require 'cunn'
require 'cudnn'
local model = cudnn.SpatialConvolution(1,1,1,1):cuda()
local model2 = nn.SpatialConvolution(1,1,1,1):cuda()

local nThreads = 8
torch.setnumthreads(nThreads)
local Threads = require 'threads'
Threads.serialization('threads.sharedserialize')
local mutex_id = Threads.Mutex():id()
local threads = Threads(nThreads,
  function()
    require 'cunn'
    require 'cudnn'
  end,
  function()
    _model = model
    _model2 = model2
    _mutex = (require 'threads').Mutex(mutex_id)
  end
)

print("Start")
for t=1,100 do
  for i=2,10 do
    threads:addjob(
      function()
        _mutex:lock()
        local inputs = torch.rand(i, 1, 1, 1):cuda()
        local outputs = _model:forward(inputs)
        --local outputs = _model2:forward(inputs)
        if i ~= outputs:size(1) then
          print("mismatch!", inputs:size(1), outputs:size(1))
        end
        _mutex:unlock()
      end
    )
  end
  threads:synchronize()
end
print("Done")