feat(arch): add the VL packed FP16 forms to the amd64 extension layer

Assisted-by: GLM 5.3 Flash

asm/extension_amd64_test.go

@@ -33,8 +33,8 @@ func TestAmd64ExtensionRegistry(t *testing.T) {
 		{"VCVTSH2SS", 1},
 		{"VCVTSI2SH", 2},
 		{"VCVTSH2SI", 2},
-		{"VADDPH", 1},
-		{"VSQRTPH", 1},
+		{"VADDPH", 3},
+		{"VSQRTPH", 3},
 		{"VSCALEFSH", 1},
 		{"VGETEXPSH", 1},
 		{"VCMPSH", 1},
@@ -54,8 +54,8 @@ func TestAmd64ExtensionRegistry(t *testing.T) {
 			t.Errorf("the %s lookup is not case-insensitive", tt.mnem)
 		}
 	}
-	if got := arch.Extensions(arch.AMD64); len(got) != 52 {
-		t.Errorf("the amd64 layer registers %d instructions, want 52", len(got))
+	if got := arch.Extensions(arch.AMD64); len(got) != 66 {
+		t.Errorf("the amd64 layer registers %d instructions, want 66", len(got))
 	}
 	if _, ok := LookupExtension(arch.AMD64, "NOSUCHINSTR"); ok {
 		t.Error("a non-extended mnemonic resolved")