fix typos in Xoshiro RNG implementation

doc/src/devdocs/subarrays.md

@@ -19,14 +19,14 @@ julia> A = rand(2,3,4);
 
 julia> S1 = view(A, :, 1, 2:3)
 2×2 view(::Array{Float64, 3}, :, 1, 2:3) with eltype Float64:
- 0.166507  0.97397
- 0.754392  0.831383
+ 0.442623  0.0530526
+ 0.201893  0.504489
 
 julia> S2 = view(A, 1, :, 2:3)
 3×2 view(::Array{Float64, 3}, 1, :, 2:3) with eltype Float64:
- 0.166507  0.97397
- 0.518957  0.0705793
- 0.503714  0.825124
+ 0.442623   0.0530526
+ 0.720089   0.661983
+ 0.0939203  0.457032
 ```
 ```@meta
 DocTestSetup = nothing

doc/src/manual/performance-tips.md

@@ -77,12 +77,12 @@ julia> function sum_global()
        end;
 
 julia> @time sum_global()
-  0.026328 seconds (9.30 k allocations: 416.747 KiB, 36.50% gc time, 99.48% compilation time)
-508.39048990953665
+  0.026174 seconds (9.07 k allocations: 373.448 KiB, 98.80% compilation time)
+496.44917496523266
 
 julia> @time sum_global()
-  0.000075 seconds (3.49 k allocations: 70.156 KiB)
-508.39048990953665
+  0.000116 seconds (3.49 k allocations: 70.156 KiB)
+496.44917496523266
 ```
 
 On the first call (`@time sum_global()`) the function gets compiled. (If you've not yet used [`@time`](@ref)
@@ -113,12 +113,12 @@ julia> function sum_arg(x)
        end;
 
 julia> @time sum_arg(x)
-  0.010298 seconds (4.23 k allocations: 226.021 KiB, 99.81% compilation time)
-508.39048990953665
+  0.009579 seconds (3.96 k allocations: 200.171 KiB, 99.77% compilation time)
+496.44917496523266
 
 julia> @time sum_arg(x)
   0.000005 seconds (1 allocation: 16 bytes)
-508.39048990953665
+496.44917496523266
 ```
 
 The 1 allocation seen is from running the `@time` macro itself in global scope. If we instead run
@@ -129,7 +129,7 @@ julia> time_sum(x) = @time sum_arg(x);
 
 julia> time_sum(x)
   0.000001 seconds
-508.39048990953665
+496.44917496523266
 ```
 
 In some situations, your function may need to allocate memory as part of its operation, and this

src/task.c

@@ -667,7 +667,7 @@ JL_DLLEXPORT uint64_t jl_tasklocal_genrandom(jl_task_t *task) JL_NOTSAFEPOINT
     uint64_t s2 = task->rngState2;
     uint64_t s3 = task->rngState3;
 
-    uint64_t t = s0 << 17;
+    uint64_t t = s1 << 17;
     uint64_t tmp = s0 + s3;
     uint64_t res = ((tmp << 23) | (tmp >> 41)) + s0;
     s2 ^= s0;

stdlib/LinearAlgebra/test/dense.jl

@@ -22,10 +22,10 @@ Random.seed!(1234323)
     @testset "for $elty" for elty in (Float32, Float64, ComplexF32, ComplexF64)
         ainit = convert(Matrix{elty}, ainit)
         for a in (copy(ainit), view(ainit, 1:n, 1:n))
-            @test cond(a,1) ≈ 50.60863783272028 atol=0.5
-            @test cond(a,2) ≈ 23.059634761613314 atol=0.5
-            @test cond(a,Inf) ≈ 45.12503933120795 atol=0.4
-            @test cond(a[:,1:5]) ≈ 5.719500544258695 atol=0.01
+            @test cond(a,1) ≈ 855.6103637603965 atol=0.5
+            @test cond(a,2) ≈ 570.5296048445405 atol=0.5
+            @test cond(a,Inf) ≈  1210.8340599789594 atol=0.4
+            @test cond(a[:,1:5]) ≈ 12.140520859885147 atol=0.01
             @test_throws ArgumentError cond(a,3)
         end
     end

stdlib/LinearAlgebra/test/uniformscaling.jl

@@ -141,7 +141,7 @@ end
 end
 
 @testset "arithmetic with Number" begin
-    α = randn()
+    α = rand()
     @test α + I == α + 1
     @test I + α == α + 1
     @test α - I == α - 1

stdlib/Random/src/Xoshiro.jl

@@ -54,7 +54,7 @@ rng_native_52(::Xoshiro) = UInt64
 @inline function rand(rng::Xoshiro, ::SamplerType{UInt64})
     s0, s1, s2, s3 = rng.s0, rng.s1, rng.s2, rng.s3
     tmp = s0 + s3
-    res = tmp << 23 | tmp >> 41
+    res = ((tmp << 23) | (tmp >> 41)) + s0
     t = s1 << 17
     s2 = xor(s2, s0)
     s3 = xor(s3, s1)

stdlib/Random/src/XoshiroSimd.jl

@@ -158,7 +158,7 @@ end
 
     i = 0
     while i+8 <= len
-        res = _rotl23(_plus(s0,s3))
+        res = _plus(_rotl23(_plus(s0,s3)),s0)
         unsafe_store!(reinterpret(Ptr{UInt64}, dst + i), f(res, T))
         t = _shl17(s1)
         s2 = _xor(s2, s0)
@@ -170,7 +170,7 @@ end
         i += 8
     end
     if i < len
-        res = _rotl23(_plus(s0,s3))
+        res = _plus(_rotl23(_plus(s0,s3)),s0)
         t = _shl17(s1)
         s2 = _xor(s2, s0)
         s3 = _xor(s3, s1)
@@ -200,7 +200,7 @@ end
 
     i = 0
     while i+8 <= len
-        res = _rotl23(_plus(s0,s3))
+        res = _plus(_rotl23(_plus(s0,s3)),s0)
         shift = 0
         while i+8 <= len && shift < 8
             resLoc = _and(_lshr(res, shift), 0x0101010101010101)
@@ -219,7 +219,7 @@ end
     end
     if i < len
         # we may overgenerate some bytes here, if len mod 64 <= 56 and len mod 8 != 0
-        res = _rotl23(_plus(s0,s3))
+        res = _plus(_rotl23(_plus(s0,s3)),s0)
         resLoc = _and(res, 0x0101010101010101)
         ref = Ref(resLoc)
         ccall(:memcpy, Ptr{Cvoid}, (Ptr{UInt8}, Ptr{UInt64}, Csize_t), dst+i, ref, len-i)
@@ -245,7 +245,7 @@ end
 
     i = 0
     while i + 8*N <= len
-        res = _rotl23(_plus(s0,s3))
+        res = _plus(_rotl23(_plus(s0,s3)),s0)
         t = _shl17(s1)
         s2 = _xor(s2, s0)
         s3 = _xor(s3, s1)
@@ -264,7 +264,7 @@ end
     msk = ntuple(i->VecElement(0x0101010101010101), Val(N))
     i = 0
     while i + 64*N <= len
-        res = _rotl23(_plus(s0,s3))
+        res = _plus(_rotl23(_plus(s0,s3)),s0)
         t = _shl17(s1)
         s2 = _xor(s2, s0)
         s3 = _xor(s3, s1)

stdlib/SparseArrays/src/sparsematrix.jl

@@ -1647,8 +1647,8 @@ julia> sprand(Bool, 2, 2, 0.5)
 
 julia> sprand(Float64, 3, 0.75)
 3-element SparseVector{Float64, Int64} with 2 stored entries:
-  [1]  =  0.523355
-  [2]  =  0.0890391
+  [1]  =  0.787459
+  [2]  =  0.544574
 ```
 """
 function sprand(r::AbstractRNG, m::Integer, n::Integer, density::AbstractFloat, rfn::Function, ::Type{T}=eltype(rfn(r, 1))) where T