diff --git a/src/frontend/A64/decoder/a64.inc b/src/frontend/A64/decoder/a64.inc
index 5cd91d1d..8fd63f8a 100644
--- a/src/frontend/A64/decoder/a64.inc
+++ b/src/frontend/A64/decoder/a64.inc
@@ -825,7 +825,7 @@ INST(USHLL,                  "USHLL, USHLL2",                             "0Q101
 //INST(SMLSL_elt,              "SMLSL, SMLSL2 (by element)",                "0Q001111zzLMmmmm0110H0nnnnnddddd")
 //INST(SQDMLSL_elt_2,          "SQDMLSL, SQDMLSL2 (by element)",            "0Q001111zzLMmmmm0111H0nnnnnddddd")
 INST(MUL_elt,                "MUL (by element)",                          "0Q001111zzLMmmmm1000H0nnnnnddddd")
-//INST(SMULL_elt,              "SMULL, SMULL2 (by element)",                "0Q001111zzLMmmmm1010H0nnnnnddddd")
+INST(SMULL_elt,              "SMULL, SMULL2 (by element)",                "0Q001111zzLMmmmm1010H0nnnnnddddd")
 //INST(SQDMULL_elt_2,          "SQDMULL, SQDMULL2 (by element)",            "0Q001111zzLMmmmm1011H0nnnnnddddd")
 INST(SQDMULH_elt_2,          "SQDMULH (by element)",                      "0Q001111zzLMmmmm1100H0nnnnnddddd")
 //INST(SQRDMULH_elt_2,         "SQRDMULH (by element)",                     "0Q001111zzLMmmmm1101H0nnnnnddddd")
diff --git a/src/frontend/A64/translate/impl/impl.h b/src/frontend/A64/translate/impl/impl.h
index a6389b23..fcf61d59 100644
--- a/src/frontend/A64/translate/impl/impl.h
+++ b/src/frontend/A64/translate/impl/impl.h
@@ -895,7 +895,7 @@ struct TranslatorVisitor final {
     bool SMLSL_elt(bool Q, Imm<2> size, bool L, bool M, Vec Vm, bool H, Vec Vn, Vec Vd);
     bool SQDMLSL_elt_2(bool Q, Imm<2> size, bool L, bool M, Vec Vm, bool H, Reg Rn, Vec Vd);
     bool MUL_elt(bool Q, Imm<2> size, Imm<1> L, Imm<1> M, Imm<4> Vmlo, Imm<1> H, Vec Vn, Vec Vd);
-    bool SMULL_elt(bool Q, Imm<2> size, bool L, bool M, Vec Vm, bool H, Vec Vn, Vec Vd);
+    bool SMULL_elt(bool Q, Imm<2> size, Imm<1> L, Imm<1> M, Imm<4> Vm, Imm<1> H, Vec Vn, Vec Vd);
     bool SQDMULL_elt_2(bool Q, Imm<2> size, bool L, bool M, Vec Vm, bool H, Reg Rn, Vec Vd);
     bool SQDMULH_elt_2(bool Q, Imm<2> size, Imm<1> L, Imm<1> M, Imm<4> Vmlo, Imm<1> H, Vec Vn, Vec Vd);
     bool SQRDMULH_elt_2(bool Q, Imm<2> size, bool L, bool M, Vec Vm, bool H, Vec Vn, Vec Vd);
diff --git a/src/frontend/A64/translate/impl/simd_vector_x_indexed_element.cpp b/src/frontend/A64/translate/impl/simd_vector_x_indexed_element.cpp
index 015ee0ad..ae79c352 100644
--- a/src/frontend/A64/translate/impl/simd_vector_x_indexed_element.cpp
+++ b/src/frontend/A64/translate/impl/simd_vector_x_indexed_element.cpp
@@ -147,6 +147,33 @@ bool TranslatorVisitor::FMUL_elt_4(bool Q, bool sz, Imm<1> L, Imm<1> M, Imm<4> V
     return FPMultiplyByElement(*this, Q, sz, L, M, Vmlo, H, Vn, Vd, ExtraBehavior::None);
 }
 
+bool TranslatorVisitor::SMULL_elt(bool Q, Imm<2> size, Imm<1> L, Imm<1> M, Imm<4> Vmlo, Imm<1> H, Vec Vn, Vec Vd) {
+    if (size == 0b00 || size == 0b11) {
+        return UnallocatedEncoding();
+    }
+
+    const size_t idxsize = H == 1 ? 128 : 64;
+    const size_t esize = 8 << size.ZeroExtend();
+    const size_t datasize = 64;
+    const auto [index, Vmhi] = [=] {
+        if (size == 0b01) {
+            return std::make_pair(concatenate(H, L, M).ZeroExtend(), Imm<1>{0});
+        }
+
+        return std::make_pair(concatenate(H, L).ZeroExtend(), M);
+    }();
+
+    const IR::U128 operand1 = Vpart(datasize, Vn, Q);
+    const IR::U128 operand2 = V(idxsize, concatenate(Vmhi, Vmlo).ZeroExtend<Vec>());
+    const IR::U128 index_vector = ir.VectorBroadcast(esize, ir.VectorGetElement(esize, operand2, index));
+    const IR::U128 result = ir.VectorMultiply(2 * esize,
+                                              ir.VectorSignExtend(esize, operand1),
+                                              ir.VectorSignExtend(esize, index_vector));
+
+    V(128, Vd, result);
+    return true;
+}
+
 bool TranslatorVisitor::SQDMULH_elt_2(bool Q, Imm<2> size, Imm<1> L, Imm<1> M, Imm<4> Vmlo, Imm<1> H, Vec Vn, Vec Vd) {
     if (size == 0b00 || size == 0b11) {
         return UnallocatedEncoding();