# Modeling Deep Learning Accelerator Enabled GPUs

arXiv: https://arxiv.org/abs/1811.08309 · HTML: https://mlsanity.com/paper/1811.08309/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Nov 2018.

## Built on by (most cited first, 10 of 10)

- [OliVe: Accelerating Large Language Models via Hardware-friendly Outlier-Victim Pair Quantization](https://mlsanity.com/paper/2304.07493/) (2023)
- [Dual-side Sparse Tensor Core](https://mlsanity.com/paper/2105.09564/) (2021)
- [MicroScopiQ: Accelerating Foundational Models through Outlier-Aware Microscaling Quantization](https://mlsanity.com/paper/2411.05282/) (2024)
- [Post-Training Sparsity-Aware Quantization](https://mlsanity.com/paper/2105.11010/) (2021)
- [APNN-TC: Accelerating Arbitrary Precision Neural Networks on Ampere GPU Tensor Cores](https://mlsanity.com/paper/2106.12169/) (2021)
- [The Case for Co-Designing Model Architectures with Hardware](https://mlsanity.com/paper/2401.14489/) (2024)
- [MX+: Pushing the Limits of Microscaling Formats for Efficient Large Language Model Serving](https://mlsanity.com/paper/2510.14557/) (2025)
- [Mustafar: Promoting Unstructured Sparsity for KV Cache Pruning in LLM Inference](https://mlsanity.com/paper/2505.22913/) (2025)
- [Bit-Accurate Modeling of GPU Matrix Multiply-Accumulate Units: Demystifying Numerical Discrepancy and Accuracy](https://mlsanity.com/paper/2511.10909/) (2025)
- [PacQ: A SIMT Microarchitecture for Efficient Dataflow in Hyper-asymmetric GEMMs](https://mlsanity.com/paper/2502.18627/) (2025)

## Abstract (arXiv)

The efficacy of deep learning has resulted in its use in a growing number of applications. The Volta graphics processor unit (GPU) architecture from NVIDIA introduced a specialized functional unit, the "tensor core", that helps meet the growing demand for higher performance for deep learning. In this paper we study the design of the tensor cores in NVIDIA's Volta and Turing architectures. We further propose an architectural model for the tensor cores in Volta. When implemented a GPU simulator, GPGPU-Sim, our tensor core model achieves 99.6% correlation versus an NVIDIA Titan~V GPU in terms of average instructions per cycle when running tensor core enabled GEMM workloads. We also describe support added to enable GPGPU-Sim to run CUTLASS, an open-source CUDA C++ template library providing customizable GEMM templates that utilize tensor cores.