[AArch64] Additional SVE instructions

This patch supports some additions to the SVE architecture prior to
its public release.

include/
	* opcode/aarch64.h (AARCH64_OPND_SVE_ADDR_RI_S4x16)
	(AARCH64_OPND_SVE_IMM_ROT1, AARCH64_OPND_SVE_IMM_ROT2)
	(AARCH64_OPND_SVE_Zm3_INDEX, AARCH64_OPND_SVE_Zm3_22_INDEX)
	(AARCH64_OPND_SVE_Zm4_INDEX): New aarch64_opnds.

opcodes/
	* aarch64-tbl.h (OP_SVE_HMH, OP_SVE_VMU_HSD, OP_SVE_VMVU_HSD)
	(OP_SVE_VMVV_HSD, OP_SVE_VMVVU_HSD, OP_SVE_VM_HSD, OP_SVE_VUVV_HSD)
	(OP_SVE_VUV_HSD, OP_SVE_VU_HSD, OP_SVE_VVVU_H, OP_SVE_VVVU_S)
	(OP_SVE_VVVU_HSD, OP_SVE_VVV_D, OP_SVE_VVV_D_H, OP_SVE_VVV_H)
	(OP_SVE_VVV_HSD, OP_SVE_VVV_S, OP_SVE_VVV_S_B, OP_SVE_VVV_SD_BH)
	(OP_SVE_VV_BHSDQ, OP_SVE_VV_HSD, OP_SVE_VZVV_HSD, OP_SVE_VZV_HSD)
	(OP_SVE_V_HSD): New macros.
	(OP_SVE_VMU_SD, OP_SVE_VMVU_SD, OP_SVE_VM_SD, OP_SVE_VUVV_SD)
	(OP_SVE_VU_SD, OP_SVE_VVVU_SD, OP_SVE_VVV_SD, OP_SVE_VZVV_SD)
	(OP_SVE_VZV_SD, OP_SVE_V_SD): Delete.
	(aarch64_opcode_table): Add new SVE instructions.
	(aarch64_opcode_table): Use imm_rotate{1,2} instead of imm_rotate
	for rotation operands.  Add new SVE operands.
	* aarch64-asm.h (ins_sve_addr_ri_s4): New inserter.
	(ins_sve_quad_index): Likewise.
	(ins_imm_rotate): Split into...
	(ins_imm_rotate1, ins_imm_rotate2): ...these two inserters.
	* aarch64-asm.c (aarch64_ins_imm_rotate): Split into...
	(aarch64_ins_imm_rotate1, aarch64_ins_imm_rotate2): ...these two
	functions.
	(aarch64_ins_sve_addr_ri_s4): New function.
	(aarch64_ins_sve_quad_index): Likewise.
	(do_misc_encoding): Handle "MOV Zn.Q, Qm".
	* aarch64-asm-2.c: Regenerate.
	* aarch64-dis.h (ext_sve_addr_ri_s4): New extractor.
	(ext_sve_quad_index): Likewise.
	(ext_imm_rotate): Split into...
	(ext_imm_rotate1, ext_imm_rotate2): ...these two extractors.
	* aarch64-dis.c (aarch64_ext_imm_rotate): Split into...
	(aarch64_ext_imm_rotate1, aarch64_ext_imm_rotate2): ...these two
	functions.
	(aarch64_ext_sve_addr_ri_s4): New function.
	(aarch64_ext_sve_quad_index): Likewise.
	(aarch64_ext_sve_index): Allow quad indices.
	(do_misc_decoding): Likewise.
	* aarch64-dis-2.c: Regenerate.
	* aarch64-opc.h (FLD_SVE_i3h, FLD_SVE_rot1, FLD_SVE_rot2): New
	aarch64_field_kinds.
	(OPD_F_OD_MASK): Widen by one bit.
	(OPD_F_NO_ZR): Bump accordingly.
	(get_operand_field_width): New function.
	* aarch64-opc.c (fields): Add new SVE fields.
	(operand_general_constraint_met_p): Handle new SVE operands.
	(aarch64_print_operand): Likewise.
	* aarch64-opc-2.c: Regenerate.

gas/
	* doc/c-aarch64.texi: Document that sve implies fp16, simd and compnum.
	* config/tc-aarch64.c (parse_vector_type_for_operand): Allow .q
	to be used with SVE registers.
	(parse_operands): Handle new SVE operands.
	(aarch64_features): Make "sve" require F16 rather than FP.  Also
	require COMPNUM.
	* testsuite/gas/aarch64/sve.s: Add tests for new instructions.
	Include compnum tests.
	* testsuite/gas/aarch64/sve.d: Update accordingly.
	* testsuite/gas/aarch64/sve-invalid.s: Add tests for new instructions.
	* testsuite/gas/aarch64/sve-invalid.l: Update accordingly.  Also
	update expected output for new FMOV and MOV alternatives.

1 files changed, 6 insertions, 0 deletions

diff --git a/opcodes/aarch64-opc-2.c b/opcodes/aarch64-opc-2.c
index 937e835..1553ce6 100644
--- a/opcodes/aarch64-opc-2.c
+++ b/opcodes/aarch64-opc-2.c
@@ -119,6 +119,7 @@ const struct aarch64_operand aarch64_operands[] =
   {AARCH64_OPND_CLASS_SYSTEM, "BARRIER_ISB", OPD_F_HAS_INSERTER | OPD_F_HAS_EXTRACTOR, {}, "the ISB option name SY or an optional 4-bit unsigned immediate"},
   {AARCH64_OPND_CLASS_SYSTEM, "PRFOP", OPD_F_HAS_INSERTER | OPD_F_HAS_EXTRACTOR, {}, "a prefetch operation specifier"},
   {AARCH64_OPND_CLASS_SYSTEM, "BARRIER_PSB", OPD_F_HAS_INSERTER | OPD_F_HAS_EXTRACTOR, {}, "the PSB option name CSYNC"},
+  {AARCH64_OPND_CLASS_ADDRESS, "SVE_ADDR_RI_S4x16", 4 << OPD_F_OD_LSB | OPD_F_HAS_INSERTER | OPD_F_HAS_EXTRACTOR, {FLD_Rn}, "an address with a 4-bit signed offset, multiplied by 16"},
   {AARCH64_OPND_CLASS_ADDRESS, "SVE_ADDR_RI_S4xVL", OPD_F_HAS_INSERTER | OPD_F_HAS_EXTRACTOR, {FLD_Rn}, "an address with a 4-bit signed offset, multiplied by VL"},
   {AARCH64_OPND_CLASS_ADDRESS, "SVE_ADDR_RI_S4x2xVL", 1 << OPD_F_OD_LSB | OPD_F_HAS_INSERTER | OPD_F_HAS_EXTRACTOR, {FLD_Rn}, "an address with a 4-bit signed offset, multiplied by 2*VL"},
   {AARCH64_OPND_CLASS_ADDRESS, "SVE_ADDR_RI_S4x3xVL", 2 << OPD_F_OD_LSB | OPD_F_HAS_INSERTER | OPD_F_HAS_EXTRACTOR, {FLD_Rn}, "an address with a 4-bit signed offset, multiplied by 3*VL"},
@@ -162,6 +163,8 @@ const struct aarch64_operand aarch64_operands[] =
   {AARCH64_OPND_CLASS_IMMEDIATE, "SVE_I1_HALF_ONE", OPD_F_HAS_INSERTER | OPD_F_HAS_EXTRACTOR, {FLD_SVE_i1}, "either 0.5 or 1.0"},
   {AARCH64_OPND_CLASS_IMMEDIATE, "SVE_I1_HALF_TWO", OPD_F_HAS_INSERTER | OPD_F_HAS_EXTRACTOR, {FLD_SVE_i1}, "either 0.5 or 2.0"},
   {AARCH64_OPND_CLASS_IMMEDIATE, "SVE_I1_ZERO_ONE", OPD_F_HAS_INSERTER | OPD_F_HAS_EXTRACTOR, {FLD_SVE_i1}, "either 0.0 or 1.0"},
+  {AARCH64_OPND_CLASS_IMMEDIATE, "SVE_IMM_ROT1", OPD_F_HAS_INSERTER | OPD_F_HAS_EXTRACTOR, {FLD_SVE_rot1}, "a 1-bit rotation specifier for complex arithmetic operations"},
+  {AARCH64_OPND_CLASS_IMMEDIATE, "SVE_IMM_ROT2", OPD_F_HAS_INSERTER | OPD_F_HAS_EXTRACTOR, {FLD_SVE_rot2}, "a 2-bit rotation specifier for complex arithmetic operations"},
   {AARCH64_OPND_CLASS_IMMEDIATE, "SVE_INV_LIMM", OPD_F_HAS_INSERTER | OPD_F_HAS_EXTRACTOR, {FLD_SVE_N,FLD_SVE_immr,FLD_SVE_imms}, "an inverted 13-bit logical immediate"},
   {AARCH64_OPND_CLASS_IMMEDIATE, "SVE_LIMM", OPD_F_HAS_INSERTER | OPD_F_HAS_EXTRACTOR, {FLD_SVE_N,FLD_SVE_immr,FLD_SVE_imms}, "a 13-bit logical immediate"},
   {AARCH64_OPND_CLASS_IMMEDIATE, "SVE_LIMM_MOV", OPD_F_HAS_INSERTER | OPD_F_HAS_EXTRACTOR, {FLD_SVE_N,FLD_SVE_immr,FLD_SVE_imms}, "a 13-bit logical move immediate"},
@@ -199,6 +202,9 @@ const struct aarch64_operand aarch64_operands[] =
   {AARCH64_OPND_CLASS_SVE_REG, "SVE_Zd", OPD_F_HAS_INSERTER | OPD_F_HAS_EXTRACTOR, {FLD_SVE_Zd}, "an SVE vector register"},
   {AARCH64_OPND_CLASS_SVE_REG, "SVE_Zm_5", OPD_F_HAS_INSERTER | OPD_F_HAS_EXTRACTOR, {FLD_SVE_Zm_5}, "an SVE vector register"},
   {AARCH64_OPND_CLASS_SVE_REG, "SVE_Zm_16", OPD_F_HAS_INSERTER | OPD_F_HAS_EXTRACTOR, {FLD_SVE_Zm_16}, "an SVE vector register"},
+  {AARCH64_OPND_CLASS_SVE_REG, "SVE_Zm3_INDEX", 3 << OPD_F_OD_LSB | OPD_F_HAS_INSERTER | OPD_F_HAS_EXTRACTOR, {FLD_SVE_Zm_16}, "an indexed SVE vector register"},
+  {AARCH64_OPND_CLASS_SVE_REG, "SVE_Zm3_22_INDEX", 3 << OPD_F_OD_LSB | OPD_F_HAS_INSERTER | OPD_F_HAS_EXTRACTOR, {FLD_SVE_i3h, FLD_SVE_Zm_16}, "an indexed SVE vector register"},
+  {AARCH64_OPND_CLASS_SVE_REG, "SVE_Zm4_INDEX", 4 << OPD_F_OD_LSB | OPD_F_HAS_INSERTER | OPD_F_HAS_EXTRACTOR, {FLD_SVE_Zm_16}, "an indexed SVE vector register"},
   {AARCH64_OPND_CLASS_SVE_REG, "SVE_Zn", OPD_F_HAS_INSERTER | OPD_F_HAS_EXTRACTOR, {FLD_SVE_Zn}, "an SVE vector register"},
   {AARCH64_OPND_CLASS_SVE_REG, "SVE_Zn_INDEX", OPD_F_HAS_INSERTER | OPD_F_HAS_EXTRACTOR, {FLD_SVE_Zn}, "an indexed SVE vector register"},
   {AARCH64_OPND_CLASS_SVE_REG, "SVE_ZnxN", OPD_F_HAS_INSERTER | OPD_F_HAS_EXTRACTOR, {FLD_SVE_Zn}, "a list of SVE vector registers"},