diff --git a/llvm/lib/Analysis/ValueTracking.cpp b/llvm/lib/Analysis/ValueTracking.cpp
--- a/llvm/lib/Analysis/ValueTracking.cpp
+++ b/llvm/lib/Analysis/ValueTracking.cpp
@@ -4187,16 +4187,12 @@
   // Look through bitcast instructions and geps.
   V = V->stripPointerCasts();
 
-  // If the value is a GEP instruction or constant expression, treat it as an
-  // offset.
   if (const GEPOperator *GEP = dyn_cast<GEPOperator>(V)) {
-    // Fail if the first GEP operand is not a constant zero and we're
-    // not indexing into the initializer.
-    const ConstantInt *FirstIdx = dyn_cast<ConstantInt>(GEP->getOperand(1));
-    if (!FirstIdx || !FirstIdx->isZero())
-      return false;
-
+    // Drill down into the first operand, ignoring any intervening casts,
+    // and determine the identity of the referenced object along with
+    // the byte offset into it.
     Value *Op0 = GEP->getOperand(0);
+    Op0 = Op0->stripPointerCasts();
     const GlobalVariable *GV = dyn_cast<GlobalVariable>(Op0);
     if (!GV)
       return false;
@@ -4288,7 +4284,7 @@
     return false;
 
   if (Slice.Array == nullptr) {
-    if (TrimAtNul) {
+    if (Slice.Length && TrimAtNul) {
       Str = StringRef();
       return true;
     }
diff --git a/llvm/test/Transforms/InstCombine/memchr-9.ll b/llvm/test/Transforms/InstCombine/memchr-9.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/Transforms/InstCombine/memchr-9.ll
@@ -0,0 +1,273 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; Verify that calls to memchr with arrays of elements larger than char
+; are folded correctly.
+; RUN: opt < %s -passes=instcombine -S -data-layout="E" | FileCheck %s
+; RUN: opt < %s -passes=instcombine -S -data-layout="e" | FileCheck %s
+;
+; Exercise folding of memchr calls with addition expressions involving
+; pointers into constant arrays of types larger than char and fractional
+; offsets.
+
+declare i8* @memchr(i8*, i32, i64)
+
+%struct.A = type { [2 x i16], [2 x i16] }
+
+; Hex byte representation: 00 00  01 01  02 02  03 03
+@a = constant [1 x %struct.A] [%struct.A { [2 x i16] [i16 0, i16 257], [2 x i16] [i16 514, i16 771] }]
+
+
+define void @fold_memchr_A_pIb_cst_cst(i8** %pchr) {
+; CHECK-LABEL: @fold_memchr_A_pIb_cst_cst(
+; CHECK-NEXT:    store i8* bitcast ([1 x %struct.A]* @a to i8*), i8** [[PCHR:%.*]], align 8
+; CHECK-NEXT:    [[PST_0_1_1:%.*]] = getelementptr i8*, i8** [[PCHR]], i64 1
+; CHECK-NEXT:    store i8* null, i8** [[PST_0_1_1]], align 8
+; CHECK-NEXT:    [[PST_0_4_4:%.*]] = getelementptr i8*, i8** [[PCHR]], i64 2
+; CHECK-NEXT:    store i8* null, i8** [[PST_0_4_4]], align 8
+; CHECK-NEXT:    [[PST_1_0_1:%.*]] = getelementptr i8*, i8** [[PCHR]], i64 3
+; CHECK-NEXT:    store i8* getelementptr (i8, i8* bitcast ([1 x %struct.A]* @a to i8*), i64 1), i8** [[PST_1_0_1]], align 8
+; CHECK-NEXT:    [[PST_1_0_3:%.*]] = getelementptr i8*, i8** [[PCHR]], i64 4
+; CHECK-NEXT:    store i8* getelementptr (i8, i8* bitcast ([1 x %struct.A]* @a to i8*), i64 1), i8** [[PST_1_0_3]], align 8
+; CHECK-NEXT:    [[PST_1_1_1:%.*]] = getelementptr i8*, i8** [[PCHR]], i64 5
+; CHECK-NEXT:    store i8* null, i8** [[PST_1_1_1]], align 8
+; CHECK-NEXT:    [[PST_1_1_2:%.*]] = getelementptr i8*, i8** [[PCHR]], i64 6
+; CHECK-NEXT:    store i8* bitcast (i16* getelementptr inbounds ([1 x %struct.A], [1 x %struct.A]* @a, i64 0, i64 0, i32 0, i64 1) to i8*), i8** [[PST_1_1_2]], align 8
+; CHECK-NEXT:    [[PST_1_3_3:%.*]] = getelementptr i8*, i8** [[PCHR]], i64 7
+; CHECK-NEXT:    store i8* null, i8** [[PST_1_3_3]], align 8
+; CHECK-NEXT:    [[PST_1_3_4:%.*]] = getelementptr i8*, i8** [[PCHR]], i64 8
+; CHECK-NEXT:    store i8* null, i8** [[PST_1_3_4]], align 8
+; CHECK-NEXT:    [[PST_1_3_6:%.*]] = getelementptr i8*, i8** [[PCHR]], i64 10
+; CHECK-NEXT:    store i8* bitcast (i16* getelementptr inbounds ([1 x %struct.A], [1 x %struct.A]* @a, i64 0, i64 0, i32 1, i64 1) to i8*), i8** [[PST_1_3_6]], align 8
+; CHECK-NEXT:    ret void
+;
+  %pa = getelementptr [1 x %struct.A], [1 x %struct.A]* @a, i64 0, i64 0
+  %pi8a = bitcast %struct.A* %pa to i8*
+
+  %pi8ap0 = getelementptr i8, i8* %pi8a, i32 0
+
+  ; Fold memchr((char*)a + 0, '\0', 1) to a.
+  %pst_0_0_1 = getelementptr i8*, i8** %pchr, i32 0
+  %chr_0_0_1 = call i8* @memchr(i8* %pi8ap0, i32 0, i64 1)
+  store i8* %chr_0_0_1, i8** %pst_0_0_1
+
+  ; Fold memchr((char*)a + 0, '\01', 1) to null.
+  %pst_0_1_1 = getelementptr i8*, i8** %pchr, i32 1
+  %chr_0_1_1 = call i8* @memchr(i8* %pi8ap0, i32 1, i64 1)
+  store i8* %chr_0_1_1, i8** %pst_0_1_1
+
+  ; Fold memchr((char*)a + 0, '\04', 4) to null.
+  %pst_0_4_4 = getelementptr i8*, i8** %pchr, i32 2
+  %chr_0_4_4 = call i8* @memchr(i8* %pi8ap0, i32 4, i64 4)
+  store i8* %chr_0_4_4, i8** %pst_0_4_4
+
+
+  %pi8ap1 = getelementptr i8, i8* %pi8a, i32 1
+
+  ; Fold memchr((char*)a + 1, '\0', 1) to (char*)a + 1.
+  %pst_1_0_1 = getelementptr i8*, i8** %pchr, i32 3
+  %chr_1_0_1 = call i8* @memchr(i8* %pi8ap1, i32 0, i64 1)
+  store i8* %chr_1_0_1, i8** %pst_1_0_1
+
+  ; Fold memchr((char*)a + 1, '\0', 3) to (char*)a + 1.
+  %pst_1_0_3 = getelementptr i8*, i8** %pchr, i32 4
+  %chr_1_0_3 = call i8* @memchr(i8* %pi8ap1, i32 0, i64 3)
+  store i8* %chr_1_0_3, i8** %pst_1_0_3
+
+  ; Fold memchr((char*)a + 1, '\01', 1) to null.
+  %pst_1_1_1 = getelementptr i8*, i8** %pchr, i32 5
+  %chr_1_1_1 = call i8* @memchr(i8* %pi8ap1, i32 1, i64 1)
+  store i8* %chr_1_1_1, i8** %pst_1_1_1
+
+  ; Fold memchr((char*)a + 1, '\01', 2) to (char*)a + 2.
+  %pst_1_1_2 = getelementptr i8*, i8** %pchr, i32 6
+  %chr_1_1_2 = call i8* @memchr(i8* %pi8ap1, i32 1, i64 2)
+  store i8* %chr_1_1_2, i8** %pst_1_1_2
+
+  ; Fold memchr((char*)a + 1, '\03', 3) to null.
+  %pst_1_3_3 = getelementptr i8*, i8** %pchr, i32 7
+  %chr_1_3_3 = call i8* @memchr(i8* %pi8ap1, i32 3, i64 3)
+  store i8* %chr_1_3_3, i8** %pst_1_3_3
+
+  ; Fold memchr((char*)a + 1, '\03', 4) to null.
+  %pst_1_3_4 = getelementptr i8*, i8** %pchr, i32 8
+  %chr_1_3_4 = call i8* @memchr(i8* %pi8ap1, i32 3, i64 4)
+  store i8* %chr_1_3_4, i8** %pst_1_3_4
+
+  ; Fold memchr((char*)a + 1, '\03', 5) to null.
+  %pst_1_3_5 = getelementptr i8*, i8** %pchr, i32 9
+  %chr_1_3_5 = call i8* @memchr(i8* %pi8ap1, i32 3, i64 5)
+  store i8* %chr_1_3_4, i8** %pst_1_3_4
+
+  ; Fold memchr((char*)a + 1, '\03', 6) to (char*)a + 5.
+  %pst_1_3_6 = getelementptr i8*, i8** %pchr, i32 10
+  %chr_1_3_6 = call i8* @memchr(i8* %pi8ap1, i32 3, i64 6)
+  store i8* %chr_1_3_6, i8** %pst_1_3_6
+
+
+  ret void
+}
+
+
+define void @fold_memchr_A_pIb_cst_N(i64 %N, i8** %pchr) {
+; CHECK-LABEL: @fold_memchr_A_pIb_cst_N(
+; CHECK-NEXT:    [[MEMCHR_CMP:%.*]] = icmp eq i64 [[N:%.*]], 0
+; CHECK-NEXT:    [[TMP1:%.*]] = select i1 [[MEMCHR_CMP]], i8* null, i8* bitcast ([1 x %struct.A]* @a to i8*)
+; CHECK-NEXT:    store i8* [[TMP1]], i8** [[PCHR:%.*]], align 8
+; CHECK-NEXT:    [[PST_0_1_N:%.*]] = getelementptr i8*, i8** [[PCHR]], i64 1
+; CHECK-NEXT:    [[MEMCHR_CMP1:%.*]] = icmp ult i64 [[N]], 3
+; CHECK-NEXT:    [[TMP2:%.*]] = select i1 [[MEMCHR_CMP1]], i8* null, i8* bitcast (i16* getelementptr inbounds ([1 x %struct.A], [1 x %struct.A]* @a, i64 0, i64 0, i32 0, i64 1) to i8*)
+; CHECK-NEXT:    store i8* [[TMP2]], i8** [[PST_0_1_N]], align 8
+; CHECK-NEXT:    [[PST_0_4_N:%.*]] = getelementptr i8*, i8** [[PCHR]], i64 2
+; CHECK-NEXT:    store i8* null, i8** [[PST_0_4_N]], align 8
+; CHECK-NEXT:    [[PST_1_0_N:%.*]] = getelementptr i8*, i8** [[PCHR]], i64 3
+; CHECK-NEXT:    [[MEMCHR_CMP2:%.*]] = icmp eq i64 [[N]], 0
+; CHECK-NEXT:    [[TMP3:%.*]] = select i1 [[MEMCHR_CMP2]], i8* null, i8* getelementptr (i8, i8* bitcast ([1 x %struct.A]* @a to i8*), i64 1)
+; CHECK-NEXT:    store i8* [[TMP3]], i8** [[PST_1_0_N]], align 8
+; CHECK-NEXT:    [[PST_1_1_N:%.*]] = getelementptr i8*, i8** [[PCHR]], i64 4
+; CHECK-NEXT:    [[MEMCHR_CMP3:%.*]] = icmp ult i64 [[N]], 2
+; CHECK-NEXT:    [[TMP4:%.*]] = select i1 [[MEMCHR_CMP3]], i8* null, i8* bitcast (i16* getelementptr inbounds ([1 x %struct.A], [1 x %struct.A]* @a, i64 0, i64 0, i32 0, i64 1) to i8*)
+; CHECK-NEXT:    store i8* [[TMP4]], i8** [[PST_1_1_N]], align 8
+; CHECK-NEXT:    [[PST_1_2_N:%.*]] = getelementptr i8*, i8** [[PCHR]], i64 5
+; CHECK-NEXT:    [[MEMCHR_CMP4:%.*]] = icmp ult i64 [[N]], 4
+; CHECK-NEXT:    [[TMP5:%.*]] = select i1 [[MEMCHR_CMP4]], i8* null, i8* bitcast (i16* getelementptr inbounds ([1 x %struct.A], [1 x %struct.A]* @a, i64 0, i64 0, i32 1, i64 0) to i8*)
+; CHECK-NEXT:    store i8* [[TMP5]], i8** [[PST_1_2_N]], align 8
+; CHECK-NEXT:    [[PST_1_3_N:%.*]] = getelementptr i8*, i8** [[PCHR]], i64 6
+; CHECK-NEXT:    [[MEMCHR_CMP5:%.*]] = icmp ult i64 [[N]], 6
+; CHECK-NEXT:    [[TMP6:%.*]] = select i1 [[MEMCHR_CMP5]], i8* null, i8* bitcast (i16* getelementptr inbounds ([1 x %struct.A], [1 x %struct.A]* @a, i64 0, i64 0, i32 1, i64 1) to i8*)
+; CHECK-NEXT:    store i8* [[TMP6]], i8** [[PST_1_3_N]], align 8
+; CHECK-NEXT:    [[PST_1_4_N:%.*]] = getelementptr i8*, i8** [[PCHR]], i64 7
+; CHECK-NEXT:    store i8* null, i8** [[PST_1_4_N]], align 8
+; CHECK-NEXT:    [[PST_2_0_N:%.*]] = getelementptr i8*, i8** [[PCHR]], i64 8
+; CHECK-NEXT:    store i8* null, i8** [[PST_2_0_N]], align 8
+; CHECK-NEXT:    [[PST_2_1_N:%.*]] = getelementptr i8*, i8** [[PCHR]], i64 9
+; CHECK-NEXT:    [[MEMCHR_CMP6:%.*]] = icmp eq i64 [[N]], 0
+; CHECK-NEXT:    [[TMP7:%.*]] = select i1 [[MEMCHR_CMP6]], i8* null, i8* bitcast (i16* getelementptr inbounds ([1 x %struct.A], [1 x %struct.A]* @a, i64 0, i64 0, i32 0, i64 1) to i8*)
+; CHECK-NEXT:    store i8* [[TMP7]], i8** [[PST_2_1_N]], align 8
+; CHECK-NEXT:    [[PST_2_2_N:%.*]] = getelementptr i8*, i8** [[PCHR]], i64 10
+; CHECK-NEXT:    [[MEMCHR_CMP7:%.*]] = icmp ult i64 [[N]], 3
+; CHECK-NEXT:    [[TMP8:%.*]] = select i1 [[MEMCHR_CMP7]], i8* null, i8* bitcast (i16* getelementptr inbounds ([1 x %struct.A], [1 x %struct.A]* @a, i64 0, i64 0, i32 1, i64 0) to i8*)
+; CHECK-NEXT:    store i8* [[TMP8]], i8** [[PST_2_2_N]], align 8
+; CHECK-NEXT:    [[PST_2_3_N:%.*]] = getelementptr i8*, i8** [[PCHR]], i64 11
+; CHECK-NEXT:    [[MEMCHR_CMP8:%.*]] = icmp ult i64 [[N]], 5
+; CHECK-NEXT:    [[TMP9:%.*]] = select i1 [[MEMCHR_CMP8]], i8* null, i8* bitcast (i16* getelementptr inbounds ([1 x %struct.A], [1 x %struct.A]* @a, i64 0, i64 0, i32 1, i64 1) to i8*)
+; CHECK-NEXT:    store i8* [[TMP9]], i8** [[PST_2_3_N]], align 8
+; CHECK-NEXT:    [[PST_2_4_N:%.*]] = getelementptr i8*, i8** [[PCHR]], i64 12
+; CHECK-NEXT:    store i8* null, i8** [[PST_2_4_N]], align 8
+; CHECK-NEXT:    ret void
+;
+  %pa = getelementptr [1 x %struct.A], [1 x %struct.A]* @a, i64 0, i64 0
+  %pi8a = bitcast %struct.A* %pa to i8*
+
+  %pi8ap0 = getelementptr i8, i8* %pi8a, i32 0
+
+  ; Fold memchr((char*)a + 0, '\0', N) to N ? a : null.
+  %pst_0_0_n = getelementptr i8*, i8** %pchr, i32 0
+  %chr_0_0_n = call i8* @memchr(i8* %pi8ap0, i32 0, i64 %N)
+  store i8* %chr_0_0_n, i8** %pst_0_0_n
+
+  ; Fold memchr((char*)a + 0, '\01', N) to N < 2 ? null : a.
+  %pst_0_1_n = getelementptr i8*, i8** %pchr, i32 1
+  %chr_0_1_n = call i8* @memchr(i8* %pi8ap0, i32 1, i64 %N)
+  store i8* %chr_0_1_n, i8** %pst_0_1_n
+
+  ; Fold memchr((char*)a + 0, '\04', N) to null.
+  %pst_0_4_n = getelementptr i8*, i8** %pchr, i32 2
+  %chr_0_4_n = call i8* @memchr(i8* %pi8ap0, i32 4, i64 %N)
+  store i8* %chr_0_4_n, i8** %pst_0_4_n
+
+
+  %pi8ap1 = getelementptr i8, i8* %pi8a, i32 1
+
+  ; Fold memchr((char*)a + 1, '\0', N) to null.
+  %pst_1_0_n = getelementptr i8*, i8** %pchr, i32 3
+  %chr_1_0_n = call i8* @memchr(i8* %pi8ap1, i32 0, i64 %N)
+  store i8* %chr_1_0_n, i8** %pst_1_0_n
+
+  ; Fold memchr((char*)a + 1, '\01', N) N ? (char*)a + 1 : null.
+  %pst_1_1_n = getelementptr i8*, i8** %pchr, i32 4
+  %chr_1_1_n = call i8* @memchr(i8* %pi8ap1, i32 1, i64 %N)
+  store i8* %chr_1_1_n, i8** %pst_1_1_n
+
+  ; Fold memchr((char*)a + 1, '\02', N) to N < 2 ? null : (char*)a + 4.
+  %pst_1_2_n = getelementptr i8*, i8** %pchr, i32 5
+  %chr_1_2_n = call i8* @memchr(i8* %pi8ap1, i32 2, i64 %N)
+  store i8* %chr_1_2_n, i8** %pst_1_2_n
+
+  ; Fold memchr((char*)a + 1, '\03', N) to N < 6 ? null : (char*)a + 6.
+  %pst_1_3_n = getelementptr i8*, i8** %pchr, i32 6
+  %chr_1_3_n = call i8* @memchr(i8* %pi8ap1, i32 3, i64 %N)
+  store i8* %chr_1_3_n, i8** %pst_1_3_n
+
+  ; Fold memchr((char*)a + 1, '\04', N) to null.
+  %pst_1_4_n = getelementptr i8*, i8** %pchr, i32 7
+  %chr_1_4_n = call i8* @memchr(i8* %pi8ap1, i32 4, i64 %N)
+  store i8* %chr_1_4_n, i8** %pst_1_4_n
+
+
+  %pi8ap2 = getelementptr i8, i8* %pi8a, i32 2
+
+  ; Fold memchr((char*)a + 2, '\0', N) to null.
+  %pst_2_0_n = getelementptr i8*, i8** %pchr, i32 8
+  %chr_2_0_n = call i8* @memchr(i8* %pi8ap2, i32 0, i64 %N)
+  store i8* %chr_2_0_n, i8** %pst_2_0_n
+
+  ; Fold memchr((char*)a + 2, '\01', N) N ? (char*)a + 2 : null.
+  %pst_2_1_n = getelementptr i8*, i8** %pchr, i32 9
+  %chr_2_1_n = call i8* @memchr(i8* %pi8ap2, i32 1, i64 %N)
+  store i8* %chr_2_1_n, i8** %pst_2_1_n
+
+  ; Fold memchr((char*)a + 2, '\02', N) to N < 3 ? null : (char*)a + 2.
+  %pst_2_2_n = getelementptr i8*, i8** %pchr, i32 10
+  %chr_2_2_n = call i8* @memchr(i8* %pi8ap2, i32 2, i64 %N)
+  store i8* %chr_2_2_n, i8** %pst_2_2_n
+
+  ; Fold memchr((char*)a + 2, '\03', N) to N < 5 ? null : (char*)a + 4.
+  %pst_2_3_n = getelementptr i8*, i8** %pchr, i32 11
+  %chr_2_3_n = call i8* @memchr(i8* %pi8ap2, i32 3, i64 %N)
+  store i8* %chr_2_3_n, i8** %pst_2_3_n
+
+  ; Fold memchr((char*)a + 2, '\04', N) to null.
+  %pst_2_4_n = getelementptr i8*, i8** %pchr, i32 12
+  %chr_2_4_n = call i8* @memchr(i8* %pi8ap2, i32 4, i64 %N)
+  store i8* %chr_2_4_n, i8** %pst_2_4_n
+
+  ret void
+}
+
+
+; Verify that calls with out of bounds offsets are not folded.
+
+define void @call_memchr_A_pIb_xs_cst(i8** %pchr) {
+; CHECK-LABEL: @call_memchr_A_pIb_xs_cst(
+;
+; Verify that the call isn't folded when the first GEP index is excessive.
+  %pa1 = getelementptr [1 x %struct.A], [1 x %struct.A]* @a, i64 1, i64 0
+  %pi8a1 = bitcast %struct.A* %pa1 to i8*
+
+  %pi8a1p0 = getelementptr i8, i8* %pi8a1, i32 0
+
+  ; Don't fold memchr((char*)&a[1] + 0, '\0', 2).
+  %pst_1_0_0_2 = getelementptr i8*, i8** %pchr, i32 0
+  %chr_1_0_0_2 = call i8* @memchr(i8* %pi8a1p0, i32 0, i64 2)
+  store i8* %chr_1_0_0_2, i8** %pst_1_0_0_2
+
+  %pi8a1p1 = getelementptr i8, i8* %pi8a1, i32 1
+
+  ; Likewise, don't fold memchr((char*)&a[1] + 1, '\0', 2).
+  %pst_1_0_1_2 = getelementptr i8*, i8** %pchr, i32 1
+  %chr_1_0_1_2 = call i8* @memchr(i8* %pi8a1p0, i32 0, i64 2)
+  store i8* %chr_1_0_1_2, i8** %pst_1_0_1_2
+
+; Verify that the call isn't folded when the first GEP index is in bounds
+; but the byte offset is excessive.
+  %pa0 = getelementptr [1 x %struct.A], [1 x %struct.A]* @a, i64 0, i64 0
+  %pi8a0 = bitcast %struct.A* %pa0 to i8*
+
+  %pi8a0p8 = getelementptr i8, i8* %pi8a0, i32 8
+
+  ; Don't fold memchr((char*)&a[0] + 8, '\0', 2).
+  %pst_0_0_8_2 = getelementptr i8*, i8** %pchr, i32 2
+  %chr_0_0_8_2 = call i8* @memchr(i8* %pi8a0p8, i32 0, i64 2)
+  store i8* %chr_0_0_8_2, i8** %pst_0_0_8_2
+
+  ret void
+}
diff --git a/llvm/test/Transforms/InstCombine/memcmp-7.ll b/llvm/test/Transforms/InstCombine/memcmp-7.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/Transforms/InstCombine/memcmp-7.ll
@@ -0,0 +1,144 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt < %s -passes=instcombine -S | FileCheck %s
+;
+; Exercise folding of memcmp calls with addition expressions involving
+; pointers into constant arrays of types larger than char and fractional
+; offsets.
+
+declare i32 @memcmp(i8*, i8*, i64)
+
+@i32a = constant [2 x i16] [i16 4386, i16 13124]
+@i32b = constant [2 x i16] [i16 4386, i16 13124]
+
+
+define void @fold_memcmp_i32a_i32b_pIb(i32 %I, i32* %pcmp)
+; CHECK-LABEL: @fold_memcmp_i32a_i32b_pIb(
+; CHECK-NEXT:    store i32 0, i32* [[PCMP:%.*]], align 4
+; CHECK-NEXT:    [[PST_1_1_2:%.*]] = getelementptr i32, i32* [[PCMP]], i64 1
+; CHECK-NEXT:    store i32 0, i32* [[PST_1_1_2]], align 4
+; CHECK-NEXT:    [[PST_1_1_3:%.*]] = getelementptr i32, i32* [[PCMP]], i64 2
+; CHECK-NEXT:    store i32 0, i32* [[PST_1_1_3]], align 4
+; CHECK-NEXT:    ret void
+;
+{
+  %pi32a = getelementptr [2 x i16], [2 x i16]* @i32a, i32 0, i32 0
+  %pi32b = getelementptr [2 x i16], [2 x i16]* @i32b, i32 0, i32 0
+
+  %pi8a = bitcast i16* %pi32a to i8*
+  %pi8b = bitcast i16* %pi32b to i8*
+
+  %pi8ap1 = getelementptr i8, i8* %pi8a, i32 1
+  %pi8bp1 = getelementptr i8, i8* %pi8b, i32 1
+
+  %pst_1_1_1 = getelementptr i32, i32* %pcmp, i32 0
+  %cmp_1_1_1 = call i32 @memcmp(i8* %pi8ap1, i8* %pi8ap1, i64 1)
+  store i32 %cmp_1_1_1, i32* %pst_1_1_1
+
+  %pst_1_1_2 = getelementptr i32, i32* %pcmp, i32 1
+  %cmp_1_1_2 = call i32 @memcmp(i8* %pi8ap1, i8* %pi8ap1, i64 2)
+  store i32 %cmp_1_1_2, i32* %pst_1_1_2
+
+  %pst_1_1_3 = getelementptr i32, i32* %pcmp, i32 2
+  %cmp_1_1_3 = call i32 @memcmp(i8* %pi8ap1, i8* %pi8ap1, i64 3)
+  store i32 %cmp_1_1_3, i32* %pst_1_1_3
+
+  ret void
+}
+
+
+%struct.A = type { [4 x i8] }
+%struct.B = type { [2 x i8], [2 x i8] }
+
+@a = constant [1 x %struct.A] [%struct.A { [4 x i8] [i8 1, i8 2, i8 3, i8 4] }]
+@b = constant [1 x %struct.B] [%struct.B { [2 x i8] [i8 1, i8 2], [2 x i8] [i8 3, i8 4]}]
+
+define void @fold_memcmp_A_B_pIb(i32 %I, i32* %pcmp) {
+; CHECK-LABEL: @fold_memcmp_A_B_pIb(
+; CHECK-NEXT:    store i32 0, i32* [[PCMP:%.*]], align 4
+; CHECK-NEXT:    [[PST_0_0_2:%.*]] = getelementptr i32, i32* [[PCMP]], i64 1
+; CHECK-NEXT:    store i32 0, i32* [[PST_0_0_2]], align 4
+; CHECK-NEXT:    [[PST_0_0_3:%.*]] = getelementptr i32, i32* [[PCMP]], i64 2
+; CHECK-NEXT:    store i32 0, i32* [[PST_0_0_3]], align 4
+; CHECK-NEXT:    [[PST_0_0_4:%.*]] = getelementptr i32, i32* [[PCMP]], i64 3
+; CHECK-NEXT:    store i32 0, i32* [[PST_0_0_4]], align 4
+; CHECK-NEXT:    [[PST_0_1_1:%.*]] = getelementptr i32, i32* [[PCMP]], i64 4
+; CHECK-NEXT:    store i32 -1, i32* [[PST_0_1_1]], align 4
+; CHECK-NEXT:    [[PST_0_1_2:%.*]] = getelementptr i32, i32* [[PCMP]], i64 5
+; CHECK-NEXT:    store i32 -1, i32* [[PST_0_1_2]], align 4
+; CHECK-NEXT:    [[PST_0_1_3:%.*]] = getelementptr i32, i32* [[PCMP]], i64 6
+; CHECK-NEXT:    store i32 -1, i32* [[PST_0_1_3]], align 4
+; CHECK-NEXT:    [[PST_1_0_1:%.*]] = getelementptr i32, i32* [[PCMP]], i64 4
+; CHECK-NEXT:    store i32 1, i32* [[PST_1_0_1]], align 4
+; CHECK-NEXT:    [[PST_1_0_2:%.*]] = getelementptr i32, i32* [[PCMP]], i64 5
+; CHECK-NEXT:    store i32 1, i32* [[PST_1_0_2]], align 4
+; CHECK-NEXT:    [[PST_1_0_3:%.*]] = getelementptr i32, i32* [[PCMP]], i64 6
+; CHECK-NEXT:    store i32 1, i32* [[PST_1_0_3]], align 4
+; CHECK-NEXT:    ret void
+;
+  %pa = getelementptr [1 x %struct.A], [1 x %struct.A]* @a, i64 0, i64 0
+  %pb = getelementptr [1 x %struct.B], [1 x %struct.B]* @b, i64 0, i64 0
+
+  %pi8a = bitcast %struct.A* %pa to i8*
+  %pi8b = bitcast %struct.B* %pb to i8*
+
+  %pi8ap0 = getelementptr i8, i8* %pi8a, i32 0
+  %pi8bp0 = getelementptr i8, i8* %pi8b, i32 0
+
+  ; Fold memcmp(&a, &b, 1) to 0;
+  %pst_0_0_1 = getelementptr i32, i32* %pcmp, i32 0
+  %cmp_0_0_1 = call i32 @memcmp(i8* %pi8ap0, i8* %pi8bp0, i64 1)
+  store i32 %cmp_0_0_1, i32* %pst_0_0_1
+
+  ; Fold memcmp(&a, &b, 2) to 0;
+  %pst_0_0_2 = getelementptr i32, i32* %pcmp, i32 1
+  %cmp_0_0_2 = call i32 @memcmp(i8* %pi8ap0, i8* %pi8bp0, i64 2)
+  store i32 %cmp_0_0_2, i32* %pst_0_0_2
+
+  ; Fold memcmp(&a, &b, 3) to 0;
+  %pst_0_0_3 = getelementptr i32, i32* %pcmp, i32 2
+  %cmp_0_0_3 = call i32 @memcmp(i8* %pi8ap0, i8* %pi8bp0, i64 3)
+  store i32 %cmp_0_0_3, i32* %pst_0_0_3
+
+  ; Fold memcmp(&a, &b, 4) to 0;
+  %pst_0_0_4 = getelementptr i32, i32* %pcmp, i32 3
+  %cmp_0_0_4 = call i32 @memcmp(i8* %pi8ap0, i8* %pi8bp0, i64 4)
+  store i32 %cmp_0_0_4, i32* %pst_0_0_4
+
+
+  %pi8bp1 = getelementptr i8, i8* %pi8b, i32 1
+
+  ; Fold memcmp(&a, (char*)&b + 1, 1) to -1;
+  %pst_0_1_1 = getelementptr i32, i32* %pcmp, i32 4
+  %cmp_0_1_1 = call i32 @memcmp(i8* %pi8ap0, i8* %pi8bp1, i64 1)
+  store i32 %cmp_0_1_1, i32* %pst_0_1_1
+
+  ; Fold memcmp(&a, (char*)&b + 1, 2) to -1;
+  %pst_0_1_2 = getelementptr i32, i32* %pcmp, i32 5
+  %cmp_0_1_2 = call i32 @memcmp(i8* %pi8ap0, i8* %pi8bp1, i64 2)
+  store i32 %cmp_0_1_2, i32* %pst_0_1_2
+
+  ; Fold memcmp(&a, (char*)&b + 1, 3) to -1;
+  %pst_0_1_3 = getelementptr i32, i32* %pcmp, i32 6
+  %cmp_0_1_3 = call i32 @memcmp(i8* %pi8ap0, i8* %pi8bp1, i64 3)
+  store i32 %cmp_0_1_3, i32* %pst_0_1_3
+
+
+  %pi8ap1 = getelementptr i8, i8* %pi8a, i32 1
+
+  ; Fold memcmp((char*)&a + 1, &b, 1) to +1;
+  %pst_1_0_1 = getelementptr i32, i32* %pcmp, i32 4
+  %cmp_1_0_1 = call i32 @memcmp(i8* %pi8ap1, i8* %pi8bp0, i64 1)
+  store i32 %cmp_1_0_1, i32* %pst_1_0_1
+
+  ; Fold memcmp((char*)&a + 1, &b, 2) to +1;
+  %pst_1_0_2 = getelementptr i32, i32* %pcmp, i32 5
+  %cmp_1_0_2 = call i32 @memcmp(i8* %pi8ap1, i8* %pi8bp0, i64 2)
+  store i32 %cmp_1_0_2, i32* %pst_1_0_2
+
+  ; Fold memcmp((char*)&a + 1, &b, 3) to +1;
+  %pst_1_0_3 = getelementptr i32, i32* %pcmp, i32 6
+  %cmp_1_0_3 = call i32 @memcmp(i8* %pi8ap1, i8* %pi8bp0, i64 3)
+  store i32 %cmp_1_0_3, i32* %pst_1_0_3
+
+  ret void
+}