Zobrazeno 1 - 10
of 44
pro vyhledávání: '"Uday Bondhugula"'
Publikováno v:
2022 55th IEEE/ACM International Symposium on Microarchitecture (MICRO).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ea34fe14b18b7a8a0e49d5b6e3d7280a
https://doi.org/10.1109/micro56248.2022.00043
https://doi.org/10.1109/micro56248.2022.00043
Autor:
Uday Bondhugula, Karan Aggarwal
Publikováno v:
ACM Transactions on Parallel Computing. 7:1-45
Sparse matrix-vector multiplication ( SpMV ) operations are commonly used in various scientific and engineering applications. The performance of the SpMV operation often depends on exploiting regularity patterns in the matrix. Various representations
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::493aa04e87b4e8115c41018517a4003b
https://doi.org/10.1145/3418075
https://doi.org/10.1145/3418075
Autor:
Uday Bondhugula, Abhinav Jangda
Publikováno v:
ACM Transactions on Programming Languages and Systems. 42:1-27
Effective models for fusion of loop nests continue to remain a challenge in both general-purpose and domain-specific language (DSL) compilers. The difficulty often arises from the combinatorial explosion of grouping choices and their interaction with
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9777e4742cd41d57ac1c3ce3528c83e7
https://doi.org/10.1145/3404846
https://doi.org/10.1145/3404846
Publikováno v:
Proceedings of the 31st ACM SIGPLAN International Conference on Compiler Construction.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::26f32b6fee51d3fa8530dc6841567aca
https://doi.org/10.1145/3497776.3517770
https://doi.org/10.1145/3497776.3517770
Publikováno v:
ICS
Loop tiling for locality is an important transformation for general-purpose and domain-specific compilation as it allows programs to exploit the benefits of deep memory hierarchies. Most code generation tools with the infrastructure to perform automa
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9032ce3e2b1bb7d4f04218ff508df658
https://doi.org/10.1145/3447818.3462213
https://doi.org/10.1145/3447818.3462213
Autor:
Andrew Davis, Nicolas Vasilache, Albert Cohen, Jacques A. Pienaar, Mehdi Amini, Oleksandr Zinenko, River Riddle, Uday Bondhugula, Chris Lattner, Tatiana Shpeisman
Publikováno v:
CGO
This work presents MLIR, a novel approach to building reusable and extensible compiler infrastructure. MLIR addresses software fragmentation, compilation for heterogeneous hardware, significantly reducing the cost of building domain specific compiler
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4d569d0d5b34f810d8f76ee692b1d2a8
https://doi.org/10.1109/cgo51591.2021.9370308
https://doi.org/10.1109/cgo51591.2021.9370308
Publikováno v:
CC
Unlike CPUs and GPUs, it is possible to use custom fixed-point data types, specified as a tuple (α, β), on FPGAs. The parameters α and β denote the number of integral and fractional bitwidths respectively. The power and area savings while perform
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::49938b426a658a661de1790115651067
https://doi.org/10.1145/3377555.3377899
https://doi.org/10.1145/3377555.3377899
Publikováno v:
PLDI
State-of-the-art algorithms used in automatic polyhedral transformation for parallelization and locality optimization typically rely on Integer Linear Programming (ILP). This poses a scalability issue when scaling to tens or hundreds of statements, a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::80f7b056f70e8469193f0e4117650d60
https://doi.org/10.1145/3296979.3192401
https://doi.org/10.1145/3296979.3192401
Autor:
Uday Bondhugula, Abhinav Jangda
Publikováno v:
PPOPP
Effective models for fusion of loop nests continue to remain a challenge in both general-purpose and domain-specific language (DSL) compilers. The difficulty often arises from the combinatorial explosion of grouping choices and their interaction with
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::33dcb32a5bf0d5d26ce8200a1fab439d
https://doi.org/10.1145/3200691.3178507
https://doi.org/10.1145/3200691.3178507
Autor:
Uday Bondhugula, Karan Aggarwal
Publikováno v:
ICS
Sparse matrix-vector multiplication (SpMV) operations are commonly used in various scientific and engineering applications. The performance of the SpMV operation often depends on exploiting regularity patterns in the matrix. Various representations a
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::470395fd2179ef1fd64bf98b9bc56747
https://doi.org/10.1145/3330345.3332469
https://doi.org/10.1145/3330345.3332469