feat(arch): the ZCNOT unary pair and the vector counter step

Assisted-by: GLM 5.3 Flash

asm/arm64_ext_asm_test.go

@@ -348,6 +348,8 @@ func TestArm64AssembleExtensionStage2Golden(t *testing.T) {
 		{"ZCLS Z7.D, P4.Z, Z13.D", 0x04c8b0ed},
 		{"ZCLZ Z7.D, P4.M, Z13.D", 0x04d9b0ed},
 		{"ZCLZ Z7.D, P4.Z, Z13.D", 0x04c9b0ed},
+		{"ZCNOT Z7.D, P4.M, Z13.D", 0x04dbb0ed},
+		{"ZCNOT Z7.D, P4.Z, Z13.D", 0x04cbb0ed},
 		{"ZCOMPACT Z7.D, P4, Z13.D", 0x05e190ed},
 		{"ZCOMPACT Z7.D, P4, Z13.D", 0x05e190ed},
 		{"ZEOR Z15.B, Z0.B, P3.M, Z0.B", 0x04190de0},
@@ -461,6 +463,7 @@ func TestArm64AssembleExtensionStage3Golden(t *testing.T) {
 		{"PFIRSTP P2.B, P14, R2", 0x2521b842},
 		{"PLASTP P2.B, P14, R2", 0x2522b842},
 		{"PDECP P14.S, ZR", 0x25ad89df},
+		{"ZDECP P14.S, Z26.S", 0x25ad81da},
 		{"PINCP P14.S, ZR", 0x25ac89df},
 		{"PSQDECP P14.S, ZR", 0x25aa8ddf},
 		{"PSQINCP P14.S, ZR", 0x25a88ddf},

asm/extension_test.go

@@ -234,8 +234,10 @@ func TestExtensionNamesARM64(t *testing.T) {
 		"ZBIC",
 		"ZCLS",
 		"ZCLZ",
+		"ZCNOT",
 		"ZCNT",
 		"ZCOMPACT",
+		"ZDECP",
 		"ZDUP",
 		"ZEOR",
 		"ZEXPAND",
@@ -491,7 +493,7 @@ func TestExtensionNamesARM64(t *testing.T) {
 	if strings.Join(got, ",") != strings.Join(want, ",") {
 		t.Errorf("ExtensionNames(ARM64) = %v, want %v", got, want)
 	}
-	if n := len(arch.Extensions(arch.ARM64)); n != 500 {
-		t.Errorf("the family registers %d instructions, want 500", n)
+	if n := len(arch.Extensions(arch.ARM64)); n != 503 {
+		t.Errorf("the family registers %d instructions, want 503", n)
 	}
 }