/* Extra machine modes for RISC-V target.
   Copyright (C) 2011-2022 Free Software Foundation, Inc.
   Contributed by Andrew Waterman (andrew@sifive.com).
   Based on MIPS target for GNU compiler.

This file is part of GCC.

GCC is free software; you can redistribute it and/or modify
it under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 3, or (at your option)
any later version.

GCC is distributed in the hope that it will be useful,
but WITHOUT ANY WARRANTY; without even the implied warranty of
MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
GNU General Public License for more details.

You should have received a copy of the GNU General Public License
along with GCC; see the file COPYING3.  If not see
<http://www.gnu.org/licenses/>.  */

FLOAT_MODE (HF, 2, ieee_half_format);
FLOAT_MODE (TF, 16, ieee_quad_format);

/* Vector modes.  */

/* Encode the ratio of SEW/LMUL into the mask types. There are the following
 * mask types.  */

/* | Mode     | MIN_VLEN = 32 | MIN_VLEN = 64 |
   |          | SEW/LMUL      | SEW/LMUL      |
   | VNx1BI   | 32            | 64            |
   | VNx2BI   | 16            | 32            |
   | VNx4BI   | 8             | 16            |
   | VNx8BI   | 4             | 8             |
   | VNx16BI  | 2             | 4             |
   | VNx32BI  | 1             | 2             |
   | VNx64BI  | N/A           | 1             |  */

/* For RVV modes, each boolean value occupies 1-bit.
   4th argument is specify the minmial possible size of the vector mode,
   and will adjust to the right size by ADJUST_BYTESIZE.  */
VECTOR_BOOL_MODE (VNx1BI, 1, BI, 1);
VECTOR_BOOL_MODE (VNx2BI, 2, BI, 1);
VECTOR_BOOL_MODE (VNx4BI, 4, BI, 1);
VECTOR_BOOL_MODE (VNx8BI, 8, BI, 1);
VECTOR_BOOL_MODE (VNx16BI, 16, BI, 2);
VECTOR_BOOL_MODE (VNx32BI, 32, BI, 4);
VECTOR_BOOL_MODE (VNx64BI, 64, BI, 8);

ADJUST_NUNITS (VNx1BI, riscv_v_adjust_nunits (VNx1BImode, 1));
ADJUST_NUNITS (VNx2BI, riscv_v_adjust_nunits (VNx2BImode, 2));
ADJUST_NUNITS (VNx4BI, riscv_v_adjust_nunits (VNx4BImode, 4));
ADJUST_NUNITS (VNx8BI, riscv_v_adjust_nunits (VNx8BImode, 8));
ADJUST_NUNITS (VNx16BI, riscv_v_adjust_nunits (VNx16BImode, 16));
ADJUST_NUNITS (VNx32BI, riscv_v_adjust_nunits (VNx32BImode, 32));
ADJUST_NUNITS (VNx64BI, riscv_v_adjust_nunits (VNx64BImode, 64));

ADJUST_ALIGNMENT (VNx1BI, 1);
ADJUST_ALIGNMENT (VNx2BI, 1);
ADJUST_ALIGNMENT (VNx4BI, 1);
ADJUST_ALIGNMENT (VNx8BI, 1);
ADJUST_ALIGNMENT (VNx16BI, 1);
ADJUST_ALIGNMENT (VNx32BI, 1);
ADJUST_ALIGNMENT (VNx64BI, 1);

ADJUST_BYTESIZE (VNx1BI, riscv_vector_chunks * riscv_bytes_per_vector_chunk);
ADJUST_BYTESIZE (VNx2BI, riscv_vector_chunks * riscv_bytes_per_vector_chunk);
ADJUST_BYTESIZE (VNx4BI, riscv_vector_chunks * riscv_bytes_per_vector_chunk);
ADJUST_BYTESIZE (VNx8BI, riscv_vector_chunks * riscv_bytes_per_vector_chunk);
ADJUST_BYTESIZE (VNx16BI, riscv_vector_chunks * riscv_bytes_per_vector_chunk);
ADJUST_BYTESIZE (VNx32BI, riscv_vector_chunks * riscv_bytes_per_vector_chunk);
ADJUST_BYTESIZE (VNx64BI, riscv_v_adjust_nunits (VNx64BImode, 8));

/*
   | Mode        | MIN_VLEN=32 | MIN_VLEN=32 | MIN_VLEN=64 | MIN_VLEN=64 |
   |             | LMUL        | SEW/LMUL    | LMUL        | SEW/LMUL    |
   | VNx1QI      | MF4         | 32          | MF8         | 64          |
   | VNx2QI      | MF2         | 16          | MF4         | 32          |
   | VNx4QI      | M1          | 8           | MF2         | 16          |
   | VNx8QI      | M2          | 4           | M1          | 8           |
   | VNx16QI     | M4          | 2           | M2          | 4           |
   | VNx32QI     | M8          | 1           | M4          | 2           |
   | VNx64QI     | N/A         | N/A         | M8          | 1           |
   | VNx1(HI|HF) | MF2         | 32          | MF4         | 64          |
   | VNx2(HI|HF) | M1          | 16          | MF2         | 32          |
   | VNx4(HI|HF) | M2          | 8           | M1          | 16          |
   | VNx8(HI|HF) | M4          | 4           | M2          | 8           |
   | VNx16(HI|HF)| M8          | 2           | M4          | 4           |
   | VNx32(HI|HF)| N/A         | N/A         | M8          | 2           |
   | VNx1(SI|SF) | M1          | 32          | MF2         | 64          |
   | VNx2(SI|SF) | M2          | 16          | M1          | 32          |
   | VNx4(SI|SF) | M4          | 8           | M2          | 16          |
   | VNx8(SI|SF) | M8          | 4           | M4          | 8           |
   | VNx16(SI|SF)| N/A         | N/A         | M8          | 4           |
   | VNx1(DI|DF) | N/A         | N/A         | M1          | 64          |
   | VNx2(DI|DF) | N/A         | N/A         | M2          | 32          |
   | VNx4(DI|DF) | N/A         | N/A         | M4          | 16          |
   | VNx8(DI|DF) | N/A         | N/A         | M8          | 8           |
*/

/* Define RVV modes whose sizes are multiples of 64-bit chunks.  */
#define RVV_MODES(NVECS, VB, VH, VS, VD)                                       \
  VECTOR_MODES_WITH_PREFIX (VNx, INT, 8 * NVECS, 0);                           \
  VECTOR_MODES_WITH_PREFIX (VNx, FLOAT, 8 * NVECS, 0);                         \
                                                                               \
  ADJUST_NUNITS (VB##QI, riscv_v_adjust_nunits (VB##QI##mode, NVECS * 8));     \
  ADJUST_NUNITS (VH##HI, riscv_v_adjust_nunits (VH##HI##mode, NVECS * 4));     \
  ADJUST_NUNITS (VS##SI, riscv_v_adjust_nunits (VS##SI##mode, NVECS * 2));     \
  ADJUST_NUNITS (VD##DI, riscv_v_adjust_nunits (VD##DI##mode, NVECS));         \
  ADJUST_NUNITS (VH##HF, riscv_v_adjust_nunits (VH##HF##mode, NVECS * 4));     \
  ADJUST_NUNITS (VS##SF, riscv_v_adjust_nunits (VS##SF##mode, NVECS * 2));     \
  ADJUST_NUNITS (VD##DF, riscv_v_adjust_nunits (VD##DF##mode, NVECS));         \
                                                                               \
  ADJUST_ALIGNMENT (VB##QI, 1);                                                \
  ADJUST_ALIGNMENT (VH##HI, 2);                                                \
  ADJUST_ALIGNMENT (VS##SI, 4);                                                \
  ADJUST_ALIGNMENT (VD##DI, 8);                                                \
  ADJUST_ALIGNMENT (VH##HF, 2);                                                \
  ADJUST_ALIGNMENT (VS##SF, 4);                                                \
  ADJUST_ALIGNMENT (VD##DF, 8);

/* 'VECTOR_MODES_WITH_PREFIX' does not allow ncomponents < 2.
   So we use 'VECTOR_MODE_WITH_PREFIX' to define VNx1DImode and VNx1DFmode.  */
VECTOR_MODE_WITH_PREFIX (VNx, INT, DI, 1, 0);
VECTOR_MODE_WITH_PREFIX (VNx, FLOAT, DF, 1, 0);
RVV_MODES (1, VNx8, VNx4, VNx2, VNx1)
RVV_MODES (2, VNx16, VNx8, VNx4, VNx2)
RVV_MODES (4, VNx32, VNx16, VNx8, VNx4)
RVV_MODES (8, VNx64, VNx32, VNx16, VNx8)

VECTOR_MODES_WITH_PREFIX (VNx, INT, 4, 0);
VECTOR_MODES_WITH_PREFIX (VNx, FLOAT, 4, 0);
ADJUST_NUNITS (VNx4QI, riscv_v_adjust_nunits (VNx4QImode, 4));
ADJUST_NUNITS (VNx2HI, riscv_v_adjust_nunits (VNx2HImode, 2));
ADJUST_NUNITS (VNx2HF, riscv_v_adjust_nunits (VNx2HFmode, 2));
ADJUST_ALIGNMENT (VNx4QI, 1);
ADJUST_ALIGNMENT (VNx2HI, 2);
ADJUST_ALIGNMENT (VNx2HF, 2);

/* 'VECTOR_MODES_WITH_PREFIX' does not allow ncomponents < 2.
   So we use 'VECTOR_MODE_WITH_PREFIX' to define VNx1SImode and VNx1SFmode.  */
VECTOR_MODE_WITH_PREFIX (VNx, INT, SI, 1, 0);
VECTOR_MODE_WITH_PREFIX (VNx, FLOAT, SF, 1, 0);
ADJUST_NUNITS (VNx1SI, riscv_v_adjust_nunits (VNx1SImode, 1));
ADJUST_NUNITS (VNx1SF, riscv_v_adjust_nunits (VNx1SFmode, 1));
ADJUST_ALIGNMENT (VNx1SI, 4);
ADJUST_ALIGNMENT (VNx1SF, 4);

VECTOR_MODES_WITH_PREFIX (VNx, INT, 2, 0);
ADJUST_NUNITS (VNx2QI, riscv_v_adjust_nunits (VNx2QImode, 2));
ADJUST_ALIGNMENT (VNx2QI, 1);

/* 'VECTOR_MODES_WITH_PREFIX' does not allow ncomponents < 2.
   So we use 'VECTOR_MODE_WITH_PREFIX' to define VNx1HImode and VNx1HFmode.  */
VECTOR_MODE_WITH_PREFIX (VNx, INT, HI, 1, 0);
VECTOR_MODE_WITH_PREFIX (VNx, FLOAT, HF, 1, 0);
ADJUST_NUNITS (VNx1HI, riscv_v_adjust_nunits (VNx1HImode, 1));
ADJUST_NUNITS (VNx1HF, riscv_v_adjust_nunits (VNx1HFmode, 1));
ADJUST_ALIGNMENT (VNx1HI, 2);
ADJUST_ALIGNMENT (VNx1HF, 2);

/* 'VECTOR_MODES_WITH_PREFIX' does not allow ncomponents < 2.
   So we use 'VECTOR_MODE_WITH_PREFIX' to define VNx1QImode.  */
VECTOR_MODE_WITH_PREFIX (VNx, INT, QI, 1, 0);
ADJUST_NUNITS (VNx1QI, riscv_v_adjust_nunits (VNx1QImode, 1));
ADJUST_ALIGNMENT (VNx1QI, 1);

/* TODO: According to RISC-V 'V' ISA spec, the maximun vector length can
   be 65536 for a single vector register which means the vector mode in
   GCC can be maximum = 65536 * 8 bits (LMUL=8).
   However, 'GET_MODE_SIZE' is using poly_uint16/unsigned short which will
   overflow if we specify vector-length = 65536. To support this feature,
   we need to change the codes outside the RISC-V port. We will support it in
   the future.  */
#define MAX_BITSIZE_MODE_ANY_MODE (4096 * 8)

/* Coefficient 1 is multiplied by the number of 64-bit/32-bit chunks in a vector
   minus one.  */
#define NUM_POLY_INT_COEFFS 2