# Copyright 2022 Alyssa Rosenzweig
# Copyright 2021 Collabora, Ltd.
# Copyright 2016 Intel Corporation
# SPDX-License-Identifier: MIT

import argparse
import sys
import math

a = 'a'
b = 'b'
c = 'c'
d = 'd'
e = 'e'

lower_sm5_shift = []

# Our shifts differ from SM5 for the upper bits. Mask to match the NIR
# behaviour. Because this happens as a late lowering, NIR won't optimize the
# masking back out (that happens in the main nir_opt_algebraic).
for s in [8, 16, 32, 64]:
    for shift in ["ishl", "ishr", "ushr"]:
        lower_sm5_shift += [((shift, f'a@{s}', b),
                             (shift, a, ('iand', b, s - 1)))]

lower_pack = [
    (('pack_half_2x16_split', a, b),
     ('pack_32_2x16_split', ('f2f16', a), ('f2f16', b))),

    # We don't have 8-bit ALU, so we need to lower this. But if we lower it like
    # this, we can at least coalesce the pack_32_2x16_split and only pay the
    # cost of the iors and ishl. (u2u16 of 8-bit is assumed free.)
    (('pack_32_4x8_split', a, b, c, d),
     ('pack_32_2x16_split', ('ior', ('u2u16', a), ('ishl', ('u2u16', b), 8)),
                            ('ior', ('u2u16', c), ('ishl', ('u2u16', d), 8)))),

    (('unpack_half_2x16_split_x', a), ('f2f32', ('unpack_32_2x16_split_x', a))),
    (('unpack_half_2x16_split_y', a), ('f2f32', ('unpack_32_2x16_split_y', a))),

    (('extract_u16', 'a@32', 0), ('u2u32', ('unpack_32_2x16_split_x', a))),
    (('extract_u16', 'a@32', 1), ('u2u32', ('unpack_32_2x16_split_y', a))),
    (('extract_i16', 'a@32', 0), ('i2i32', ('unpack_32_2x16_split_x', a))),
    (('extract_i16', 'a@32', 1), ('i2i32', ('unpack_32_2x16_split_y', a))),

    # For optimizing extract->convert sequences for unpack/pack norm
    (('u2f32', ('u2u32', a)), ('u2f32', a)),
    (('i2f32', ('i2i32', a)), ('i2f32', a)),

    # Chew through some 8-bit before the backend has to deal with it
    (('f2u8', a), ('u2u8', ('f2u16', a))),
    (('f2i8', a), ('i2i8', ('f2i16', a))),

    # Duplicated from nir_opt_algebraic since this pattern is generated by our
    # bounds checking optimization which needs to run relatively late.
    (('unpack_64_2x32_split_x', ('pack_64_2x32_split', a, b)), a),
    (('unpack_64_2x32_split_y', ('pack_64_2x32_split', a, b)), b),

    # Based on the VIR lowering
    (('f2f16_rtz', 'a@32'),
     ('bcsel', ('flt', ('fabs', a), ('fabs', ('f2f32', ('f2f16_rtne', a)))),
      ('isub', ('f2f16_rtne', a), 1), ('f2f16_rtne', a))),

    # These are based on the lowerings from nir_opt_algebraic, but conditioned
    # on the number of bits not being constant. If the bit count is constant
    # (the happy path) we can use our native instruction instead.
    (('ibitfield_extract', 'value', 'offset', 'bits(is_not_const)'),
     ('bcsel', ('ieq', 0, 'bits'),
      0,
      ('ishr',
       ('ishl', 'value', ('isub', ('isub', 32, 'bits'), 'offset')),
       ('isub', 32, 'bits')))),

    (('ubitfield_extract', 'value', 'offset', 'bits(is_not_const)'),
     ('iand',
      ('ushr', 'value', 'offset'),
      ('bcsel', ('ieq', 'bits', 32),
       0xffffffff,
       ('isub', ('ishl', 1, 'bits'), 1)))),

    # Codegen depends on this trivial case being optimized out.
    (('ubitfield_extract', 'value', 'offset', 0), 0),
    (('ibitfield_extract', 'value', 'offset', 0), 0),

    # At this point, bitfield extracts are constant. We can only do constant
    # unsigned bitfield extract, so lower signed to unsigned + sign extend.
    (('ibitfield_extract', a, b, '#bits'),
     ('ishr', ('ishl', ('ubitfield_extract', a, b, 'bits'), ('isub', 32, 'bits')),
      ('isub', 32, 'bits'))),
]

lower_selects = []
for T, sizes, one in [('f', [16, 32], 1.0),
                      ('i', [8, 16, 32], 1),
                      ('b', [16, 32], -1)]:
    for size in sizes:
        lower_selects.extend([
            ((f'b2{T}{size}', ('inot', 'a@1')), ('bcsel', a, 0, one)),
            ((f'b2{T}{size}', 'a@1'), ('bcsel', a, one, 0)),
        ])

# Rewriting bcsel(a || b, ...) in terms of bcsel(a, ...) and bcsel(b, ...) lets
# our rules to fuse compare-and-select do a better job, assuming that a and b
# are comparisons themselves.
#
# This needs to be a separate pass that runs after lower_selects, in order to
# pick up patterns like b2f32(iand(...))
opt_selects = [
        (('bcsel', ('ior(is_used_once)', ('inot', a), b), c, d),
         ('bcsel', a, ('bcsel', b, c, d), c)),

        (('bcsel', ('ior(is_used_once)', a, b), c, d),
         ('bcsel', a, c, ('bcsel', b, c, d))),

        (('bcsel', ('iand(is_used_once)', ('inot', a), b), c, d),
         ('bcsel', a, d, ('bcsel', b, c, d))),

        (('bcsel', ('iand(is_used_once)', a, b), c, d),
         ('bcsel', a, ('bcsel', b, c, d), d)),
]

# When the ior/iand is used multiple times, we can instead fuse the other way.
opt_selects.extend([
        (('iand', ('inot', 'a@1'), b), ('bcsel', a, False, b)),
        (('iand', 'a@1', b), ('bcsel', a, b, False)),

        (('ior', ('inot', 'a@1'), b), ('bcsel', a, b, True)),
        (('ior', 'a@1', b), ('bcsel', a, True, b)),
])

# Rewriting fneg to ixor costs a uniform but lets us CSE the bcsel if this is
# applied to a whole vector, hence the has_multiple_uses heuristic.
opt_selects.extend([
        (('bcsel', 'a(has_multiple_uses)', ('fneg(is_used_once)', 'b@32'), b),
         ('ixor', b, ('bcsel', a, 1 << 31, 0))),

        (('bcsel', 'a(has_multiple_uses)', b, ('fneg(is_used_once)', 'b@32')),
         ('ixor', b, ('bcsel', a, 0, 1 << 31))),
])

fuse_extr = []
for start in range(32):
    fuse_extr.extend([
        (('ior', ('ushr', 'a@32', start), ('ishl', 'b@32', 32 - start)),
         ('extr_agx', a, b, start, 0)),
    ])

fuse_ubfe = []
for bits in range(1, 32):
    fuse_ubfe.extend([
        (('iand', ('ushr', 'a@32', b), (1 << bits) - 1),
         ('ubitfield_extract', a, b, bits))
    ])

# (x * y) + s = (x * y) + (s << 0)
def imad(x, y, z):
    return ('imadshl_agx', x, y, z, 0)

# (x * y) - s = (x * y) - (s << 0)
def imsub(x, y, z):
    return ('imsubshl_agx', x, y, z, 0)

# x + (y << s) = (x * 1) + (y << s)
def iaddshl(x, y, s):
    return ('imadshl_agx', x, 1, y, s)

# x - (y << s) = (x * 1) - (y << s)
def isubshl(x, y, s):
    return ('imsubshl_agx', x, 1, y, s)

fuse_imad = [
    # Reassociate imul+iadd chain in order to fuse imads. This pattern comes up
    # in compute shader lowering.
    (('iadd', ('iadd(is_used_once)', ('imul(is_used_once)', a, b),
              ('imul(is_used_once)', c, d)), e),
     imad(a, b, imad(c, d, e))),

    # Fuse regular imad
    (('iadd', ('imul(is_used_once)', a, b), c), imad(a, b, c)),
    (('isub', ('imul(is_used_once)', a, b), c), imsub(a, b, c)),
]

for s in range(1, 5):
    fuse_imad += [
        # Definitions
        (('iadd', a, ('ishl(is_used_once)', b, s)), iaddshl(a, b, s)),
        (('isub', a, ('ishl(is_used_once)', b, s)), isubshl(a, b, s)),

        # ineg(x) is 0 - x
        (('ineg', ('ishl(is_used_once)', b, s)), isubshl(0, b, s)),

        # Definitions
        (imad(a, b, ('ishl(is_used_once)', c, s)), ('imadshl_agx', a, b, c, s)),
        (imsub(a, b, ('ishl(is_used_once)', c, s)), ('imsubshl_agx', a, b, c, s)),

        # The above but after the below shift lowering
        (imad(a, b, ('imadshl_agx(is_used_once)', 0, 1, c, s)), ('imadshl_agx', a, b, c, s)),
        (imsub(a, b, ('imadshl_agx(is_used_once)', 0, 1, c, s)), ('imsubshl_agx', a, b, c, s)),

        # a + (a << s) = a + a * (1 << s) = a * (1 + (1 << s))
        (('imul', a, 1 + (1 << s)), iaddshl(a, a, s)),

        # a - (a << s) = a - a * (1 << s) = a * (1 - (1 << s))
        (('imul', a, 1 - (1 << s)), isubshl(a, a, s)),

        # a - (a << s) = a * (1 - (1 << s)) = -(a * (1 << s) - 1)
        (('ineg', ('imul(is_used_once)', a, (1 << s) - 1)), isubshl(a, a, s)),

        # iadd is SCIB, general shfit is IC (slower)
        (('ishl', a, s), iaddshl(0, a, s)),
    ]

# If the above rules failed, we have a large constant shift on the IC unit.
# Might as well fuse an add to form an imad, if we're on the IC anyway.
fuse_imad += [
    (('iadd', a, ('ishl(is_used_once)', b, '#c')), imad(b, ('ishl', 1, c), a)),
]

# Discard lowering generates this pattern, clean it up
ixor_bcsel = [
   (('ixor', ('bcsel', a, '#b', '#c'), '#d'),
    ('bcsel', a, ('ixor', b, d), ('ixor', c, d))),
]

# The main NIR optimizer works on imul, not iadd. We need just enough patterns
# for amul to let us fuse lea.
cleanup_amul = [
   # Neither operation overflows so we can keep the amul.
   (('amul', ('amul', a, '#b'), '#c'), ('amul', a, ('imul', b, c))),

   # Result of u2u64 has zero in upper half, so the shift doesn't overflow, so
   # neither multiplication overflows.
   (('amul', ('ishl', ('u2u64', 'a@32'), '#b(is_ult_32)'), '#c'),
    ('amul', ('u2u64', a), ('ishl', c, b))),

   # We depending on simplifying this.
   (('iadd', a, 0), a),
]

fuse_lea = []

# Handle 64-bit address arithmetic (OpenCL)
for s in range(1, 5):
    pot = 1 << s

    fuse_lea += [
        # A + (#b + c) 2^s = (A + c 2^s) + #b 2^s
        (('iadd', 'a@64', ('amul', pot, ('iadd', '#b(is_upper_half_zero)', ('u2u64', 'c@32')))),
         ('ulea_agx', ('ulea_agx', a, c, s), ('u2u32', b), s)),

        # A + (B + c) 2^s = (A + B 2^s) + c 2^s
        (('iadd', 'a@64', ('amul', ('iadd', 'b@64', ('i2i64', 'c@32')), pot)),
         ('ilea_agx', ('iadd', a, ('ishl', b, s)), c, s)),

        # A + 2^s (B + (C + d)) = (A + (B + C)2^s) + d 2^s
        (('iadd', 'a@64', ('amul', ('iadd', 'b@64',
                                   ('iadd', 'c@64', ('u2u64', 'd@32'))), pot)),
         ('ulea_agx', ('iadd', a, ('ishl', ('iadd', b, c), s)), d, s)),
    ]

    for sgn in ["u", "i"]:
        upconv = f'{sgn}2{sgn}64'
        lea = f'{sgn}lea_agx'

        fuse_lea += [
            # Basic pattern match
            (('iadd', 'a@64', ('amul', (upconv, 'b@32'), pot)), (lea, a, b, s)),
            (('iadd', 'a@64', ('ishl', (upconv, 'b@32'), s)), (lea, a, b, s)),
        ]

# Handle relaxed 32-bit address arithmetic (OpenGL, Vulkan)
for s_ in range(1, 5):
    # Iterate backwards
    s = 5 - s_

    v = 1 << s
    is_mult = f'(is_unsigned_multiple_of_{v})'

    fuse_lea += [
        # A + b * s = A + B * s with relaxed multiply
        (('iadd', 'a@64', ('u2u64', ('amul', 'b@32', v))),
         ('ulea_agx', a, b, s)),

        # A + (b * c 2^s) = A + (b * c) 2^s with relaxed multiply
        (('iadd', 'a@64', ('u2u64', ('amul', 'b@32', f'#c{is_mult}'))),
         ('ulea_agx', a, ('imul', b, ('ushr', c, s)), s)),

        # A + (b 2^s + c d 2^s) = A + (b + cd) 2^s with relaxation.
        #
        # amul is bounded by the buffer size by definition, and both the GL & VK
        # limit UBOs and SSBOs to INT32_MAX bytes. Therefore, amul has no signed
        # wrap.
        #
        # Further, because we are zero-extending the 32-bit result, the 32-bit
        # sum must be nonnegative -- if it were negative, it would represent an
        # offset above INT32_MAX which would be invalid given the amul and
        # max buffer size. Thus with signed math
        #
        #   0 <= b 2^s + cd 2^s < INT32_MAX
        #
        # ..and hence
        #
        #   0 <= b + cd < INT32_MAX
        #
        # Those bounds together with distributivity mean that
        #
        #   (b 2^s + cd 2^s) mod 2^32 = 2^s ((b + cd) mod 2^32)
        #
        # ...which is exactly what we need to factor out the shift.
        (('iadd', 'a@64', ('u2u64', ('iadd', f'#b{is_mult}',
                                     ('amul', 'c@32', f'#d{is_mult}')))),
         ('ulea_agx', a, ('iadd', ('ishr', b, s),
                                  ('amul', 'c@32', ('ishr', d, s))), s)),
    ]

# 8-bit rules are lowest precedence since we really like to fuse shifts
fuse_lea += [
    (('iadd', a, ('u2u64', 'b@32')), ('ulea_agx', a, b, 0)),
    (('iadd', a, ('i2i64', 'b@32')), ('ilea_agx', a, b, 0)),

    (('iadd', a, ('iadd', ('u2u64', 'b@32'), c)),
     ('ulea_agx', ('iadd', a, c), b, 0)),
    (('iadd', a, ('iadd', ('i2i64', 'b@32'), c)),
     ('ilea_agx', ('iadd', a, c), b, 0)),
]

# After lowering address arithmetic, the various address arithmetic opcodes are
# no longer useful. Lower them to regular arithmetic to let nir_opt_algebraic
# take over.
lower_lea = [
    (('amul', a, b), ('imul', a, b)),
    (('ulea_agx', a, b, c), ('iadd', a, ('ishl', ('u2u64', b), c))),
    (('ilea_agx', a, b, c), ('iadd', a, ('ishl', ('i2i64', b), c))),
]

def main():
    parser = argparse.ArgumentParser()
    parser.add_argument('-p', '--import-path', required=True)
    args = parser.parse_args()
    sys.path.insert(0, args.import_path)
    run()

def run():
    import nir_algebraic  # pylint: disable=import-error

    print('#include "agx_nir.h"')

    print(nir_algebraic.AlgebraicPass("agx_nir_cleanup_amul", cleanup_amul).render())
    print(nir_algebraic.AlgebraicPass("agx_nir_fuse_lea", fuse_lea).render())
    print(nir_algebraic.AlgebraicPass("agx_nir_lower_lea", lower_lea).render())

    print(nir_algebraic.AlgebraicPass("agx_nir_lower_algebraic_late",
                                      lower_sm5_shift + lower_pack +
                                      lower_selects).render())
    print(nir_algebraic.AlgebraicPass("agx_nir_fuse_selects",
                                      opt_selects).render())
    print(nir_algebraic.AlgebraicPass("agx_nir_fuse_algebraic_late",
                                      fuse_extr + fuse_ubfe +
                                      fuse_imad + ixor_bcsel).render())


if __name__ == '__main__':
    main()