diff --git a/src/frontend/A64/decoder/a64.inc b/src/frontend/A64/decoder/a64.inc
index a37012b7..70a2461e 100644
--- a/src/frontend/A64/decoder/a64.inc
+++ b/src/frontend/A64/decoder/a64.inc
@@ -899,7 +899,7 @@ INST(FCVTZU_float_int,       "FCVTZU (scalar, integer)",                  "z0011
 INST(FMOV_float,             "FMOV (register)",                           "00011110yy100000010000nnnnnddddd")
 INST(FABS_float,             "FABS (scalar)",                             "00011110yy100000110000nnnnnddddd")
 INST(FNEG_float,             "FNEG (scalar)",                             "00011110yy100001010000nnnnnddddd")
-//INST(FSQRT_float,            "FSQRT (scalar)",                            "00011110yy100001110000nnnnnddddd")
+INST(FSQRT_float,            "FSQRT (scalar)",                            "00011110yy100001110000nnnnnddddd")
 INST(FCVT_float,             "FCVT",                                      "00011110yy10001oo10000nnnnnddddd")
 //INST(FRINTN_float,           "FRINTN (scalar)",                           "00011110yy100100010000nnnnnddddd")
 //INST(FRINTP_float,           "FRINTP (scalar)",                           "00011110yy100100110000nnnnnddddd")
diff --git a/src/frontend/A64/translate/impl/floating_point_data_processing_one_register.cpp b/src/frontend/A64/translate/impl/floating_point_data_processing_one_register.cpp
index ceef79a8..4eea893a 100644
--- a/src/frontend/A64/translate/impl/floating_point_data_processing_one_register.cpp
+++ b/src/frontend/A64/translate/impl/floating_point_data_processing_one_register.cpp
@@ -58,6 +58,18 @@ bool TranslatorVisitor::FNEG_float(Imm<2> type, Vec Vn, Vec Vd) {
     return true;
 }
 
+bool TranslatorVisitor::FSQRT_float(Imm<2> type, Vec Vn, Vec Vd) {
+    boost::optional<size_t> datasize = GetDataSize(type);
+    if (!datasize || *datasize == 16) {
+        return UnallocatedEncoding();
+    }
+
+    const IR::U32U64 operand = V_scalar(*datasize, Vn);
+    const IR::U32U64 result = ir.FPSqrt(operand);
+    V_scalar(*datasize, Vd, result);
+    return true;
+}
+
 bool TranslatorVisitor::FMOV_float_imm(Imm<2> type, Imm<8> imm8, Vec Vd) {
     boost::optional<size_t> datasize = GetDataSize(type);
     if (!datasize) {