Skip to content

GPU optimization for maxabs #481

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

Draft
kshyatt wants to merge 2 commits into
base: main
Choose a base branch
from
Draft

GPU optimization for maxabs #481

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
53ba7c0
GPU optimization for maxabs
kshyatt Oct 29, 2026
81d68de
Fix maxabs use in rrule
kshyatt Oct 29, 2026
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
12 changes: 12 additions & 0 deletions ext/PEPSKitGPUArraysExt.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,4 +12,16 @@ function PEPSKit._column_vectors(::Type{A}, m::AbstractMatrix) where {A <: AnyGP
end
PEPSKit._indexable_diagview(m::AnyGPUArray) = collect(MatrixAlgebraKit.diagview(m))

# Reduce into a 0-dimensional device array instead of returning a host scalar. `sdiag_pow` only
# feeds this into a broadcast, and a 0-dim array broadcasts as a scalar, so the value never has to
# come back to the CPU. Returning a scalar here would force a device sync on every call, and
# `sdiag_pow` runs once per bond per weight absorption in simple update.
function PEPSKit._maxabs(data::AnyGPUArray)
T = real(eltype(data))
acc = similar(data, T, ())
fill!(acc, zero(T))
Base.mapreducedim!(abs, max, acc, data)
return acc
end

end
4 changes: 2 additions & 2 deletions src/utility/util.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -37,7 +37,7 @@ function sdiag_pow(s::DiagonalTensorMap, pow::Real; tol::Real = eps(real(scalart
return spow
end
function sdiag_pow(
s::AbstractTensorMap{T, S, 1, 1}, pow::Real; tol::Real = eps(real(scalartype(s)))^(3 / 4)
s::AbstractTensorMap{T, S, 1, 1}, pow::Real; tol::Real = eps(real(scalartype(s)))^(3 / 4)
) where {T, S}
tol *= _maxabs(s)
spow = similar(s)
Expand All @@ -53,7 +53,7 @@ function ChainRulesCore.rrule(
::typeof(sdiag_pow), s::AbstractTensorMap, pow::Real;
tol::Real = eps(real(scalartype(s)))^(3 / 4),
)
tol *= _maxabs(s)
tol *= norm(s, Inf)
spow = sdiag_pow(s, pow; tol)
spow_minus1_conj = scale!(sdiag_pow(s', pow - 1; tol), pow)
function sdiag_pow_pullback(c̄_)
Expand Down
Loading