commit | 13a93fa138791d2200e49f85e5bff8464c4c0525 | [log] [tgz] |
---|---|---|
author | Frank Barchard <fbarchard@google.com> | Wed Apr 15 10:31:19 2020 -0700 |
committer | XNNPACK Team <xnnpack-github-robot@google.com> | Wed Apr 15 10:31:48 2020 -0700 |
tree | a2bfaaa6db7b47616824f17eae5f3e40855db932 | |
parent | 1b555e0e77a5733754005de2e009edacc8c9fc89 [diff] |
1x12 Cortex A64 F32 GEMM use 2 sets of accumulators 6% faster on Cortex A55 Was f32_gemm_1x12__aarch64_neonfma_cortex_a53 131745415 Now f32_gemm_1x12__aarch64_neonfma_cortex_a53 124287952 Based on 1x8 which does the following 2 sets of accumulators to reduce FMA stalls LDR for B and co-issue FMA Pipelined load of A and reload B just after each use. PiperOrigin-RevId: 306671100
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 2 (BCM2836), ms | RPi 3+ (BCM2837B0), ms | RPi 4 (BCM2711), ms |
---|---|---|---|
MobileNet v1 1.0X | 341 | 115 | 75 |
MobileNet v2 1.0X | 197 | 79 | 44 |
MobileNet v3 Large | 165 | 67 | 41 |
MobileNet v3 Small | 53 | 23 | 14 |
Benchmarked on February 12, 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. Unlike QNNPACK, XNNPACK focuses entirely on floating-point operators, and its API is no longer compatible with QNNPACK.