Created
July 11, 2016 17:56
-
-
Save fac2003/0c58131f97afcad22954deea0f3b29f5 to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| [Stage 4:===> (2 + 30) / 32]CUDA error at /skymind/libnd4j/blas/cuda/NativeOps.cu:2831 code=77(<unknown>) "cudaStreamSynchronize(*stream)" | |
| CUDA error at /skymind/libnd4j/blas/cuda/NativeOps.cu:3921 code=77(<unknown>) "cudaStreamSynchronize(*pStream)" | |
| CUDA error at /skymind/libnd4j/blas/cuda/NativeOps.cu:3921 code=77(<unknown>) "cudaStreamSynchronize(*pStream)" | |
| CUDA error at /skymind/libnd4j/blas/cuda/NativeOps.cu:3947 code=77(<unknown>) "result" | |
| CUDA error at /skymind/libnd4j/blas/cuda/NativeOps.cu:3947 code=77(<unknown>) "result" | |
| CUDA error at /skymind/libnd4j/blas/cuda/NativeOps.cu:3921 code=77(<unknown>) "cudaStreamSynchronize(*pStream)" | |
| CUDA error at /skymind/libnd4j/blas/cuda/NativeOps.cu:3947 code=77(<unknown>) "result" | |
| CUDA error at /skymind/libnd4j/blas/cuda/NativeOps.cu:3921 code=77(<unknown>) "cudaStreamSynchronize(*pStream)" | |
| CUDA error at /skymind/libnd4j/blas/cuda/NativeOps.cu:3947 code=77(<unknown>) "result" | |
| CUDA error at /skymind/libnd4j/blas/cuda/NativeOps.cu:3921 code=77(<unknown>) "cudaStreamSynchronize(*pStream)" | |
| CUDA error at /skymind/libnd4j/blas/cuda/NativeOps.cu:3947 code=77(<unknown>) "result" | |
| CUDA error at /skymind/libnd4j/blas/cuda/NativeOps.cu:2831 code=77(<unknown>) "cudaStreamSynchronize(*stream)" | |
| CUDA error at /skymind/libnd4j/blas/cuda/NativeOps.cu:2831 code=77(<unknown>) "cudaStreamSynchronize(*stream)" | |
| Exception in thread "main" org.apache.spark.SparkException: Job aborted due to stage failure: Task 16 in stage 4.0 failed 1 times, most recent failure: Lost task 16.0 in stage 4.0 (TID 144, localhost): java.lang.IllegalStateException: MemcpyAsync relocate H2D failed: [36012556288] -> [180810547200] | |
| at org.nd4j.jita.handler.impl.CudaZeroHandler.relocate(CudaZeroHandler.java:366) | |
| at org.nd4j.jita.handler.impl.CudaZeroHandler.getDevicePointer(CudaZeroHandler.java:733) | |
| at org.nd4j.jita.allocator.impl.AtomicAllocator.getPointer(AtomicAllocator.java:256) | |
| at org.nd4j.linalg.jcublas.ops.executioner.JCudaExecutioner.invoke(JCudaExecutioner.java:1001) | |
| at org.nd4j.linalg.jcublas.ops.executioner.JCudaExecutioner.exec(JCudaExecutioner.java:552) | |
| at org.nd4j.linalg.api.ndarray.BaseNDArray.assign(BaseNDArray.java:2943) | |
| at org.nd4j.linalg.factory.BaseNDArrayFactory.ones(BaseNDArrayFactory.java:1247) | |
| at org.nd4j.linalg.factory.BaseNDArrayFactory.ones(BaseNDArrayFactory.java:972) | |
| at org.nd4j.linalg.factory.Nd4j.ones(Nd4j.java:4504) | |
| at org.deeplearning4j.nn.multilayer.MultiLayerNetwork.initMask(MultiLayerNetwork.java:1879) | |
| at org.deeplearning4j.nn.multilayer.MultiLayerNetwork.init(MultiLayerNetwork.java:416) | |
| at org.deeplearning4j.spark.impl.paramavg.ParameterAveragingTrainingWorker.getInitialModel(ParameterAveragingTrainingWorker.java:44) | |
| at org.deeplearning4j.spark.api.worker.ExecuteWorkerFlatMap.call(ExecuteWorkerFlatMap.java:68) | |
| at org.deeplearning4j.spark.api.worker.ExecuteWorkerFlatMap.call(ExecuteWorkerFlatMap.java:26) | |
| at org.apache.spark.api.java.JavaRDDLike$$anonfun$fn$4$1.apply(JavaRDDLike.scala:156) | |
| at org.apache.spark.api.java.JavaRDDLike$$anonfun$fn$4$1.apply(JavaRDDLike.scala:156) | |
| at org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$17.apply(RDD.scala:706) | |
| at org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$17.apply(RDD.scala:706) | |
| at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) | |
| at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297) | |
| at org.apache.spark.rdd.RDD.iterator(RDD.scala:264) | |
| at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66) | |
| at org.apache.spark.scheduler.Task.run(Task.scala:88) | |
| at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214) | |
| at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142) | |
| at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617) | |
| at java.lang.Thread.run(Thread.java:745) | |
| Driver stacktrace: | |
| at org.apache.spark.scheduler.DAGScheduler.org$apache$spark$scheduler$DAGScheduler$$failJobAndIndependentStages(DAGScheduler.scala:1280) | |
| at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1268) | |
| at org.apache.spark.scheduler.DAGScheduler$$anonfun$abortStage$1.apply(DAGScheduler.scala:1267) | |
| at scala.collection.mutable.ResizableArray$class.foreach(ResizableArray.scala:59) | |
| at scala.collection.mutable.ArrayBuffer.foreach(ArrayBuffer.scala:48) | |
| at org.apache.spark.scheduler.DAGScheduler.abortStage(DAGScheduler.scala:1267) | |
| at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:697) | |
| at org.apache.spark.scheduler.DAGScheduler$$anonfun$handleTaskSetFailed$1.apply(DAGScheduler.scala:697) | |
| at scala.Option.foreach(Option.scala:257) | |
| at org.apache.spark.scheduler.DAGScheduler.handleTaskSetFailed(DAGScheduler.scala:697) | |
| at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.doOnReceive(DAGScheduler.scala:1493) | |
| at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1455) | |
| at org.apache.spark.scheduler.DAGSchedulerEventProcessLoop.onReceive(DAGScheduler.scala:1444) | |
| at org.apache.spark.util.EventLoop$$anon$1.run(EventLoop.scala:48) | |
| at org.apache.spark.scheduler.DAGScheduler.runJob(DAGScheduler.scala:567) | |
| at org.apache.spark.SparkContext.runJob(SparkContext.scala:1813) | |
| at org.apache.spark.SparkContext.runJob(SparkContext.scala:1933) | |
| at org.apache.spark.rdd.RDD$$anonfun$aggregate$1.apply(RDD.scala:1078) | |
| at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:147) | |
| at org.apache.spark.rdd.RDDOperationScope$.withScope(RDDOperationScope.scala:108) | |
| at org.apache.spark.rdd.RDD.withScope(RDD.scala:306) | |
| at org.apache.spark.rdd.RDD.aggregate(RDD.scala:1071) | |
| at org.apache.spark.api.java.JavaRDDLike$class.aggregate(JavaRDDLike.scala:416) | |
| at org.apache.spark.api.java.AbstractJavaRDDLike.aggregate(JavaRDDLike.scala:47) | |
| at org.deeplearning4j.spark.impl.paramavg.ParameterAveragingTrainingMaster.processResults(ParameterAveragingTrainingMaster.java:407) | |
| at org.deeplearning4j.spark.impl.paramavg.ParameterAveragingTrainingMaster.doIteration(ParameterAveragingTrainingMaster.java:339) | |
| at org.deeplearning4j.spark.impl.paramavg.ParameterAveragingTrainingMaster.executeTraining(ParameterAveragingTrainingMaster.java:181) | |
| at org.deeplearning4j.spark.impl.multilayer.SparkDl4jMultiLayer.fit(SparkDl4jMultiLayer.java:201) | |
| at org.deeplearning4j.examples.rnn.GravesLSTMCharModellingExample.main(GravesLSTMCharModellingExample.java:116) | |
| Caused by: java.lang.IllegalStateException: MemcpyAsync relocate H2D failed: [36012556288] -> [180810547200] | |
| at org.nd4j.jita.handler.impl.CudaZeroHandler.relocate(CudaZeroHandler.java:366) | |
| at org.nd4j.jita.handler.impl.CudaZeroHandler.getDevicePointer(CudaZeroHandler.java:733) | |
| at org.nd4j.jita.allocator.impl.AtomicAllocator.getPointer(AtomicAllocator.java:256) | |
| at org.nd4j.linalg.jcublas.ops.executioner.JCudaExecutioner.invoke(JCudaExecutioner.java:1001) | |
| at org.nd4j.linalg.jcublas.ops.executioner.JCudaExecutioner.exec(JCudaExecutioner.java:552) | |
| at org.nd4j.linalg.api.ndarray.BaseNDArray.assign(BaseNDArray.java:2943) | |
| at org.nd4j.linalg.factory.BaseNDArrayFactory.ones(BaseNDArrayFactory.java:1247) | |
| at org.nd4j.linalg.factory.BaseNDArrayFactory.ones(BaseNDArrayFactory.java:972) | |
| at org.nd4j.linalg.factory.Nd4j.ones(Nd4j.java:4504) | |
| at org.deeplearning4j.nn.multilayer.MultiLayerNetwork.initMask(MultiLayerNetwork.java:1879) | |
| at org.deeplearning4j.nn.multilayer.MultiLayerNetwork.init(MultiLayerNetwork.java:416) | |
| at org.deeplearning4j.spark.impl.paramavg.ParameterAveragingTrainingWorker.getInitialModel(ParameterAveragingTrainingWorker.java:44) | |
| at org.deeplearning4j.spark.api.worker.ExecuteWorkerFlatMap.call(ExecuteWorkerFlatMap.java:68) | |
| at org.deeplearning4j.spark.api.worker.ExecuteWorkerFlatMap.call(ExecuteWorkerFlatMap.java:26) | |
| at org.apache.spark.api.java.JavaRDDLike$$anonfun$fn$4$1.apply(JavaRDDLike.scala:156) | |
| at org.apache.spark.api.java.JavaRDDLike$$anonfun$fn$4$1.apply(JavaRDDLike.scala:156) | |
| at org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$17.apply(RDD.scala:706) | |
| at org.apache.spark.rdd.RDD$$anonfun$mapPartitions$1$$anonfun$apply$17.apply(RDD.scala:706) | |
| at org.apache.spark.rdd.MapPartitionsRDD.compute(MapPartitionsRDD.scala:38) | |
| at org.apache.spark.rdd.RDD.computeOrReadCheckpoint(RDD.scala:297) | |
| at org.apache.spark.rdd.RDD.iterator(RDD.scala:264) | |
| at org.apache.spark.scheduler.ResultTask.runTask(ResultTask.scala:66) | |
| at org.apache.spark.scheduler.Task.run(Task.scala:88) | |
| at org.apache.spark.executor.Executor$TaskRunner.run(Executor.scala:214) | |
| at java.util.concurrent.ThreadPoolExecutor.runWorker(ThreadPoolExecutor.java:1142) | |
| at java.util.concurrent.ThreadPoolExecutor$Worker.run(ThreadPoolExecutor.java:617) | |
| at java.lang.Thread.run(Thread.java:745) | |
| CUDA error at /skymind/libnd4j/blas/cuda/NativeOps.cu:2831 code=77(<unknown>) "cudaStreamSynchronize(*stream)" | |
| CUDA error at /skymind/libnd4j/blas/cuda/NativeOps.cu:3921 code=77(<unknown>) "cudaStreamSynchronize(*pStream)" | |
| CUDA error at /skymind/libnd4j/blas/cuda/NativeOps.cu:3947 code=77(<unknown>) "result" | |
| CUDA error at /skymind/libnd4j/blas/cuda/NativeOps.cu:3921 code=77(<unknown>) "cudaStreamSynchronize(*pStream)" | |
| CUDA error at /skymind/libnd4j/blas/cuda/NativeOps.cu:3947 code=77(<unknown>) "result" |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment