+static unsigned
+neon_scalar_for_vcmla (unsigned opnd, unsigned elsize)
+{
+ unsigned regno = NEON_SCALAR_REG (opnd);
+ unsigned elno = NEON_SCALAR_INDEX (opnd);
+
+ if (elsize == 16 && elno < 2 && regno < 16)
+ return regno | (elno << 4);
+ else if (elsize == 32 && elno == 0)
+ return regno;
+
+ first_error (_("scalar out of range"));
+ return 0;
+}
+
+static void
+do_vcmla (void)
+{
+ constraint (!ARM_CPU_HAS_FEATURE (cpu_variant, fpu_neon_ext_armv8),
+ _(BAD_FPU));
+ constraint (inst.reloc.exp.X_op != O_constant, _("expression too complex"));
+ unsigned rot = inst.reloc.exp.X_add_number;
+ constraint (rot != 0 && rot != 90 && rot != 180 && rot != 270,
+ _("immediate out of range"));
+ rot /= 90;
+ if (inst.operands[2].isscalar)
+ {
+ enum neon_shape rs = neon_select_shape (NS_DDSI, NS_QQSI, NS_NULL);
+ unsigned size = neon_check_type (3, rs, N_EQK, N_EQK,
+ N_KEY | N_F16 | N_F32).size;
+ unsigned m = neon_scalar_for_vcmla (inst.operands[2].reg, size);
+ inst.is_neon = 1;
+ inst.instruction = 0xfe000800;
+ inst.instruction |= LOW4 (inst.operands[0].reg) << 12;
+ inst.instruction |= HI1 (inst.operands[0].reg) << 22;
+ inst.instruction |= LOW4 (inst.operands[1].reg) << 16;
+ inst.instruction |= HI1 (inst.operands[1].reg) << 7;
+ inst.instruction |= LOW4 (m);
+ inst.instruction |= HI1 (m) << 5;
+ inst.instruction |= neon_quad (rs) << 6;
+ inst.instruction |= rot << 20;
+ inst.instruction |= (size == 32) << 23;
+ }
+ else
+ {
+ enum neon_shape rs = neon_select_shape (NS_DDDI, NS_QQQI, NS_NULL);
+ unsigned size = neon_check_type (3, rs, N_EQK, N_EQK,
+ N_KEY | N_F16 | N_F32).size;
+ neon_three_same (neon_quad (rs), 0, -1);
+ inst.instruction &= 0x00ffffff; /* Undo neon_dp_fixup. */
+ inst.instruction |= 0xfc200800;
+ inst.instruction |= rot << 23;
+ inst.instruction |= (size == 32) << 20;
+ }
+}
+
+static void
+do_vcadd (void)
+{
+ constraint (!ARM_CPU_HAS_FEATURE (cpu_variant, fpu_neon_ext_armv8),
+ _(BAD_FPU));
+ constraint (inst.reloc.exp.X_op != O_constant, _("expression too complex"));
+ unsigned rot = inst.reloc.exp.X_add_number;
+ constraint (rot != 90 && rot != 270, _("immediate out of range"));
+ enum neon_shape rs = neon_select_shape (NS_DDDI, NS_QQQI, NS_NULL);
+ unsigned size = neon_check_type (3, rs, N_EQK, N_EQK,
+ N_KEY | N_F16 | N_F32).size;
+ neon_three_same (neon_quad (rs), 0, -1);
+ inst.instruction &= 0x00ffffff; /* Undo neon_dp_fixup. */
+ inst.instruction |= 0xfc800800;
+ inst.instruction |= (rot == 270) << 24;
+ inst.instruction |= (size == 32) << 20;
+}
+