Index: lib/CodeGen/SelectionDAG/DAGCombiner.cpp
===================================================================
--- lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -3788,6 +3788,16 @@
   if (LoadN->getNumValues() > 2)
     return false;
 
+  // Only allow byte offsets.
+  if (ShAmt % 8)
+    return false;
+
+  // Ensure that this isn't going to produce an unsupported unaligned access.
+  if (ShAmt && !TLI.allowsMemoryAccess(*DAG.getContext(), DAG.getDataLayout(),
+                                       ExtVT, LoadN->getAddressSpace(),
+                                       ShAmt / 8))
+    return false;
+
   // If the load that we're shrinking is an extload and we're not just
   // discarding the extension we can't simply shrink the load. Bail.
   // TODO: It would be possible to merge the extensions in some cases.
@@ -8274,6 +8284,19 @@
       // then the result of the shift+trunc is zero/undef (handled elsewhere).
       if (ShAmt >= cast<LoadSDNode>(N0)->getMemoryVT().getSizeInBits())
         return SDValue();
+
+      // If the SRL is only used by a masking AND, we may be able to adjust
+      // the ExtVT to make the AND redundant.
+      SDNode *Mask = *(N->use_begin());
+      if (Mask->getOpcode() == ISD::AND &&
+          isa<ConstantSDNode>(Mask->getOperand(1))) {
+        const APInt &ShiftMask =
+          cast<ConstantSDNode>(Mask->getOperand(1))->getAPIntValue();
+        // Recompute the type.
+        if (ShiftMask.isMask() && (ShiftMask.countTrailingOnes() % 8 == 0))
+          ExtVT = EVT::getIntegerVT(*DAG.getContext(),
+                                    ShiftMask.countTrailingOnes());
+      }
     }
   }
 
Index: test/CodeGen/ARM/shift-combine.ll
===================================================================
--- test/CodeGen/ARM/shift-combine.ll
+++ test/CodeGen/ARM/shift-combine.ll
@@ -217,10 +217,23 @@
   ret i32 %conv
 }
 
-; CHECK-LABEL: test_shift8_mask8
+; CHECK-LABEL: test_shift7_mask8
 ; CHECK-BE:         ldr r1, [r0]
 ; CHECK-COMMON:     ldr r1, [r0]
-; CHECK-COMMON:     ubfx r1, r1, #8, #8
+; CHECK-COMMON:     ubfx r1, r1, #7, #8
+; CHECK-COMMON:     str r1, [r0]
+define arm_aapcscc void @test_shift7_mask8(i32* nocapture %p) {
+entry:
+  %0 = load i32, i32* %p, align 4
+  %shl = lshr i32 %0, 7
+  %and = and i32 %shl, 255
+  store i32 %and, i32* %p, align 4
+  ret void
+}
+
+; CHECK-LABEL: test_shift8_mask8
+; CHECK-BE:         ldrb r1, [r0, #2]
+; CHECK-COMMON:     ldrb r1, [r0, #1]
 ; CHECK-COMMON:     str r1, [r0]
 define arm_aapcscc void @test_shift8_mask8(i32* nocapture %p) {
 entry:
@@ -231,10 +244,40 @@
   ret void
 }
 
-; CHECK-LABEL: test_shift8_mask16
+; CHECK-LABEL: test_shift8_mask7
 ; CHECK-BE:         ldr r1, [r0]
 ; CHECK-COMMON:     ldr r1, [r0]
-; CHECK-COMMON:     ubfx r1, r1, #8, #16
+; CHECK-COMMON:     ubfx r1, r1, #8, #7
+; CHECK-COMMON:     str r1, [r0]
+define arm_aapcscc void @test_shift8_mask7(i32* nocapture %p) {
+entry:
+  %0 = load i32, i32* %p, align 4
+  %shl = lshr i32 %0, 8
+  %and = and i32 %shl, 127
+  store i32 %and, i32* %p, align 4
+  ret void
+}
+
+; CHECK-LABEL: test_shift9_mask8
+; CHECK-BE:         ldr r1, [r0]
+; CHECK-COMMON:     ldr r1, [r0]
+; CHECK-COMMON:     ubfx r1, r1, #9, #8
+; CHECK-COMMON:     str r1, [r0]
+define arm_aapcscc void @test_shift9_mask8(i32* nocapture %p) {
+entry:
+  %0 = load i32, i32* %p, align 4
+  %shl = lshr i32 %0, 9
+  %and = and i32 %shl, 255
+  store i32 %and, i32* %p, align 4
+  ret void
+}
+
+; CHECK-LABEL: test_shift8_mask16
+; CHECK-ALIGN:      ldr r1, [r0]
+; CHECK-ALIGN:      ubfx r1, r1, #8, #16
+; CHECK-BE:         ldrh r1, [r0, #1]
+; CHECK-ARM:        ldrh r1, [r0, #1]
+; CHECK-THUMB:      ldrh.w r1, [r0, #1]
 ; CHECK-COMMON:     str r1, [r0]
 define arm_aapcscc void @test_shift8_mask16(i32* nocapture %p) {
 entry:
@@ -245,6 +288,33 @@
   ret void
 }
 
+; CHECK-LABEL: test_shift15_mask16
+; CHECK-COMMON:     ldr r1, [r0]
+; CHECK-COMMON:     ubfx r1, r1, #15, #16
+; CHECK-COMMON:     str r1, [r0]
+define arm_aapcscc void @test_shift15_mask16(i32* nocapture %p) {
+entry:
+  %0 = load i32, i32* %p, align 4
+  %shl = lshr i32 %0, 15
+  %and = and i32 %shl, 65535
+  store i32 %and, i32* %p, align 4
+  ret void
+}
+
+; CHECK-LABEL: test_shift16_mask15
+; CHECK-BE:         ldrh r1, [r0]
+; CHECK-COMMON:     ldrh r1, [r0, #2]
+; CHECK-COMMON:     bfc r1, #15, #17
+; CHECK-COMMON:     str r1, [r0]
+define arm_aapcscc void @test_shift16_mask15(i32* nocapture %p) {
+entry:
+  %0 = load i32, i32* %p, align 4
+  %shl = lshr i32 %0, 16
+  %and = and i32 %shl, 32767
+  store i32 %and, i32* %p, align 4
+  ret void
+}
+
 ; CHECK-LABEL: test_sext_shift8_mask8
 ; CHECK-BE:         ldrb r0, [r0]
 ; CHECK-COMMON:     ldrb r0, [r0, #1]
Index: test/CodeGen/X86/h-registers-1.ll
===================================================================
--- test/CodeGen/X86/h-registers-1.ll
+++ test/CodeGen/X86/h-registers-1.ll
@@ -9,11 +9,12 @@
 ; CHECK: foo:
 ; CHECK: movzbl %{{[abcd]}}h, %e
 ; CHECK: movzbl %{{[abcd]}}h, %e
+; CHECK: movq   %rax, %r
 ; CHECK: movzbl %{{[abcd]}}h, %e
 ; CHECK: movzbl %{{[abcd]}}h, %e
+; CHECK: movq   %r8, %r
 ; CHECK: movzbl %{{[abcd]}}h, %e
-; CHECK: movzbl %{{[abcd]}}h, %e
-; CHECK: movzbl %{{[abcd]}}h, %e
+; CHECK: movq   %r9, %r
 ; CHECK: movzbl %{{[abcd]}}h, %e
 ; CHECK: ret