Skip to content

Don't use VectorizationBase in tests to reduce latency #37

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
merged 1 commit into from
Dec 29, 2021
Merged

Don't use VectorizationBase in tests to reduce latency #37

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
3 changes: 1 addition & 2 deletions Project.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,7 +16,6 @@ Aqua = "4c88cf16-eb10-579e-8560-4a9242c79595"
InteractiveUtils = "b77e0a4c-d291-57a0-90e8-8db25a27a240"
StaticArrays = "90137ffa-7385-5640-81b9-e52037218182"
Test = "8dfed614-e22c-5e08-85e1-65c5234f0b40"
VectorizationBase = "3d5dd08c-fd9d-11e8-17fa-ed2836048c2f"

[targets]
test = ["Aqua", "InteractiveUtils", "StaticArrays", "Test", "VectorizationBase"]
test = ["Aqua", "InteractiveUtils", "StaticArrays", "Test"]
2 changes: 0 additions & 2 deletions src/threadtasks.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -25,9 +25,7 @@ function (tt::ThreadTask)()
GC.@preserve THREADPOOL begin
while true
if _atomic_state(p) == TASK
# if _atomic_cas_cmp!(p, TASK, EXEC)
_call(p)
# store!(p, SPIN)
_atomic_store!(p, SPIN)
wait_counter = zero(UInt32)
continue
Expand Down
2 changes: 1 addition & 1 deletion test/internals.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,7 @@
@test ThreadingUtilities.store!(pointer(UInt[]), nothing, 1) == 1
x = zeros(UInt, 100);
GC.@preserve x begin
t1 = (1.0, C_NULL, Val(7), (3, UInt(17)), VectorizationBase.stridedpointer(x))
t1 = (1.0, C_NULL, Val(7), (3, UInt(17)), (pointer(x), strides(x)))
@test ThreadingUtilities.store!(pointer(x), t1, 0) === mapreduce(sizeof, +, t1)
@test ThreadingUtilities.store!(pointer(x), Val(0), 0) == 0
@test ThreadingUtilities.load(pointer(x), typeof(t1), 0) === (mapreduce(sizeof, +, t1), t1)
Expand Down
1 change: 0 additions & 1 deletion test/testsetup.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,5 @@
using ThreadingUtilities
using Test
using VectorizationBase

import InteractiveUtils

6 changes: 3 additions & 3 deletions test/threadingutilities.jl
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,7 @@ function (::Copy{P})(p::Ptr{UInt}) where {P}
_, (ptry,ptrx,N) = ThreadingUtilities.load(p, P, 2*sizeof(UInt))
N > 0 || throw("This function throws if N == 0 for testing purposes.")
@simd ivdep for n ∈ 1:N
vstore!(ptry, vload(ptrx, (n,)), (n,))
unsafe_store!(ptry, unsafe_load(ptrx, n), n)
end
end
@generated function copy_ptr(::A, ::B) where {A,B}
Expand All @@ -15,8 +15,8 @@ end
function setup_copy!(p, y, x)
N = length(y)
@assert length(x) == N
py = stridedpointer(y)
px = stridedpointer(x)
py = pointer(y)
px = pointer(x)
fptr = copy_ptr(py, px)
offset = ThreadingUtilities.store!(p, fptr, sizeof(UInt))
ThreadingUtilities.store!(p, (py,px,N), offset)
Expand Down