Intel Contributes AI Acceleration to PyTorch 2.0
March 17, 2023 | IntelEstimated reading time: 1 minute

?In the release of Python 2.0, contributions from Intel using Intel® Extension for PyTorch , oneAPI Deep Neural Network Library (oneDNN) and additional support for Intel® CPUs enable developers to optimize inference and training performance for artificial intelligence (AI).
As part of the PyTorch 2.0 compilation stack, the TorchInductor CPU backend optimization by Intel Extension for PyTorch and PyTorch ATen CPU achieved up to 1.7 times faster FP32 inference performance when benchmarked with TorchBench, HuggingFace and timm.1 This update brings notable performance improvements to graph compilation over the PyTorch eager mode.
Other optimizations include:
- Improved message-passing between adjacent neural network nodes to support graph neural network in PyTorch Geometric (PyG) for enhanced inference and performance training on Intel CPUs.
- New x86 quantization backend – a combination of FBGEMM (Facebook General Matrix-Matrix Multiplication) and oneDNN backends – replaces FBGEMM as the default quantization backend for x86 CPU platforms to enable better end-to-end int8 inference performance.
- Extended use of oneDNN with oneDNN Graph API to maximize efficient code generation on AI hardware by automatically identifying the graph partitions to be accelerated through fusion. BFloat16 and Float32 data types are supported and only inference workloads can be optimized; BF16 is only optimized on machines with AVX512_BF16 ISA support.
Testimonial
"Our marketing partnership with I-Connect007 is already delivering. Just a day after our press release went live, we received a direct inquiry about our updated products!"
Rachael Temple - AlltematedSuggested Items
Beyond Thermal Conductivity: Exploring Polymer-based TIM Strategies for High-power-density Electronics
10/13/2025 | Padmanabha Shakthivelu and Nico Bruijnis, MacDermid Alpha Electronics SolutionsAs power density and thermal loads continue to increase, effective thermal management becomes increasingly important. Rapid and efficient heat transfer from power semiconductor chip packages is essential for achieving optimal performance and ensuring long-term reliability of temperature-sensitive components. This is particularly crucial in power systems that support advanced applications such as green energy generation, electric vehicles, aerospace, and defense, along with high-speed computing for data centers and artificial intelligence (AI).
The Latest Issue: Advanced Electronics Packaging Digest to Explore Critical Minerals, Substrates, and Reliability Standards Driving Next-Gen Electronics
10/09/2025 | I-Connect007I-Connect007 is pleased to announce the upcoming issue of Advanced Electronics Packaging Digest (AEPD) on October 13, 2025, featuring expert insights on the technologies shaping the future of advanced packaging. As the electronics industry evolves, this issue takes a closer look at the materials, designs, and standards redefining performance and reliability across global markets.
Now Available—The Companion Guide to… SMT Inspection: Today, Tomorrow, and Beyond: Mastering Metrology for Advanced Semiconductor Packages
10/03/2025 | I-Connect007I-Connect007 is pleased to announce the release of an 18-page resource for engineers, technologists, and decision-makers in electronics manufacturing: The Companion Guide to SMT Inspection: Today, Tomorrow, and Beyond: Mastering Metrology for Advanced Semiconductor Packages.
Target Condition: Rethinking the PCB Stackup Recipe
10/01/2025 | Kelly Dack -- Column: Target ConditionMarie Antoinette is attributed with saying, “Let them eat cake,” but historians now agree she likely never said it. It was probably revolutionary propaganda to paint her as out of touch with the starving masses. Yet, the phrase still lingers, and oddly enough, it applies to the world of PCB design.
Empower Sets New Benchmark with 20x Faster Response and Breakthrough Sustainability Demonstrated at OCP Global Summit 2025
09/25/2025 | Empower SemiconductorEmpower Semiconductor, the world leader in powering AI-class processors, announced that its Crescendo chipset, an artificial intelligence (AI) and high-performance computing (HPC) processor true vertical power delivery platform, is available now for final sampling, with mass production slated for late 2025.