program.species   gemm

 program.species   lstm

 program.species   reshape

 program.species   resizebilinear

 program.species   softmax

 result   AutoML&systems - Image Classification - MobileNet (all)

 result   AutoML&systems - Image Classification - MobileNet (highlights)

 result   detection-mlperf-coco-tf-cpu-benchmark-linux-portable-workflows

 result   MLPerf Inference v0.5 - Image Classification - MultiStream (number of streams)

 result   MLPerf Inference v0.5 - Image Classification - Offline (samples per second)

 result   MLPerf Inference v0.5 - Image Classification - Server (queries per second)

 result   MLPerf Inference v0.5 - Image Classification - SingleStream (milliseconds per sample)

 result   MLPerf Inference v0.5 - Machine Translation - MultiStream (number of streams)

 result   MLPerf Inference v0.5 - Machine Translation - Offline (samples per second)

 result   MLPerf Inference v0.5 - Machine Translation - Server (queries per second)

 result   MLPerf Inference v0.5 - Machine Translation - SingleStream (milliseconds per sample)

 result   MLPerf Inference v0.5 - Object Detection - MultiStream (number of streams)

 result   MLPerf Inference v0.5 - Object Detection - Offline (samples per second)

 result   MLPerf Inference v0.5 - Object Detection - Server (queries per second)

 result   MLPerf Inference v0.5 - Object Detection - SingleStream (milliseconds per sample)

 result   NNTest (collaboratively benchmarking and optimizing neural network operations)

 result   SOTA: MLPerf inference benchmark v0.5 results snapshot (closed, Available) for collaborative validation

 result   SOTA: MLPerf inference benchmark v0.5 results snapshot (closed, Preview) for collaborative validation

 result   SOTA: MLPerf inference benchmark v0.5 results snapshot (closed, Research, Development, and Other) for collaborative validation

 result   SOTA: MLPerf inference benchmark v0.5 results snapshot (open, Available) for collaborative validation

 result   SOTA: MLPerf inference benchmark v0.5 results snapshot (open, Research, Development, and Other) for collaborative validation

 result   SOTA: Validating MLPerf inference benchmark v0.5 results (object detection) via cK crowd-benchmarking

 script   cached-benchmark

 script   dse-acc

 script   dse-perf-docker