Index: lib/Target/WebAssembly/WebAssemblyFastISel.cpp
===================================================================
--- lib/Target/WebAssembly/WebAssemblyFastISel.cpp
+++ lib/Target/WebAssembly/WebAssemblyFastISel.cpp
@@ -69,6 +69,7 @@
     bool isFIBase() const { return Kind == FrameIndexBase; }
     void setReg(unsigned Reg) {
       assert(isRegBase() && "Invalid base register access!");
+      assert(Base.Reg == 0 && "Overwriting non-zero register");
       Base.Reg = Reg;
     }
     unsigned getReg() const {
@@ -261,22 +262,24 @@
             TmpOffset += CI->getSExtValue() * S;
             break;
           }
+          if (!canFoldAddIntoGEP(U, Op)) {
+            goto unsupported_gep;
+          }
           if (S == 1 && Addr.isRegBase() && Addr.getReg() == 0) {
+            // assert(isa<AddOperator>(Op) && "Must be an add");
+            // assert(isa<ConstantInt>(cast<AddOperator>(Op)->getOperand(1)) &&
+            //        "Must have a constant operand");
             // An unscaled add of a register. Set it as the new base.
             Addr.setReg(getRegForValue(Op));
             break;
           }
-          if (canFoldAddIntoGEP(U, Op)) {
-            // A compatible add with a constant operand. Fold the constant.
-            ConstantInt *CI =
-                cast<ConstantInt>(cast<AddOperator>(Op)->getOperand(1));
-            TmpOffset += CI->getSExtValue() * S;
-            // Iterate on the other operand.
-            Op = cast<AddOperator>(Op)->getOperand(0);
-            continue;
-          }
-          // Unsupported
-          goto unsupported_gep;
+          // A compatible add with a constant operand. Fold the constant.
+          ConstantInt *CI =
+              cast<ConstantInt>(cast<AddOperator>(Op)->getOperand(1));
+          TmpOffset += CI->getSExtValue() * S;
+          // Iterate on the other operand.
+          Op = cast<AddOperator>(Op)->getOperand(0);
+          continue;
         }
       }
     }
Index: test/CodeGen/WebAssembly/offset-fastisel.ll
===================================================================
--- /dev/null
+++ test/CodeGen/WebAssembly/offset-fastisel.ll
@@ -0,0 +1,100 @@
+; RUN: llc < %s -asm-verbose=false -disable-wasm-explicit-locals -fast-isel | FileCheck %s
+
+; TODO: Merge this with offset.ll when fast-isel matches better.
+
+target datalayout = "e-m:e-p:32:32-i64:64-n32:64-S128"
+target triple = "wasm32-unknown-unknown-elf"
+
+; CHECK-LABEL: store_i8_with_variable_gep_offset:
+; CHECK: i32.add    $push[[L0:[0-9]+]]=, $0, $1{{$}}
+; CHECK: i32.const  $push[[L1:[0-9]+]]=, 0{{$}}
+; CHECK: i32.store8 0($pop[[L0]]), $pop[[L1]]{{$}}
+define void @store_i8_with_variable_gep_offset(i8* %p, i32 %idx) {
+  %s = getelementptr inbounds i8, i8* %p, i32 %idx
+  store i8 0, i8* %s
+  ret void
+}
+
+; CHECK-LABEL: store_i8_with_array_alloca_gep:
+; CHECK: i32.const   $push[[L0:[0-9]+]]=, 0{{$}}
+; CHECK: i32.load    $push[[L1:[0-9]+]]=, __stack_pointer($pop[[L0]]){{$}}
+; CHECK: i32.const   $push[[L2:[0-9]+]]=, 32{{$}}
+; CHECK: i32.sub     $push{{[0-9]+}}=, $pop[[L1]], $pop[[L2]]{{$}}
+; CHECK: i32.add     $push[[L4:[0-9]+]]=, $pop{{[0-9]+}}, $0{{$}}
+; CHECK: i32.const   $push[[L5:[0-9]+]]=, 0{{$}}
+; CHECK: i32.store8  0($pop[[L4]]), $pop[[L5]]{{$}}
+define hidden void @store_i8_with_array_alloca_gep(i32 %idx) {
+  %A = alloca [30 x i8], align 16
+  %s = getelementptr inbounds [30 x i8], [30 x i8]* %A, i32 0, i32 %idx
+  store i8 0, i8* %s, align 1
+  ret void
+}
+
+; CHECK-LABEL: store_i32_with_unfolded_gep_offset:
+; CHECK: i32.const $push[[L0:[0-9]+]]=, 24{{$}}
+; CHECK: i32.add   $push[[L1:[0-9]+]]=, $0, $pop[[L0]]{{$}}
+; CHECK: i32.const $push[[L2:[0-9]+]]=, 0{{$}}
+; CHECK: i32.store 0($pop[[L1]]), $pop[[L2]]{{$}}
+define void @store_i32_with_unfolded_gep_offset(i32* %p) {
+  %s = getelementptr i32, i32* %p, i32 6
+  store i32 0, i32* %s
+  ret void
+}
+
+; CHECK-LABEL: store_i32_with_folded_gep_offset:
+; CHECK: i32.store 24($0), $pop{{[0-9]+$}}
+define void @store_i32_with_folded_gep_offset(i32* %p) {
+  %s = getelementptr inbounds i32, i32* %p, i32 6
+  store i32 0, i32* %s
+  ret void
+}
+
+; CHECK-LABEL: load_i32_with_folded_gep_offset:
+; CHECK: i32.load  $push{{[0-9]+}}=, 24($0){{$}}
+define i32 @load_i32_with_folded_gep_offset(i32* %p) {
+  %s = getelementptr inbounds i32, i32* %p, i32 6
+  %t = load i32, i32* %s
+  ret i32 %t
+}
+
+; CHECK-LABEL: store_i64_with_unfolded_gep_offset:
+; CHECK: i32.const $push[[L0:[0-9]+]]=, 24{{$}}
+; CHECK: i32.add   $push[[L1:[0-9]+]]=, $0, $pop[[L0]]{{$}}
+; CHECK: i64.const $push[[L2:[0-9]+]]=, 0{{$}}
+; CHECK: i64.store 0($pop[[L1]]), $pop[[L2]]{{$}}
+define void @store_i64_with_unfolded_gep_offset(i64* %p) {
+  %s = getelementptr i64, i64* %p, i32 3
+  store i64 0, i64* %s
+  ret void
+}
+
+; CHECK-LABEL: store_i8_with_folded_gep_offset:
+; CHECK: i32.store8 24($0), $pop{{[0-9]+$}}
+define void @store_i8_with_folded_gep_offset(i8* %p) {
+  %s = getelementptr inbounds i8, i8* %p, i32 24
+  store i8 0, i8* %s
+  ret void
+}
+
+; CHECK-LABEL: load_i8_u_with_folded_offset:
+; CHECK: i32.load8_u $push{{[0-9]+}}=, 24($0){{$}}
+define i32 @load_i8_u_with_folded_offset(i8* %p) {
+  %q = ptrtoint i8* %p to i32
+  %r = add nuw i32 %q, 24
+  %s = inttoptr i32 %r to i8*
+  %t = load i8, i8* %s
+  %u = zext i8 %t to i32
+  ret i32 %u
+}
+
+; TODO: this should be load8_s, need to fold sign-/zero-extend in fast-isel
+; CHECK-LABEL: load_i8_s_with_folded_offset:
+; CHECK: i32.load8_u $push{{[0-9]+}}=, 24($0){{$}}
+define i32 @load_i8_s_with_folded_offset(i8* %p) {
+  %q = ptrtoint i8* %p to i32
+  %r = add nuw i32 %q, 24
+  %s = inttoptr i32 %r to i8*
+  %t = load i8, i8* %s
+  %u = sext i8 %t to i32
+  ret i32 %u
+}