Release Notes

What's in Qualcomm Neural Processing SDK v1.29?

  • Added support for dlc reorder tool
  • Optimization of HTA d32 conversions
  • Added tf space_to_depth op for SNPE CPU and DSP runtime
  • Benchmarking scripts enhanced for showing further break down of execution time, across various components
  • Added support for additional ONNX binary element-wise ops
  • Optimized deconv layer for improving performance
  • Fixed an issue related to runtime error in DSP runtime
  • Performance Optimization of SNPE GPU Runtime for Shufflenet V2 by using profiling level config

What's in Qualcomm Neural Processing SDK v1.28?

  • Added an optional argument to isRuntimeAvailable for the DSP runtime so that it doesn't activate the DSP
  • Allow UB_T8 and UB_FLOAT output for snpe-net-run
  • Added a new command line option for snpe-dlc-diff to check layer names
  • Updated the --dlc argument to --output_path for snpe-caffe-to-dlc to align with the ONNX converter
  • Added --dry_run argument to snpe-onnx-to-dlc to allow evaluation for successful conversion on an ONNX model
  • Added support for the gather op in the DSP runtime
  • Added support to convert the TF MobileNet-V1-FPN-SSD model
  • Fixed a memory leak in the DSP runtime that is seen when repeatedly loading and unloading a network
  • Addressed issues on V66 DSPs related to acquiring VTCM memory
  • Fixed an issue related to multiple inputs for the Caffe converter
  • Fixed an issue in the TF converter related to element-wise sun and the atrous parameter
  • Fixed an issue in the TF converter related to tf.crop_and_resize when there are only 2 inputs
  • Fixed additional cases of uncaught exceptions with the aarch64-android-clang6.0 platform

What's in Qualcomm Neural Processing SDK v1.27.2?

  • Added support for SM8150P
  • Fixed memory leak issue on AIP runtime
  • Fixed additional cases of uncaught exceptions with the aarch64-android-clang6.0 platform

What's in Qualcomm Neural Processing SDK v1.27.1?

  • Updated the AIP runtime to support new features and to fix critical bugs related to HTA. On new Android builds, HTA can support new layers, Bilinear Resize and Prelu
  • Fixed issues relating to uncaught exceptions on the aarch64-android-clang6.0 platform

What's in Qualcomm Neural Processing SDK v1.27?

  • Added new APIs support for setting output tensor names to snpeBuilder and to fetch output tensor names for a given output layer name
  • Improved the peak memory usage with DLC v3 format
  • Fixed few issues with performance and runtime failures on DSP runtime
  • Fixed few issues and improved error handling for platform validator
  • Fixed the issues with Pooling and Instance norm layers of Tensorflow converter

What's in Qualcomm Neural Processing SDK v1.26?

  • Added support for the ONNX Gather Op in the ONNX Converter and CPU runtime
  • Optimized DeConvolution Layer for the DSP runtime
  • Support for tf.nn.moments in the TF converter, CPU and DSP runtimes
  • Added TF Reflect Pad support for the DSP runtime
  • Added symmetric quantizer option in snpe-dlc-quantize
  • Added support for batch > 1 when using the Scale Layer on the DSP runtime
  • Updated Platform Validator python script to be OS-independent
  • Added additional optimizations for HTA input conversion

What's in Qualcomm Neural Processing SDK v1.25.1?

This release focuses on a few key bug fixes for the AIP runtime.

  • Fixed accuracy issues on the AIP runtime
  • Added support for UB_TF8 with the AIP runtime
  • Added support for dilated depthwise convolution on GPU runtime

What's in Qualcomm Neural Processing SDK v1.25?

This release focuses on adding the support for multiple subnets within the AIP runtime and upgrading the DLC format to improve load time performance and memory consumption. In addition, this release fixes critical issues on DSP runtime and adds support for new operations on Tensorflow, ONNX converters and on DSP runtime.

  • There is a known issue with mobilenet benchmark performance regression due to variance in benchmarks and changes for improving accuracy
  • Added option to request larger memory allocations on DSP for improved init time, at the expense of more memory use
  • AIP runtime does not support ub_tf8 data mode currently
  • Support for Android GCC build variants will be discontinued after the 1.25.0 release
  • The last release for the Qualcomm Flight platform (arm-linux-gcc4.8hf) will be the 1.25.0 release
  • x86 architecture support will move to Ubuntu 16.04 OS from Ubuntu 14.04 after the 1.27.0 release
  • The x86 binaries will move to clang 7 after the 1.26.0 release
  • Few performance improvements on DSP numbers, as measurements are reported on quantized DLCs from 1.25.0 release

What's in Qualcomm Neural Processing SDK v1.24?

This release focuses on adding the support for multiple inputs and multiple outputs on each subnet of AIP runtime and allows the setProfilingLevel API support for AIP and CPU runtimes.

  • There is a known conversion issue with the snpe-caffe-to-dlc-udl tool for converting a custom UDL layer which will be resolved in next release
  • Support for Android GCC build variants will be discontinued after the 1.25.0 release
  • x86 architecture support will move to Ubuntu 16.04 OS from Ubuntu 14.04, after the 1.27.0
  • The x86 binaries will move to clang 7 after the 1.26.0 release

What's in Qualcomm Neural Processing SDK v1.23.1?

This release focuses on improving the initialization/de-initialization times along with adding important timing/accuracy fixes for various Ops.

  • Added support for non max suppression, crop and resize layers on Tensorflow converter
  • Fixed the output inconsistency when multiple instances running concurrently on DSP runtime
  • Support for Android GCC build variants will be discontinued after the 1.25.0 release
  • x86 architecture support will move to Ubuntu 16.04 OS from Ubuntu 14.04, after the 1.27.0

What's in Qualcomm Neural Processing SDK v1.22.0?

This is a major release that adds support for two new Snapdragon Mobile Platforms, Snapdragon 855 and Snapdragon 675. We introduce support for the Qualcomm® Hexagon™ Tensor Accelerator (“HTA”) though the new “AIP” runtime that executes neural networks on HTA and falls back to HVX where necessary. The following are the major features that complete the usual collection of bug fixes and smaller features:

  • Support for the Snapdragon 855 mobile platform on the Hexagon DSP with Tensor Accelerator and Vector eXtensions, Adreno GPU and CPU
  • Support for the Snapdragon 675 mobile platform on the Hexagon DSP, Adreno GPU and CPU
  • Added new AIP runtime for 855
  • Added priority control for DSP workloads
  • Support for manually setting quantization ranges
  • Added new ‘snpe-throughput-net-run’ tool with support for simultaneous execution on different cores

What's in Qualcomm Neural Processing SDK v1.19.2?

The focus of this release is to add new operations and to fill gaps in operators support and to optimize existing operations such as Deconvolution.

  • Support for the Qualcomm QCS605 SoC on the Hexagon DSP (Android, Linux) and on Adreno GPU and CPU
  • Added support for the ELU operation for TensorFlow and ONNX on GPU and CPU
  • Added support for the Power operation for Caffe2 on GPU
  • Added support for Python 3.4
  • Optimized the Deconvolution, Slice and large Softmax operations on DSP

What's in Qualcomm Neural Processing SDK v1.18.0?

This release brings in support for three Snapdragon Mobile Platforms, broadens compatibility with MobileNet SSD networks and expands the supported operations on TensorFlow and ONNX converters. In addition, this release optimizes support for batching, especially when executing MobileNets on the DSP runtime.

  • Support for the Snapdragon 632 mobile platform on the Hexagon DSP, Adreno GPU and CPU
  • Support for the Snapdragon 439 and 429 mobile platforms on Adreno GPU and CPU
  • Improved compatibility of MobileNets networks, including an extended support for MobileNet SSD variations
  • Support for the TensorFlow ‘pad’ and elementwise subtraction on Adreno GPUs
  • Added support for ChannelShuffle to the TensorFlow converter
  • Added support for Shape and Pad to the ONNX converter

What's in Qualcomm Neural Processing SDK v1.17.0?

This release completes a few features and focuses on quality and stability while bringing some minor optimizations with it.

  • Added batching support to DSP. All runtimes have basic batching support now.
  • Extended batching support to the ChannelShuffle layer
  • Extended Caffe Scale layer support to Snapdragon DSPs
  • Optimizations around effective utilization of the DSPs
  • Updated SDK examples

What's in Qualcomm Neural Processing SDK v1.16.0?

The major addition of this release is support for input batching, which means being able to process input tensors with more than one element on the ‘batch’ dimension. This applies to models in Caffe, Caffe2, TensorFlow and ONNX models and when run on the Snapdragon GPU and CPU cores.

  • Input batching on Snapdragon GPU and CPU
  • Support for a new layer: ChannelShuffle (on GPU and CPU, for Caffe2 models)
  • Optimized the Sigmoid, Batch Normalization and Instance Normalization layers
  • Added the Inception-v3 model to the example APP

What's in Qualcomm Neural Processing SDK v1.15.0?

This release adds support for Caffe-based MobileNet SSD networks, and introduces accelerated Instance Normalization, and initial support for Grouped Deconvolutions and per-channel Batch Normalization and a Power layer. See the Layers and Limitations sections of the Reference Guide (available online and in the SDK) for more details.

  • Support for Caffe-based MobileNet SSD
  • Support for new layers: Instance Normalization
  • Extended support with Grouped Deconvolution and 1D Batch normalization
  • MobileNet SSD is 49% faster on GPU 16-bit
  • On average networks are 9% faster across supported chipsets and acceleration cores

What's new in Qualcomm Neural Processing SDK v1.14.0?

The ONNX 1.0 open format for deep learning models is welcomed in our March SDK release. For the list of supported operations please refer to the documentation in the SDK, or to the Documentation section of this website. This release also adds support for two new layers and a new performance profile mode.

  • Support for ONNX 1.0 models (Beta)
  • Support for new layers: Generate Proposals, and RoIAlign
  • Added a manual performance mode

What's new in Qualcomm Neural Processing SDK v1.13.0?

This update increases inference performance, and in particular adds support for the new digital signal processor included in the Snapdragon 845 mobile platform. This release also adds optimization to the 16-bit floating point runtime.

  • Support for the digital signal processor in the Snapdragon 845 mobile platform
  • Performance increase on the 16-bit floating point runtime
  • Performance improvements on the GPU runtimes
  • Initial support for Generate Proposals and RoiAlign layers for Caffe2, on the DSP runtime

What's new in Qualcomm Neural Processing SDK v1.12.0?

This large update introduces a full new accelerated runtime for 16-bit GPU computation, and support for a TensorFlow-style SSD network with MobileNets. We also introduce new library variations optimization.

  • Support for MobileNet SSD support on CPU and GPU
  • Added a GPU 16-bit floating-point runtime
  • Optimizations to the DSP runtime for the Snapdragon 845 mobile platform
  • Added Android LLVM libraries
  • Support for shared Symphony System Manager SDK libraries

What's new in Qualcomm Neural Processing SDK v1.10.1?

This release adds support for new Snapdragon platforms, deploys a fully new DSP runtime, fixes bugs and completes MobileNets support.

  • Initial support for the Snapdragon 845 mobile platform
  • Support for MobileNets on DSP; note that 8-bit quantization may not work well on this network structure
  • Upgraded the DSP acceleration runtime for greater performance and broader compatibility
  • Fixed Faster R-CNN UserBuffers operation
  • Support for Snapdragon Flight boards

What's new in Qualcomm Neural Processing SDK v1.8.0?

This release adds support for a new network architecture and extends support for Snapdragon processors.

  • MobileNets support for CPU, GPU
  • Support for Snapdragon 636
  • Added Android ARM 64 bit libraries

What's new in Qualcomm Neural Processing SDK v1.6.0?

This release brings stability and fixes a number of important issues reported by the AI ecosystem as well as our community of developers.

  • Support for Qualcomm® Snapdragon™ 450 processors - CPU, GPU
  • Bugfixes and performance improvements, including an issue where the NPE would not run if the OpenCL library was missing

What's new in Qualcomm Neural Processing SDK v1.4.0?

This release adds support for a new network architecture and extends support for Snapdragon processors.

  • Support for Snapdragon 630 - CPU, GPU
  • Support for Snapdragon 820 Automotive Processors – ADSP
  • Support for FasterRCNN - CPU, DSP

What's new in Qualcomm Neural Processing SDK v1.2.2

This is our first public release on Qualcomm Developer Network.

  • Available on Qualcomm Developer Network for download and usage
  • Support for reshape and permute layers
  • Enhancements to Caffe2
  • Documentation updates

What's in Qualcomm Neural Processing SDK v1.2.0?

This release was primarily meant for Caffe2 support.

What's in Qualcomm Neural Processing SDK v1.0.2?

This release was meant to add support for the newest Snapdragon mobile platforms.

What's in Qualcomm Neural Processing SDK v1.0?

This release mainly introduced TensorFlow support and stabilized the APIs.

  • Official TensorFlow conversion support
  • DSP runtime support
  • New dlc-quantize tool
  • API changes (non-backwards compatible changes were made)
    • DLC files created prior to 1.0 release need to be regenerated