In the current version of my function, not a single temporary array is created. And the portion of time used by GC is less than 5% (reported by the @time macro). So I think the new GC algorithm will not help too much.
在 2015年2月22日星期日 UTC+8上午1:30:10，Viral Shah写道： > > 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] <javascript:> 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 > >
