diff --git a/src/host/random.jl b/src/host/random.jl
index 256ecea9..7759e841 100644
--- a/src/host/random.jl
+++ b/src/host/random.jl
@@ -96,9 +96,10 @@ function Random.randn!(rng::RNG, A::AnyGPUArray{T}) where T <: Number
     threads = (length(A) - 1) ÷ 2 + 1
     @kernel function randn!(a, randstates)
         i = @index(Global, Linear)
+        threadidx = @index(Local, Linear)
         idx = 2*(i - 1) + 1
-        U1 = gpu_rand(T, i, randstates)
-        U2 = gpu_rand(T, i, randstates)
+        U1 = gpu_rand(T, threadidx, randstates)
+        U2 = gpu_rand(T, threadidx, randstates)
         Z0 = sqrt(T(-2.0)*log(U1))*cos(T(2pi)*U2)
         Z1 = sqrt(T(-2.0)*log(U1))*sin(T(2pi)*U2)
         @inbounds a[idx] = Z0
diff --git a/test/testsuite/random.jl b/test/testsuite/random.jl
index f2cf832a..f9430258 100644
--- a/test/testsuite/random.jl
+++ b/test/testsuite/random.jl
@@ -44,7 +44,7 @@
     @testset "randn" begin  # normally-distributed
         # XXX: randn calls sqrt, and Base's sqrt(::Complex) performs
         #      checked type conversions that throw boxed numbers.
-        for T in filter(isrealfloattype, eltypes), d in (2, (2,2))
+        for T in filter(isrealfloattype, eltypes), d in (2, (2, 2), (128, 128))
             A = AT{T}(undef, d)
             B = copy(A)
             randn!(rng, A)
@@ -56,7 +56,7 @@
             randn!(rng, A)
             Random.seed!(rng, 1)
             randn!(rng, B)
-            @test Array(A) == Array(B)
+            @test Array(A) ≈ Array(B)
 
             if rng != cpu_rng
                 randn!(cpu_rng, A)