shader: support V_CMPX_GT_U16 SDWA

src/graphics/shader/recompiler/frontend/decode/ShaderDecoder.h

@@ -378,6 +378,7 @@ enum class Opcode {
 	V_CMP_EQ_U16,
 	V_CMP_LE_U16,
 	V_CMP_GT_U16,
+	V_CMPX_GT_U16,
 	V_CMP_NE_U16,
 	V_CMP_GE_U16,
 	V_CMP_F_U32,

src/graphics/shader/recompiler/frontend/decode/VectorAluOps.cpp

@@ -224,7 +224,8 @@ constexpr VopcOpcodeInfo VOPC_OPCODE_LIST[] = {
     {0x96u, Opcode::V_CMPX_GE_I32},       {0xa9u, Opcode::V_CMP_LT_U16},
     {0xaau, Opcode::V_CMP_EQ_U16},        {0xabu, Opcode::V_CMP_LE_U16},
     {0xacu, Opcode::V_CMP_GT_U16},        {0xadu, Opcode::V_CMP_NE_U16},
-    {0xaeu, Opcode::V_CMP_GE_U16},        {0xc0u, Opcode::V_CMP_F_U32},
+    {0xaeu, Opcode::V_CMP_GE_U16},        {0xbcu, Opcode::V_CMPX_GT_U16},
+    {0xc0u, Opcode::V_CMP_F_U32},
     {0xc1u, Opcode::V_CMP_LT_U32},        {0xc2u, Opcode::V_CMP_EQ_U32},
     {0xc3u, Opcode::V_CMP_LE_U32},        {0xc4u, Opcode::V_CMP_GT_U32},
     {0xc5u, Opcode::V_CMP_NE_U32},        {0xc6u, Opcode::V_CMP_GE_U32},
@@ -1506,6 +1507,7 @@ bool IsVopcCompareExec(Opcode opcode) {
 		case Opcode::V_CMPX_GE_U32:
 		case Opcode::V_CMPX_NE_I64:
 		case Opcode::V_CMPX_NE_U64:
+		case Opcode::V_CMPX_GT_U16:
 		case Opcode::V_CMPX_LT_F16:
 		case Opcode::V_CMPX_EQ_F16:
 		case Opcode::V_CMPX_LE_F16:

src/graphics/shader/recompiler/frontend/translate/Vector.cpp

@@ -124,6 +124,9 @@ bool Translator::EmitVector(const Decoder::Instruction& inst, std::string* error
 		case O::V_CMP_GT_U16:
 			EmitInteger16Compare(inst, IR::ValueOpcode::UGreaterThan32, false, false);
 			return true;
+		case O::V_CMPX_GT_U16:
+			EmitInteger16Compare(inst, IR::ValueOpcode::UGreaterThan32, false, true);
+			return true;
 		case O::V_CMP_GE_U16:
 			EmitInteger16Compare(inst, IR::ValueOpcode::UGreaterThanEqual32, false, false);
 			return true;

tests/ShaderRecompilerComputeTests.cpp

@@ -15746,6 +15746,32 @@ TestCase VectorVopcSdwaCmpxWritesExecMask() {
           {O::V_MOV_B32, O::V_CMPX_LT_U32, O::BUFFER_STORE_DWORD, O::S_ENDPGM}};
 }
 
+TestCase VectorVopcCmpxGtU16CapturedSdwaExecMask() {
+  using O = ShaderOpcode;
+
+  std::vector<u32> code;
+  AppendVMovU32(&code, 2, 0x00008000u);
+  AppendVMovU32(&code, 3, 7);
+  AppendVMovU32(&code, 31, 0);
+  code.insert(code.end(), {0x7d7900f9u, 0x86060002u});
+  AppendBufferStoreDword(&code, 3, 31);
+  AppendVMovU32(&code, 2, 0x00010000u);
+  AppendVMovU32(&code, 3, 9);
+  AppendVMovU32(&code, 31, 4);
+  code.insert(code.end(), {0x7d7900f9u, 0x86060002u});
+  AppendBufferStoreDword(&code, 3, 31);
+  AppendEnd(&code);
+
+  TestCase test{"VectorVopcCmpxGtU16CapturedSdwaExecMask",
+                code,
+                {0x11111111u, 0x22222222u},
+                {7, 0x22222222u},
+                {O::V_MOV_B32, O::V_CMPX_GT_U16, O::BUFFER_STORE_DWORD,
+                 O::S_ENDPGM}};
+  test.decoded_counts = {{"V_CMPX_GT_U16", 2}};
+  return test;
+}
+
 TestCase VectorCompareInvertedMaskSelect() {
   using O = ShaderOpcode;
 
@@ -20270,6 +20296,7 @@ std::vector<TestCase> MakeCases() {
   AddCase(VectorVop3FloatCompareNegSourceModifier);
   AddCase(VectorVop3CmpxWritesExecMask);
   AddCase(VectorVopcSdwaCmpxWritesExecMask);
+  AddCase(VectorVopcCmpxGtU16CapturedSdwaExecMask);
   AddCase(VectorCompareInvertedMaskSelect);
   AddCase(BranchSelect);
   AddCase(SimpleLoop);