Reduced-Precision Floating-Point Arithmetic in Systolic Arrays with Skewed Pipelines | IEEE Conference Publication | IEEE Xplore

Reduced-Precision Floating-Point Arithmetic in Systolic Arrays with Skewed Pipelines


Abstract:

The acceleration of deep-learning kernels in hardware relies on matrix multiplications that are executed efficiently on Systolic Arrays (SA). To effectively trade off dee...Show More

Abstract:

The acceleration of deep-learning kernels in hardware relies on matrix multiplications that are executed efficiently on Systolic Arrays (SA). To effectively trade off deep-learning training/inference quality with hardware cost, SA accelerators employ reduced-precision Floating-Point (FP) arithmetic. In this work, we demonstrate the need for new pipeline organizations to reduce latency and improve energy efficiency of reduced-precision FP operators for the chained multiply-add operation imposed by the structure of the SA. The proposed skewed pipeline design reorganizes the pipelined operation of the FP multiplyadd units to enable new forwarding paths for the exponent logic, which allow for parallel execution of the pipeline stages of consecutive PEs. As a result, the latency of the matrix multiplication operation within the SA is significantly reduced with minimal hardware cost, thereby yielding an energy reduction of 8% and 11% for the examined state-of-the-art CNNs.
Date of Conference: 11-13 June 2023
Date Added to IEEE Xplore: 07 July 2023
ISBN Information:

ISSN Information:

Conference Location: Hangzhou, China

References

References is not available for this document.