It is also worth trying out one of the 0.4-dev nightlies and compare the performance. The code does avoid creating temporaries to a large extent, but it may be worth checking if the new GC helps.
-viral > On 21-Feb-2015, at 10:09 pm, [email protected] wrote: > > What's the type of c.outputs? In train_one it seems to be Int64, in prdict! > it seems to be Float64. > > On Thursday, February 19, 2015 at 3:51:20 PM UTC+1, Zhixuan Yang wrote: > Hello everyone, > > Recently I'm working on my first Julia project, a word embedding training > program similar to Google's word2vec (the code of word2vec is indeed very > high-quality, but I want to add more features, so I decided to write a new > one). Thanks to Julia's expressiveness, it cost me less than 2 days to write > the entire program. But it runs really slow, about 100x slower than the C > code of word2vec (the algorithm is the same). I've been trying to optimize > my code for several days (adding type annotations, using BLAS to do > computation, eliminating memory allocations ...), but it is still 30x slower > than the C code. > > The critical part of my program is the following function (it also consumes > most of the time according to the profiling result): > > function train_one(c :: LinearClassifier, x :: Array{Float64}, y :: Int64; α > :: Float64 = 0.025, input_gradient :: Union(Nothing, Array{Float64}) = > nothing) > predict!(c, x) > c.outputs[y] -= 1 > > if input_gradient != nothing > # input_gradient = ( c.weights * outputs' )' > BLAS.gemv!('N', α, c.weights, c.outputs, 1.0, input_gradient) > end > > # c.weights -= α * x' * outputs; > BLAS.ger!(-α, vec(x), c.outputs, c.weights) > end > > function predict!(c :: LinearClassifier, x :: Array{Float64}) > c.outputs = vec(softmax(x * c.weights)) > end > > type LinearClassifier > k :: Int64 # number of outputs > n :: Int64 # number of inputs > weights :: Array{Float64, 2} # k * n weight matrix > > outputs :: Vector{Float64} > end > > And the entire program can be found here. Could you please check my code and > tell me what I can do to get performance comparable to C. > > Regards. > Yang Zhixuan
