The following version uses 32-bit integers in the arrays (to reduce cache
pressure) and 32-bit integer remainder operations, with everything else
64-bit, and is nearly 3x faster than the original code on my machine:
rem32(x::Int32, y::Int32) =
Base.box(Int32,Base.srem_int(Base.unbox(Int32,x),Base.unbox(Int32,y)))
function test3()
p = Int32[0 for i=1:20000]
result = Int32[0 for i=1:20000]
k = 0
n = 2
while k < int32(20000)
i::Int32 = 0
while (i < k) && ( rem32(int32(n), p[i+1]) != 0 )
i = i + 1
end
if i == k
k = k + 1
p[k] = n
result[k] = n
end
n = n + 1
end
print(sum(result),"\r\n")
end
