Merge pull request #60 from Krastanov/master

kwargs are now gensym-ed

Author: chriselrod

Project.toml

@@ -1,7 +1,7 @@
 name = "Polyester"
 uuid = "f517fe37-dbe3-4b94-8317-1923a5111588"
 authors = ["Chris Elrod <elrodc@gmail.com> and contributors"]
-version = "0.6.0"
+version = "0.6.1"
 
 [deps]
 ArrayInterface = "4fba245c-0d91-5ea0-9b3e-6abc04ee57a9"

README.md

@@ -9,6 +9,7 @@
 
 Polyester.jl provides low overhead threading.
 The primary API is `@batch`, which can be used in place of `Threads.@threads`.
+The number of available threads is still governed by [`--threads` or `JULIA_NUM_THREADS`](https://docs.julialang.org/en/v1.6/manual/multi-threading/#Starting-Julia-with-multiple-threads), as reported by `Threads.nthreads()`.
 Lets look at a simple benchmark.
 ```julia
 using Polyester, LinearAlgebra, BenchmarkHistograms
@@ -18,7 +19,7 @@ function axpy_serial!(y, a, x)
         y[i] = muladd(a, x[i], y[i])
     end
 end
-# One thread per core, the default
+# One thread per core, the default (the threads are not pinned)
 function axpy_per_core!(y, a, x)
     @batch per=core for i in eachindex(y,x)
         y[i] = muladd(a, x[i], y[i])

src/closure.jl

@@ -106,6 +106,7 @@ function extractargs!(arguments::Vector{Symbol}, defined::Dict{Symbol,Symbol}, e
       end
     end
   elseif head === :kw
+    args[2] = getgensym!(defined, args[2])
     return
   end
   for i ∈ startind:length(args)
@@ -388,6 +389,9 @@ LoopVectorization.jl currently only uses up to 1 thread per physical core. Becau
 is some overhead to switching the number of threads used, `per=core` is `@batch`'s default,
 so that `Polyester.@batch` and `LoopVectorization.@tturbo` work well together by default.
 
+Threads are not pinned to a given CPU core and the total number of available threads is
+still governed by `--threads` or `JULIA_NUM_THREADS`.
+
 You can pass both `per=(core/thread)` and `minbatch=N` options at the same time, e.g.
 
     @batch per=thread minbatch=2000 for i in Iter; ...; end

test/runtests.jl

@@ -345,6 +345,16 @@ end
   @test allocated(f) < 300 + 40*Threads.nthreads()
 end
 
+@testset "gensym" begin
+  # issue 59 (lack of gensym for keyword arguments)
+  function f(; kw=10) kw end
+  buf = [0,0]
+  @batch for i in 1:2
+    buf[i] = f(; kw=i)
+  end
+  @test buf==[1,2]
+end
+
 if VERSION ≥ v"1.6"
   println("Package tests complete. Running `Aqua` checks.")
   Aqua.test_all(Polyester)