Skip to content

Optimize Fixed --> Float conversions #172

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

Merged
kimikage merged 1 commit into from
Feb 2, 2020
Merged

Optimize Fixed --> Float conversions #172

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
8 changes: 4 additions & 4 deletions src/fixed.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -85,10 +85,10 @@ rem(x::Integer, ::Type{Fixed{T,f}}) where {T,f} = Fixed{T,f}(rem(x,T)<<f,0)
rem(x::Real, ::Type{Fixed{T,f}}) where {T,f} = Fixed{T,f}(rem(Integer(trunc(x)),T)<<f + rem(Integer(round(rem(x,1)*(one(widen1(T))<<f))),T),0)


Base.BigFloat(x::Fixed{T,f}) where {T,f} =
BigFloat(x.i>>f) + BigFloat(x.i&(one(widen1(T))<<f - 1))/BigFloat(one(widen1(T))<<f)
(::Type{TF})(x::Fixed{T,f}) where {TF <: AbstractFloat,T,f} =
TF(x.i>>f) + TF(x.i&(one(widen1(T))<<f - 1))/TF(one(widen1(T))<<f)
(::Type{Tf})(x::Fixed{T,f}) where {Tf <: AbstractFloat, T, f} = Tf(Tf(x.i) * Tf(@exp2(-f)))
Base.Float16(x::Fixed{T,f}) where {T, f} = Float16(Float32(x))
Base.Float32(x::Fixed{T,f}) where {T, f} = Float32(x.i) * Float32(@exp2(-f))
Base.Float64(x::Fixed{T,f}) where {T, f} = Float64(x.i) * @exp2(-f)

function Base.Rational(x::Fixed{T,f}) where {T, f}
f < bitwidth(T)-1 ? x.i//rawone(x) : x.i//(one(widen1(T))<<f)
Expand Down
37 changes: 37 additions & 0 deletions test/fixed.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -270,6 +270,43 @@ end
@test isa(float(one(Fixed{Int32,25})), Float64)
end

@testset "conversions to float" begin
for T in (Float16, Float32, Float64, BigFloat)
@test isa(convert(T, Q0f7(0.3)), T)
end

for Tf in (Float16, Float32, Float64)
@testset "$Tf(::Fixed{$T})" for T in (Int8, Int16)
@testset "$Tf(::Fixed{$T,$f})" for f = 0:bitwidth(T)-1
F = Fixed{T,f}
float_err = 0.0
for i = typemin(T):typemax(T)
f_expected = Tf(i * BigFloat(2)^-f)
f_actual = Tf(reinterpret(F, i))
float_err += abs(f_actual - f_expected)
end
@test float_err == 0.0
end
end
@testset "$Tf(::Fixed{$T})" for T in (Int32, Int64, Int128)
@testset "$Tf(::Fixed{$T,$f})" for f = 0:bitwidth(T)-1
F = Fixed{T,f}
error_count = 0
for i in vcat(typemin(T):(typemin(T)+0xFF),
-T(0xFF):T(0xFF),
(typemax(T)-0xFF):typemax(T))
f_expected = Tf(i * BigFloat(2)^-f)
isinf(f_expected) && break # for Float16() and Float32()
f_actual = Tf(reinterpret(F, i))
f_actual == f_expected && continue
error_count += 1
end
@test error_count == 0
end
end
end
end

@testset "predicates" begin
@test isfinite(1Q7f8)
@test !isnan(1Q7f8)
Expand Down