Evolving CUDA PTX programs by quantum inspired linear genetic programming

Cupertino, Leandro Fontoura; Silva, Cleomar P.; Dias, Douglas Mota; Pacheco, Marco Aurélio Cavalcanti; Bentes, Cristiana

doi:10.1145/2001858.2002026

Cited by 9 publications

(5 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The first part of this work, which accomplished to develop a version of QILGP whose programs are evaluated by a GPU, is described in [6]. This full migration to GPU, and not just the evaluation of programs, would result in a substantial acceleration of the model, since the programs would not need to be constantly transfered through the PCI bus during the evolution no more.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Describing Quantum-Inspired Linear Genetic Programming from symbolic regression problems

Dias

Pacheco

2012

2012 IEEE Congress on Evolutionary Computation

View full text Add to dashboard Cite

Quantum-inspired evolutionary algorithms (QIEAs) exploit principles of quantum mechanics to improve the performance of classical evolutionary algorithms. This paper describes the latest version of a QIEA model ("Quantum-Inspired Linear Genetic Programming" -QILGP) to evolve machine code programs. QILGP is inspired on multilevel quantum systems and its operation is based on quantum individuals, which represent a superposition of all programs of search space (solutions). Symbolic regression problems and the current more efficient model to evolve machine code (AIMGP) are used in comparative tests, which aim to evaluate the performance impact of introducing demes (subpopulations) and a limited migration strategy in this version of QILGP. It outperforms AIMGP by obtaining better solutions with fewer parameters and operators. The performance improvement achieved by this latest version of QILGP encourages its ongoing and future enhancements. Thus, this paper concludes that the quantum inspiration paradigm can be a competitive approach to evolve programs more efficiently.Index Terms-Quantum-inspired algorithm, multilevel quantum system, linear genetic programming.

show abstract

Section: Discussionmentioning

confidence: 99%

“…This description also intends to assist a deeper understanding of this model operation in other works where it has been used [5], [6]. The experiments also aim to evaluate the division of the population in demes (i.e.…”

Section: Introductionmentioning

confidence: 99%

Describing Quantum-Inspired Linear Genetic Programming from symbolic regression problems

Dias

Pacheco

2012

2012 IEEE Congress on Evolutionary Computation

View full text Add to dashboard Cite

show abstract

“…The data and codes transmitted between the API library and the daemon are all encapsulated into messages. One message mainly contains two fields: FunctionID and PTX (Parallel Thread eXecution) code 20–22 . The FunctionID field of the header indicates which GPU call is made; the parameters of this call and the PTX code are encapsulated in the message body.…”

Section: Adaptive and Transparent Task Schedulingmentioning

confidence: 99%

Adaptive and transparent task scheduling of GPU‐powered clusters

Yang

et al. 2020

Concurrency and Computation

View full text Add to dashboard Cite

GPGPU-powered supercomputers are vital for various science and engineering applications. On each cluster node, the GPU works as a coprocessor of the CPU, and the computing task runs alternatively on CPU and GPU. Due to this characteristic, traditional task scheduling strategy tends to result in significant workload imbalance and underutilization of GPUs. We design an adaptive scheduling strategy to alleviate such imbalance and underutilization. Our strategy proposes to logically treats all GPUs in the cluster as a whole. Every cluster node maintains a local information table of all GPUs. Once a GPU call request is received, a node selects a GPU to run the task in an adaptive manner based on this table. In addition, our strategy does not rely on a global queue, and thus avoids excessive internode communication overhead. Moreover, we encapsulate our strategy into an intermedia module between the cluster and users. Consequently, underlying details of task scheduling is transparent to users, which enhances usability. We validate our strategy through experiments.

show abstract

“…However, this is just the evaluation phase of GP alone, the average compilation time took approximately 0.05 seconds per individual which significantly reduces the speed. Cupertino et al (2011) used quantum inspired linear GP to generate PTX kernels to evaluate on a GPU. Comparisons are made with a CPU version with a 25x speedup reported for a large number of fitness cases.…”

Section: Accelerating Genetic Programmingmentioning

confidence: 99%

Faster GPU-based genetic programming using a two-dimensional stack

Chitty

2016

Soft Comput

View full text Add to dashboard Cite

Genetic Programming (GP) is a computationally intensive technique which also has a high degree of natural parallelism. Parallel computing architectures have become commonplace especially with regards Graphics Processing Units (GPU). Hence, versions of GP have been implemented that utilise these highly parallel computing platforms enabling significant gains in the computational speed of GP to be achieved. However, recently a two dimensional stack approach to GP using a multicore CPU also demonstrated considerable performance gains. Indeed, performances equivalent to or exceeding that achieved by a GPU were demonstrated. This paper will demonstrate that a similar two dimensional stack approach can also be applied to a GPU based approach to GP to better exploit the underlying technology. Performance gains are achieved over a standard single dimensional stack approach when utilising a GPU. Overall, a peak computational speed of over 55 billion Genetic Programming Operations per Second are observed, a two fold improvement over the best GPU based single dimensional stack approach from the literature.

show abstract

Evolving CUDA PTX programs by quantum inspired linear genetic programming

Cited by 9 publications

References 15 publications

Describing Quantum-Inspired Linear Genetic Programming from symbolic regression problems

Describing Quantum-Inspired Linear Genetic Programming from symbolic regression problems

Adaptive and transparent task scheduling of GPU‐powered clusters

Faster GPU-based genetic programming using a two-dimensional stack

Contact Info

Product

Resources

About