diff --git a/src/frontend/A64/decoder/a64.inc b/src/frontend/A64/decoder/a64.inc
index d762a15e..a1c0e0ad 100644
--- a/src/frontend/A64/decoder/a64.inc
+++ b/src/frontend/A64/decoder/a64.inc
@@ -835,7 +835,7 @@ INST(MUL_elt,                "MUL (by element)",                          "0Q001
 //INST(FMLS_elt_3,             "FMLS (by element)",                         "0Q00111100LMmmmm0101H0nnnnnddddd")
 //INST(FMLS_elt_4,             "FMLS (by element)",                         "0Q0011111zLMmmmm0101H0nnnnnddddd")
 //INST(FMUL_elt_3,             "FMUL (by element)",                         "0Q00111100LMmmmm1001H0nnnnnddddd")
-//INST(FMUL_elt_4,             "FMUL (by element)",                         "0Q0011111zLMmmmm1001H0nnnnnddddd")
+INST(FMUL_elt_4,             "FMUL (by element)",                         "0Q0011111zLMmmmm1001H0nnnnnddddd")
 //INST(FMLAL_elt_1,            "FMLAL, FMLAL2 (by element)",                "0Q0011111zLMmmmm0000H0nnnnnddddd")
 //INST(FMLAL_elt_2,            "FMLAL, FMLAL2 (by element)",                "0Q1011111zLMmmmm1000H0nnnnnddddd")
 //INST(FMLSL_elt_1,            "FMLSL, FMLSL2 (by element)",                "0Q0011111zLMmmmm0100H0nnnnnddddd")
diff --git a/src/frontend/A64/translate/impl/impl.h b/src/frontend/A64/translate/impl/impl.h
index 2475d13c..776493af 100644
--- a/src/frontend/A64/translate/impl/impl.h
+++ b/src/frontend/A64/translate/impl/impl.h
@@ -658,35 +658,20 @@ struct TranslatorVisitor final {
 
     // Data Processing - FP and SIMD - SIMD Scalar x indexed element
     bool SQDMLAL_elt_1(Imm<2> size, bool L, bool M, Vec Vm, bool H, Reg Rn, Vec Vd);
-    bool SQDMLAL_elt_2(bool Q, Imm<2> size, bool L, bool M, Vec Vm, bool H, Reg Rn, Vec Vd);
     bool SQDMLSL_elt_1(Imm<2> size, bool L, bool M, Vec Vm, bool H, Reg Rn, Vec Vd);
-    bool SQDMLSL_elt_2(bool Q, Imm<2> size, bool L, bool M, Vec Vm, bool H, Reg Rn, Vec Vd);
     bool SQDMULL_elt_1(Imm<2> size, bool L, bool M, Vec Vm, bool H, Reg Rn, 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_1(Imm<2> size, bool L, bool M, Vec Vm, bool H, Vec Vn, Vec Vd);
-    bool SQDMULH_elt_2(bool Q, Imm<2> size, bool L, bool M, Vec Vm, bool H, Vec Vn, Vec Vd);
     bool SQRDMULH_elt_1(Imm<2> size, bool L, bool M, Vec Vm, bool 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);
     bool FMLA_elt_1(bool L, bool M, Vec Vm, bool H, Vec Vn, Vec Vd);
     bool FMLA_elt_2(bool sz, bool L, bool M, Vec Vm, bool H, Vec Vn, Vec Vd);
-    bool FMLA_elt_3(bool Q, bool L, bool M, Vec Vm, bool H, Vec Vn, Vec Vd);
-    bool FMLA_elt_4(bool Q, bool sz, bool L, bool M, Vec Vm, bool H, Vec Vn, Vec Vd);
     bool FMLS_elt_1(bool L, bool M, Vec Vm, bool H, Vec Vn, Vec Vd);
     bool FMLS_elt_2(bool sz, bool L, bool M, Vec Vm, bool H, Vec Vn, Vec Vd);
-    bool FMLS_elt_3(bool Q, bool L, bool M, Vec Vm, bool H, Vec Vn, Vec Vd);
-    bool FMLS_elt_4(bool Q, bool sz, bool L, bool M, Vec Vm, bool H, Vec Vn, Vec Vd);
     bool FMUL_elt_1(bool L, bool M, Vec Vm, bool H, Vec Vn, Vec Vd);
     bool FMUL_elt_2(bool sz, bool L, bool M, Vec Vm, bool H, Vec Vn, Vec Vd);
-    bool FMUL_elt_3(bool Q, bool L, bool M, Vec Vm, bool H, Vec Vn, Vec Vd);
-    bool FMUL_elt_4(bool Q, bool sz, bool L, bool M, Vec Vm, bool H, Vec Vn, Vec Vd);
     bool SQRDMLAH_elt_1(Imm<2> size, bool L, bool M, Vec Vm, bool H, Vec Vn, Vec Vd);
-    bool SQRDMLAH_elt_2(bool Q, Imm<2> size, bool L, bool M, Vec Vm, bool H, Vec Vn, Vec Vd);
     bool SQRDMLSH_elt_1(Imm<2> size, bool L, bool M, Vec Vm, bool H, Vec Vn, Vec Vd);
-    bool SQRDMLSH_elt_2(bool Q, Imm<2> size, bool L, bool M, Vec Vm, bool H, Vec Vn, Vec Vd);
     bool FMULX_elt_1(bool L, bool M, Vec Vm, bool H, Vec Vn, Vec Vd);
     bool FMULX_elt_2(bool sz, bool L, bool M, Vec Vm, bool H, Vec Vn, Vec Vd);
-    bool FMULX_elt_3(bool Q, bool L, bool M, Vec Vm, bool H, Vec Vn, Vec Vd);
-    bool FMULX_elt_4(bool Q, bool sz, bool L, bool M, Vec Vm, bool H, Vec Vn, Vec Vd);
 
     // Data Processing - FP and SIMD - SIMD Table Lookup
     bool TBL(bool Q, Vec Vm, Imm<2> len, Vec Vn, Vec Vd);
@@ -907,10 +892,21 @@ struct TranslatorVisitor final {
 
     // Data Processing - FP and SIMD - SIMD vector x indexed element
     bool SMLAL_elt(bool Q, Imm<2> size, bool L, bool M, Vec Vm, bool H, Vec Vn, Vec Vd);
+    bool SQDMLAL_elt_2(bool Q, Imm<2> size, bool L, bool M, Vec Vm, bool H, Reg Rn, Vec Vd);
     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 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, bool L, bool M, Vec Vm, bool 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);
     bool SDOT_elt(bool Q, Imm<2> size, bool L, bool M, Vec Vm, bool H, Vec Vn, Vec Vd);
+    bool FMLA_elt_3(bool Q, bool L, bool M, Vec Vm, bool H, Vec Vn, Vec Vd);
+    bool FMLA_elt_4(bool Q, bool sz, bool L, bool M, Vec Vm, bool H, Vec Vn, Vec Vd);
+    bool FMLS_elt_3(bool Q, bool L, bool M, Vec Vm, bool H, Vec Vn, Vec Vd);
+    bool FMLS_elt_4(bool Q, bool sz, bool L, bool M, Vec Vm, bool H, Vec Vn, Vec Vd);
+    bool FMUL_elt_3(bool Q, bool L, bool M, Vec Vm, bool H, Vec Vn, Vec Vd);
+    bool FMUL_elt_4(bool Q, bool sz, Imm<1> L, Imm<1> M, Imm<4> Vmlo, Imm<1> H, Vec Vn, Vec Vd);
     bool FMLAL_elt_1(bool Q, bool sz, bool L, bool M, Vec Vm, bool H, Vec Vn, Vec Vd);
     bool FMLAL_elt_2(bool Q, bool sz, bool L, bool M, Vec Vm, bool H, Vec Vn, Vec Vd);
     bool FMLSL_elt_1(bool Q, bool sz, bool L, bool M, Vec Vm, bool H, Vec Vn, Vec Vd);
@@ -920,7 +916,11 @@ struct TranslatorVisitor final {
     bool MLS_elt(bool Q, Imm<2> size, Imm<1> L, Imm<1> M, Imm<4> Vmlo, Imm<1> H, Vec Vn, Vec Vd);
     bool UMLSL_elt(bool Q, Imm<2> size, bool L, bool M, Vec Vm, bool H, Vec Vn, Vec Vd);
     bool UMULL_elt(bool Q, Imm<2> size, bool L, bool M, Vec Vm, bool H, Vec Vn, Vec Vd);
+    bool SQRDMLAH_elt_2(bool Q, Imm<2> size, bool L, bool M, Vec Vm, bool H, Vec Vn, Vec Vd);
     bool UDOT_elt(bool Q, Imm<2> size, bool L, bool M, Vec Vm, bool H, Vec Vn, Vec Vd);
+    bool SQRDMLSH_elt_2(bool Q, Imm<2> size, bool L, bool M, Vec Vm, bool H, Vec Vn, Vec Vd);
+    bool FMULX_elt_3(bool Q, bool L, bool M, Vec Vm, bool H, Vec Vn, Vec Vd);
+    bool FMULX_elt_4(bool Q, bool sz, bool L, bool M, Vec Vm, bool H, Vec Vn, Vec Vd);
     bool FCMLA_elt(bool Q, Imm<2> size, bool L, bool M, Vec Vm, Imm<2> rot, bool H, Vec Vn, Vec Vd);
 
     // Data Processing - FP and SIMD - Cryptographic three register
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 63ac9fda..9abf2e5f 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
@@ -72,4 +72,27 @@ bool TranslatorVisitor::MUL_elt(bool Q, Imm<2> size, Imm<1> L, Imm<1> M, Imm<4>
     return true;
 }
 
+bool TranslatorVisitor::FMUL_elt_4(bool Q, bool sz, Imm<1> L, Imm<1> M, Imm<4> Vmlo, Imm<1> H, Vec Vn, Vec Vd) {
+    if (sz && L == 1) {
+        return UnallocatedEncoding();
+    }
+    if (sz && !Q) {
+        return ReservedValue();
+    }
+
+    const size_t idxdsize = H == 1 ? 128 : 64;
+    const size_t index = sz ? H.ZeroExtend() : concatenate(H, L).ZeroExtend();
+    const Vec Vm = concatenate(M, Vmlo).ZeroExtend<Vec>();
+    const size_t esize = sz ? 64 : 32;
+    const size_t datasize = Q ? 128 : 64;
+
+    const IR::UAny element2 = ir.VectorGetElement(esize, V(idxdsize, Vm), index);
+    const IR::U128 operand1 = V(datasize, Vn);
+    const IR::U128 operand2 = Q ? ir.VectorBroadcast(esize, element2) : ir.VectorBroadcastLower(esize, element2);
+
+    const IR::U128 result = ir.FPVectorMul(esize, operand1, operand2);
+    V(datasize, Vd, result);
+    return true;
+}
+
 } // namespace Dynarmic::A64