feat(asm): extend arm64 encoder with atomics, bitfield, SIMD and more test kernels

Assisted-by: MiMo V2.5 Pro

asm/arm64_encode_test.go

@@ -48,7 +48,8 @@ func TestArm64EpilogueSmallEncoding(t *testing.T) {
 	if len(ret) != 12 {
 		t.Fatalf("epilogue length: got %d, want 12", len(ret))
 	}
-	expected := []uint32{0x9100a3fd, 0x9100c3ff, 0xd65f03c0}
+	// Non-leaf small frame: LDR FP, [SP, #-8]; LDR.P LR, [SP], #48; RET
+	expected := []uint32{0xf85f83fd, 0xf84307fe, 0xd65f03c0}
 	for i, w := range leWords(ret) {
 		if w != expected[i] {
 			t.Errorf("epilogue word %d: got %08x, want %08x", i, w, expected[i])
@@ -161,7 +162,7 @@ func TestArm64Bitmask(t *testing.T) {
 		ok            bool
 	}{
 		{1, 1, 1, 0, 0, true},                     // single bit at pos 0
-		{2, 1, 1, 1, 0, true},                     // single bit at pos 1 (rotated right by1)
+		{2, 1, 1, 63, 0, true},                    // single bit at pos 1 (immr = esize-1)
 		{0, 1, 0, 0, 0, false},                    // zero is not a bitmask
 		{0xFFFFFFFFFFFFFFFF, 1, 0, 0, 0, false},   // all ones is not a bitmask
 		{0x5555555555555555, 1, 0, 0, 0x3E, true}, // alternating bits (esize=2, ones=1)