[Auto-gen] Update bfloat16 documents under ../auto-generated. (make g…

…it-commit-autogen-bf16-doc)

auto-generated/bfloat16/intrinsic_funcs.adoc

@@ -1543,6 +1543,46 @@ vfloat32m8_t __riscv_vfwmaccbf16_vf_f32m8_rm_m(vbool4_t vm, vfloat32m8_t vd,
                                                unsigned int frm, size_t vl);
 ----
 
+[[vector-bf16-move]]
+==== Vector BFloat16 Move Intrinsics
+
+[,c]
+----
+vbfloat16mf4_t __riscv_vmv_v_v_bf16mf4(vbfloat16mf4_t vs1, size_t vl);
+vbfloat16mf4_t __riscv_vfmv_v_f_bf16mf4(__bf16 rs1, size_t vl);
+vbfloat16mf2_t __riscv_vmv_v_v_bf16mf2(vbfloat16mf2_t vs1, size_t vl);
+vbfloat16mf2_t __riscv_vfmv_v_f_bf16mf2(__bf16 rs1, size_t vl);
+vbfloat16m1_t __riscv_vmv_v_v_bf16m1(vbfloat16m1_t vs1, size_t vl);
+vbfloat16m1_t __riscv_vfmv_v_f_bf16m1(__bf16 rs1, size_t vl);
+vbfloat16m2_t __riscv_vmv_v_v_bf16m2(vbfloat16m2_t vs1, size_t vl);
+vbfloat16m2_t __riscv_vfmv_v_f_bf16m2(__bf16 rs1, size_t vl);
+vbfloat16m4_t __riscv_vmv_v_v_bf16m4(vbfloat16m4_t vs1, size_t vl);
+vbfloat16m4_t __riscv_vfmv_v_f_bf16m4(__bf16 rs1, size_t vl);
+vbfloat16m8_t __riscv_vmv_v_v_bf16m8(vbfloat16m8_t vs1, size_t vl);
+vbfloat16m8_t __riscv_vfmv_v_f_bf16m8(__bf16 rs1, size_t vl);
+----
+
+[[vector-bf16-merge]]
+==== Vector BFloat16 Merge Intrinsics
+
+[,c]
+----
+vbfloat16mf4_t __riscv_vmerge_vvm_bf16mf4(vbfloat16mf4_t vs2,
+                                          vbfloat16mf4_t vs1, vbool64_t v0,
+                                          size_t vl);
+vbfloat16mf2_t __riscv_vmerge_vvm_bf16mf2(vbfloat16mf2_t vs2,
+                                          vbfloat16mf2_t vs1, vbool32_t v0,
+                                          size_t vl);
+vbfloat16m1_t __riscv_vmerge_vvm_bf16m1(vbfloat16m1_t vs2, vbfloat16m1_t vs1,
+                                        vbool16_t v0, size_t vl);
+vbfloat16m2_t __riscv_vmerge_vvm_bf16m2(vbfloat16m2_t vs2, vbfloat16m2_t vs1,
+                                        vbool8_t v0, size_t vl);
+vbfloat16m4_t __riscv_vmerge_vvm_bf16m4(vbfloat16m4_t vs2, vbfloat16m4_t vs1,
+                                        vbool4_t v0, size_t vl);
+vbfloat16m8_t __riscv_vmerge_vvm_bf16m8(vbfloat16m8_t vs2, vbfloat16m8_t vs1,
+                                        vbool2_t v0, size_t vl);
+----
+
 === BFloat16 Miscellaneous Vector Utility Intrinsics
 
 [[reinterpret-cast-conversion]]

auto-generated/bfloat16/intrinsic_funcs/03_bfloat16_arithmetic_intrinsics.adoc

@@ -127,3 +127,43 @@ vfloat32m8_t __riscv_vfwmaccbf16_vf_f32m8_rm_m(vbool4_t vm, vfloat32m8_t vd,
                                                __bf16 vs1, vbfloat16m4_t vs2,
                                                unsigned int frm, size_t vl);
 ----
+
+[[vector-bf16-move]]
+==== Vector BFloat16 Move Intrinsics
+
+[,c]
+----
+vbfloat16mf4_t __riscv_vmv_v_v_bf16mf4(vbfloat16mf4_t vs1, size_t vl);
+vbfloat16mf4_t __riscv_vfmv_v_f_bf16mf4(__bf16 rs1, size_t vl);
+vbfloat16mf2_t __riscv_vmv_v_v_bf16mf2(vbfloat16mf2_t vs1, size_t vl);
+vbfloat16mf2_t __riscv_vfmv_v_f_bf16mf2(__bf16 rs1, size_t vl);
+vbfloat16m1_t __riscv_vmv_v_v_bf16m1(vbfloat16m1_t vs1, size_t vl);
+vbfloat16m1_t __riscv_vfmv_v_f_bf16m1(__bf16 rs1, size_t vl);
+vbfloat16m2_t __riscv_vmv_v_v_bf16m2(vbfloat16m2_t vs1, size_t vl);
+vbfloat16m2_t __riscv_vfmv_v_f_bf16m2(__bf16 rs1, size_t vl);
+vbfloat16m4_t __riscv_vmv_v_v_bf16m4(vbfloat16m4_t vs1, size_t vl);
+vbfloat16m4_t __riscv_vfmv_v_f_bf16m4(__bf16 rs1, size_t vl);
+vbfloat16m8_t __riscv_vmv_v_v_bf16m8(vbfloat16m8_t vs1, size_t vl);
+vbfloat16m8_t __riscv_vfmv_v_f_bf16m8(__bf16 rs1, size_t vl);
+----
+
+[[vector-bf16-merge]]
+==== Vector BFloat16 Merge Intrinsics
+
+[,c]
+----
+vbfloat16mf4_t __riscv_vmerge_vvm_bf16mf4(vbfloat16mf4_t vs2,
+                                          vbfloat16mf4_t vs1, vbool64_t v0,
+                                          size_t vl);
+vbfloat16mf2_t __riscv_vmerge_vvm_bf16mf2(vbfloat16mf2_t vs2,
+                                          vbfloat16mf2_t vs1, vbool32_t v0,
+                                          size_t vl);
+vbfloat16m1_t __riscv_vmerge_vvm_bf16m1(vbfloat16m1_t vs2, vbfloat16m1_t vs1,
+                                        vbool16_t v0, size_t vl);
+vbfloat16m2_t __riscv_vmerge_vvm_bf16m2(vbfloat16m2_t vs2, vbfloat16m2_t vs1,
+                                        vbool8_t v0, size_t vl);
+vbfloat16m4_t __riscv_vmerge_vvm_bf16m4(vbfloat16m4_t vs2, vbfloat16m4_t vs1,
+                                        vbool4_t v0, size_t vl);
+vbfloat16m8_t __riscv_vmerge_vvm_bf16m8(vbfloat16m8_t vs2, vbfloat16m8_t vs1,
+                                        vbool2_t v0, size_t vl);
+----

auto-generated/bfloat16/overloaded_intrinsic_funcs.adoc

@@ -1123,6 +1123,38 @@ vfloat32m8_t __riscv_vfwmaccbf16(vbool4_t vm, vfloat32m8_t vd, __bf16 vs1,
                                  size_t vl);
 ----
 
+[[overloaded-vector-bf16-move]]
+==== Vector BFloat16 Move Intrinsics
+
+[,c]
+----
+vbfloat16mf4_t __riscv_vmv_v(vbfloat16mf4_t vs1, size_t vl);
+vbfloat16mf2_t __riscv_vmv_v(vbfloat16mf2_t vs1, size_t vl);
+vbfloat16m1_t __riscv_vmv_v(vbfloat16m1_t vs1, size_t vl);
+vbfloat16m2_t __riscv_vmv_v(vbfloat16m2_t vs1, size_t vl);
+vbfloat16m4_t __riscv_vmv_v(vbfloat16m4_t vs1, size_t vl);
+vbfloat16m8_t __riscv_vmv_v(vbfloat16m8_t vs1, size_t vl);
+----
+
+[[overloaded-vector-bf16-merge]]
+==== Vector BFloat16 Merge Intrinsics
+
+[,c]
+----
+vbfloat16mf4_t __riscv_vmerge(vbfloat16mf4_t vs2, vbfloat16mf4_t vs1,
+                              vbool64_t v0, size_t vl);
+vbfloat16mf2_t __riscv_vmerge(vbfloat16mf2_t vs2, vbfloat16mf2_t vs1,
+                              vbool32_t v0, size_t vl);
+vbfloat16m1_t __riscv_vmerge(vbfloat16m1_t vs2, vbfloat16m1_t vs1, vbool16_t v0,
+                             size_t vl);
+vbfloat16m2_t __riscv_vmerge(vbfloat16m2_t vs2, vbfloat16m2_t vs1, vbool8_t v0,
+                             size_t vl);
+vbfloat16m4_t __riscv_vmerge(vbfloat16m4_t vs2, vbfloat16m4_t vs1, vbool4_t v0,
+                             size_t vl);
+vbfloat16m8_t __riscv_vmerge(vbfloat16m8_t vs2, vbfloat16m8_t vs1, vbool2_t v0,
+                             size_t vl);
+----
+
 === BFloat16 Miscellaneous Vector Utility Intrinsics
 
 [[overloaded-reinterpret-cast-conversion]]

auto-generated/bfloat16/overloaded_intrinsic_funcs/03_bfloat16_arithmetic_intrinsics.adoc

@@ -111,3 +111,35 @@ vfloat32m8_t __riscv_vfwmaccbf16(vbool4_t vm, vfloat32m8_t vd, __bf16 vs1,
                                  vbfloat16m4_t vs2, unsigned int frm,
                                  size_t vl);
 ----
+
+[[overloaded-vector-bf16-move]]
+==== Vector BFloat16 Move Intrinsics
+
+[,c]
+----
+vbfloat16mf4_t __riscv_vmv_v(vbfloat16mf4_t vs1, size_t vl);
+vbfloat16mf2_t __riscv_vmv_v(vbfloat16mf2_t vs1, size_t vl);
+vbfloat16m1_t __riscv_vmv_v(vbfloat16m1_t vs1, size_t vl);
+vbfloat16m2_t __riscv_vmv_v(vbfloat16m2_t vs1, size_t vl);
+vbfloat16m4_t __riscv_vmv_v(vbfloat16m4_t vs1, size_t vl);
+vbfloat16m8_t __riscv_vmv_v(vbfloat16m8_t vs1, size_t vl);
+----
+
+[[overloaded-vector-bf16-merge]]
+==== Vector BFloat16 Merge Intrinsics
+
+[,c]
+----
+vbfloat16mf4_t __riscv_vmerge(vbfloat16mf4_t vs2, vbfloat16mf4_t vs1,
+                              vbool64_t v0, size_t vl);
+vbfloat16mf2_t __riscv_vmerge(vbfloat16mf2_t vs2, vbfloat16mf2_t vs1,
+                              vbool32_t v0, size_t vl);
+vbfloat16m1_t __riscv_vmerge(vbfloat16m1_t vs2, vbfloat16m1_t vs1, vbool16_t v0,
+                             size_t vl);
+vbfloat16m2_t __riscv_vmerge(vbfloat16m2_t vs2, vbfloat16m2_t vs1, vbool8_t v0,
+                             size_t vl);
+vbfloat16m4_t __riscv_vmerge(vbfloat16m4_t vs2, vbfloat16m4_t vs1, vbool4_t v0,
+                             size_t vl);
+vbfloat16m8_t __riscv_vmerge(vbfloat16m8_t vs2, vbfloat16m8_t vs1, vbool2_t v0,
+                             size_t vl);
+----

auto-generated/bfloat16/policy_funcs/intrinsic_funcs.adoc

@@ -2855,6 +2855,64 @@ vfloat32m8_t __riscv_vfwmaccbf16_vf_f32m8_rm_mu(vbool4_t vm, vfloat32m8_t vd,
                                                 unsigned int frm, size_t vl);
 ----
 
+[[policy-variant-vector-bf16-move]]
+==== Vector BFloat16 Move Intrinsics
+
+[,c]
+----
+vbfloat16mf4_t __riscv_vmv_v_v_bf16mf4_tu(vbfloat16mf4_t vd, vbfloat16mf4_t vs1,
+                                          size_t vl);
+vbfloat16mf4_t __riscv_vfmv_v_f_bf16mf4_tu(vbfloat16mf4_t vd, __bf16 rs1,
+                                           size_t vl);
+vbfloat16mf2_t __riscv_vmv_v_v_bf16mf2_tu(vbfloat16mf2_t vd, vbfloat16mf2_t vs1,
+                                          size_t vl);
+vbfloat16mf2_t __riscv_vfmv_v_f_bf16mf2_tu(vbfloat16mf2_t vd, __bf16 rs1,
+                                           size_t vl);
+vbfloat16m1_t __riscv_vmv_v_v_bf16m1_tu(vbfloat16m1_t vd, vbfloat16m1_t vs1,
+                                        size_t vl);
+vbfloat16m1_t __riscv_vfmv_v_f_bf16m1_tu(vbfloat16m1_t vd, __bf16 rs1,
+                                         size_t vl);
+vbfloat16m2_t __riscv_vmv_v_v_bf16m2_tu(vbfloat16m2_t vd, vbfloat16m2_t vs1,
+                                        size_t vl);
+vbfloat16m2_t __riscv_vfmv_v_f_bf16m2_tu(vbfloat16m2_t vd, __bf16 rs1,
+                                         size_t vl);
+vbfloat16m4_t __riscv_vmv_v_v_bf16m4_tu(vbfloat16m4_t vd, vbfloat16m4_t vs1,
+                                        size_t vl);
+vbfloat16m4_t __riscv_vfmv_v_f_bf16m4_tu(vbfloat16m4_t vd, __bf16 rs1,
+                                         size_t vl);
+vbfloat16m8_t __riscv_vmv_v_v_bf16m8_tu(vbfloat16m8_t vd, vbfloat16m8_t vs1,
+                                        size_t vl);
+vbfloat16m8_t __riscv_vfmv_v_f_bf16m8_tu(vbfloat16m8_t vd, __bf16 rs1,
+                                         size_t vl);
+----
+
+[[policy-variant-vector-bf16-merge]]
+==== Vector BFloat16 Merge Intrinsics
+
+[,c]
+----
+vbfloat16mf4_t __riscv_vmerge_vvm_bf16mf4_tu(vbfloat16mf4_t vd,
+                                             vbfloat16mf4_t vs2,
+                                             vbfloat16mf4_t vs1, vbool64_t v0,
+                                             size_t vl);
+vbfloat16mf2_t __riscv_vmerge_vvm_bf16mf2_tu(vbfloat16mf2_t vd,
+                                             vbfloat16mf2_t vs2,
+                                             vbfloat16mf2_t vs1, vbool32_t v0,
+                                             size_t vl);
+vbfloat16m1_t __riscv_vmerge_vvm_bf16m1_tu(vbfloat16m1_t vd, vbfloat16m1_t vs2,
+                                           vbfloat16m1_t vs1, vbool16_t v0,
+                                           size_t vl);
+vbfloat16m2_t __riscv_vmerge_vvm_bf16m2_tu(vbfloat16m2_t vd, vbfloat16m2_t vs2,
+                                           vbfloat16m2_t vs1, vbool8_t v0,
+                                           size_t vl);
+vbfloat16m4_t __riscv_vmerge_vvm_bf16m4_tu(vbfloat16m4_t vd, vbfloat16m4_t vs2,
+                                           vbfloat16m4_t vs1, vbool4_t v0,
+                                           size_t vl);
+vbfloat16m8_t __riscv_vmerge_vvm_bf16m8_tu(vbfloat16m8_t vd, vbfloat16m8_t vs2,
+                                           vbfloat16m8_t vs1, vbool2_t v0,
+                                           size_t vl);
+----
+
 === BFloat16 Miscellaneous Vector Utility Intrinsics
 
 [[policy-variant-reinterpret-cast-conversion]]

auto-generated/bfloat16/policy_funcs/intrinsic_funcs/03_bfloat16_arithmetic_intrinsics.adoc

@@ -271,3 +271,61 @@ vfloat32m8_t __riscv_vfwmaccbf16_vf_f32m8_rm_mu(vbool4_t vm, vfloat32m8_t vd,
                                                 __bf16 vs1, vbfloat16m4_t vs2,
                                                 unsigned int frm, size_t vl);
 ----
+
+[[policy-variant-vector-bf16-move]]
+==== Vector BFloat16 Move Intrinsics
+
+[,c]
+----
+vbfloat16mf4_t __riscv_vmv_v_v_bf16mf4_tu(vbfloat16mf4_t vd, vbfloat16mf4_t vs1,
+                                          size_t vl);
+vbfloat16mf4_t __riscv_vfmv_v_f_bf16mf4_tu(vbfloat16mf4_t vd, __bf16 rs1,
+                                           size_t vl);
+vbfloat16mf2_t __riscv_vmv_v_v_bf16mf2_tu(vbfloat16mf2_t vd, vbfloat16mf2_t vs1,
+                                          size_t vl);
+vbfloat16mf2_t __riscv_vfmv_v_f_bf16mf2_tu(vbfloat16mf2_t vd, __bf16 rs1,
+                                           size_t vl);
+vbfloat16m1_t __riscv_vmv_v_v_bf16m1_tu(vbfloat16m1_t vd, vbfloat16m1_t vs1,
+                                        size_t vl);
+vbfloat16m1_t __riscv_vfmv_v_f_bf16m1_tu(vbfloat16m1_t vd, __bf16 rs1,
+                                         size_t vl);
+vbfloat16m2_t __riscv_vmv_v_v_bf16m2_tu(vbfloat16m2_t vd, vbfloat16m2_t vs1,
+                                        size_t vl);
+vbfloat16m2_t __riscv_vfmv_v_f_bf16m2_tu(vbfloat16m2_t vd, __bf16 rs1,
+                                         size_t vl);
+vbfloat16m4_t __riscv_vmv_v_v_bf16m4_tu(vbfloat16m4_t vd, vbfloat16m4_t vs1,
+                                        size_t vl);
+vbfloat16m4_t __riscv_vfmv_v_f_bf16m4_tu(vbfloat16m4_t vd, __bf16 rs1,
+                                         size_t vl);
+vbfloat16m8_t __riscv_vmv_v_v_bf16m8_tu(vbfloat16m8_t vd, vbfloat16m8_t vs1,
+                                        size_t vl);
+vbfloat16m8_t __riscv_vfmv_v_f_bf16m8_tu(vbfloat16m8_t vd, __bf16 rs1,
+                                         size_t vl);
+----
+
+[[policy-variant-vector-bf16-merge]]
+==== Vector BFloat16 Merge Intrinsics
+
+[,c]
+----
+vbfloat16mf4_t __riscv_vmerge_vvm_bf16mf4_tu(vbfloat16mf4_t vd,
+                                             vbfloat16mf4_t vs2,
+                                             vbfloat16mf4_t vs1, vbool64_t v0,
+                                             size_t vl);
+vbfloat16mf2_t __riscv_vmerge_vvm_bf16mf2_tu(vbfloat16mf2_t vd,
+                                             vbfloat16mf2_t vs2,
+                                             vbfloat16mf2_t vs1, vbool32_t v0,
+                                             size_t vl);
+vbfloat16m1_t __riscv_vmerge_vvm_bf16m1_tu(vbfloat16m1_t vd, vbfloat16m1_t vs2,
+                                           vbfloat16m1_t vs1, vbool16_t v0,
+                                           size_t vl);
+vbfloat16m2_t __riscv_vmerge_vvm_bf16m2_tu(vbfloat16m2_t vd, vbfloat16m2_t vs2,
+                                           vbfloat16m2_t vs1, vbool8_t v0,
+                                           size_t vl);
+vbfloat16m4_t __riscv_vmerge_vvm_bf16m4_tu(vbfloat16m4_t vd, vbfloat16m4_t vs2,
+                                           vbfloat16m4_t vs1, vbool4_t v0,
+                                           size_t vl);
+vbfloat16m8_t __riscv_vmerge_vvm_bf16m8_tu(vbfloat16m8_t vd, vbfloat16m8_t vs2,
+                                           vbfloat16m8_t vs1, vbool2_t v0,
+                                           size_t vl);
+----

auto-generated/bfloat16/policy_funcs/overloaded_intrinsic_funcs.adoc

@@ -2069,6 +2069,46 @@ vfloat32m8_t __riscv_vfwmaccbf16_mu(vbool4_t vm, vfloat32m8_t vd, __bf16 vs1,
                                     size_t vl);
 ----
 
+[[policy-variant-overloadedvector-bf16-move]]
+==== Vector BFloat16 Move Intrinsics
+
+[,c]
+----
+vbfloat16mf4_t __riscv_vmv_v_tu(vbfloat16mf4_t vd, vbfloat16mf4_t vs1,
+                                size_t vl);
+vbfloat16mf4_t __riscv_vfmv_v_tu(vbfloat16mf4_t vd, __bf16 rs1, size_t vl);
+vbfloat16mf2_t __riscv_vmv_v_tu(vbfloat16mf2_t vd, vbfloat16mf2_t vs1,
+                                size_t vl);
+vbfloat16mf2_t __riscv_vfmv_v_tu(vbfloat16mf2_t vd, __bf16 rs1, size_t vl);
+vbfloat16m1_t __riscv_vmv_v_tu(vbfloat16m1_t vd, vbfloat16m1_t vs1, size_t vl);
+vbfloat16m1_t __riscv_vfmv_v_tu(vbfloat16m1_t vd, __bf16 rs1, size_t vl);
+vbfloat16m2_t __riscv_vmv_v_tu(vbfloat16m2_t vd, vbfloat16m2_t vs1, size_t vl);
+vbfloat16m2_t __riscv_vfmv_v_tu(vbfloat16m2_t vd, __bf16 rs1, size_t vl);
+vbfloat16m4_t __riscv_vmv_v_tu(vbfloat16m4_t vd, vbfloat16m4_t vs1, size_t vl);
+vbfloat16m4_t __riscv_vfmv_v_tu(vbfloat16m4_t vd, __bf16 rs1, size_t vl);
+vbfloat16m8_t __riscv_vmv_v_tu(vbfloat16m8_t vd, vbfloat16m8_t vs1, size_t vl);
+vbfloat16m8_t __riscv_vfmv_v_tu(vbfloat16m8_t vd, __bf16 rs1, size_t vl);
+----
+
+[[policy-variant-overloadedvector-bf16-merge]]
+==== Vector BFloat16 Merge Intrinsics
+
+[,c]
+----
+vbfloat16mf4_t __riscv_vmerge_tu(vbfloat16mf4_t vd, vbfloat16mf4_t vs2,
+                                 vbfloat16mf4_t vs1, vbool64_t v0, size_t vl);
+vbfloat16mf2_t __riscv_vmerge_tu(vbfloat16mf2_t vd, vbfloat16mf2_t vs2,
+                                 vbfloat16mf2_t vs1, vbool32_t v0, size_t vl);
+vbfloat16m1_t __riscv_vmerge_tu(vbfloat16m1_t vd, vbfloat16m1_t vs2,
+                                vbfloat16m1_t vs1, vbool16_t v0, size_t vl);
+vbfloat16m2_t __riscv_vmerge_tu(vbfloat16m2_t vd, vbfloat16m2_t vs2,
+                                vbfloat16m2_t vs1, vbool8_t v0, size_t vl);
+vbfloat16m4_t __riscv_vmerge_tu(vbfloat16m4_t vd, vbfloat16m4_t vs2,
+                                vbfloat16m4_t vs1, vbool4_t v0, size_t vl);
+vbfloat16m8_t __riscv_vmerge_tu(vbfloat16m8_t vd, vbfloat16m8_t vs2,
+                                vbfloat16m8_t vs1, vbool2_t v0, size_t vl);
+----
+
 === BFloat16 Miscellaneous Vector Utility Intrinsics
 
 [[policy-variant-overloadedreinterpret-cast-conversion]]

auto-generated/bfloat16/policy_funcs/overloaded_intrinsic_funcs/03_bfloat16_arithmetic_intrinsics.adoc

@@ -230,3 +230,43 @@ vfloat32m8_t __riscv_vfwmaccbf16_mu(vbool4_t vm, vfloat32m8_t vd, __bf16 vs1,
                                     vbfloat16m4_t vs2, unsigned int frm,
                                     size_t vl);
 ----
+
+[[policy-variant-overloadedvector-bf16-move]]
+==== Vector BFloat16 Move Intrinsics
+
+[,c]
+----
+vbfloat16mf4_t __riscv_vmv_v_tu(vbfloat16mf4_t vd, vbfloat16mf4_t vs1,
+                                size_t vl);
+vbfloat16mf4_t __riscv_vfmv_v_tu(vbfloat16mf4_t vd, __bf16 rs1, size_t vl);
+vbfloat16mf2_t __riscv_vmv_v_tu(vbfloat16mf2_t vd, vbfloat16mf2_t vs1,
+                                size_t vl);
+vbfloat16mf2_t __riscv_vfmv_v_tu(vbfloat16mf2_t vd, __bf16 rs1, size_t vl);
+vbfloat16m1_t __riscv_vmv_v_tu(vbfloat16m1_t vd, vbfloat16m1_t vs1, size_t vl);
+vbfloat16m1_t __riscv_vfmv_v_tu(vbfloat16m1_t vd, __bf16 rs1, size_t vl);
+vbfloat16m2_t __riscv_vmv_v_tu(vbfloat16m2_t vd, vbfloat16m2_t vs1, size_t vl);
+vbfloat16m2_t __riscv_vfmv_v_tu(vbfloat16m2_t vd, __bf16 rs1, size_t vl);
+vbfloat16m4_t __riscv_vmv_v_tu(vbfloat16m4_t vd, vbfloat16m4_t vs1, size_t vl);
+vbfloat16m4_t __riscv_vfmv_v_tu(vbfloat16m4_t vd, __bf16 rs1, size_t vl);
+vbfloat16m8_t __riscv_vmv_v_tu(vbfloat16m8_t vd, vbfloat16m8_t vs1, size_t vl);
+vbfloat16m8_t __riscv_vfmv_v_tu(vbfloat16m8_t vd, __bf16 rs1, size_t vl);
+----
+
+[[policy-variant-overloadedvector-bf16-merge]]
+==== Vector BFloat16 Merge Intrinsics
+
+[,c]
+----
+vbfloat16mf4_t __riscv_vmerge_tu(vbfloat16mf4_t vd, vbfloat16mf4_t vs2,
+                                 vbfloat16mf4_t vs1, vbool64_t v0, size_t vl);
+vbfloat16mf2_t __riscv_vmerge_tu(vbfloat16mf2_t vd, vbfloat16mf2_t vs2,
+                                 vbfloat16mf2_t vs1, vbool32_t v0, size_t vl);
+vbfloat16m1_t __riscv_vmerge_tu(vbfloat16m1_t vd, vbfloat16m1_t vs2,
+                                vbfloat16m1_t vs1, vbool16_t v0, size_t vl);
+vbfloat16m2_t __riscv_vmerge_tu(vbfloat16m2_t vd, vbfloat16m2_t vs2,
+                                vbfloat16m2_t vs1, vbool8_t v0, size_t vl);
+vbfloat16m4_t __riscv_vmerge_tu(vbfloat16m4_t vd, vbfloat16m4_t vs2,
+                                vbfloat16m4_t vs1, vbool4_t v0, size_t vl);
+vbfloat16m8_t __riscv_vmerge_tu(vbfloat16m8_t vd, vbfloat16m8_t vs2,
+                                vbfloat16m8_t vs1, vbool2_t v0, size_t vl);
+----