blob: 8032f50eef9e5a413e628565be25f4ec25cffb04 [file] [log] [blame]
//=- AArch64SVEInstrInfo.td - AArch64 SVE Instructions -*- tablegen -*-----=//
//
// The LLVM Compiler Infrastructure
//
// This file is distributed under the University of Illinois Open Source
// License. See LICENSE.TXT for details.
//
//===----------------------------------------------------------------------===//
//
// AArch64 Scalable Vector Extension (SVE) Instruction definitions.
//
//===----------------------------------------------------------------------===//
let Predicates = [HasSVE] in {
defm ADD_ZZZ : sve_int_bin_cons_arit_0<0b000, "add">;
defm SUB_ZZZ : sve_int_bin_cons_arit_0<0b001, "sub">;
def AND_ZZZ : sve_int_bin_cons_log<0b00, "and">;
def ORR_ZZZ : sve_int_bin_cons_log<0b01, "orr">;
def EOR_ZZZ : sve_int_bin_cons_log<0b10, "eor">;
def BIC_ZZZ : sve_int_bin_cons_log<0b11, "bic">;
defm ADD_ZPmZ : sve_int_bin_pred_arit_0<0b000, "add">;
defm SUB_ZPmZ : sve_int_bin_pred_arit_0<0b001, "sub">;
defm ORR_ZPmZ : sve_int_bin_pred_log<0b000, "orr">;
defm EOR_ZPmZ : sve_int_bin_pred_log<0b001, "eor">;
defm AND_ZPmZ : sve_int_bin_pred_log<0b010, "and">;
defm BIC_ZPmZ : sve_int_bin_pred_log<0b011, "bic">;
defm ADD_ZI : sve_int_arith_imm0<0b000, "add">;
defm SUB_ZI : sve_int_arith_imm0<0b001, "sub">;
defm ORR_ZI : sve_int_log_imm<0b00, "orr", "orn">;
defm EOR_ZI : sve_int_log_imm<0b01, "eor", "eon">;
defm AND_ZI : sve_int_log_imm<0b10, "and", "bic">;
defm FADD_ZPmI : sve_fp_2op_i_p_zds<0b000, "fadd", sve_fpimm_half_one>;
defm FMUL_ZPmI : sve_fp_2op_i_p_zds<0b010, "fmul", sve_fpimm_half_two>;
defm FMAX_ZPmI : sve_fp_2op_i_p_zds<0b110, "fmax", sve_fpimm_zero_one>;
// Splat immediate (unpredicated)
defm DUP_ZI : sve_int_dup_imm<"dup">;
defm FDUP_ZI : sve_int_dup_fpimm<"fdup">;
defm DUPM_ZI : sve_int_dup_mask_imm<"dupm">;
// Splat immediate (predicated)
defm CPY_ZPmI : sve_int_dup_imm_pred_merge<"cpy">;
defm CPY_ZPzI : sve_int_dup_imm_pred_zero<"cpy">;
defm FCPY_ZPmI : sve_int_dup_fpimm_pred<"fcpy">;
// Splat scalar register (unpredicated, GPR or vector + element index)
defm DUP_ZR : sve_int_perm_dup_r<"dup">;
defm DUP_ZZI : sve_int_perm_dup_i<"dup">;
// Splat scalar register (predicated)
defm CPY_ZPmR : sve_int_perm_cpy_r<"cpy">;
defm CPY_ZPmV : sve_int_perm_cpy_v<"cpy">;
// Select elements from either vector (predicated)
defm SEL_ZPZZ : sve_int_sel_vvv<"sel">;
def AND_PPzPP : sve_int_pred_log<0b0000, "and">;
def BIC_PPzPP : sve_int_pred_log<0b0001, "bic">;
def EOR_PPzPP : sve_int_pred_log<0b0010, "eor">;
def SEL_PPPP : sve_int_pred_log<0b0011, "sel">;
def ANDS_PPzPP : sve_int_pred_log<0b0100, "ands">;
def BICS_PPzPP : sve_int_pred_log<0b0101, "bics">;
def EORS_PPzPP : sve_int_pred_log<0b0110, "eors">;
def ORR_PPzPP : sve_int_pred_log<0b1000, "orr">;
def ORN_PPzPP : sve_int_pred_log<0b1001, "orn">;
def NOR_PPzPP : sve_int_pred_log<0b1010, "nor">;
def NAND_PPzPP : sve_int_pred_log<0b1011, "nand">;
def ORRS_PPzPP : sve_int_pred_log<0b1100, "orrs">;
def ORNS_PPzPP : sve_int_pred_log<0b1101, "orns">;
def NORS_PPzPP : sve_int_pred_log<0b1110, "nors">;
def NANDS_PPzPP : sve_int_pred_log<0b1111, "nands">;
// continuous load with reg+immediate
defm LD1B_IMM : sve_mem_cld_si<0b0000, "ld1b", Z_b, ZPR8>;
defm LD1B_H_IMM : sve_mem_cld_si<0b0001, "ld1b", Z_h, ZPR16>;
defm LD1B_S_IMM : sve_mem_cld_si<0b0010, "ld1b", Z_s, ZPR32>;
defm LD1B_D_IMM : sve_mem_cld_si<0b0011, "ld1b", Z_d, ZPR64>;
defm LD1SW_D_IMM : sve_mem_cld_si<0b0100, "ld1sw", Z_d, ZPR64>;
defm LD1H_IMM : sve_mem_cld_si<0b0101, "ld1h", Z_h, ZPR16>;
defm LD1H_S_IMM : sve_mem_cld_si<0b0110, "ld1h", Z_s, ZPR32>;
defm LD1H_D_IMM : sve_mem_cld_si<0b0111, "ld1h", Z_d, ZPR64>;
defm LD1SH_D_IMM : sve_mem_cld_si<0b1000, "ld1sh", Z_d, ZPR64>;
defm LD1SH_S_IMM : sve_mem_cld_si<0b1001, "ld1sh", Z_s, ZPR32>;
defm LD1W_IMM : sve_mem_cld_si<0b1010, "ld1w", Z_s, ZPR32>;
defm LD1W_D_IMM : sve_mem_cld_si<0b1011, "ld1w", Z_d, ZPR64>;
defm LD1SB_D_IMM : sve_mem_cld_si<0b1100, "ld1sb", Z_d, ZPR64>;
defm LD1SB_S_IMM : sve_mem_cld_si<0b1101, "ld1sb", Z_s, ZPR32>;
defm LD1SB_H_IMM : sve_mem_cld_si<0b1110, "ld1sb", Z_h, ZPR16>;
defm LD1D_IMM : sve_mem_cld_si<0b1111, "ld1d", Z_d, ZPR64>;
// LD1R loads (splat scalar to vector)
defm LD1RB_IMM : sve_mem_ld_dup<0b00, 0b00, "ld1rb", Z_b, ZPR8, uimm6s1>;
defm LD1RB_H_IMM : sve_mem_ld_dup<0b00, 0b01, "ld1rb", Z_h, ZPR16, uimm6s1>;
defm LD1RB_S_IMM : sve_mem_ld_dup<0b00, 0b10, "ld1rb", Z_s, ZPR32, uimm6s1>;
defm LD1RB_D_IMM : sve_mem_ld_dup<0b00, 0b11, "ld1rb", Z_d, ZPR64, uimm6s1>;
defm LD1RSW_IMM : sve_mem_ld_dup<0b01, 0b00, "ld1rsw", Z_d, ZPR64, uimm6s4>;
defm LD1RH_IMM : sve_mem_ld_dup<0b01, 0b01, "ld1rh", Z_h, ZPR16, uimm6s2>;
defm LD1RH_S_IMM : sve_mem_ld_dup<0b01, 0b10, "ld1rh", Z_s, ZPR32, uimm6s2>;
defm LD1RH_D_IMM : sve_mem_ld_dup<0b01, 0b11, "ld1rh", Z_d, ZPR64, uimm6s2>;
defm LD1RSH_D_IMM : sve_mem_ld_dup<0b10, 0b00, "ld1rsh", Z_d, ZPR64, uimm6s2>;
defm LD1RSH_S_IMM : sve_mem_ld_dup<0b10, 0b01, "ld1rsh", Z_s, ZPR32, uimm6s2>;
defm LD1RW_IMM : sve_mem_ld_dup<0b10, 0b10, "ld1rw", Z_s, ZPR32, uimm6s4>;
defm LD1RW_D_IMM : sve_mem_ld_dup<0b10, 0b11, "ld1rw", Z_d, ZPR64, uimm6s4>;
defm LD1RSB_D_IMM : sve_mem_ld_dup<0b11, 0b00, "ld1rsb", Z_d, ZPR64, uimm6s1>;
defm LD1RSB_S_IMM : sve_mem_ld_dup<0b11, 0b01, "ld1rsb", Z_s, ZPR32, uimm6s1>;
defm LD1RSB_H_IMM : sve_mem_ld_dup<0b11, 0b10, "ld1rsb", Z_h, ZPR16, uimm6s1>;
defm LD1RD_IMM : sve_mem_ld_dup<0b11, 0b11, "ld1rd", Z_d, ZPR64, uimm6s8>;
// LD1RQ loads (load quadword-vector and splat to scalable vector)
defm LD1RQ_B_IMM : sve_mem_ldqr_si<0b00, "ld1rqb", Z_b, ZPR8>;
defm LD1RQ_H_IMM : sve_mem_ldqr_si<0b01, "ld1rqh", Z_h, ZPR16>;
defm LD1RQ_W_IMM : sve_mem_ldqr_si<0b10, "ld1rqw", Z_s, ZPR32>;
defm LD1RQ_D_IMM : sve_mem_ldqr_si<0b11, "ld1rqd", Z_d, ZPR64>;
defm LD1RQ_B : sve_mem_ldqr_ss<0b00, "ld1rqb", Z_b, ZPR8, GPR64NoXZRshifted8>;
defm LD1RQ_H : sve_mem_ldqr_ss<0b01, "ld1rqh", Z_h, ZPR16, GPR64NoXZRshifted16>;
defm LD1RQ_W : sve_mem_ldqr_ss<0b10, "ld1rqw", Z_s, ZPR32, GPR64NoXZRshifted32>;
defm LD1RQ_D : sve_mem_ldqr_ss<0b11, "ld1rqd", Z_d, ZPR64, GPR64NoXZRshifted64>;
// continuous load with reg+reg addressing.
defm LD1B : sve_mem_cld_ss<0b0000, "ld1b", Z_b, ZPR8, GPR64NoXZRshifted8>;
defm LD1B_H : sve_mem_cld_ss<0b0001, "ld1b", Z_h, ZPR16, GPR64NoXZRshifted8>;
defm LD1B_S : sve_mem_cld_ss<0b0010, "ld1b", Z_s, ZPR32, GPR64NoXZRshifted8>;
defm LD1B_D : sve_mem_cld_ss<0b0011, "ld1b", Z_d, ZPR64, GPR64NoXZRshifted8>;
defm LD1SW_D : sve_mem_cld_ss<0b0100, "ld1sw", Z_d, ZPR64, GPR64NoXZRshifted32>;
defm LD1H : sve_mem_cld_ss<0b0101, "ld1h", Z_h, ZPR16, GPR64NoXZRshifted16>;
defm LD1H_S : sve_mem_cld_ss<0b0110, "ld1h", Z_s, ZPR32, GPR64NoXZRshifted16>;
defm LD1H_D : sve_mem_cld_ss<0b0111, "ld1h", Z_d, ZPR64, GPR64NoXZRshifted16>;
defm LD1SH_D : sve_mem_cld_ss<0b1000, "ld1sh", Z_d, ZPR64, GPR64NoXZRshifted16>;
defm LD1SH_S : sve_mem_cld_ss<0b1001, "ld1sh", Z_s, ZPR32, GPR64NoXZRshifted16>;
defm LD1W : sve_mem_cld_ss<0b1010, "ld1w", Z_s, ZPR32, GPR64NoXZRshifted32>;
defm LD1W_D : sve_mem_cld_ss<0b1011, "ld1w", Z_d, ZPR64, GPR64NoXZRshifted32>;
defm LD1SB_D : sve_mem_cld_ss<0b1100, "ld1sb", Z_d, ZPR64, GPR64NoXZRshifted8>;
defm LD1SB_S : sve_mem_cld_ss<0b1101, "ld1sb", Z_s, ZPR32, GPR64NoXZRshifted8>;
defm LD1SB_H : sve_mem_cld_ss<0b1110, "ld1sb", Z_h, ZPR16, GPR64NoXZRshifted8>;
defm LD1D : sve_mem_cld_ss<0b1111, "ld1d", Z_d, ZPR64, GPR64NoXZRshifted64>;
// non-faulting continuous load with reg+immediate
defm LDNF1B_IMM : sve_mem_cldnf_si<0b0000, "ldnf1b", Z_b, ZPR8>;
defm LDNF1B_H_IMM : sve_mem_cldnf_si<0b0001, "ldnf1b", Z_h, ZPR16>;
defm LDNF1B_S_IMM : sve_mem_cldnf_si<0b0010, "ldnf1b", Z_s, ZPR32>;
defm LDNF1B_D_IMM : sve_mem_cldnf_si<0b0011, "ldnf1b", Z_d, ZPR64>;
defm LDNF1SW_D_IMM : sve_mem_cldnf_si<0b0100, "ldnf1sw", Z_d, ZPR64>;
defm LDNF1H_IMM : sve_mem_cldnf_si<0b0101, "ldnf1h", Z_h, ZPR16>;
defm LDNF1H_S_IMM : sve_mem_cldnf_si<0b0110, "ldnf1h", Z_s, ZPR32>;
defm LDNF1H_D_IMM : sve_mem_cldnf_si<0b0111, "ldnf1h", Z_d, ZPR64>;
defm LDNF1SH_D_IMM : sve_mem_cldnf_si<0b1000, "ldnf1sh", Z_d, ZPR64>;
defm LDNF1SH_S_IMM : sve_mem_cldnf_si<0b1001, "ldnf1sh", Z_s, ZPR32>;
defm LDNF1W_IMM : sve_mem_cldnf_si<0b1010, "ldnf1w", Z_s, ZPR32>;
defm LDNF1W_D_IMM : sve_mem_cldnf_si<0b1011, "ldnf1w", Z_d, ZPR64>;
defm LDNF1SB_D_IMM : sve_mem_cldnf_si<0b1100, "ldnf1sb", Z_d, ZPR64>;
defm LDNF1SB_S_IMM : sve_mem_cldnf_si<0b1101, "ldnf1sb", Z_s, ZPR32>;
defm LDNF1SB_H_IMM : sve_mem_cldnf_si<0b1110, "ldnf1sb", Z_h, ZPR16>;
defm LDNF1D_IMM : sve_mem_cldnf_si<0b1111, "ldnf1d", Z_d, ZPR64>;
// First-faulting loads with reg+reg addressing.
defm LDFF1B : sve_mem_cldff_ss<0b0000, "ldff1b", Z_b, ZPR8, GPR64shifted8>;
defm LDFF1B_H : sve_mem_cldff_ss<0b0001, "ldff1b", Z_h, ZPR16, GPR64shifted8>;
defm LDFF1B_S : sve_mem_cldff_ss<0b0010, "ldff1b", Z_s, ZPR32, GPR64shifted8>;
defm LDFF1B_D : sve_mem_cldff_ss<0b0011, "ldff1b", Z_d, ZPR64, GPR64shifted8>;
defm LDFF1SW_D : sve_mem_cldff_ss<0b0100, "ldff1sw", Z_d, ZPR64, GPR64shifted32>;
defm LDFF1H : sve_mem_cldff_ss<0b0101, "ldff1h", Z_h, ZPR16, GPR64shifted16>;
defm LDFF1H_S : sve_mem_cldff_ss<0b0110, "ldff1h", Z_s, ZPR32, GPR64shifted16>;
defm LDFF1H_D : sve_mem_cldff_ss<0b0111, "ldff1h", Z_d, ZPR64, GPR64shifted16>;
defm LDFF1SH_D : sve_mem_cldff_ss<0b1000, "ldff1sh", Z_d, ZPR64, GPR64shifted16>;
defm LDFF1SH_S : sve_mem_cldff_ss<0b1001, "ldff1sh", Z_s, ZPR32, GPR64shifted16>;
defm LDFF1W : sve_mem_cldff_ss<0b1010, "ldff1w", Z_s, ZPR32, GPR64shifted32>;
defm LDFF1W_D : sve_mem_cldff_ss<0b1011, "ldff1w", Z_d, ZPR64, GPR64shifted32>;
defm LDFF1SB_D : sve_mem_cldff_ss<0b1100, "ldff1sb", Z_d, ZPR64, GPR64shifted8>;
defm LDFF1SB_S : sve_mem_cldff_ss<0b1101, "ldff1sb", Z_s, ZPR32, GPR64shifted8>;
defm LDFF1SB_H : sve_mem_cldff_ss<0b1110, "ldff1sb", Z_h, ZPR16, GPR64shifted8>;
defm LDFF1D : sve_mem_cldff_ss<0b1111, "ldff1d", Z_d, ZPR64, GPR64shifted64>;
// LD(2|3|4) structured loads with reg+immediate
defm LD2B_IMM : sve_mem_eld_si<0b00, 0b01, ZZ_b, "ld2b", simm4s2>;
defm LD3B_IMM : sve_mem_eld_si<0b00, 0b10, ZZZ_b, "ld3b", simm4s3>;
defm LD4B_IMM : sve_mem_eld_si<0b00, 0b11, ZZZZ_b, "ld4b", simm4s4>;
defm LD2H_IMM : sve_mem_eld_si<0b01, 0b01, ZZ_h, "ld2h", simm4s2>;
defm LD3H_IMM : sve_mem_eld_si<0b01, 0b10, ZZZ_h, "ld3h", simm4s3>;
defm LD4H_IMM : sve_mem_eld_si<0b01, 0b11, ZZZZ_h, "ld4h", simm4s4>;
defm LD2W_IMM : sve_mem_eld_si<0b10, 0b01, ZZ_s, "ld2w", simm4s2>;
defm LD3W_IMM : sve_mem_eld_si<0b10, 0b10, ZZZ_s, "ld3w", simm4s3>;
defm LD4W_IMM : sve_mem_eld_si<0b10, 0b11, ZZZZ_s, "ld4w", simm4s4>;
defm LD2D_IMM : sve_mem_eld_si<0b11, 0b01, ZZ_d, "ld2d", simm4s2>;
defm LD3D_IMM : sve_mem_eld_si<0b11, 0b10, ZZZ_d, "ld3d", simm4s3>;
defm LD4D_IMM : sve_mem_eld_si<0b11, 0b11, ZZZZ_d, "ld4d", simm4s4>;
// LD(2|3|4) structured loads (register + register)
def LD2B : sve_mem_eld_ss<0b00, 0b01, ZZ_b, "ld2b", GPR64NoXZRshifted8>;
def LD3B : sve_mem_eld_ss<0b00, 0b10, ZZZ_b, "ld3b", GPR64NoXZRshifted8>;
def LD4B : sve_mem_eld_ss<0b00, 0b11, ZZZZ_b, "ld4b", GPR64NoXZRshifted8>;
def LD2H : sve_mem_eld_ss<0b01, 0b01, ZZ_h, "ld2h", GPR64NoXZRshifted16>;
def LD3H : sve_mem_eld_ss<0b01, 0b10, ZZZ_h, "ld3h", GPR64NoXZRshifted16>;
def LD4H : sve_mem_eld_ss<0b01, 0b11, ZZZZ_h, "ld4h", GPR64NoXZRshifted16>;
def LD2W : sve_mem_eld_ss<0b10, 0b01, ZZ_s, "ld2w", GPR64NoXZRshifted32>;
def LD3W : sve_mem_eld_ss<0b10, 0b10, ZZZ_s, "ld3w", GPR64NoXZRshifted32>;
def LD4W : sve_mem_eld_ss<0b10, 0b11, ZZZZ_s, "ld4w", GPR64NoXZRshifted32>;
def LD2D : sve_mem_eld_ss<0b11, 0b01, ZZ_d, "ld2d", GPR64NoXZRshifted64>;
def LD3D : sve_mem_eld_ss<0b11, 0b10, ZZZ_d, "ld3d", GPR64NoXZRshifted64>;
def LD4D : sve_mem_eld_ss<0b11, 0b11, ZZZZ_d, "ld4d", GPR64NoXZRshifted64>;
// Gathers using unscaled 32-bit offsets, e.g.
// ld1h z0.s, p0/z, [x0, z0.s, uxtw]
defm GLD1SB_S : sve_mem_32b_gld_vs_32_unscaled<0b0000, "ld1sb", ZPR32ExtSXTW8Only, ZPR32ExtUXTW8Only>;
defm GLDFF1SB_S : sve_mem_32b_gld_vs_32_unscaled<0b0001, "ldff1sb", ZPR32ExtSXTW8Only, ZPR32ExtUXTW8Only>;
defm GLD1B_S : sve_mem_32b_gld_vs_32_unscaled<0b0010, "ld1b", ZPR32ExtSXTW8Only, ZPR32ExtUXTW8Only>;
defm GLDFF1B_S : sve_mem_32b_gld_vs_32_unscaled<0b0011, "ldff1b", ZPR32ExtSXTW8Only, ZPR32ExtUXTW8Only>;
defm GLD1SH_S : sve_mem_32b_gld_vs_32_unscaled<0b0100, "ld1sh", ZPR32ExtSXTW8, ZPR32ExtUXTW8>;
defm GLDFF1SH_S : sve_mem_32b_gld_vs_32_unscaled<0b0101, "ldff1sh", ZPR32ExtSXTW8, ZPR32ExtUXTW8>;
defm GLD1H_S : sve_mem_32b_gld_vs_32_unscaled<0b0110, "ld1h", ZPR32ExtSXTW8, ZPR32ExtUXTW8>;
defm GLDFF1H_S : sve_mem_32b_gld_vs_32_unscaled<0b0111, "ldff1h", ZPR32ExtSXTW8, ZPR32ExtUXTW8>;
defm GLD1W : sve_mem_32b_gld_vs_32_unscaled<0b1010, "ld1w", ZPR32ExtSXTW8, ZPR32ExtUXTW8>;
defm GLDFF1W : sve_mem_32b_gld_vs_32_unscaled<0b1011, "ldff1w", ZPR32ExtSXTW8, ZPR32ExtUXTW8>;
// Gathers using scaled 32-bit offsets, e.g.
// ld1h z0.s, p0/z, [x0, z0.s, uxtw #1]
defm GLD1SH_S : sve_mem_32b_gld_sv_32_scaled<0b0100, "ld1sh", ZPR32ExtSXTW16, ZPR32ExtUXTW16>;
defm GLDFF1SH_S : sve_mem_32b_gld_sv_32_scaled<0b0101, "ldff1sh", ZPR32ExtSXTW16, ZPR32ExtUXTW16>;
defm GLD1H_S : sve_mem_32b_gld_sv_32_scaled<0b0110, "ld1h", ZPR32ExtSXTW16, ZPR32ExtUXTW16>;
defm GLDFF1H_S : sve_mem_32b_gld_sv_32_scaled<0b0111, "ldff1h", ZPR32ExtSXTW16, ZPR32ExtUXTW16>;
defm GLD1W : sve_mem_32b_gld_sv_32_scaled<0b1010, "ld1w", ZPR32ExtSXTW32, ZPR32ExtUXTW32>;
defm GLDFF1W : sve_mem_32b_gld_sv_32_scaled<0b1011, "ldff1w", ZPR32ExtSXTW32, ZPR32ExtUXTW32>;
// Gathers using scaled 32-bit pointers with offset, e.g.
// ld1h z0.s, p0/z, [z0.s, #16]
defm GLD1SB_S : sve_mem_32b_gld_vi_32_ptrs<0b0000, "ld1sb", imm0_31>;
defm GLDFF1SB_S : sve_mem_32b_gld_vi_32_ptrs<0b0001, "ldff1sb", imm0_31>;
defm GLD1B_S : sve_mem_32b_gld_vi_32_ptrs<0b0010, "ld1b", imm0_31>;
defm GLDFF1B_S : sve_mem_32b_gld_vi_32_ptrs<0b0011, "ldff1b", imm0_31>;
defm GLD1SH_S : sve_mem_32b_gld_vi_32_ptrs<0b0100, "ld1sh", uimm5s2>;
defm GLDFF1SH_S : sve_mem_32b_gld_vi_32_ptrs<0b0101, "ldff1sh", uimm5s2>;
defm GLD1H_S : sve_mem_32b_gld_vi_32_ptrs<0b0110, "ld1h", uimm5s2>;
defm GLDFF1H_S : sve_mem_32b_gld_vi_32_ptrs<0b0111, "ldff1h", uimm5s2>;
defm GLD1W : sve_mem_32b_gld_vi_32_ptrs<0b1010, "ld1w", uimm5s4>;
defm GLDFF1W : sve_mem_32b_gld_vi_32_ptrs<0b1011, "ldff1w", uimm5s4>;
// Gathers using scaled 64-bit pointers with offset, e.g.
// ld1h z0.d, p0/z, [z0.d, #16]
defm GLD1SB_D : sve_mem_64b_gld_vi_64_ptrs<0b0000, "ld1sb", imm0_31>;
defm GLDFF1SB_D : sve_mem_64b_gld_vi_64_ptrs<0b0001, "ldff1sb", imm0_31>;
defm GLD1B_D : sve_mem_64b_gld_vi_64_ptrs<0b0010, "ld1b", imm0_31>;
defm GLDFF1B_D : sve_mem_64b_gld_vi_64_ptrs<0b0011, "ldff1b", imm0_31>;
defm GLD1SH_D : sve_mem_64b_gld_vi_64_ptrs<0b0100, "ld1sh", uimm5s2>;
defm GLDFF1SH_D : sve_mem_64b_gld_vi_64_ptrs<0b0101, "ldff1sh", uimm5s2>;
defm GLD1H_D : sve_mem_64b_gld_vi_64_ptrs<0b0110, "ld1h", uimm5s2>;
defm GLDFF1H_D : sve_mem_64b_gld_vi_64_ptrs<0b0111, "ldff1h", uimm5s2>;
defm GLD1SW_D : sve_mem_64b_gld_vi_64_ptrs<0b1000, "ld1sw", uimm5s4>;
defm GLDFF1SW_D : sve_mem_64b_gld_vi_64_ptrs<0b1001, "ldff1sw", uimm5s4>;
defm GLD1W_D : sve_mem_64b_gld_vi_64_ptrs<0b1010, "ld1w", uimm5s4>;
defm GLDFF1W_D : sve_mem_64b_gld_vi_64_ptrs<0b1011, "ldff1w", uimm5s4>;
defm GLD1D : sve_mem_64b_gld_vi_64_ptrs<0b1110, "ld1d", uimm5s8>;
defm GLDFF1D : sve_mem_64b_gld_vi_64_ptrs<0b1111, "ldff1d", uimm5s8>;
// Gathers using unscaled 64-bit offsets, e.g.
// ld1h z0.d, p0/z, [x0, z0.d]
defm GLD1SB_D : sve_mem_64b_gld_vs2_64_unscaled<0b0000, "ld1sb">;
defm GLDFF1SB_D : sve_mem_64b_gld_vs2_64_unscaled<0b0001, "ldff1sb">;
defm GLD1B_D : sve_mem_64b_gld_vs2_64_unscaled<0b0010, "ld1b">;
defm GLDFF1B_D : sve_mem_64b_gld_vs2_64_unscaled<0b0011, "ldff1b">;
defm GLD1SH_D : sve_mem_64b_gld_vs2_64_unscaled<0b0100, "ld1sh">;
defm GLDFF1SH_D : sve_mem_64b_gld_vs2_64_unscaled<0b0101, "ldff1sh">;
defm GLD1H_D : sve_mem_64b_gld_vs2_64_unscaled<0b0110, "ld1h">;
defm GLDFF1H_D : sve_mem_64b_gld_vs2_64_unscaled<0b0111, "ldff1h">;
defm GLD1SW_D : sve_mem_64b_gld_vs2_64_unscaled<0b1000, "ld1sw">;
defm GLDFF1SW_D : sve_mem_64b_gld_vs2_64_unscaled<0b1001, "ldff1sw">;
defm GLD1W_D : sve_mem_64b_gld_vs2_64_unscaled<0b1010, "ld1w">;
defm GLDFF1W_D : sve_mem_64b_gld_vs2_64_unscaled<0b1011, "ldff1w">;
defm GLD1D : sve_mem_64b_gld_vs2_64_unscaled<0b1110, "ld1d">;
defm GLDFF1D : sve_mem_64b_gld_vs2_64_unscaled<0b1111, "ldff1d">;
// Gathers using scaled 64-bit offsets, e.g.
// ld1h z0.d, p0/z, [x0, z0.d, lsl #1]
defm GLD1SH_D : sve_mem_64b_gld_sv2_64_scaled<0b0100, "ld1sh", ZPR64ExtLSL16>;
defm GLDFF1SH_D : sve_mem_64b_gld_sv2_64_scaled<0b0101, "ldff1sh", ZPR64ExtLSL16>;
defm GLD1H_D : sve_mem_64b_gld_sv2_64_scaled<0b0110, "ld1h", ZPR64ExtLSL16>;
defm GLDFF1H_D : sve_mem_64b_gld_sv2_64_scaled<0b0111, "ldff1h", ZPR64ExtLSL16>;
defm GLD1SW_D : sve_mem_64b_gld_sv2_64_scaled<0b1000, "ld1sw", ZPR64ExtLSL32>;
defm GLDFF1SW_D : sve_mem_64b_gld_sv2_64_scaled<0b1001, "ldff1sw", ZPR64ExtLSL32>;
defm GLD1W_D : sve_mem_64b_gld_sv2_64_scaled<0b1010, "ld1w", ZPR64ExtLSL32>;
defm GLDFF1W_D : sve_mem_64b_gld_sv2_64_scaled<0b1011, "ldff1w", ZPR64ExtLSL32>;
defm GLD1D : sve_mem_64b_gld_sv2_64_scaled<0b1110, "ld1d", ZPR64ExtLSL64>;
defm GLDFF1D : sve_mem_64b_gld_sv2_64_scaled<0b1111, "ldff1d", ZPR64ExtLSL64>;
// Gathers using unscaled 32-bit offsets unpacked in 64-bits elements, e.g.
// ld1h z0.d, p0/z, [x0, z0.d, uxtw]
defm GLD1SB_D : sve_mem_64b_gld_vs_32_unscaled<0b0000, "ld1sb", ZPR64ExtSXTW8Only, ZPR64ExtUXTW8Only>;
defm GLDFF1SB_D : sve_mem_64b_gld_vs_32_unscaled<0b0001, "ldff1sb", ZPR64ExtSXTW8Only, ZPR64ExtUXTW8Only>;
defm GLD1B_D : sve_mem_64b_gld_vs_32_unscaled<0b0010, "ld1b", ZPR64ExtSXTW8Only, ZPR64ExtUXTW8Only>;
defm GLDFF1B_D : sve_mem_64b_gld_vs_32_unscaled<0b0011, "ldff1b", ZPR64ExtSXTW8Only, ZPR64ExtUXTW8Only>;
defm GLD1SH_D : sve_mem_64b_gld_vs_32_unscaled<0b0100, "ld1sh", ZPR64ExtSXTW8, ZPR64ExtUXTW8>;
defm GLDFF1SH_D : sve_mem_64b_gld_vs_32_unscaled<0b0101, "ldff1sh", ZPR64ExtSXTW8, ZPR64ExtUXTW8>;
defm GLD1H_D : sve_mem_64b_gld_vs_32_unscaled<0b0110, "ld1h", ZPR64ExtSXTW8, ZPR64ExtUXTW8>;
defm GLDFF1H_D : sve_mem_64b_gld_vs_32_unscaled<0b0111, "ldff1h", ZPR64ExtSXTW8, ZPR64ExtUXTW8>;
defm GLD1SW_D : sve_mem_64b_gld_vs_32_unscaled<0b1000, "ld1sw", ZPR64ExtSXTW8, ZPR64ExtUXTW8>;
defm GLDFF1SW_D : sve_mem_64b_gld_vs_32_unscaled<0b1001, "ldff1sw", ZPR64ExtSXTW8, ZPR64ExtUXTW8>;
defm GLD1W_D : sve_mem_64b_gld_vs_32_unscaled<0b1010, "ld1w", ZPR64ExtSXTW8, ZPR64ExtUXTW8>;
defm GLDFF1W_D : sve_mem_64b_gld_vs_32_unscaled<0b1011, "ldff1w", ZPR64ExtSXTW8, ZPR64ExtUXTW8>;
defm GLD1D : sve_mem_64b_gld_vs_32_unscaled<0b1110, "ld1d", ZPR64ExtSXTW8, ZPR64ExtUXTW8>;
defm GLDFF1D : sve_mem_64b_gld_vs_32_unscaled<0b1111, "ldff1d", ZPR64ExtSXTW8, ZPR64ExtUXTW8>;
// Gathers using scaled 32-bit offsets unpacked in 64-bits elements, e.g.
// ld1h z0.d, p0/z, [x0, z0.d, uxtw #1]
defm GLD1SH_D : sve_mem_64b_gld_sv_32_scaled<0b0100, "ld1sh", ZPR64ExtSXTW16, ZPR64ExtUXTW16>;
defm GLDFF1SH_D : sve_mem_64b_gld_sv_32_scaled<0b0101, "ldff1sh",ZPR64ExtSXTW16, ZPR64ExtUXTW16>;
defm GLD1H_D : sve_mem_64b_gld_sv_32_scaled<0b0110, "ld1h", ZPR64ExtSXTW16, ZPR64ExtUXTW16>;
defm GLDFF1H_D : sve_mem_64b_gld_sv_32_scaled<0b0111, "ldff1h", ZPR64ExtSXTW16, ZPR64ExtUXTW16>;
defm GLD1SW_D : sve_mem_64b_gld_sv_32_scaled<0b1000, "ld1sw", ZPR64ExtSXTW32, ZPR64ExtUXTW32>;
defm GLDFF1SW_D : sve_mem_64b_gld_sv_32_scaled<0b1001, "ldff1sw",ZPR64ExtSXTW32, ZPR64ExtUXTW32>;
defm GLD1W_D : sve_mem_64b_gld_sv_32_scaled<0b1010, "ld1w", ZPR64ExtSXTW32, ZPR64ExtUXTW32>;
defm GLDFF1W_D : sve_mem_64b_gld_sv_32_scaled<0b1011, "ldff1w", ZPR64ExtSXTW32, ZPR64ExtUXTW32>;
defm GLD1D : sve_mem_64b_gld_sv_32_scaled<0b1110, "ld1d", ZPR64ExtSXTW64, ZPR64ExtUXTW64>;
defm GLDFF1D : sve_mem_64b_gld_sv_32_scaled<0b1111, "ldff1d", ZPR64ExtSXTW64, ZPR64ExtUXTW64>;
// Non-temporal contiguous loads (register + immediate)
defm LDNT1B_ZRI : sve_mem_cldnt_si<0b00, "ldnt1b", Z_b, ZPR8>;
defm LDNT1H_ZRI : sve_mem_cldnt_si<0b01, "ldnt1h", Z_h, ZPR16>;
defm LDNT1W_ZRI : sve_mem_cldnt_si<0b10, "ldnt1w", Z_s, ZPR32>;
defm LDNT1D_ZRI : sve_mem_cldnt_si<0b11, "ldnt1d", Z_d, ZPR64>;
// Non-temporal contiguous loads (register + register)
defm LDNT1B_ZRR : sve_mem_cldnt_ss<0b00, "ldnt1b", Z_b, ZPR8, GPR64NoXZRshifted8>;
defm LDNT1H_ZRR : sve_mem_cldnt_ss<0b01, "ldnt1h", Z_h, ZPR16, GPR64NoXZRshifted16>;
defm LDNT1W_ZRR : sve_mem_cldnt_ss<0b10, "ldnt1w", Z_s, ZPR32, GPR64NoXZRshifted32>;
defm LDNT1D_ZRR : sve_mem_cldnt_ss<0b11, "ldnt1d", Z_d, ZPR64, GPR64NoXZRshifted64>;
// contiguous store with immediates
defm ST1B_IMM : sve_mem_cst_si<0b00, 0b00, "st1b", Z_b, ZPR8>;
defm ST1B_H_IMM : sve_mem_cst_si<0b00, 0b01, "st1b", Z_h, ZPR16>;
defm ST1B_S_IMM : sve_mem_cst_si<0b00, 0b10, "st1b", Z_s, ZPR32>;
defm ST1B_D_IMM : sve_mem_cst_si<0b00, 0b11, "st1b", Z_d, ZPR64>;
defm ST1H_IMM : sve_mem_cst_si<0b01, 0b01, "st1h", Z_h, ZPR16>;
defm ST1H_S_IMM : sve_mem_cst_si<0b01, 0b10, "st1h", Z_s, ZPR32>;
defm ST1H_D_IMM : sve_mem_cst_si<0b01, 0b11, "st1h", Z_d, ZPR64>;
defm ST1W_IMM : sve_mem_cst_si<0b10, 0b10, "st1w", Z_s, ZPR32>;
defm ST1W_D_IMM : sve_mem_cst_si<0b10, 0b11, "st1w", Z_d, ZPR64>;
defm ST1D_IMM : sve_mem_cst_si<0b11, 0b11, "st1d", Z_d, ZPR64>;
// contiguous store with reg+reg addressing.
defm ST1B : sve_mem_cst_ss<0b0000, "st1b", Z_b, ZPR8, GPR64NoXZRshifted8>;
defm ST1B_H : sve_mem_cst_ss<0b0001, "st1b", Z_h, ZPR16, GPR64NoXZRshifted8>;
defm ST1B_S : sve_mem_cst_ss<0b0010, "st1b", Z_s, ZPR32, GPR64NoXZRshifted8>;
defm ST1B_D : sve_mem_cst_ss<0b0011, "st1b", Z_d, ZPR64, GPR64NoXZRshifted8>;
defm ST1H : sve_mem_cst_ss<0b0101, "st1h", Z_h, ZPR16, GPR64NoXZRshifted16>;
defm ST1H_S : sve_mem_cst_ss<0b0110, "st1h", Z_s, ZPR32, GPR64NoXZRshifted16>;
defm ST1H_D : sve_mem_cst_ss<0b0111, "st1h", Z_d, ZPR64, GPR64NoXZRshifted16>;
defm ST1W : sve_mem_cst_ss<0b1010, "st1w", Z_s, ZPR32, GPR64NoXZRshifted32>;
defm ST1W_D : sve_mem_cst_ss<0b1011, "st1w", Z_d, ZPR64, GPR64NoXZRshifted32>;
defm ST1D : sve_mem_cst_ss<0b1111, "st1d", Z_d, ZPR64, GPR64NoXZRshifted64>;
// Scatters using unscaled 32-bit offsets, e.g.
// st1h z0.s, p0, [x0, z0.s, uxtw]
// and unpacked:
// st1h z0.d, p0, [x0, z0.d, uxtw]
defm SST1B_D : sve_mem_sst_sv_32_unscaled<0b000, "st1b", Z_d, ZPR64, ZPR64ExtSXTW8Only, ZPR64ExtUXTW8Only>;
defm SST1B_S : sve_mem_sst_sv_32_unscaled<0b001, "st1b", Z_s, ZPR32, ZPR32ExtSXTW8Only, ZPR32ExtUXTW8Only>;
defm SST1H_D : sve_mem_sst_sv_32_unscaled<0b010, "st1h", Z_d, ZPR64, ZPR64ExtSXTW8, ZPR64ExtUXTW8>;
defm SST1H_S : sve_mem_sst_sv_32_unscaled<0b011, "st1h", Z_s, ZPR32, ZPR32ExtSXTW8, ZPR32ExtUXTW8>;
defm SST1W_D : sve_mem_sst_sv_32_unscaled<0b100, "st1w", Z_d, ZPR64, ZPR64ExtSXTW8, ZPR64ExtUXTW8>;
defm SST1W : sve_mem_sst_sv_32_unscaled<0b101, "st1w", Z_s, ZPR32, ZPR32ExtSXTW8, ZPR32ExtUXTW8>;
defm SST1D : sve_mem_sst_sv_32_unscaled<0b110, "st1d", Z_d, ZPR64, ZPR64ExtSXTW8, ZPR64ExtUXTW8>;
// Scatters using scaled 32-bit offsets, e.g.
// st1h z0.s, p0, [x0, z0.s, uxtw #1]
// and unpacked:
// st1h z0.d, p0, [x0, z0.d, uxtw #1]
defm SST1H_D : sve_mem_sst_sv_32_scaled<0b010, "st1h", Z_d, ZPR64, ZPR64ExtSXTW16, ZPR64ExtUXTW16>;
defm SST1H_S : sve_mem_sst_sv_32_scaled<0b011, "st1h", Z_s, ZPR32, ZPR32ExtSXTW16, ZPR32ExtUXTW16>;
defm SST1W_D : sve_mem_sst_sv_32_scaled<0b100, "st1w", Z_d, ZPR64, ZPR64ExtSXTW32, ZPR64ExtUXTW32>;
defm SST1W : sve_mem_sst_sv_32_scaled<0b101, "st1w", Z_s, ZPR32, ZPR32ExtSXTW32, ZPR32ExtUXTW32>;
defm SST1D : sve_mem_sst_sv_32_scaled<0b110, "st1d", Z_d, ZPR64, ZPR64ExtSXTW64, ZPR64ExtUXTW64>;
// Scatters using 32/64-bit pointers with offset, e.g.
// st1h z0.s, p0, [z0.s, #16]
// st1h z0.d, p0, [z0.d, #16]
defm SST1B_D : sve_mem_sst_vi_ptrs<0b000, "st1b", Z_d, ZPR64, imm0_31>;
defm SST1B_S : sve_mem_sst_vi_ptrs<0b001, "st1b", Z_s, ZPR32, imm0_31>;
defm SST1H_D : sve_mem_sst_vi_ptrs<0b010, "st1h", Z_d, ZPR64, uimm5s2>;
defm SST1H_S : sve_mem_sst_vi_ptrs<0b011, "st1h", Z_s, ZPR32, uimm5s2>;
defm SST1W_D : sve_mem_sst_vi_ptrs<0b100, "st1w", Z_d, ZPR64, uimm5s4>;
defm SST1W : sve_mem_sst_vi_ptrs<0b101, "st1w", Z_s, ZPR32, uimm5s4>;
defm SST1D : sve_mem_sst_vi_ptrs<0b110, "st1d", Z_d, ZPR64, uimm5s8>;
// Scatters using unscaled 64-bit offsets, e.g.
// st1h z0.d, p0, [x0, z0.d]
defm SST1B_D : sve_mem_sst_sv_64_unscaled<0b00, "st1b">;
defm SST1H_D : sve_mem_sst_sv_64_unscaled<0b01, "st1h">;
defm SST1W_D : sve_mem_sst_sv_64_unscaled<0b10, "st1w">;
defm SST1D : sve_mem_sst_sv_64_unscaled<0b11, "st1d">;
// Scatters using scaled 64-bit offsets, e.g.
// st1h z0.d, p0, [x0, z0.d, lsl #1]
defm SST1H_D_SCALED : sve_mem_sst_sv_64_scaled<0b01, "st1h", ZPR64ExtLSL16>;
defm SST1W_D_SCALED : sve_mem_sst_sv_64_scaled<0b10, "st1w", ZPR64ExtLSL32>;
defm SST1D_SCALED : sve_mem_sst_sv_64_scaled<0b11, "st1d", ZPR64ExtLSL64>;
// ST(2|3|4) structured stores (register + immediate)
defm ST2B_IMM : sve_mem_est_si<0b00, 0b01, ZZ_b, "st2b", simm4s2>;
defm ST3B_IMM : sve_mem_est_si<0b00, 0b10, ZZZ_b, "st3b", simm4s3>;
defm ST4B_IMM : sve_mem_est_si<0b00, 0b11, ZZZZ_b, "st4b", simm4s4>;
defm ST2H_IMM : sve_mem_est_si<0b01, 0b01, ZZ_h, "st2h", simm4s2>;
defm ST3H_IMM : sve_mem_est_si<0b01, 0b10, ZZZ_h, "st3h", simm4s3>;
defm ST4H_IMM : sve_mem_est_si<0b01, 0b11, ZZZZ_h, "st4h", simm4s4>;
defm ST2W_IMM : sve_mem_est_si<0b10, 0b01, ZZ_s, "st2w", simm4s2>;
defm ST3W_IMM : sve_mem_est_si<0b10, 0b10, ZZZ_s, "st3w", simm4s3>;
defm ST4W_IMM : sve_mem_est_si<0b10, 0b11, ZZZZ_s, "st4w", simm4s4>;
defm ST2D_IMM : sve_mem_est_si<0b11, 0b01, ZZ_d, "st2d", simm4s2>;
defm ST3D_IMM : sve_mem_est_si<0b11, 0b10, ZZZ_d, "st3d", simm4s3>;
defm ST4D_IMM : sve_mem_est_si<0b11, 0b11, ZZZZ_d, "st4d", simm4s4>;
// ST(2|3|4) structured stores (register + register)
def ST2B : sve_mem_est_ss<0b00, 0b01, ZZ_b, "st2b", GPR64NoXZRshifted8>;
def ST3B : sve_mem_est_ss<0b00, 0b10, ZZZ_b, "st3b", GPR64NoXZRshifted8>;
def ST4B : sve_mem_est_ss<0b00, 0b11, ZZZZ_b, "st4b", GPR64NoXZRshifted8>;
def ST2H : sve_mem_est_ss<0b01, 0b01, ZZ_h, "st2h", GPR64NoXZRshifted16>;
def ST3H : sve_mem_est_ss<0b01, 0b10, ZZZ_h, "st3h", GPR64NoXZRshifted16>;
def ST4H : sve_mem_est_ss<0b01, 0b11, ZZZZ_h, "st4h", GPR64NoXZRshifted16>;
def ST2W : sve_mem_est_ss<0b10, 0b01, ZZ_s, "st2w", GPR64NoXZRshifted32>;
def ST3W : sve_mem_est_ss<0b10, 0b10, ZZZ_s, "st3w", GPR64NoXZRshifted32>;
def ST4W : sve_mem_est_ss<0b10, 0b11, ZZZZ_s, "st4w", GPR64NoXZRshifted32>;
def ST2D : sve_mem_est_ss<0b11, 0b01, ZZ_d, "st2d", GPR64NoXZRshifted64>;
def ST3D : sve_mem_est_ss<0b11, 0b10, ZZZ_d, "st3d", GPR64NoXZRshifted64>;
def ST4D : sve_mem_est_ss<0b11, 0b11, ZZZZ_d, "st4d", GPR64NoXZRshifted64>;
// Non-temporal contiguous stores (register + immediate)
defm STNT1B_ZRI : sve_mem_cstnt_si<0b00, "stnt1b", Z_b, ZPR8>;
defm STNT1H_ZRI : sve_mem_cstnt_si<0b01, "stnt1h", Z_h, ZPR16>;
defm STNT1W_ZRI : sve_mem_cstnt_si<0b10, "stnt1w", Z_s, ZPR32>;
defm STNT1D_ZRI : sve_mem_cstnt_si<0b11, "stnt1d", Z_d, ZPR64>;
// Non-temporal contiguous stores (register + register)
defm STNT1B_ZRR : sve_mem_cstnt_ss<0b00, "stnt1b", Z_b, ZPR8, GPR64NoXZRshifted8>;
defm STNT1H_ZRR : sve_mem_cstnt_ss<0b01, "stnt1h", Z_h, ZPR16, GPR64NoXZRshifted16>;
defm STNT1W_ZRR : sve_mem_cstnt_ss<0b10, "stnt1w", Z_s, ZPR32, GPR64NoXZRshifted32>;
defm STNT1D_ZRR : sve_mem_cstnt_ss<0b11, "stnt1d", Z_d, ZPR64, GPR64NoXZRshifted64>;
// Fill/Spill
defm LDR_ZXI : sve_mem_z_fill<"ldr">;
defm LDR_PXI : sve_mem_p_fill<"ldr">;
defm STR_ZXI : sve_mem_z_spill<"str">;
defm STR_PXI : sve_mem_p_spill<"str">;
// Contiguous prefetch (register + immediate)
defm PRFB_PRI : sve_mem_prfm_si<0b00, "prfb">;
defm PRFH_PRI : sve_mem_prfm_si<0b01, "prfh">;
defm PRFW_PRI : sve_mem_prfm_si<0b10, "prfw">;
defm PRFD_PRI : sve_mem_prfm_si<0b11, "prfd">;
// Contiguous prefetch (register + register)
def PRFB_PRR : sve_mem_prfm_ss<0b001, "prfb", GPR64NoXZRshifted8>;
def PRFH_PRR : sve_mem_prfm_ss<0b011, "prfh", GPR64NoXZRshifted16>;
def PRFS_PRR : sve_mem_prfm_ss<0b101, "prfw", GPR64NoXZRshifted32>;
def PRFD_PRR : sve_mem_prfm_ss<0b111, "prfd", GPR64NoXZRshifted64>;
// Gather prefetch using scaled 32-bit offsets, e.g.
// prfh pldl1keep, p0, [x0, z0.s, uxtw #1]
defm PRFB_S : sve_mem_32b_prfm_sv_scaled<0b00, "prfb", ZPR32ExtSXTW8Only, ZPR32ExtUXTW8Only>;
defm PRFH_S : sve_mem_32b_prfm_sv_scaled<0b01, "prfh", ZPR32ExtSXTW16, ZPR32ExtUXTW16>;
defm PRFW_S : sve_mem_32b_prfm_sv_scaled<0b10, "prfw", ZPR32ExtSXTW32, ZPR32ExtUXTW32>;
defm PRFD_S : sve_mem_32b_prfm_sv_scaled<0b11, "prfd", ZPR32ExtSXTW64, ZPR32ExtUXTW64>;
// Gather prefetch using unpacked, scaled 32-bit offsets, e.g.
// prfh pldl1keep, p0, [x0, z0.d, uxtw #1]
defm PRFB_D : sve_mem_64b_prfm_sv_ext_scaled<0b00, "prfb", ZPR64ExtSXTW8Only, ZPR64ExtUXTW8Only>;
defm PRFH_D : sve_mem_64b_prfm_sv_ext_scaled<0b01, "prfh", ZPR64ExtSXTW16, ZPR64ExtUXTW16>;
defm PRFW_D : sve_mem_64b_prfm_sv_ext_scaled<0b10, "prfw", ZPR64ExtSXTW32, ZPR64ExtUXTW32>;
defm PRFD_D : sve_mem_64b_prfm_sv_ext_scaled<0b11, "prfd", ZPR64ExtSXTW64, ZPR64ExtUXTW64>;
// Gather prefetch using scaled 64-bit offsets, e.g.
// prfh pldl1keep, p0, [x0, z0.d, lsl #1]
defm PRFB_D_SCALED : sve_mem_64b_prfm_sv_lsl_scaled<0b00, "prfb", ZPR64ExtLSL8>;
defm PRFH_D_SCALED : sve_mem_64b_prfm_sv_lsl_scaled<0b01, "prfh", ZPR64ExtLSL16>;
defm PRFW_D_SCALED : sve_mem_64b_prfm_sv_lsl_scaled<0b10, "prfw", ZPR64ExtLSL32>;
defm PRFD_D_SCALED : sve_mem_64b_prfm_sv_lsl_scaled<0b11, "prfd", ZPR64ExtLSL64>;
// Gather prefetch using 32/64-bit pointers with offset, e.g.
// prfh pldl1keep, p0, [z0.s, #16]
// prfh pldl1keep, p0, [z0.d, #16]
defm PRFB_S_PZI : sve_mem_32b_prfm_vi<0b00, "prfb", imm0_31>;
defm PRFH_S_PZI : sve_mem_32b_prfm_vi<0b01, "prfh", uimm5s2>;
defm PRFW_S_PZI : sve_mem_32b_prfm_vi<0b10, "prfw", uimm5s4>;
defm PRFD_S_PZI : sve_mem_32b_prfm_vi<0b11, "prfd", uimm5s8>;
defm PRFB_D_PZI : sve_mem_64b_prfm_vi<0b00, "prfb", imm0_31>;
defm PRFH_D_PZI : sve_mem_64b_prfm_vi<0b01, "prfh", uimm5s2>;
defm PRFW_D_PZI : sve_mem_64b_prfm_vi<0b10, "prfw", uimm5s4>;
defm PRFD_D_PZI : sve_mem_64b_prfm_vi<0b11, "prfd", uimm5s8>;
defm ZIP1_ZZZ : sve_int_perm_bin_perm_zz<0b000, "zip1">;
defm ZIP2_ZZZ : sve_int_perm_bin_perm_zz<0b001, "zip2">;
defm ZIP1_PPP : sve_int_perm_bin_perm_pp<0b000, "zip1">;
defm ZIP2_PPP : sve_int_perm_bin_perm_pp<0b001, "zip2">;
def RDVLI_XI : sve_int_read_vl_a<0b0, 0b11111, "rdvl">;
def ADDVL_XXI : sve_int_arith_vl<0b0, "addvl">;
def ADDPL_XXI : sve_int_arith_vl<0b1, "addpl">;
defm INCB_XPiI : sve_int_pred_pattern_a<0b000, "incb">;
defm DECB_XPiI : sve_int_pred_pattern_a<0b001, "decb">;
defm INCH_XPiI : sve_int_pred_pattern_a<0b010, "inch">;
defm DECH_XPiI : sve_int_pred_pattern_a<0b011, "dech">;
defm INCW_XPiI : sve_int_pred_pattern_a<0b100, "incw">;
defm DECW_XPiI : sve_int_pred_pattern_a<0b101, "decw">;
defm INCD_XPiI : sve_int_pred_pattern_a<0b110, "incd">;
defm DECD_XPiI : sve_int_pred_pattern_a<0b111, "decd">;
defm CMPHS_PPzZZ : sve_int_cmp_0<0b000, "cmphs">;
defm CMPHI_PPzZZ : sve_int_cmp_0<0b001, "cmphi">;
defm CMPGE_PPzZZ : sve_int_cmp_0<0b100, "cmpge">;
defm CMPGT_PPzZZ : sve_int_cmp_0<0b101, "cmpgt">;
defm CMPEQ_PPzZZ : sve_int_cmp_0<0b110, "cmpeq">;
defm CMPNE_PPzZZ : sve_int_cmp_0<0b111, "cmpne">;
defm CMPEQ_WIDE_PPzZZ : sve_int_cmp_0_wide<0b010, "cmpeq">;
defm CMPNE_WIDE_PPzZZ : sve_int_cmp_0_wide<0b011, "cmpne">;
defm CMPGE_WIDE_PPzZZ : sve_int_cmp_1_wide<0b000, "cmpge">;
defm CMPGT_WIDE_PPzZZ : sve_int_cmp_1_wide<0b001, "cmpgt">;
defm CMPLT_WIDE_PPzZZ : sve_int_cmp_1_wide<0b010, "cmplt">;
defm CMPLE_WIDE_PPzZZ : sve_int_cmp_1_wide<0b011, "cmple">;
defm CMPHS_WIDE_PPzZZ : sve_int_cmp_1_wide<0b100, "cmphs">;
defm CMPHI_WIDE_PPzZZ : sve_int_cmp_1_wide<0b101, "cmphi">;
defm CMPLO_WIDE_PPzZZ : sve_int_cmp_1_wide<0b110, "cmplo">;
defm CMPLS_WIDE_PPzZZ : sve_int_cmp_1_wide<0b111, "cmpls">;
defm SQINCB_XPiI : sve_int_pred_pattern_b_x64<0b00100, "sqincb">;
defm UQINCB_XPiI : sve_int_pred_pattern_b_x64<0b00101, "uqincb">;
defm SQDECB_XPiI : sve_int_pred_pattern_b_x64<0b00110, "sqdecb">;
defm UQDECB_XPiI : sve_int_pred_pattern_b_x64<0b00111, "uqdecb">;
defm SQINCH_XPiI : sve_int_pred_pattern_b_x64<0b01100, "sqinch">;
defm UQINCH_XPiI : sve_int_pred_pattern_b_x64<0b01101, "uqinch">;
defm SQDECH_XPiI : sve_int_pred_pattern_b_x64<0b01110, "sqdech">;
defm UQDECH_XPiI : sve_int_pred_pattern_b_x64<0b01111, "uqdech">;
defm SQINCW_XPiI : sve_int_pred_pattern_b_x64<0b10100, "sqincw">;
defm UQINCW_XPiI : sve_int_pred_pattern_b_x64<0b10101, "uqincw">;
defm SQDECW_XPiI : sve_int_pred_pattern_b_x64<0b10110, "sqdecw">;
defm UQDECW_XPiI : sve_int_pred_pattern_b_x64<0b10111, "uqdecw">;
defm SQINCD_XPiI : sve_int_pred_pattern_b_x64<0b11100, "sqincd">;
defm UQINCD_XPiI : sve_int_pred_pattern_b_x64<0b11101, "uqincd">;
defm SQDECD_XPiI : sve_int_pred_pattern_b_x64<0b11110, "sqdecd">;
defm UQDECD_XPiI : sve_int_pred_pattern_b_x64<0b11111, "uqdecd">;
defm INDEX_RR : sve_int_index_rr<"index">;
defm INDEX_IR : sve_int_index_ir<"index">;
defm INDEX_RI : sve_int_index_ri<"index">;
defm INDEX_II : sve_int_index_ii<"index">;
defm LSR_ZZI : sve_int_bin_cons_shift_b_right<0b01, "lsr">;
defm LSL_ZZI : sve_int_bin_cons_shift_b_left< 0b11, "lsl">;
defm LSR_ZPmZ : sve_int_bin_pred_shift_1<0b001, "lsr">;
defm LSL_ZPmZ : sve_int_bin_pred_shift_1<0b011, "lsl">;
// InstAliases
def : InstAlias<"mov $Zd, $Zn",
(ORR_ZZZ ZPR64:$Zd, ZPR64:$Zn, ZPR64:$Zn), 1>;
def : InstAlias<"mov $Pd, $Pg/m, $Pn",
(SEL_PPPP PPR8:$Pd, PPRAny:$Pg, PPR8:$Pn, PPR8:$Pd), 1>;
def : InstAlias<"mov $Pd, $Pn",
(ORR_PPzPP PPR8:$Pd, PPR8:$Pn, PPR8:$Pn, PPR8:$Pn), 1>;
def : InstAlias<"mov $Pd, $Pg/z, $Pn",
(AND_PPzPP PPR8:$Pd, PPRAny:$Pg, PPR8:$Pn, PPR8:$Pn), 1>;
def : InstAlias<"movs $Pd, $Pn",
(ORRS_PPzPP PPR8:$Pd, PPR8:$Pn, PPR8:$Pn, PPR8:$Pn), 1>;
def : InstAlias<"movs $Pd, $Pg/z, $Pn",
(ANDS_PPzPP PPR8:$Pd, PPRAny:$Pg, PPR8:$Pn, PPR8:$Pn), 1>;
def : InstAlias<"not $Pd, $Pg/z, $Pn",
(EOR_PPzPP PPR8:$Pd, PPRAny:$Pg, PPR8:$Pn, PPRAny:$Pg), 1>;
def : InstAlias<"nots $Pd, $Pg/z, $Pn",
(EORS_PPzPP PPR8:$Pd, PPRAny:$Pg, PPR8:$Pn, PPRAny:$Pg), 1>;
def : InstAlias<"cmple $Zd, $Pg/z, $Zm, $Zn",
(CMPGE_PPzZZ_B PPR8:$Zd, PPR3bAny:$Pg, ZPR8:$Zn, ZPR8:$Zm), 0>;
def : InstAlias<"cmple $Zd, $Pg/z, $Zm, $Zn",
(CMPGE_PPzZZ_H PPR16:$Zd, PPR3bAny:$Pg, ZPR16:$Zn, ZPR16:$Zm), 0>;
def : InstAlias<"cmple $Zd, $Pg/z, $Zm, $Zn",
(CMPGE_PPzZZ_S PPR32:$Zd, PPR3bAny:$Pg, ZPR32:$Zn, ZPR32:$Zm), 0>;
def : InstAlias<"cmple $Zd, $Pg/z, $Zm, $Zn",
(CMPGE_PPzZZ_D PPR64:$Zd, PPR3bAny:$Pg, ZPR64:$Zn, ZPR64:$Zm), 0>;
def : InstAlias<"cmplo $Zd, $Pg/z, $Zm, $Zn",
(CMPHI_PPzZZ_B PPR8:$Zd, PPR3bAny:$Pg, ZPR8:$Zn, ZPR8:$Zm), 0>;
def : InstAlias<"cmplo $Zd, $Pg/z, $Zm, $Zn",
(CMPHI_PPzZZ_H PPR16:$Zd, PPR3bAny:$Pg, ZPR16:$Zn, ZPR16:$Zm), 0>;
def : InstAlias<"cmplo $Zd, $Pg/z, $Zm, $Zn",
(CMPHI_PPzZZ_S PPR32:$Zd, PPR3bAny:$Pg, ZPR32:$Zn, ZPR32:$Zm), 0>;
def : InstAlias<"cmplo $Zd, $Pg/z, $Zm, $Zn",
(CMPHI_PPzZZ_D PPR64:$Zd, PPR3bAny:$Pg, ZPR64:$Zn, ZPR64:$Zm), 0>;
def : InstAlias<"cmpls $Zd, $Pg/z, $Zm, $Zn",
(CMPHS_PPzZZ_B PPR8:$Zd, PPR3bAny:$Pg, ZPR8:$Zn, ZPR8:$Zm), 0>;
def : InstAlias<"cmpls $Zd, $Pg/z, $Zm, $Zn",
(CMPHS_PPzZZ_H PPR16:$Zd, PPR3bAny:$Pg, ZPR16:$Zn, ZPR16:$Zm), 0>;
def : InstAlias<"cmpls $Zd, $Pg/z, $Zm, $Zn",
(CMPHS_PPzZZ_S PPR32:$Zd, PPR3bAny:$Pg, ZPR32:$Zn, ZPR32:$Zm), 0>;
def : InstAlias<"cmpls $Zd, $Pg/z, $Zm, $Zn",
(CMPHS_PPzZZ_D PPR64:$Zd, PPR3bAny:$Pg, ZPR64:$Zn, ZPR64:$Zm), 0>;
def : InstAlias<"cmplt $Zd, $Pg/z, $Zm, $Zn",
(CMPGT_PPzZZ_B PPR8:$Zd, PPR3bAny:$Pg, ZPR8:$Zn, ZPR8:$Zm), 0>;
def : InstAlias<"cmplt $Zd, $Pg/z, $Zm, $Zn",
(CMPGT_PPzZZ_H PPR16:$Zd, PPR3bAny:$Pg, ZPR16:$Zn, ZPR16:$Zm), 0>;
def : InstAlias<"cmplt $Zd, $Pg/z, $Zm, $Zn",
(CMPGT_PPzZZ_S PPR32:$Zd, PPR3bAny:$Pg, ZPR32:$Zn, ZPR32:$Zm), 0>;
def : InstAlias<"cmplt $Zd, $Pg/z, $Zm, $Zn",
(CMPGT_PPzZZ_D PPR64:$Zd, PPR3bAny:$Pg, ZPR64:$Zn, ZPR64:$Zm), 0>;
}