8000 Convolution FP32 in oneDNN Changed from gemm:acl to gemm:ref in TensorFlow 2.16 · Issue #4068 · tensorflow/serving · GitHub
[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content
Convolution FP32 in oneDNN Changed from gemm:acl to gemm:ref in TensorFlow 2.16 #4068
Open
@rpushkarr

Description

@rpushkarr

In TensorFlow version 2.16 (and later), the convolution operation implementation for FP32 data type in oneDNN was changed from gemm:acl to gemm:ref. However, this change has resulted in performance degradation compared to TensorFlow version 2.15, where gemm:acl was used.

System Information:

  • TensorFlow Version: 2.16
  • Previous Working Version: 2.15
  • oneDNN Version: 3.2.1
  • Hardware: Aarch64
  • Operating System: Ubuntu 22.04

Issue Summary:

  • In TensorFlow 2.15, the convolution operation for FP32 data type was routed through gemm:acl in oneDNN, which provided better performance.
  • In TensorFlow 2.16 (and later), the implementation was changed to use gemm:ref, leading to a noticeable performance drop.

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions

      0