commit | 0b0437454ae08684071307d042707e4097c2e5dd | [log] [tgz] |
---|---|---|
author | Marat Dukhan <maratek@google.com> | Wed Jun 02 18:29:11 2021 -0700 |
committer | XNNPACK Team <xnnpack-github-robot@google.com> | Wed Jun 02 18:29:55 2021 -0700 |
tree | 9e02c5c7fce5cdc81d0a556c946339bd5436962a | |
parent | 8b0e3812b59bb86db6a27d6f3ff735f4e7598ec3 [diff] |
Support QC8 GEMM microkernels - Minimal set of 8-bit fixed-point microkernels with per-channel quantization (QC8) optimized for AVX2. - Extend packing functions to allow extra space after the kernel data. Per-channel quantization parameters are later packed into that space. - Extend GemmMicrokernelTester to support unit testing of QC8 GEMM. PiperOrigin-RevId: 377191090
XNNPACK is a highly optimized library of floating-point neural network inference operators for ARM, WebAssembly, and x86 platforms. XNNPACK is not intended for direct use by deep learning practitioners and researchers; instead it provides low-level performance primitives for accelerating high-level machine learning frameworks, such as TensorFlow Lite, TensorFlow.js, PyTorch, and MediaPipe.
XNNPACK implements the following neural network operators:
All operators in XNNPACK support NHWC layout, but additionally allow custom stride along the Channel dimension. Thus, operators can consume a subset of channels in the input tensor, and produce a subset of channels in the output tensor, providing a zero-cost Channel Split and Channel Concatenation operations.
The table below presents single-threaded performance of XNNPACK library on three generations of MobileNet models and three generations of Pixel phones.
Model | Pixel, ms | Pixel 2, ms | Pixel 3a, ms |
---|---|---|---|
MobileNet v1 1.0X | 82 | 86 | 88 |
MobileNet v2 1.0X | 49 | 53 | 55 |
MobileNet v3 Large | 39 | 42 | 44 |
MobileNet v3 Small | 12 | 14 | 14 |
The following table presents multi-threaded (using as many threads as there are big cores) performance of XNNPACK library on three generations of MobileNet models and three generations of Pixel phones.
Model | Pixel, ms | Pixel 2, ms | Pixel 3a, ms |
---|---|---|---|
MobileNet v1 1.0X | 43 | 27 | 46 |
MobileNet v2 1.0X | 26 | 18 | 28 |
MobileNet v3 Large | 22 | 16 | 24 |
MobileNet v3 Small | 7 | 6 | 8 |
Benchmarked on March 27, 2020 with end2end_bench --benchmark_min_time=5
on an Android/ARM64 build with Android NDK r21 (bazel build -c opt --config android_arm64 :end2end_bench
) and neural network models with randomized weights and inputs.
The table below presents multi-threaded performance of XNNPACK library on three generations of MobileNet models and three generations of Raspberry Pi boards.
Model | RPi Zero W (BCM2835), ms | RPi 2 (BCM2836), ms | RPi 3+ (BCM2837B0), ms | RPi 4 (BCM2711), ms |
---|---|---|---|---|
MobileNet v1 1.0X | 4004 | 337 | 116 | 72 |
MobileNet v2 1.0X | 2011 | 195 | 83 | 41 |
MobileNet v3 Large | 1694 | 163 | 70 | 38 |
MobileNet v3 Small | 482 | 52 | 23 | 13 |
Benchmarked on May 22, 2020 with end2end-bench --benchmark_min_time=5
on a Raspbian Buster build with CMake (./scripts/build-local.sh
) and neural network models with randomized weights and inputs.
XNNPACK is a based on QNNPACK library. Over time its codebase diverged a lot, and XNNPACK API is no longer compatible with QNNPACK.