diff --git a/vta/config/vta_config.json b/vta/config/vta_config.json
index 8a7bcc01af62b..27a2289b2b8b7 100644
--- a/vta/config/vta_config.json
+++ b/vta/config/vta_config.json
@@ -1,5 +1,5 @@
 {
-  "TARGET" : "pynq",
+  "TARGET" : "sim",
   "HW_VER" : "0.0.2",
   "HW_FREQ" : 100,
   "HW_CLK_TARGET" : 7,
diff --git a/vta/src/sim/sim_driver.cc b/vta/src/sim/sim_driver.cc
index 8123d73c0fb58..58d322a07c8ad 100644
--- a/vta/src/sim/sim_driver.cc
+++ b/vta/src/sim/sim_driver.cc
@@ -483,6 +483,11 @@ class Device {
             return std::min(x, y);
           });
       }
+      case VTA_ALU_OPCODE_MUL: {
+        return RunALULoop<use_imm>(op, [](int32_t x, int32_t y) {
+            return x * y;
+          });
+      }
       case VTA_ALU_OPCODE_SHR: {
         return RunALULoop<use_imm>(op, [](int32_t x, int32_t y) {
             if (y >= 0) {
diff --git a/vta/tests/python/integration/test_benchmark_topi_conv2d.py b/vta/tests/python/integration/test_benchmark_topi_conv2d.py
index 5b7ceb7404e60..91ac6b5f6f264 100644
--- a/vta/tests/python/integration/test_benchmark_topi_conv2d.py
+++ b/vta/tests/python/integration/test_benchmark_topi_conv2d.py
@@ -202,6 +202,7 @@ def run_vta_conv2d(env, remote, key, batch_size, wl, profile=True):
         res = topi.add(res, bias)
         res = topi.multiply(res, coeff)
         res = my_clip(res, 0, (1 << env.OUT_WIDTH-1)-1)
+        res = topi.cast(res, "int8")
 
         # Handle quantized outputs (less than 8 bits)
         # o_pack_factor = 1 << (3 - env.LOG_OUT_WIDTH)