Saved in:
Bibliographic Details
Main Authors: Rout, Nikhil, Tine, Blaise
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.00053
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910104167645184
author Rout, Nikhil
Tine, Blaise
author_facet Rout, Nikhil
Tine, Blaise
contents Efficient mixed-precision matrix multiply accumulate (MMA) operations are critical for accelerating deep learning workloads on GPGPUs. However, existing open-source dot product implementations for Tensor Cores rely on discrete arithmetic units, leading to high latency, accumulated rounding errors, and poor resource utilization. To address these challenges, we propose Ten-Four, a scalable mixed-precision fused dot product unit that integrates both the floating-point and integer arithmetic pipelines within a single fused architecture, implemented as part of the open-source RISC-V-based Vortex GPGPU's Tensor Core Unit extension. Our design supports low-precision multiplication in FP16/BF16/FP8/BF8/INT8/INT4 formats and higher-precision accumulation in FP32/INT32, with native support for Microscaling (MX) and sparse lane clock-gating for dynamic power reduction, while matching NVIDIA Tensor Core's numerical accuracy. Ten-Four achieves 4-cycle operation latency at 262.325 MHz Fmax, delivering 134.308 GFLOPS peak throughput per Tensor Core on the AMD Xilinx Alveo U55C FPGA, demonstrating ~3.1x performance improvement over an equivalent Berkeley HardFloat-based implementation at less than 60% the area cost.
format Preprint
id arxiv_https___arxiv_org_abs_2512_00053
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Ten-Four: An Open-Source Fused Dot Product Unit for Mixed-Precision GPGPU Tensor Cores
Rout, Nikhil
Tine, Blaise
Hardware Architecture
C.1.4
Efficient mixed-precision matrix multiply accumulate (MMA) operations are critical for accelerating deep learning workloads on GPGPUs. However, existing open-source dot product implementations for Tensor Cores rely on discrete arithmetic units, leading to high latency, accumulated rounding errors, and poor resource utilization. To address these challenges, we propose Ten-Four, a scalable mixed-precision fused dot product unit that integrates both the floating-point and integer arithmetic pipelines within a single fused architecture, implemented as part of the open-source RISC-V-based Vortex GPGPU's Tensor Core Unit extension. Our design supports low-precision multiplication in FP16/BF16/FP8/BF8/INT8/INT4 formats and higher-precision accumulation in FP32/INT32, with native support for Microscaling (MX) and sparse lane clock-gating for dynamic power reduction, while matching NVIDIA Tensor Core's numerical accuracy. Ten-Four achieves 4-cycle operation latency at 262.325 MHz Fmax, delivering 134.308 GFLOPS peak throughput per Tensor Core on the AMD Xilinx Alveo U55C FPGA, demonstrating ~3.1x performance improvement over an equivalent Berkeley HardFloat-based implementation at less than 60% the area cost.
title Ten-Four: An Open-Source Fused Dot Product Unit for Mixed-Precision GPGPU Tensor Cores
topic Hardware Architecture
C.1.4
url https://arxiv.org/abs/2512.00053