Pretražite po imenu i prezimenu autora, mentora, urednika, prevoditelja

Napredna pretraga

Pregled bibliografske jedinice broj: 1207084

Towards intelligent compiler optimization


Kovac, Mihael; Brcic, Mario; Krajna, Agneza; Krleza, Dalibor
Towards intelligent compiler optimization // 2022 45th Jubilee International Convention on Information, Communication and Electronic Technology (MIPRO)
Opatija, Hrvatska: IEEE, 2022. str. 948-953 doi:10.23919/mipro55190.2022.9803630 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)


CROSBI ID: 1207084 Za ispravke kontaktirajte CROSBI podršku putem web obrasca

Naslov
Towards intelligent compiler optimization

Autori
Kovac, Mihael ; Brcic, Mario ; Krajna, Agneza ; Krleza, Dalibor

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
2022 45th Jubilee International Convention on Information, Communication and Electronic Technology (MIPRO) / - : IEEE, 2022, 948-953

Skup
2022 45th Jubilee International Convention on Information, Communication and Electronic Technology (MIPRO)

Mjesto i datum
Opatija, Hrvatska, 23-27.05.2022

Vrsta sudjelovanja
Predavanje

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
compiler optimization , GNN , reinforcement learning , edge computing , heterogeneous computing , polyhedral model , machine learning

Sažetak
The future of computation is massively parallel and heterogeneous with specialized accelerator devices and instruction sets in both edge- and cluster-computing. However, software development is bound to become the bottleneck. To extract the potential of hardware wonders, the software would have to solve the following problems: heterogeneous device mapping, capability discovery, parallelization, adaptation to new ISAs, and many others. This systematic complexity will be impossible to manually tame for human developers. These problems need to be offloaded to intelligent compilers. In this paper, we present the current research that utilizes deep learning, polyhedral optimization, reinforcement learning, etc. We envision the future of compilers as consisting of empirical testing, automatic statistics collection, continual learning, device capability discovery, multiphase compiling – precompiling and JIT tuning, and classification of workloads. We devise a simple classification experiment to demonstrate the power of simple graph neural networks (GNNs) paired with program graphs. The test performance demonstrates the effectiveness and representational appropriateness of GNNs for compiler optimizations in heterogeneous systems. The benefits of intelligent compilers are time savings for the economy, energy savings for the environment, and greater democratization of software development.

Izvorni jezik
Engleski

Znanstvena područja
Matematika, Računarstvo, Interdisciplinarne tehničke znanosti



POVEZANOST RADA


Ustanove:
Fakultet elektrotehnike i računarstva, Zagreb

Profili:

Avatar Url Agneza Krajna (autor)

Avatar Url Dalibor Krleža (autor)

Avatar Url Mario Brčić (autor)

Poveznice na cjeloviti tekst rada:

doi

Citiraj ovu publikaciju:

Kovac, Mihael; Brcic, Mario; Krajna, Agneza; Krleza, Dalibor
Towards intelligent compiler optimization // 2022 45th Jubilee International Convention on Information, Communication and Electronic Technology (MIPRO)
Opatija, Hrvatska: IEEE, 2022. str. 948-953 doi:10.23919/mipro55190.2022.9803630 (predavanje, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
Kovac, M., Brcic, M., Krajna, A. & Krleza, D. (2022) Towards intelligent compiler optimization. U: 2022 45th Jubilee International Convention on Information, Communication and Electronic Technology (MIPRO) doi:10.23919/mipro55190.2022.9803630.
@article{article, author = {Kovac, Mihael and Brcic, Mario and Krajna, Agneza and Krleza, Dalibor}, year = {2022}, pages = {948-953}, DOI = {10.23919/mipro55190.2022.9803630}, keywords = {compiler optimization , GNN , reinforcement learning , edge computing , heterogeneous computing , polyhedral model , machine learning}, doi = {10.23919/mipro55190.2022.9803630}, title = {Towards intelligent compiler optimization}, keyword = {compiler optimization , GNN , reinforcement learning , edge computing , heterogeneous computing , polyhedral model , machine learning}, publisher = {IEEE}, publisherplace = {Opatija, Hrvatska} }
@article{article, author = {Kovac, Mihael and Brcic, Mario and Krajna, Agneza and Krleza, Dalibor}, year = {2022}, pages = {948-953}, DOI = {10.23919/mipro55190.2022.9803630}, keywords = {compiler optimization , GNN , reinforcement learning , edge computing , heterogeneous computing , polyhedral model , machine learning}, doi = {10.23919/mipro55190.2022.9803630}, title = {Towards intelligent compiler optimization}, keyword = {compiler optimization , GNN , reinforcement learning , edge computing , heterogeneous computing , polyhedral model , machine learning}, publisher = {IEEE}, publisherplace = {Opatija, Hrvatska} }

Citati:





    Contrast
    Increase Font
    Decrease Font
    Dyslexic Font