fix(asm): set the CASALH opcode bit fifteen

The CASALH entry carried the CASB/CASH opcode pattern where the acquire
forms take the full fixed field, so the word differed from the
toolchain's in one opcode bit.  Pinned against the oracle word.

Assisted-by: GLM 5.3 Flash

asm/arm64_encode.go

@@ -823,7 +823,7 @@ func init() {
 		"CASLH":    0x48a0fc00,
 		"CASAW":    0x88e07c00,
 		"CASAD":    0xc8e07c00,
-		"CASALH":   0x48e07c00,
+		"CASALH":   0x48e0fc00,
 		"LDADDALD": 0xf8e00000,
 		"LDADDALW": 0xb8e00000,
 		"LDADDAD":  0xf8a00000,

asm/arm64_encode_test.go

@@ -661,7 +661,8 @@ func TestArm64PairLoadStore(t *testing.T) {
 func TestArm64AcquireRelease(t *testing.T) {
 	got := arm64Words(t, "\tLDAR (R27), R22\n\tLDARB (R25), R2\n\tLDARW (R12), R29\n\tSTLR R3, (R24)\n\tSTLRB R11, (R22)\n"+
 		"\tCASALD R5, (R6), R7\n\tLDADDALD R5, (R6), R7\n\tLDCLRALB R5, (R6), R7\n\tLDORALD R5, (RSP), R7\n\tSWPALW R5, (R6), R7\n"+
-		"\tLDEORALD R5, (R6), R7\n\tLDEORALW R5, (RSP), R7\n")
+		"\tLDEORALD R5, (R6), R7\n\tLDEORALW R5, (RSP), R7\n"+
+		"\tCASALH ZR, (R5), R8\n")
 	want := []uint32{
 		0xc8dfff76, // LDAR R22, (R27)
 		0x08dfff22, // LDARB R2, (R25)
@@ -675,6 +676,7 @@ func TestArm64AcquireRelease(t *testing.T) {
 		0xb8e580c7, // SWPALW R7, (R6), R5
 		0xf8e520c7, // LDEORALD R7, (R6), R5
 		0xb8e523e7, // LDEORALW R7, (RSP), R5
+		0x48fffca8, // CASALH R8, (R5), ZR
 		0xd65f03c0,
 	}
 	if len(got) != len(want) {