XNNPACK is a highly optimized solution for neural network inference on ARM, x86, WebAssembly, and RISC-V 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, ONNX Runtime, and MediaPipe.

• ARM64 on Android, iOS, macOS, Linux, and Windows
• ARMv7 (with NEON) on Android
• ARMv6 (with VFPv2) on Linux
• x86 and x86-64 (up to AVX512) on Windows, Linux, macOS, Android, and iOS simulator
• WebAssembly MVP
• WebAssembly SIMD
• WebAssembly Relaxed SIMD (experimental)
• RISC-V (RV32GC and RV64GC)

XNNPACK implements the following neural network operators:

• 2D Convolution (including grouped and depthwise)
• 2D Deconvolution (AKA Transposed Convolution)
• 2D Average Pooling
• 2D Max Pooling
• 2D ArgMax Pooling (Max Pooling + indices)
• 2D Unpooling
• 2D Bilinear Resize
• 2D Depth-to-Space (AKA Pixel Shuffle)
• Add (including broadcasting, two inputs only)
• Subtract (including broadcasting)
• Divide (including broadcasting)
• Maximum (including broadcasting)
• Minimum (including broadcasting)
• Multiply (including broadcasting)
• Squared Difference (including broadcasting)
• Global Average Pooling
• Channel Shuffle
• Fully Connected
• Abs (absolute value)
• Bankers' Rounding (rounding to nearest, ties to even)
• Ceiling (rounding to integer above)
• Clamp (includes ReLU and ReLU6)
• Convert (includes fixed-point and half-precision quantization and dequantization)
• Copy
• ELU
• Floor (rounding to integer below)
• HardSwish
• Leaky ReLU
• Negate
• Sigmoid
• Softmax
• Square
• Tanh
• Transpose
• Truncation (rounding to integer towards zero)
• PReLU

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.

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.

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.

Benchmarked on Feb 8, 2022 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. INT8 inference was evaluated on per-channel quantization schema.

• C11
• C++14
• Python 3

• Marat Dukhan "The Indirect Convolution Algorithm". Presented on Efficient Deep Learning for Compute Vision (ECV) 2019 workshop (slides, paper on ArXiv).
• Erich Elsen, Marat Dukhan, Trevor Gale, Karen Simonyan "Fast Sparse ConvNets". Paper on ArXiv, pre-trained sparse models.
• Marat Dukhan, Artsiom Ablavatski "The Two-Pass Softmax Algorithm". Paper on ArXiv.
• Yury Pisarchyk, Juhyun Lee "Efficient Memory Management for Deep Neural Net Inference". Paper on ArXiv.

• TensorFlow Lite.
• TensorFlow.js WebAssembly backend.
• PyTorch Mobile.
• ONNX Runtime Mobile
• MediaPipe for the Web.
• Alibaba HALO (Heterogeneity-Aware Lowering and Optimization)
• Samsung ONE (On-device Neural Engine)

XNNPACK is a based on QNNPACK library. Over time its codebase diverged a lot, and XNNPACK API is no longer compatible with QNNPACK.