src/simd/archsimd/_gen/simdgen/ops/BitwiseLogic/go_amd64.yaml

!sum
# In the XED data, *all* floating point bitwise logic operation has their
# operand type marked as uint. We are not trying to understand why Intel
# decided that they want FP bit-wise logic operations, but this irregularity
# has to be dealed with in separate rules with some overwrites.

# For many bit-wise operations, we have the following non-orthogonal
# choices:
#
# - Non-masked AVX operations have no element width (because it
# doesn't matter), but only cover 128 and 256 bit vectors.
#
# - Masked AVX-512 operations have an element width (because it needs
# to know how to interpret the mask), and cover 128, 256, and 512 bit
# vectors. These only cover 32- and 64-bit element widths.
#
# - Non-masked AVX-512 operations still have an element width (because
# they're just the masked operations with an implicit K0 mask) but it
# doesn't matter! This is the only option for non-masked 512 bit
# operations, and we can pick any of the element widths.
#
# We unify with ALL of these operations and the compiler generator
# picks when there are multiple options.

# TODO: We don't currently generate unmasked bit-wise operations on 512 bit
# vectors of 8- or 16-bit elements. AVX-512 only has *masked* bit-wise
# operations for 32- and 64-bit elements; while the element width doesn't matter
# for unmasked operations, right now we don't realize that we can just use the
# 32- or 64-bit version for the unmasked form. Maybe in the XED decoder we
# should recognize bit-wise operations when generating unmasked versions and
# omit the element width.

# For binary operations, we constrain their two inputs and one output to the
# same Go type using a variable.

- go: And
  asm: "VPAND[DQ]?"
  in:
  - &any
    go: $t
  - *any
  out:
  - *any

- go: And
  asm: "VPANDD" # Fill in the gap, And is missing for Uint8x64 and Int8x64
  inVariant: []
  in: &twoI8x64
  - &i8x64
    go: $t
    overwriteElementBits: 8
  - *i8x64
  out: &oneI8x64
  - *i8x64

- go: And
  asm: "VPANDD" # Fill in the gap, And is missing for Uint16x32 and Int16x32
  inVariant: []
  in: &twoI16x32
  - &i16x32
    go: $t
    overwriteElementBits: 16
  - *i16x32
  out: &oneI16x32
  - *i16x32

- go: AndNot
  asm: "VPANDN[DQ]?"
  operandOrder: "21" # switch the arg order
  in:
  - *any
  - *any
  out:
  - *any

- go: AndNot
  asm: "VPANDND" # Fill in the gap, AndNot is missing for Uint8x64 and Int8x64
  operandOrder: "21" # switch the arg order
  inVariant: []
  in: *twoI8x64
  out: *oneI8x64

- go: AndNot
  asm: "VPANDND" # Fill in the gap, AndNot is missing for Uint16x32 and Int16x32
  operandOrder: "21" # switch the arg order
  inVariant: []
  in: *twoI16x32
  out: *oneI16x32

- go: Or
  asm: "VPOR[DQ]?"
  in:
  - *any
  - *any
  out:
  - *any

- go: Or
  asm: "VPORD" # Fill in the gap, Or is missing for Uint8x64 and Int8x64
  inVariant: []
  in: *twoI8x64
  out: *oneI8x64

- go: Or
  asm: "VPORD" # Fill in the gap, Or is missing for Uint16x32 and Int16x32
  inVariant: []
  in: *twoI16x32
  out: *oneI16x32

- go: Xor
  asm: "VPXOR[DQ]?"
  in:
  - *any
  - *any
  out:
  - *any

- go: Xor
  asm: "VPXORD" # Fill in the gap, Or is missing for Uint8x64 and Int8x64
  inVariant: []
  in: *twoI8x64
  out: *oneI8x64

- go: Xor
  asm: "VPXORD" # Fill in the gap, Or is missing for Uint16x32 and Int16x32
  inVariant: []
  in: *twoI16x32
  out: *oneI16x32

- go: tern
  asm: "VPTERNLOGD|VPTERNLOGQ"
  in:
  - class: immediate
    immOffset: 0
    name: table
  - &tern_op
    go: $t
  - *tern_op
  - *tern_op
  inVariant: []
  out:
  - *tern_op