• Amy Zhuang's avatar
    Reuse memory for CPU backend. (#2238) · b277627a
    Amy Zhuang authored
    * Reuse memory for CPU backend.
    
    * Use NGRAPH_REUSE_MEMORY to enable memory reuse.
    
    * Add a test.
    
    * Move make_function to test_tools.cpp.
    
    * Add more comments.
    
    * Address PR Feedback: add a method to CPU backend.
    
    * *Add a member to CPUOpAnnotations to remove redundant code.
    
    *Overload compile function for CPU backend.
    
    * Move make_function out of test_tools.
    
    * Address PR Feedback.
    
    * Use modified liveness analysis in CPUMemoryAssignment pass.
    
    * Use lambda expression.
    
    * Fix style error.
    
    * Check if any user of the tensor has destructive io when building tensor alias map.
    
    * Fix a bug.
    
    * Check if tensor has multiple users.
    
    * Allow tensor alias for destructive oi node.
    
    * Update multiple_users_tensor set along the chain of in place ops.
    
    * No tensor alias if input is parameter or constant.
    
    * Use buffer sets in cpu memory assignment,
    tensors sharing the same memory buffer are put into the same set.
    
    * Add more checks and do not combine sets when allowing destructive oi.
    
    * Style fix.
    
    * Do no allow destructive oi if the input tensor uses function input memory.
    
    Update set label.
    
    * Add unit tests.
    
    * Style fix.
    
    * Get the correct size for memcpy when the input is padded.
    
    * Style fix.
    
    * Address PR feedback.
    
    * Address PR feedback.
    
    * Move make_function in cpu_test after #if 0 and before the disabled test.
    
    * Add utility functions.
    
    Use iterator.
    
    Rename variables.
    
    * Add pass attributes and move cpu memory assignment to common passes (#2504)
    b277627a
Name
Last commit
Last update
..
10_bucket_LSTM.json add nGraph quantize op (#1661)
1_lstm_cell_forward.json LSTM fusion + RNN fusion across time slice's for single layer (#826)
1rnn_layer_3lstm_cell.json Pruthvi/fix rnn precision (#1874)
2layer_3timestep_ic100oc100.json Pruthvi/fix rnn precision (#1874)
2rnn_layer_1timestep.json Pruthvi/fix rnn output (#1135)
2rnn_layer_3lstm_cell.json LSTM fusion + RNN fusion across time slice's for single layer (#826)
3_lstm_cell_forward.json NGRAPH-1605 Sigmoid multiply fusion (#964)
Graph_fprop_sigmoid.json Pruthvi/sigmoid (#614)
LSTM_backward.json Get value types out of public API, multi-values from Function (#340)
LSTM_forward.json Get value types out of public API, multi-values from Function (#340)
Seq2Seq_backward.json Add mxnet seq2seq serialized model for benchmarking (#385)
Seq2Seq_forward.json Add mxnet seq2seq serialized model for benchmarking (#385)
Sockeye_Seq2Seq_backward.json add mxnet sockeye Seq2Seq model (#508)
Sockeye_Seq2Seq_forward.json add mxnet sockeye Seq2Seq model (#508)
batch_dot_3.json ngraph-1676 batch dot fusion (#1071)
bn_bprop.json Reshape Transformations + Simplification pass (#427)
bn_fprop.json Reshape Transformations + Simplification pass (#427)
bn_fprop_b2c3h2w2.json pattern matcher for BatchnormFprop + mkldnn integration in the CPU emitter (#468)
gru_debug.json Pruthvi/fix input matrix fusion (#2381)
lstm_bi_directional.json Pruthvi/bi rnn (#2232)
mnist_mlp_forward.json add nGraph quantize op (#1661)
mxnet_densenet121_inference_batch1_float32.json Reuse memory for CPU backend. (#2238)
rnn-10-step-fusion-test.json RNN Fusion using Pattern Matcher (#741)
tranpose.json Reshape Transformations + Simplification pass (#427)