diff --git a/llvm/include/llvm/IR/IntrinsicsAMDGPU.td b/llvm/include/llvm/IR/IntrinsicsAMDGPU.td
--- a/llvm/include/llvm/IR/IntrinsicsAMDGPU.td
+++ b/llvm/include/llvm/IR/IntrinsicsAMDGPU.td
@@ -2364,6 +2364,8 @@
 def int_amdgcn_wmma_f32_16x16x16_bf16  : AMDGPUWmmaIntrinsic<llvm_v16i16_ty, llvm_anyfloat_ty>;
 def int_amdgcn_wmma_f16_16x16x16_f16   : AMDGPUWmmaIntrinsicOPSEL<llvm_v16f16_ty, llvm_anyfloat_ty>;
 def int_amdgcn_wmma_bf16_16x16x16_bf16 : AMDGPUWmmaIntrinsicOPSEL<llvm_v16i16_ty, llvm_anyint_ty>;
+def int_amdgcn_wmma_tied_f16_16x16x16_f16   : AMDGPUWmmaIntrinsicOPSEL<llvm_v16f16_ty, llvm_anyfloat_ty>;
+def int_amdgcn_wmma_tied_bf16_16x16x16_bf16 : AMDGPUWmmaIntrinsicOPSEL<llvm_v16i16_ty, llvm_anyint_ty>;
 def int_amdgcn_wmma_i32_16x16x16_iu8   : AMDGPUWmmaIntrinsicIU<llvm_v4i32_ty, llvm_anyint_ty>;
 def int_amdgcn_wmma_i32_16x16x16_iu4   : AMDGPUWmmaIntrinsicIU<llvm_v2i32_ty, llvm_anyint_ty>;
 
diff --git a/llvm/lib/Target/AMDGPU/AMDGPURegisterBankInfo.cpp b/llvm/lib/Target/AMDGPU/AMDGPURegisterBankInfo.cpp
--- a/llvm/lib/Target/AMDGPU/AMDGPURegisterBankInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/AMDGPURegisterBankInfo.cpp
@@ -4252,6 +4252,8 @@
     case Intrinsic::amdgcn_sudot8:
     case Intrinsic::amdgcn_wmma_bf16_16x16x16_bf16:
     case Intrinsic::amdgcn_wmma_f16_16x16x16_f16:
+    case Intrinsic::amdgcn_wmma_tied_bf16_16x16x16_bf16:
+    case Intrinsic::amdgcn_wmma_tied_f16_16x16x16_f16:
     case Intrinsic::amdgcn_wmma_f32_16x16x16_bf16:
     case Intrinsic::amdgcn_wmma_f32_16x16x16_f16:
     case Intrinsic::amdgcn_wmma_i32_16x16x16_iu4:
diff --git a/llvm/lib/Target/AMDGPU/VOP3PInstructions.td b/llvm/lib/Target/AMDGPU/VOP3PInstructions.td
--- a/llvm/lib/Target/AMDGPU/VOP3PInstructions.td
+++ b/llvm/lib/Target/AMDGPU/VOP3PInstructions.td
@@ -865,35 +865,26 @@
 //    it converts the default pseudo to the pseudo where src2 is not the same as vdst.
 // 3) @earlyclobber on the destination satisfies the constraint during RA.
 
-multiclass WMMAInst<string Suffix, string Instr, VOPProfile P, SDPatternOperator node = null_frag, RegisterOperand _Src01RC64 = VRegSrc_256, WMMAType Type> {
+multiclass WMMAInst<string Suffix, string Instr, VOPProfile P, SDPatternOperator node = null_frag, RegisterOperand _Src01RC64 = VRegSrc_256, WMMAType Type, bit convertibleTo3Addr> {
 
   defvar WMMAConstraints2Addr = "@earlyclobber $vdst,$vdst = $src2";
   defvar WMMAConstraints3Addr = "@earlyclobber $vdst";
 
   defvar WMMAProfile = VOPProfileWMMA<P, Suffix, _Src01RC64, Type.hasClamp, Type.hasOpsel>;
-  if !eq(Suffix, "_w32") then {
     let Mnemonic = Instr, mayRaiseFPException = 0, ReadsModeReg = 0 in {
-      let Constraints = WMMAConstraints2Addr, isConvertibleToThreeAddress = 1 in {
-        def _twoaddr_w32 : VOP3P_Pseudo<Instr # Suffix, WMMAProfile>;
-      }
-      let Constraints = WMMAConstraints3Addr, SchedRW = [Write32Bit, Write32Bit] in {
-        def _threeaddr_w32 : VOP3P_Pseudo<Instr # Suffix, WMMAProfile>;
+      let Constraints = WMMAConstraints2Addr, isConvertibleToThreeAddress = convertibleTo3Addr in {
+        def _twoaddr # Suffix : VOP3P_Pseudo<Instr # Suffix, WMMAProfile>;
       }
     }
-    def : WMMAOpcodeMapping<!cast<Instruction>(NAME # _twoaddr_w32),
-                            !cast<Instruction>(NAME # _threeaddr_w32)>;
-  } else if !eq(Suffix, "_w64") then {
-    let Mnemonic = Instr, mayRaiseFPException = 0, ReadsModeReg = 0 in {
-      let Constraints = WMMAConstraints2Addr, isConvertibleToThreeAddress = 1 in {
-        def _twoaddr_w64 : VOP3P_Pseudo<Instr # Suffix, WMMAProfile>;
-      }
-      let Constraints = WMMAConstraints3Addr, SchedRW = [Write32Bit, Write32Bit] in {
-        def _threeaddr_w64 : VOP3P_Pseudo<Instr # Suffix, WMMAProfile>;
+    if !eq(convertibleTo3Addr, 1) then {
+      let Mnemonic = Instr, mayRaiseFPException = 0, ReadsModeReg = 0 in {
+        let Constraints = WMMAConstraints3Addr, SchedRW = [Write32Bit, Write32Bit] in {
+          def _threeaddr # Suffix : VOP3P_Pseudo<Instr # Suffix, WMMAProfile>;
+        }
       }
+      def : WMMAOpcodeMapping<!cast<Instruction>(NAME # _twoaddr # Suffix),
+                            !cast<Instruction>(NAME # _threeaddr # Suffix)>;
     }
-    def : WMMAOpcodeMapping<!cast<Instruction>(NAME # _twoaddr_w64),
-                            !cast<Instruction>(NAME # _threeaddr_w64)>;
-  }
 
   if !eq(Type, WMMAOpSel) then {
     def : WMMAOpSelPat<!cast<Instruction>(NAME # _twoaddr # Suffix), node, P>;
@@ -906,21 +897,25 @@
 
 
 let WaveSizePredicate = isWave32 in {
-  defm V_WMMA_F32_16X16X16_F16   : WMMAInst<"_w32", "v_wmma_f32_16x16x16_f16",  VOP_V8F32_V16F16_V16F16_V8F32, int_amdgcn_wmma_f32_16x16x16_f16, VRegSrc_256, WMMARegular>;
-  defm V_WMMA_F32_16X16X16_BF16  : WMMAInst<"_w32", "v_wmma_f32_16x16x16_bf16", VOP_V8F32_V16I16_V16I16_V8F32, int_amdgcn_wmma_f32_16x16x16_bf16, VRegSrc_256, WMMARegular>;
-  defm V_WMMA_F16_16X16X16_F16   : WMMAInst<"_w32", "v_wmma_f16_16x16x16_f16",   VOP_V16F16_V16F16_V16F16_V16F16, int_amdgcn_wmma_f16_16x16x16_f16, VRegSrc_256, WMMAOpSel>;
-  defm V_WMMA_BF16_16X16X16_BF16 : WMMAInst<"_w32", "v_wmma_bf16_16x16x16_bf16", VOP_V16I16_V16I16_V16I16_V16I16, int_amdgcn_wmma_bf16_16x16x16_bf16, VRegSrc_256, WMMAOpSel>;
-  defm V_WMMA_I32_16X16X16_IU8   : WMMAInst<"_w32", "v_wmma_i32_16x16x16_iu8",   VOP_V8I32_V4I32_V4I32_V8I32, int_amdgcn_wmma_i32_16x16x16_iu8, VRegSrc_128, WMMAUIClamp>;
-  defm V_WMMA_I32_16X16X16_IU4   : WMMAInst<"_w32", "v_wmma_i32_16x16x16_iu4",   VOP_V8I32_V2I32_V2I32_V8I32, int_amdgcn_wmma_i32_16x16x16_iu4, VRegSrc_64,  WMMAUIClamp>;
+  defm V_WMMA_F32_16X16X16_F16   : WMMAInst<"_w32", "v_wmma_f32_16x16x16_f16",  VOP_V8F32_V16F16_V16F16_V8F32, int_amdgcn_wmma_f32_16x16x16_f16, VRegSrc_256, WMMARegular, 1>;
+  defm V_WMMA_F32_16X16X16_BF16  : WMMAInst<"_w32", "v_wmma_f32_16x16x16_bf16", VOP_V8F32_V16I16_V16I16_V8F32, int_amdgcn_wmma_f32_16x16x16_bf16, VRegSrc_256, WMMARegular, 1>;
+  defm V_WMMA_F16_16X16X16_F16   : WMMAInst<"_w32", "v_wmma_f16_16x16x16_f16",   VOP_V16F16_V16F16_V16F16_V16F16, int_amdgcn_wmma_f16_16x16x16_f16, VRegSrc_256, WMMAOpSel, 1>;
+  defm V_WMMA_BF16_16X16X16_BF16 : WMMAInst<"_w32", "v_wmma_bf16_16x16x16_bf16", VOP_V16I16_V16I16_V16I16_V16I16, int_amdgcn_wmma_bf16_16x16x16_bf16, VRegSrc_256, WMMAOpSel, 1>;
+  defm V_WMMA_TIED_F16_16X16X16_F16   : WMMAInst<"_w32", "v_wmma_f16_16x16x16_f16",   VOP_V16F16_V16F16_V16F16_V16F16, int_amdgcn_wmma_tied_f16_16x16x16_f16, VRegSrc_256, WMMAOpSel, 0>;
+  defm V_WMMA_TIED_BF16_16X16X16_BF16 : WMMAInst<"_w32", "v_wmma_bf16_16x16x16_bf16", VOP_V16I16_V16I16_V16I16_V16I16, int_amdgcn_wmma_tied_bf16_16x16x16_bf16, VRegSrc_256, WMMAOpSel, 0>;
+  defm V_WMMA_I32_16X16X16_IU8   : WMMAInst<"_w32", "v_wmma_i32_16x16x16_iu8",   VOP_V8I32_V4I32_V4I32_V8I32, int_amdgcn_wmma_i32_16x16x16_iu8, VRegSrc_128, WMMAUIClamp, 1>;
+  defm V_WMMA_I32_16X16X16_IU4   : WMMAInst<"_w32", "v_wmma_i32_16x16x16_iu4",   VOP_V8I32_V2I32_V2I32_V8I32, int_amdgcn_wmma_i32_16x16x16_iu4, VRegSrc_64,  WMMAUIClamp, 1>;
 }
 
 let WaveSizePredicate = isWave64 in {
-  defm V_WMMA_F32_16X16X16_F16   : WMMAInst<"_w64", "v_wmma_f32_16x16x16_f16",   VOP_V4F32_V16F16_V16F16_V4F32, int_amdgcn_wmma_f32_16x16x16_f16, VRegSrc_256, WMMARegular>;
-  defm V_WMMA_F32_16X16X16_BF16  : WMMAInst<"_w64", "v_wmma_f32_16x16x16_bf16",  VOP_V4F32_V16I16_V16I16_V4F32, int_amdgcn_wmma_f32_16x16x16_bf16, VRegSrc_256, WMMARegular>;
-  defm V_WMMA_F16_16X16X16_F16   : WMMAInst<"_w64", "v_wmma_f16_16x16x16_f16",   VOP_V8F16_V16F16_V16F16_V8F16, int_amdgcn_wmma_f16_16x16x16_f16, VRegSrc_256, WMMAOpSel>;
-  defm V_WMMA_BF16_16X16X16_BF16 : WMMAInst<"_w64", "v_wmma_bf16_16x16x16_bf16", VOP_V8I16_V16I16_V16I16_V8I16, int_amdgcn_wmma_bf16_16x16x16_bf16, VRegSrc_256, WMMAOpSel>;
-  defm V_WMMA_I32_16X16X16_IU8   : WMMAInst<"_w64", "v_wmma_i32_16x16x16_iu8",   VOP_V4I32_V4I32_V4I32_V4I32, int_amdgcn_wmma_i32_16x16x16_iu8, VRegSrc_128, WMMAUIClamp>;
-  defm V_WMMA_I32_16X16X16_IU4   : WMMAInst<"_w64", "v_wmma_i32_16x16x16_iu4",   VOP_V4I32_V2I32_V2I32_V4I32, int_amdgcn_wmma_i32_16x16x16_iu4, VRegSrc_64, WMMAUIClamp>;
+  defm V_WMMA_F32_16X16X16_F16   : WMMAInst<"_w64", "v_wmma_f32_16x16x16_f16",   VOP_V4F32_V16F16_V16F16_V4F32, int_amdgcn_wmma_f32_16x16x16_f16, VRegSrc_256, WMMARegular, 1>;
+  defm V_WMMA_F32_16X16X16_BF16  : WMMAInst<"_w64", "v_wmma_f32_16x16x16_bf16",  VOP_V4F32_V16I16_V16I16_V4F32, int_amdgcn_wmma_f32_16x16x16_bf16, VRegSrc_256, WMMARegular, 1>;
+  defm V_WMMA_F16_16X16X16_F16   : WMMAInst<"_w64", "v_wmma_f16_16x16x16_f16",   VOP_V8F16_V16F16_V16F16_V8F16, int_amdgcn_wmma_f16_16x16x16_f16, VRegSrc_256, WMMAOpSel, 1>;
+  defm V_WMMA_BF16_16X16X16_BF16 : WMMAInst<"_w64", "v_wmma_bf16_16x16x16_bf16", VOP_V8I16_V16I16_V16I16_V8I16, int_amdgcn_wmma_bf16_16x16x16_bf16, VRegSrc_256, WMMAOpSel, 1>;
+  defm V_WMMA_TIED_F16_16X16X16_F16   : WMMAInst<"_w64", "v_wmma_f16_16x16x16_f16",   VOP_V8F16_V16F16_V16F16_V8F16, int_amdgcn_wmma_tied_f16_16x16x16_f16, VRegSrc_256, WMMAOpSel, 0>;
+  defm V_WMMA_TIED_BF16_16X16X16_BF16 : WMMAInst<"_w64", "v_wmma_bf16_16x16x16_bf16", VOP_V8I16_V16I16_V16I16_V8I16, int_amdgcn_wmma_tied_bf16_16x16x16_bf16, VRegSrc_256, WMMAOpSel, 0>;
+  defm V_WMMA_I32_16X16X16_IU8   : WMMAInst<"_w64", "v_wmma_i32_16x16x16_iu8",   VOP_V4I32_V4I32_V4I32_V4I32, int_amdgcn_wmma_i32_16x16x16_iu8, VRegSrc_128, WMMAUIClamp, 1>;
+  defm V_WMMA_I32_16X16X16_IU4   : WMMAInst<"_w64", "v_wmma_i32_16x16x16_iu4",   VOP_V4I32_V2I32_V2I32_V4I32, int_amdgcn_wmma_i32_16x16x16_iu4, VRegSrc_64, WMMAUIClamp, 1>;
 
 }