José María González-Linares
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
José María González-Linares has a total of 49 co-authors. Here are the top co-authors by number of shared publications:
- Nicolás Guil
University of Malaga
32 shared publications - Juan Gómez-Luna
NVIDIA, Zürich, Switzerland
14 shared publications - Julian Ramos Cozar
University of Malaga
12 shared publications E.L. Zapata
6 shared publicationsJosé Ignacio Benavides
4 shared publications- Antonio-Jose Lázaro-Muñoz
University of Malaga
2 shared publications
Latest Publications
- Open Access
- 2 June 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-11
Real-time multiple people gait recognition in the edge
Deploying deep learning models on edge devices offers advantages in terms of data security and communication latency. However, optimizing these models to achieve fast computing speeds without sacrificing accuracy can be challenging, especially in video surveillance applications where real-time processing is crucial. In this study, we investigate the deployment of gait recognition models as a multi-objective selection problem in which we seek to simultaneously minimize several objectives, such as latency and energy consumption, while maintaining accuracy. The decision space of a problem comprises all models that can be built by varying parameters, such as the size of the model, the operating frequency of the device, and the precision of the operations. From this problem definition, a subset of Pareto optimal models can be selected to be deployed on the target device. We conducted experiments with two different gait recognition models on NVIDIA Jetson Orin Nano and Jetson AGX Orin to explore their decision spaces. In addition, we investigated different strategies to increase the throughput of the deployed models by taking advantage of batching and concurrent execution. Together, these techniques allowed us to design real-time solutions for gait recognition in scenarios with multiple subjects. These solutions can process between 42 and 188 simultaneous subjects at 25 inferences per second with an energy consumption ranging from 6.31 to 9.71 mJ per inference, depending on the device and the deployed model.
- 2 June 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-11
Open AccessReal-time multiple people gait recognition in the edge
Deploying deep learning models on edge devices offers advantages in terms of data security and communication latency. However, optimizing these models to achieve fast computing speeds without sacrificing accuracy can be challenging, especially in video surveillance applications where real-time processing is crucial. In this study, we investigate the deployment of gait recognition models as a multi-objective selection problem in which we seek to simultaneously minimize several objectives, such as latency and energy consumption, while maintaining accuracy. The decision space of a problem comprises all models that can be built by varying parameters, such as the size of the model, the operating frequency of the device, and the precision of the operations. From this problem definition, a subset of Pareto optimal models can be selected to be deployed on the target device. We conducted experiments with two different gait recognition models on NVIDIA Jetson Orin Nano and Jetson AGX Orin to explore their decision spaces. In addition, we investigated different strategies to increase the throughput of the deployed models by taking advantage of batching and concurrent execution. Together, these techniques allowed us to design real-time solutions for gait recognition in scenarios with multiple subjects. These solutions can process between 42 and 188 simultaneous subjects at 25 inferences per second with an energy consumption ranging from 6.31 to 9.71 mJ per inference, depending on the device and the deployed model.
- 1 August 2022
- Published by Springer Nature
- p. 369-384
A Hybrid Piece-Wise Slowdown Model for Concurrent Kernel Execution on GPU
- 1 August 2022
- Published by Springer Nature
- p. 369-384
A Hybrid Piece-Wise Slowdown Model for Concurrent Kernel Execution on GPU
- Open Access
- 29 November 2021
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 78 (6) , 7556-7590
CAVLCU: an efficient GPU-based implementation of CAVLC
CAVLC (Context-Adaptive Variable Length Coding) is a high-performance entropy method for video and image compression. It is the most commonly used entropy method in the video standard H.264. In recent years, several hardware accelerators for CAVLC have been designed. In contrast, high-performance software implementations of CAVLC (e.g., GPU-based) are scarce. A high-performance GPU-based implementation of CAVLC is desirable in several scenarios. On the one hand, it can be exploited as the entropy component in GPU-based H.264 encoders, which are a very suitable solution when GPU built-in H.264 hardware encoders lack certain necessary functionality, such as data encryption and information hiding. On the other hand, a GPU-based implementation of CAVLC can be reused in a wide variety of GPU-based compression systems for encoding images and videos in formats other than H.264, such as medical images. This is not possible with hardware implementations of CAVLC, as they are non-separable components of hardware H.264 encoders. In this paper, we present CAVLCU, an efficient implementation of CAVLC on GPU, which is based on four key ideas. First, we use only one kernel to avoid the long latency global memory accesses required to transmit intermediate results among different kernels, and the costly launches and terminations of additional kernels. Second, we apply an efficient synchronization mechanism for thread-blocks (In this paper, to prevent confusion, a block of pixels of a frame will be referred to as simply block and a GPU thread block as thread-block.) that process adjacent frame regions (in horizontal and vertical dimensions) to share results in global memory space. Third, we exploit fully the available global memory bandwidth by using vectorized loads to move directly the quantized transform coefficients to registers. Fourth, we use register tiling to implement the zigzag sorting, thus obtaining high instruction-level parallelism. An exhaustive experimental evaluation showed that our approach is between 2.5 $$\times$$ and 5.4 $$\times$$ faster than the only state-of-the-art GPU-based implementation of CAVLC.- 29 November 2021
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 78 (6) , 7556-7590
Open AccessCAVLCU: an efficient GPU-based implementation of CAVLC
CAVLC (Context-Adaptive Variable Length Coding) is a high-performance entropy method for video and image compression. It is the most commonly used entropy method in the video standard H.264. In recent years, several hardware accelerators for CAVLC have been designed. In contrast, high-performance software implementations of CAVLC (e.g., GPU-based) are scarce. A high-performance GPU-based implementation of CAVLC is desirable in several scenarios. On the one hand, it can be exploited as the entropy component in GPU-based H.264 encoders, which are a very suitable solution when GPU built-in H.264 hardware encoders lack certain necessary functionality, such as data encryption and information hiding. On the other hand, a GPU-based implementation of CAVLC can be reused in a wide variety of GPU-based compression systems for encoding images and videos in formats other than H.264, such as medical images. This is not possible with hardware implementations of CAVLC, as they are non-separable components of hardware H.264 encoders. In this paper, we present CAVLCU, an efficient implementation of CAVLC on GPU, which is based on four key ideas. First, we use only one kernel to avoid the long latency global memory accesses required to transmit intermediate results among different kernels, and the costly launches and terminations of additional kernels. Second, we apply an efficient synchronization mechanism for thread-blocks (In this paper, to prevent confusion, a block of pixels of a frame will be referred to as simply block and a GPU thread block as thread-block.) that process adjacent frame regions (in horizontal and vertical dimensions) to share results in global memory space. Third, we exploit fully the available global memory bandwidth by using vectorized loads to move directly the quantized transform coefficients to registers. Fourth, we use register tiling to implement the zigzag sorting, thus obtaining high instruction-level parallelism. An exhaustive experimental evaluation showed that our approach is between 2.5 $$\times$$ and 5.4 $$\times$$ faster than the only state-of-the-art GPU-based implementation of CAVLC. - 19 May 2021
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 78 (1) , 43-71
FlexSched: Efficient scheduling techniques for concurrent kernel execution on GPUs
- 19 May 2021
- Published by Springer Nature in The Journal of Supercomputing
- Vol. 78 (1) , 43-71
FlexSched: Efficient scheduling techniques for concurrent kernel execution on GPUs
- 19 November 2019
- Published by Wiley in Concurrency and Computation: Practice and Experience
- Vol. 32 (20)
Heuristics for concurrent task scheduling on GPUs
Summary: Concurrent execution of tasks in GPUs can reduce the computation time of a workload by overlapping data transfer and execution commands. However, it is difficult to implement an efficient runtime scheduler that minimizes the workload makespan as many execution orderings should be evaluated. In this paper, we employ scheduling theory to build a model that takes into account the device capabilities, workload characteristics, constraints, and objective functions. In our model, GPU tasks scheduling is reformulated as a flow shop scheduling problem, which allow us to apply and compare well‐known heuristics already developed in the operations research field. In addition, we develop a new heuristic, specifically focused on executing GPU commands, that achieves better scheduling results than previous ones. It leverages on a precise GPU command execution model for both computation and data transfers to carry out more advantageous scheduling decisions. A comprehensive evaluation, showing the suitability and robustness of this new approach, is conducted in three different NVIDIA architectures (Kepler, Maxwell, and Pascal). Results confirm the proposed heuristic achieves the best results in more than 90% of the experiments. Furthermore, a comparison has been made with MPS (Multi‐Process Service), the NVIDIA API that deals with the execution of concurrent tasks, which shows that our solution obtains speed‐ups ranging from 1.15 to 1.20.
- 19 November 2019
- Published by Wiley in Concurrency and Computation: Practice and Experience
- Vol. 32 (20)
Heuristics for concurrent task scheduling on GPUs
Summary: Concurrent execution of tasks in GPUs can reduce the computation time of a workload by overlapping data transfer and execution commands. However, it is difficult to implement an efficient runtime scheduler that minimizes the workload makespan as many execution orderings should be evaluated. In this paper, we employ scheduling theory to build a model that takes into account the device capabilities, workload characteristics, constraints, and objective functions. In our model, GPU tasks scheduling is reformulated as a flow shop scheduling problem, which allow us to apply and compare well‐known heuristics already developed in the operations research field. In addition, we develop a new heuristic, specifically focused on executing GPU commands, that achieves better scheduling results than previous ones. It leverages on a precise GPU command execution model for both computation and data transfers to carry out more advantageous scheduling decisions. A comprehensive evaluation, showing the suitability and robustness of this new approach, is conducted in three different NVIDIA architectures (Kepler, Maxwell, and Pascal). Results confirm the proposed heuristic achieves the best results in more than 90% of the experiments. Furthermore, a comparison has been made with MPS (Multi‐Process Service), the NVIDIA API that deals with the execution of concurrent tasks, which shows that our solution obtains speed‐ups ranging from 1.15 to 1.20.
- Open Access
- 26 March 2019
- Published by Springer Nature
- p. 146-159
A Scheduling Theory Framework for GPU Tasks Efficient Execution
- 26 March 2019
- Published by Springer Nature
- p. 146-159
Open AccessA Scheduling Theory Framework for GPU Tasks Efficient Execution
- 1 November 2017
- Published by Elsevier in Journal of Parallel and Distributed Computing
- Vol. 109, 258-271
A tasks reordering model to reduce transfers overhead on GPUs
- 1 November 2017
- Published by Elsevier in Journal of Parallel and Distributed Computing
- Vol. 109, 258-271
A tasks reordering model to reduce transfers overhead on GPUs
- 1 November 2015
- Published by Elsevier in Journal of Systems Architecture
- Vol. 61 (10) , 659-667
Calculation of dense trajectory descriptors on a heterogeneous embedded architecture
- 1 November 2015
- Published by Elsevier in Journal of Systems Architecture
- Vol. 61 (10) , 659-667
Calculation of dense trajectory descriptors on a heterogeneous embedded architecture
- 17 September 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 65 (7) , 2045-2058
Configurable XOR Hash Functions for Banked Scratchpad Memories in GPUs
Scratchpad memories in GPU architectures are employed as software-controlled caches to increase the effective GPU memory bandwidth. Through the use of well-known optimization techniques, such as privatization and tiling, they are properly exploited. Typically, they are banked memories which are addressed with a$\text{mod}(2^N)$ bank indexing scheme. Although their bandwidth is fully exploited for linear memory accesses, their performance is burdened when non-unit strides appear in memory access patterns because they provoke bank conflicts. This paper explores the use of configurable bit-vector and bitwise XOR-based hash functions to evenly distribute memory addresses of the access patterns over the memory banks, reducing the number of bank conflicts. An exhaustive, but lightweight, search is used to configure bit-vector hash functions. Bitwise hash functions are configured with heuristics. Hardware and software implementations are carried out. For the hardware approach, the experimental results show 24 percent performance speed-up for 22 benchmarks on GPGPU-Sim, a Fermi-like simulator. Bank conflicts are reduced by 96 percent with bit-vector hash functions, and 97 percent with bitwise hash functions using our proposed Minimum Imbalance Heuristic. The software approach, using bit-vector hash functions, demonstrates 23 percent speed-up and 96 percent bank conflict reduction on a Fermi GPU, and 33 percent speed-up and 99 percent bank conflict reduction on a Kepler GPU.- 17 September 2015
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 65 (7) , 2045-2058
Configurable XOR Hash Functions for Banked Scratchpad Memories in GPUs
Scratchpad memories in GPU architectures are employed as software-controlled caches to increase the effective GPU memory bandwidth. Through the use of well-known optimization techniques, such as privatization and tiling, they are properly exploited. Typically, they are banked memories which are addressed with a$\text{mod}(2^N)$ bank indexing scheme. Although their bandwidth is fully exploited for linear memory accesses, their performance is burdened when non-unit strides appear in memory access patterns because they provoke bank conflicts. This paper explores the use of configurable bit-vector and bitwise XOR-based hash functions to evenly distribute memory addresses of the access patterns over the memory banks, reducing the number of bank conflicts. An exhaustive, but lightweight, search is used to configure bit-vector hash functions. Bitwise hash functions are configured with heuristics. Hardware and software implementations are carried out. For the hardware approach, the experimental results show 24 percent performance speed-up for 22 benchmarks on GPGPU-Sim, a Fermi-like simulator. Bank conflicts are reduced by 96 percent with bit-vector hash functions, and 97 percent with bitwise hash functions using our proposed Minimum Imbalance Heuristic. The software approach, using bit-vector hash functions, demonstrates 23 percent speed-up and 96 percent bank conflict reduction on a Fermi GPU, and 33 percent speed-up and 99 percent bank conflict reduction on a Kepler GPU.