�ݺ�ߣshows by User: gmarkom

�ݺ�ߣshows by User: gmarkom / http://www.slideshare.net/images/logo.gif �ݺ�ߣshows by User: gmarkom / Tue, 01 Mar 2022 09:34:20 GMT �ݺ�ߣShare feed for �ݺ�ߣshows by User: gmarkom Evaluating GPU programming Models for the LUMI Supercomputer /slideshow/evaluating-gpu-programming-models-for-the-lumi-supercomputer/251265083 evaluatinggpuprogrammingmodelsforthelumi-220301093420
It is common in the HPC community that the achieved performance with just CPUs is limited for many computational cases. The EuroHPC pre-exascale and the coming exascale systems are mainly focused on accelerators, and some of the largest upcoming supercomputers such as LUMI and Frontier will be powered by AMD Instinct accelerators. However, these new systems create many challenges for developers who are not familiar with the new ecosystem or with the required programming models that can be used to program for heterogeneous architectures. In this paper, we present some of the more well-known programming models to program for current and future GPU systems. We then measure the performance of each approach using a benchmark and a mini-app, test with various compilers, and tune the codes where necessary. Finally, we compare the performance, where possible, between the NVIDIA Volta (V100), Ampere (A100) GPUs, and the AMD MI100 GPU. Presentation of a paper accepted in Supercomputing Frontiers Asia 2022]]>
It is common in the HPC community that the achieved performance with just CPUs is limited for many computational cases. The EuroHPC pre-exascale and the coming exascale systems are mainly focused on accelerators, and some of the largest upcoming supercomputers such as LUMI and Frontier will be powered by AMD Instinct accelerators. However, these new systems create many challenges for developers who are not familiar with the new ecosystem or with the required programming models that can be used to program for heterogeneous architectures. In this paper, we present some of the more well-known programming models to program for current and future GPU systems. We then measure the performance of each approach using a benchmark and a mini-app, test with various compilers, and tune the codes where necessary. Finally, we compare the performance, where possible, between the NVIDIA Volta (V100), Ampere (A100) GPUs, and the AMD MI100 GPU. Presentation of a paper accepted in Supercomputing Frontiers Asia 2022]]> Tue, 01 Mar 2022 09:34:20 GMT /slideshow/evaluating-gpu-programming-models-for-the-lumi-supercomputer/251265083 gmarkom@slideshare.net(gmarkom) Evaluating GPU programming Models for the LUMI Supercomputer gmarkom It is common in the HPC community that the achieved performance with just CPUs is limited for many computational cases. The EuroHPC pre-exascale and the coming exascale systems are mainly focused on accelerators, and some of the largest upcoming supercomputers such as LUMI and Frontier will be powered by AMD Instinct accelerators. However, these new systems create many challenges for developers who are not familiar with the new ecosystem or with the required programming models that can be used to program for heterogeneous architectures. In this paper, we present some of the more well-known programming models to program for current and future GPU systems. We then measure the performance of each approach using a benchmark and a mini-app, test with various compilers, and tune the codes where necessary. Finally, we compare the performance, where possible, between the NVIDIA Volta (V100), Ampere (A100) GPUs, and the AMD MI100 GPU. Presentation of a paper accepted in Supercomputing Frontiers Asia 2022 <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/evaluatinggpuprogrammingmodelsforthelumi-220301093420-thumbnail.jpg?width=120&height=120&fit=bounds" /> It is common in the HPC community that the achieved performance with just CPUs is limited for many computational cases. The EuroHPC pre-exascale and the coming exascale systems are mainly focused on accelerators, and some of the largest upcoming supercomputers such as LUMI and Frontier will be powered by AMD Instinct accelerators. However, these new systems create many challenges for developers who are not familiar with the new ecosystem or with the required programming models that can be used to program for heterogeneous architectures. In this paper, we present some of the more well-known programming models to program for current and future GPU systems. We then measure the performance of each approach using a benchmark and a mini-app, test with various compilers, and tune the codes where necessary. Finally, we compare the performance, where possible, between the NVIDIA Volta (V100), Ampere (A100) GPUs, and the AMD MI100 GPU. Presentation of a paper accepted in Supercomputing Frontiers Asia 2022

Evaluating GPU programming Models for the LUMI Supercomputer from George Markomanolis

]]> 301 0 https://cdn.slidesharecdn.com/ss_thumbnails/evaluatinggpuprogrammingmodelsforthelumi-220301093420-thumbnail.jpg?width=120&height=120&fit=bounds presentation 000000 http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Utilizing AMD GPUs: Tuning, programming models, and roadmap /slideshow/utilizing-amd-gpus-tuning-programming-models-and-roadmap/251157378 fosdem22hpcamdgpusmarkomanolis-220211181714
A presentation at FOSDEM 2022 about AMD GPUs, tuning, programming models and software roadmap. This is continuation from the previous talk (FOSDEM 2021)]]>
A presentation at FOSDEM 2022 about AMD GPUs, tuning, programming models and software roadmap. This is continuation from the previous talk (FOSDEM 2021)]]> Fri, 11 Feb 2022 18:17:13 GMT /slideshow/utilizing-amd-gpus-tuning-programming-models-and-roadmap/251157378 gmarkom@slideshare.net(gmarkom) Utilizing AMD GPUs: Tuning, programming models, and roadmap gmarkom A presentation at FOSDEM 2022 about AMD GPUs, tuning, programming models and software roadmap. This is continuation from the previous talk (FOSDEM 2021) <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/fosdem22hpcamdgpusmarkomanolis-220211181714-thumbnail.jpg?width=120&height=120&fit=bounds" /> A presentation at FOSDEM 2022 about AMD GPUs, tuning, programming models and software roadmap. This is continuation from the previous talk (FOSDEM 2021)

Utilizing AMD GPUs: Tuning, programming models, and roadmap from George Markomanolis

]]> 240 0 https://cdn.slidesharecdn.com/ss_thumbnails/fosdem22hpcamdgpusmarkomanolis-220211181714-thumbnail.jpg?width=120&height=120&fit=bounds presentation 000000 http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Exploring the Programming Models for the LUMI Supercomputer /slideshow/exploring-the-programming-models-for-the-lumi-supercomputer/250340958 hpc-wsmarkomanolis-210930101533
A presentation that I gave during the ECMWF HPC workshop in Meteorology about the programming models that could be utilized on LUMI supercomputer]]>
A presentation that I gave during the ECMWF HPC workshop in Meteorology about the programming models that could be utilized on LUMI supercomputer]]> Thu, 30 Sep 2021 10:15:33 GMT /slideshow/exploring-the-programming-models-for-the-lumi-supercomputer/250340958 gmarkom@slideshare.net(gmarkom) Exploring the Programming Models for the LUMI Supercomputer gmarkom A presentation that I gave during the ECMWF HPC workshop in Meteorology about the programming models that could be utilized on LUMI supercomputer <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/hpc-wsmarkomanolis-210930101533-thumbnail.jpg?width=120&height=120&fit=bounds" /> A presentation that I gave during the ECMWF HPC workshop in Meteorology about the programming models that could be utilized on LUMI supercomputer

Exploring the Programming Models for the LUMI Supercomputer from George Markomanolis

]]> 107 0 https://cdn.slidesharecdn.com/ss_thumbnails/hpc-wsmarkomanolis-210930101533-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Getting started with AMD GPUs /slideshow/getting-started-with-amd-gpus/242379255 gettingstartedwithamdgpus-210207121625
A short introduction to AMD ecosystem, architecture of Mi100, HIP, how to port applications from CUDA to HIP and benchmarking on NVIDIA GPUs.]]>
A short introduction to AMD ecosystem, architecture of Mi100, HIP, how to port applications from CUDA to HIP and benchmarking on NVIDIA GPUs.]]> Sun, 07 Feb 2021 12:16:25 GMT /slideshow/getting-started-with-amd-gpus/242379255 gmarkom@slideshare.net(gmarkom) Getting started with AMD GPUs gmarkom A short introduction to AMD ecosystem, architecture of Mi100, HIP, how to port applications from CUDA to HIP and benchmarking on NVIDIA GPUs. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/gettingstartedwithamdgpus-210207121625-thumbnail.jpg?width=120&height=120&fit=bounds" /> A short introduction to AMD ecosystem, architecture of Mi100, HIP, how to port applications from CUDA to HIP and benchmarking on NVIDIA GPUs.

Getting started with AMD GPUs from George Markomanolis

]]> 173 0 https://cdn.slidesharecdn.com/ss_thumbnails/gettingstartedwithamdgpus-210207121625-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Analyzing ECP Proxy Apps with the Profiling Tool Score-P /slideshow/analyzing-ecp-proxy-apps-with-the-profiling-tool-scorep/227294328 ecptutorialscorep-200207171348
Using ECP-Proxy with Score-P profiling tool on Summit]]>
Using ECP-Proxy with Score-P profiling tool on Summit]]> Fri, 07 Feb 2020 17:13:48 GMT /slideshow/analyzing-ecp-proxy-apps-with-the-profiling-tool-scorep/227294328 gmarkom@slideshare.net(gmarkom) Analyzing ECP Proxy Apps with the Profiling Tool Score-P gmarkom Using ECP-Proxy with Score-P profiling tool on Summit <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/ecptutorialscorep-200207171348-thumbnail.jpg?width=120&height=120&fit=bounds" /> Using ECP-Proxy with Score-P profiling tool on Summit

Analyzing ECP Proxy Apps with the Profiling Tool Score-P from George Markomanolis

]]> 232 0 https://cdn.slidesharecdn.com/ss_thumbnails/ecptutorialscorep-200207171348-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Introduction to Extrae/Paraver, part I /slideshow/introduction-to-extraeparaver-part-i/169011917 introductiontoextraeparaverparti-190904141115
How to use Extrae and Paraver on Summit Supercomputer]]>
How to use Extrae and Paraver on Summit Supercomputer]]> Wed, 04 Sep 2019 14:11:15 GMT /slideshow/introduction-to-extraeparaver-part-i/169011917 gmarkom@slideshare.net(gmarkom) Introduction to Extrae/Paraver, part I gmarkom How to use Extrae and Paraver on Summit Supercomputer <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/introductiontoextraeparaverparti-190904141115-thumbnail.jpg?width=120&height=120&fit=bounds" /> How to use Extrae and Paraver on Summit Supercomputer

Introduction to Extrae/Paraver, part I from George Markomanolis

]]> 476 0 https://cdn.slidesharecdn.com/ss_thumbnails/introductiontoextraeparaverparti-190904141115-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Performance Analysis with Scalasca, part II /slideshow/performance-analysis-with-scalasca-part-ii/169011311 performanceanalysiswithscalascapartii-190904140905
How to use Scalasca on Summit supercomputer for performance analysis with real applications, part II]]>
How to use Scalasca on Summit supercomputer for performance analysis with real applications, part II]]> Wed, 04 Sep 2019 14:09:05 GMT /slideshow/performance-analysis-with-scalasca-part-ii/169011311 gmarkom@slideshare.net(gmarkom) Performance Analysis with Scalasca, part II gmarkom How to use Scalasca on Summit supercomputer for performance analysis with real applications, part II <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/performanceanalysiswithscalascapartii-190904140905-thumbnail.jpg?width=120&height=120&fit=bounds" /> How to use Scalasca on Summit supercomputer for performance analysis with real applications, part II

Performance Analysis with Scalasca, part II from George Markomanolis

]]> 85 0 https://cdn.slidesharecdn.com/ss_thumbnails/performanceanalysiswithscalascapartii-190904140905-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Performance Analysis with Scalasca on Summit Supercomputer part I /slideshow/performance-analysis-with-scalasca-on-summit-supercomputer-part-i/169010672 performanceanalysiswithscalascaparti-190904140648
Performance Analysis with Scalasca on Summit Supercomputer, part I]]>
Performance Analysis with Scalasca on Summit Supercomputer, part I]]> Wed, 04 Sep 2019 14:06:48 GMT /slideshow/performance-analysis-with-scalasca-on-summit-supercomputer-part-i/169010672 gmarkom@slideshare.net(gmarkom) Performance Analysis with Scalasca on Summit Supercomputer part I gmarkom Performance Analysis with Scalasca on Summit Supercomputer, part I <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/performanceanalysiswithscalascaparti-190904140648-thumbnail.jpg?width=120&height=120&fit=bounds" /> Performance Analysis with Scalasca on Summit Supercomputer, part I

Performance Analysis with Scalasca on Summit Supercomputer part I from George Markomanolis

]]> 106 0 https://cdn.slidesharecdn.com/ss_thumbnails/performanceanalysiswithscalascaparti-190904140648-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Performance Analysis with TAU on Summit Supercomputer, part II /slideshow/performance-analysis-with-tau-on-summit-supercomputer-part-ii/169008956 performanceanalysiswithtaupartii-190904140049
The second part of how to use TAU profiling tool on Summit Supercomputer with real examples]]>
The second part of how to use TAU profiling tool on Summit Supercomputer with real examples]]> Wed, 04 Sep 2019 14:00:49 GMT /slideshow/performance-analysis-with-tau-on-summit-supercomputer-part-ii/169008956 gmarkom@slideshare.net(gmarkom) Performance Analysis with TAU on Summit Supercomputer, part II gmarkom The second part of how to use TAU profiling tool on Summit Supercomputer with real examples <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/performanceanalysiswithtaupartii-190904140049-thumbnail.jpg?width=120&height=120&fit=bounds" /> The second part of how to use TAU profiling tool on Summit Supercomputer with real examples

Performance Analysis with TAU on Summit Supercomputer, part II from George Markomanolis

]]> 75 0 https://cdn.slidesharecdn.com/ss_thumbnails/performanceanalysiswithtaupartii-190904140049-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 How to use TAU for Performance Analysis on Summit Supercomputer /slideshow/how-to-use-tau-for-performance-analysis-on-summit-supercomputer/169008198 howtousetaudaysummit1-190904135823
The first part of how to use TAU profiling tool on Summit Supercomputer with real examples]]>
The first part of how to use TAU profiling tool on Summit Supercomputer with real examples]]> Wed, 04 Sep 2019 13:58:23 GMT /slideshow/how-to-use-tau-for-performance-analysis-on-summit-supercomputer/169008198 gmarkom@slideshare.net(gmarkom) How to use TAU for Performance Analysis on Summit Supercomputer gmarkom The first part of how to use TAU profiling tool on Summit Supercomputer with real examples <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/howtousetaudaysummit1-190904135823-thumbnail.jpg?width=120&height=120&fit=bounds" /> The first part of how to use TAU profiling tool on Summit Supercomputer with real examples

How to use TAU for Performance Analysis on Summit Supercomputer from George Markomanolis

]]> 277 0 https://cdn.slidesharecdn.com/ss_thumbnails/howtousetaudaysummit1-190904135823-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Introducing IO-500 benchmark /slideshow/introducing-io500-benchmark/87910928 io500talkibmspectrumscalenov2017-180213070327
In this presentation during IBM Spectrum Scale user group meeting, I introduced the IO-500 benchmark. I discussed why it is necessary for the future HPC storage procurement and how to use it.]]>
In this presentation during IBM Spectrum Scale user group meeting, I introduced the IO-500 benchmark. I discussed why it is necessary for the future HPC storage procurement and how to use it.]]> Tue, 13 Feb 2018 07:03:27 GMT /slideshow/introducing-io500-benchmark/87910928 gmarkom@slideshare.net(gmarkom) Introducing IO-500 benchmark gmarkom In this presentation during IBM Spectrum Scale user group meeting, I introduced the IO-500 benchmark. I discussed why it is necessary for the future HPC storage procurement and how to use it. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/io500talkibmspectrumscalenov2017-180213070327-thumbnail.jpg?width=120&height=120&fit=bounds" /> In this presentation during IBM Spectrum Scale user group meeting, I introduced the IO-500 benchmark. I discussed why it is necessary for the future HPC storage procurement and how to use it.

Introducing IO-500 benchmark from George Markomanolis

]]> 2171 0 https://cdn.slidesharecdn.com/ss_thumbnails/io500talkibmspectrumscalenov2017-180213070327-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Experience using the IO-500 /slideshow/experience-using-the-io500/87910807 sc-bof-markomanolis-180213070058
In this presentation during SC17 IO500 BOF, I did discuss about my experience using the IO-500 benchmark, how to use it and the IO analysis of the benchmarks]]>
In this presentation during SC17 IO500 BOF, I did discuss about my experience using the IO-500 benchmark, how to use it and the IO analysis of the benchmarks]]> Tue, 13 Feb 2018 07:00:58 GMT /slideshow/experience-using-the-io500/87910807 gmarkom@slideshare.net(gmarkom) Experience using the IO-500 gmarkom In this presentation during SC17 IO500 BOF, I did discuss about my experience using the IO-500 benchmark, how to use it and the IO analysis of the benchmarks <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/sc-bof-markomanolis-180213070058-thumbnail.jpg?width=120&height=120&fit=bounds" /> In this presentation during SC17 IO500 BOF, I did discuss about my experience using the IO-500 benchmark, how to use it and the IO analysis of the benchmarks

Experience using the IO-500 from George Markomanolis

]]> 411 0 https://cdn.slidesharecdn.com/ss_thumbnails/sc-bof-markomanolis-180213070058-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Harshad - Handle Darshan Data /slideshow/harshad-handle-darshan-data/87909320 harshadpresentation-180213063142
In this talk, a tool that handles Darshan data, called HarshaD is presented. The tool visualizes Darshan data without the user being aware of the procedure. Moreover, you can compare two Darshan output to understand how your modifications impact on IO. ]]>
In this talk, a tool that handles Darshan data, called HarshaD is presented. The tool visualizes Darshan data without the user being aware of the procedure. Moreover, you can compare two Darshan output to understand how your modifications impact on IO. ]]> Tue, 13 Feb 2018 06:31:42 GMT /slideshow/harshad-handle-darshan-data/87909320 gmarkom@slideshare.net(gmarkom) Harshad - Handle Darshan Data gmarkom In this talk, a tool that handles Darshan data, called HarshaD is presented. The tool visualizes Darshan data without the user being aware of the procedure. Moreover, you can compare two Darshan output to understand how your modifications impact on IO. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/harshadpresentation-180213063142-thumbnail.jpg?width=120&height=120&fit=bounds" /> In this talk, a tool that handles Darshan data, called HarshaD is presented. The tool visualizes Darshan data without the user being aware of the procedure. Moreover, you can compare two Darshan output to understand how your modifications impact on IO.

Harshad - Handle Darshan Data from George Markomanolis

]]> 78 0 https://cdn.slidesharecdn.com/ss_thumbnails/harshadpresentation-180213063142-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Lustre Best Practices /slideshow/lustre-best-practices/87909135 lustrepracticesv2-180213062649
In this presentation, you will learn how to use Lustre filesystem more efficient and the best practices. Moreover, Darshan tool will be used to analyze the IO.]]>
In this presentation, you will learn how to use Lustre filesystem more efficient and the best practices. Moreover, Darshan tool will be used to analyze the IO.]]> Tue, 13 Feb 2018 06:26:49 GMT /slideshow/lustre-best-practices/87909135 gmarkom@slideshare.net(gmarkom) Lustre Best Practices gmarkom In this presentation, you will learn how to use Lustre filesystem more efficient and the best practices. Moreover, Darshan tool will be used to analyze the IO. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/lustrepracticesv2-180213062649-thumbnail.jpg?width=120&height=120&fit=bounds" /> In this presentation, you will learn how to use Lustre filesystem more efficient and the best practices. Moreover, Darshan tool will be used to analyze the IO.

Lustre Best Practices from George Markomanolis

]]> 623 0 https://cdn.slidesharecdn.com/ss_thumbnails/lustrepracticesv2-180213062649-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Burst Buffer: From Alpha to Omega /slideshow/burst-buffer-from-alpha-to-omega/71323096 burstbuffertraining-170124100806
This is the material of a Burst Buffer training that was presented for the early users program. It covers introduction about parallel I/O, Lustre, Darshan tool, Burst Buffer, and optimization parameters for MPI I/O. Full video: https://youtu.be/8zLcZmiTweg]]>
This is the material of a Burst Buffer training that was presented for the early users program. It covers introduction about parallel I/O, Lustre, Darshan tool, Burst Buffer, and optimization parameters for MPI I/O. Full video: https://youtu.be/8zLcZmiTweg]]> Tue, 24 Jan 2017 10:08:06 GMT /slideshow/burst-buffer-from-alpha-to-omega/71323096 gmarkom@slideshare.net(gmarkom) Burst Buffer: From Alpha to Omega gmarkom This is the material of a Burst Buffer training that was presented for the early users program. It covers introduction about parallel I/O, Lustre, Darshan tool, Burst Buffer, and optimization parameters for MPI I/O. Full video: https://youtu.be/8zLcZmiTweg <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/burstbuffertraining-170124100806-thumbnail.jpg?width=120&height=120&fit=bounds" /> This is the material of a Burst Buffer training that was presented for the early users program. It covers introduction about parallel I/O, Lustre, Darshan tool, Burst Buffer, and optimization parameters for MPI I/O. Full video: https://youtu.be/8zLcZmiTweg

Burst Buffer: From Alpha to Omega from George Markomanolis

]]> 708 0 https://cdn.slidesharecdn.com/ss_thumbnails/burstbuffertraining-170124100806-thumbnail.jpg?width=120&height=120&fit=bounds presentation Black http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Optimizing an Earth Science Atmospheric Application with the OmpSs Programming Model /slideshow/optimizing-an-earth-science-atmospheric-application-with-the-ompss-programming-model/63405405 13670-optimizing-earth-science-atmosphere-application-ompss-programming-model-160624075344
Using OmpSs programming model to optimise an Earth Science application based on taskifying computation and overlap computation with communication.]]>
Using OmpSs programming model to optimise an Earth Science application based on taskifying computation and overlap computation with communication.]]> Fri, 24 Jun 2016 07:53:44 GMT /slideshow/optimizing-an-earth-science-atmospheric-application-with-the-ompss-programming-model/63405405 gmarkom@slideshare.net(gmarkom) Optimizing an Earth Science Atmospheric Application with the OmpSs Programming Model gmarkom Using OmpSs programming model to optimise an Earth Science application based on taskifying computation and overlap computation with communication. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/13670-optimizing-earth-science-atmosphere-application-ompss-programming-model-160624075344-thumbnail.jpg?width=120&height=120&fit=bounds" /> Using OmpSs programming model to optimise an Earth Science application based on taskifying computation and overlap computation with communication.

Optimizing an Earth Science Atmospheric Application with the OmpSs Programming Model from George Markomanolis

]]> 398 0 https://cdn.slidesharecdn.com/ss_thumbnails/13670-optimizing-earth-science-atmosphere-application-ompss-programming-model-160624075344-thumbnail.jpg?width=120&height=120&fit=bounds presentation 000000 http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 markomanolis_phd_defense /slideshow/markomanolisphddefense/63404966 df11c625-b0f4-4ac8-99a2-983e60de374a-160624073930
]]>
]]> Fri, 24 Jun 2016 07:39:30 GMT /slideshow/markomanolisphddefense/63404966 gmarkom@slideshare.net(gmarkom) markomanolis_phd_defense gmarkom <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/df11c625-b0f4-4ac8-99a2-983e60de374a-160624073930-thumbnail.jpg?width=120&height=120&fit=bounds" />

markomanolis_phd_defense from George Markomanolis

]]> 176 0 https://cdn.slidesharecdn.com/ss_thumbnails/df11c625-b0f4-4ac8-99a2-983e60de374a-160624073930-thumbnail.jpg?width=120&height=120&fit=bounds presentation 000000 http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Porting an MPI application to hybrid MPI+OpenMP with Reveal tool on Shaheen II /gmarkom/porting-an-mpi-application-to-hybrid-mpiopenmp-with-reveal-tool-on-shaheen-ii reveal-160624072822
This tutorial guides you to port an MPI application to MPI+OpenMP with the help of Reveal tool provided by Cray on Shaheen II supercomputer]]>
This tutorial guides you to port an MPI application to MPI+OpenMP with the help of Reveal tool provided by Cray on Shaheen II supercomputer]]> Fri, 24 Jun 2016 07:28:22 GMT /gmarkom/porting-an-mpi-application-to-hybrid-mpiopenmp-with-reveal-tool-on-shaheen-ii gmarkom@slideshare.net(gmarkom) Porting an MPI application to hybrid MPI+OpenMP with Reveal tool on Shaheen II gmarkom This tutorial guides you to port an MPI application to MPI+OpenMP with the help of Reveal tool provided by Cray on Shaheen II supercomputer <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/reveal-160624072822-thumbnail.jpg?width=120&height=120&fit=bounds" /> This tutorial guides you to port an MPI application to MPI+OpenMP with the help of Reveal tool provided by Cray on Shaheen II supercomputer

Porting an MPI application to hybrid MPI+OpenMP with Reveal tool on Shaheen II from George Markomanolis

]]> 518 1 https://cdn.slidesharecdn.com/ss_thumbnails/reveal-160624072822-thumbnail.jpg?width=120&height=120&fit=bounds presentation 000000 http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 Introduction to Performance Analysis tools on Shaheen II /slideshow/introduction-to-performance-analysis-tools-on-shaheen-ii/61013053 performanceworkshop-160417162950
This workshop is a hands-on using Perftools from Cray with NAS Benchmarks step by step on Shaheen II. I present CrayPat, Apprentice2, and Reveal tools. There is a short introduction to Extrae/Paraver from Barcelona Supercomputing Centre.]]>
This workshop is a hands-on using Perftools from Cray with NAS Benchmarks step by step on Shaheen II. I present CrayPat, Apprentice2, and Reveal tools. There is a short introduction to Extrae/Paraver from Barcelona Supercomputing Centre.]]> Sun, 17 Apr 2016 16:29:50 GMT /slideshow/introduction-to-performance-analysis-tools-on-shaheen-ii/61013053 gmarkom@slideshare.net(gmarkom) Introduction to Performance Analysis tools on Shaheen II gmarkom This workshop is a hands-on using Perftools from Cray with NAS Benchmarks step by step on Shaheen II. I present CrayPat, Apprentice2, and Reveal tools. There is a short introduction to Extrae/Paraver from Barcelona Supercomputing Centre. <img style="border:1px solid #C3E6D8;float:right;" alt="" src="https://cdn.slidesharecdn.com/ss_thumbnails/performanceworkshop-160417162950-thumbnail.jpg?width=120&height=120&fit=bounds" /> This workshop is a hands-on using Perftools from Cray with NAS Benchmarks step by step on Shaheen II. I present CrayPat, Apprentice2, and Reveal tools. There is a short introduction to Extrae/Paraver from Barcelona Supercomputing Centre.

Introduction to Performance Analysis tools on Shaheen II from George Markomanolis

]]> 476 0 https://cdn.slidesharecdn.com/ss_thumbnails/performanceworkshop-160417162950-thumbnail.jpg?width=120&height=120&fit=bounds presentation 000000 http://activitystrea.ms/schema/1.0/post

http://activitystrea.ms/schema/1.0/posted

0 https://cdn.slidesharecdn.com/profile-photo-gmarkom-48x48.jpg?cb=1666010000 www.markomanolis.com https://cdn.slidesharecdn.com/ss_thumbnails/evaluatinggpuprogrammingmodelsforthelumi-220301093420-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/evaluating-gpu-programming-models-for-the-lumi-supercomputer/251265083 Evaluating GPU program... https://cdn.slidesharecdn.com/ss_thumbnails/fosdem22hpcamdgpusmarkomanolis-220211181714-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/utilizing-amd-gpus-tuning-programming-models-and-roadmap/251157378 Utilizing AMD GPUs: Tu... https://cdn.slidesharecdn.com/ss_thumbnails/hpc-wsmarkomanolis-210930101533-thumbnail.jpg?width=320&height=320&fit=bounds slideshow/exploring-the-programming-models-for-the-lumi-supercomputer/250340958 Exploring the Programm...