A, label %B
+A:
+  store <2 x i32> %a, ptr %alloca
+  br label %sink
+B:
+  store <4 x i32> %b, ptr %alloca
+  br label %sink
+sink:
+  %val = load <4 x i32>, ptr %alloca
+  ret <4 x i32> %val
+}
+
+%struct.half = type { half };
+
+define %struct.half @one_elem_struct_merge(i1 %cond, %struct.half %a, half %b) {
+; CHECK-LABEL: @one_elem_struct_merge(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    br i1 [[COND:%.*]], label [[BB0:%.*]], label [[BB1:%.*]]
+; CHECK:       BB0:
+; CHECK-NEXT:    [[TMP0:%.*]] = extractvalue [[STRUCT_HALF:%.*]] [[A:%.*]], 0
+; CHECK-NEXT:    br label [[SINK:%.*]]
+; CHECK:       BB1:
+; CHECK-NEXT:    br label [[SINK]]
+; CHECK:       sink:
+; CHECK-NEXT:    [[STOREMERGE:%.*]] = phi half [ [[TMP0]], [[BB0]] ], [ [[B:%.*]], [[BB1]] ]
+; CHECK-NEXT:    [[VAL1:%.*]] = insertvalue [[STRUCT_HALF]] poison, half [[STOREMERGE]], 0
+; CHECK-NEXT:    ret [[STRUCT_HALF]] [[VAL1]]
+;
+entry:
+  %alloca = alloca i64
+  br i1 %cond, label %BB0, label %BB1
+BB0:
+  store %struct.half %a, ptr %alloca
+  br label %sink
+BB1:
+  store half %b, ptr %alloca
+  br label %sink
+sink:
+  %val = load %struct.half, ptr %alloca
+  ret %struct.half %val
+}
+
+%struct.tup = type { half, i32 };
+
+define %struct.tup @multi_elem_struct_no_merge(i1 %cond, %struct.tup %a, half %b) {
+; CHECK-LABEL: @multi_elem_struct_no_merge(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[ALLOCA:%.*]] = alloca i64, align 8
+; CHECK-NEXT:    br i1 [[COND:%.*]], label [[A:%.*]], label [[B:%.*]]
+; CHECK:       A:
+; CHECK-NEXT:    store [[STRUCT_TUP:%.*]] [[A:%.*]], ptr [[ALLOCA]], align 8
+; CHECK-NEXT:    br label [[SINK:%.*]]
+; CHECK:       B:
+; CHECK-NEXT:    store half [[B:%.*]], ptr [[ALLOCA]], align 8
+; CHECK-NEXT:    br label [[SINK]]
+; CHECK:       sink:
+; CHECK-NEXT:    [[VAL:%.*]] = load [[STRUCT_TUP]], ptr [[ALLOCA]], align 8
+; CHECK-NEXT:    ret [[STRUCT_TUP]] [[VAL]]
+;
+entry:
+  %alloca = alloca i64
+  br i1 %cond, label %A, label %B
+A:
+  store %struct.tup %a, ptr %alloca
+  br label %sink
+B:
+  store half %b, ptr %alloca
+  br label %sink
+sink:
+  %val = load %struct.tup, ptr %alloca
+  ret %struct.tup %val
+}
+
+define i16 @same_types_diff_align_no_merge(i1 %cond, i16 %a, i16 %b) {
+; CHECK-LABEL: @same_types_diff_align_no_merge(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[ALLOCA:%.*]] = alloca i16, align 4
+; CHECK-NEXT:    br i1 [[COND:%.*]], label [[BB0:%.*]], label [[BB1:%.*]]
+; CHECK:       BB0:
+; CHECK-NEXT:    store i16 [[A:%.*]], ptr [[ALLOCA]], align 8
+; CHECK-NEXT:    br label [[SINK:%.*]]
+; CHECK:       BB1:
+; CHECK-NEXT:    store i16 [[B:%.*]], ptr [[ALLOCA]], align 4
+; CHECK-NEXT:    br label [[SINK]]
+; CHECK:       sink:
+; CHECK-NEXT:    [[VAL:%.*]] = load i16, ptr [[ALLOCA]], align 4
+; CHECK-NEXT:    ret i16 [[VAL]]
+;
+entry:
+  %alloca = alloca i16, align 4
+  br i1 %cond, label %BB0, label %BB1
+BB0:
+  store i16 %a, ptr %alloca, align 8
+  br label %sink
+BB1:
+  store i16 %b, ptr %alloca, align 4
+  br label %sink
+sink:
+  %val = load i16, ptr %alloca
+  ret i16 %val
+}
+
+define i64 @ptrtoint_merge(i1 %cond, i64 %a, ptr %b) {
+; CHECK-LABEL: @ptrtoint_merge(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    br i1 [[COND:%.*]], label [[BB0:%.*]], label [[BB1:%.*]]
+; CHECK:       BB0:
+; CHECK-NEXT:    br label [[SINK:%.*]]
+; CHECK:       BB1:
+; CHECK-NEXT:    [[TMP0:%.*]] = ptrtoint ptr [[B:%.*]] to i64
+; CHECK-NEXT:    br label [[SINK]]
+; CHECK:       sink:
+; CHECK-NEXT:    [[STOREMERGE:%.*]] = phi i64 [ [[A:%.*]], [[BB0]] ], [ [[TMP0]], [[BB1]] ]
+; CHECK-NEXT:    ret i64 [[STOREMERGE]]
+;
+entry:
+  %alloca = alloca ptr
+  br i1 %cond, label %BB0, label %BB1
+BB0:
+  store i64 %a, ptr %alloca
+  br label %sink
+BB1:
+  store ptr %b, ptr %alloca
+  br label %sink
+sink:
+  %val = load i64, ptr %alloca
+  ret i64 %val
+}
diff --git a/llvm/test/Transforms/InstCombine/store.ll b/llvm/test/Transforms/InstCombine/store.ll
--- a/llvm/test/Transforms/InstCombine/store.ll
+++ b/llvm/test/Transforms/InstCombine/store.ll
@@ -115,12 +115,15 @@
 ; "if then"
 define i32 @test4(i1 %C) {
 ; CHECK-LABEL: @test4(
+; CHECK-NEXT:    [[A:%.*]] = alloca i32, align 4
+; CHECK-NEXT:    store i32 47, ptr [[A]], align 4
 ; CHECK-NEXT:    br i1 [[C:%.*]], label [[COND:%.*]], label [[CONT:%.*]]
 ; CHECK:       Cond:
+; CHECK-NEXT:    store i32 -987654321, ptr [[A]], align 4
 ; CHECK-NEXT:    br label [[CONT]]
 ; CHECK:       Cont:
-; CHECK-NEXT:    [[STOREMERGE:%.*]] = phi i32 [ -987654321, [[COND]] ], [ 47, [[TMP0:%.*]] ]
-; CHECK-NEXT:    ret i32 [[STOREMERGE]]
+; CHECK-NEXT:    [[V:%.*]] = load i32, ptr [[A]], align 4
+; CHECK-NEXT:    ret i32 [[V]]
 ;
   %A = alloca i32
   store i32 47, ptr %A
@@ -138,12 +141,12 @@
 ; "if then"
 define void @test5(i1 %C, ptr %P) {
 ; CHECK-LABEL: @test5(
+; CHECK-NEXT:    store i32 47, ptr [[P:%.*]], align 1
 ; CHECK-NEXT:    br i1 [[C:%.*]], label [[COND:%.*]], label [[CONT:%.*]]
 ; CHECK:       Cond:
+; CHECK-NEXT:    store i32 -987654321, ptr [[P]], align 1
 ; CHECK-NEXT:    br label [[CONT]]
 ; CHECK:       Cont:
-; CHECK-NEXT:    [[STOREMERGE:%.*]] = phi i32 [ -987654321, [[COND]] ], [ 47, [[TMP0:%.*]] ]
-; CHECK-NEXT:    store i32 [[STOREMERGE]], ptr [[P:%.*]], align 1
 ; CHECK-NEXT:    ret void
 ;
   store i32 47, ptr %P, align 1
diff --git a/llvm/test/Transforms/LoopVectorize/invariant-store-vectorization.ll b/llvm/test/Transforms/LoopVectorize/invariant-store-vectorization.ll
--- a/llvm/test/Transforms/LoopVectorize/invariant-store-vectorization.ll
+++ b/llvm/test/Transforms/LoopVectorize/invariant-store-vectorization.ll
@@ -499,14 +499,15 @@
 ; CHECK-NEXT:    [[ARRAYIDX:%.*]] = getelementptr inbounds i32, ptr [[VAR2:%.*]], i64 [[INDVARS_IV]]
 ; CHECK-NEXT:    [[TMP2:%.*]] = load i32, ptr [[ARRAYIDX]], align 4
 ; CHECK-NEXT:    [[ADD:%.*]] = add nsw i32 [[TMP1]], [[TMP2]]
+; CHECK-NEXT:    store i32 [[ADD]], ptr [[ARRAYIDX5]], align 4
 ; CHECK-NEXT:    [[TMP3:%.*]] = icmp ugt i32 [[ADD]], 42
 ; CHECK-NEXT:    br i1 [[TMP3]], label [[COND_STORE:%.*]], label [[LATCH]]
 ; CHECK:       cond_store:
 ; CHECK-NEXT:    [[TMP4:%.*]] = add nsw i32 [[ADD]], 1
+; CHECK-NEXT:    store i32 [[TMP4]], ptr [[ARRAYIDX5]], align 4
 ; CHECK-NEXT:    br label [[LATCH]]
 ; CHECK:       latch:
 ; CHECK-NEXT:    [[TMP5]] = phi i32 [ [[TMP4]], [[COND_STORE]] ], [ [[ADD]], [[FOR_BODY3]] ]
-; CHECK-NEXT:    store i32 [[TMP5]], ptr [[ARRAYIDX5]], align 4
 ; CHECK-NEXT:    [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1
 ; CHECK-NEXT:    [[LFTR_WIDEIV:%.*]] = trunc i64 [[INDVARS_IV_NEXT]] to i32
 ; CHECK-NEXT:    [[EXITCOND:%.*]] = icmp eq i32 [[LFTR_WIDEIV]], [[ITR]]