Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[wip] Creating fmaddsub for these intrinsics #89

Draft
wants to merge 5 commits into
base: master
Choose a base branch
from
Draft

[wip] Creating fmaddsub for these intrinsics #89

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
5c2560b
Initial commits
dannys4 Jul 22, 2021
d8180c9
Add `fmaddsub` to `MULADD_INTRINSICS`
dannys4 Jul 23, 2021
0718fd0
Changing how to call it
dannys4 Jul 23, 2021
e27c75d
Generating and interpolating `fmaddsub`
dannys4 Jul 24, 2021
1e6b689
Adding `vfmasubadd`
dannys4 Jul 24, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
18 changes: 18 additions & 0 deletions src/LLVM_intrinsics.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -418,6 +418,7 @@ end
const MULADD_INTRINSICS = [
:fmuladd,
:fma,

]

for f in MULADD_INTRINSICS
Expand All @@ -430,6 +431,23 @@ for f in MULADD_INTRINSICS
end
end

const AVX_EXTS = [("d" , 2, Float64), ("s" , 4, Float32),
("d.256", 4, Float64), ("s.256", 8, Float32),
# ("d.512", 8, Float64), ("s.512", 16, Float32) # These don't seem supported by LLVM yet
]
const MULALTADD_INTRINSICS = [:vfmaddsub, :vfmsubadd]

for f in MULALTADD_INTRINSICS
for (t, N, T) in AVX_EXTS
@eval @generated function ($f)(a::LVec{$N, $T}, b::LVec{$N, $T}, c::LVec{$N, $T})
ff = "llvm.x86.fma."*(string($f))*".p"*($t)
return :(
$(Expr(:meta, :inline));
ccall($ff, llvmcall, LVec{$($N), $($T)}, (LVec{$($N), $($T)}, LVec{$($N), $($T)}, LVec{$($N), $($T)}), a, b, c)
)
end
end
Copy link
Owner

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

In the end we will also need test cases.

end

################
# Load / store #
Expand Down
2 changes: 1 addition & 1 deletion src/SIMD.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,7 @@ using Base: @propagate_inbounds

export Vec, vload, vloada, vloadnt, vloadx, vstore, vstorea, vstorent, vstorec,
vgather, vgathera, vscatter, vscattera, shufflevector, vifelse, valloc,
VecRange
VecRange, vfmaddsub, vfmasubadd

const VE = Base.VecElement
const LVec{N, T} = NTuple{N, VE{T}}
Expand Down
3 changes: 3 additions & 0 deletions src/simdvec.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -435,6 +435,9 @@ for (op, llvmop) in [(:fma, Intrinsics.fma), (:muladd, Intrinsics.fmuladd)]
end
end

@inline vfmaddsub(a::Vec{N,T}, b::Vec{N,T}, c::Vec{N,T}) where {N, T <: FloatingTypes} = Vec{N,T}(Intrinsics.vfmaddsub(a.data, b.data, c.data))
@inline vfmsubadd(a::Vec{N,T}, b::Vec{N,T}, c::Vec{N,T}) where {N, T <: FloatingTypes} = Vec{N,T}(Intrinsics.vfmaddsub(a.data, b.data, c.data))

if isdefined(Base, :bitrotate)
@inline Base.bitrotate(x::Vec, k::Vec) = Vec(Intrinsics.fshl(x.data, x.data, k.data))
@inline Base.bitrotate(x::Vec{N, T}, k::Integer) where {N, T} = bitrotate(x, Vec{N, T}(k))
Expand Down