{"id":967329,"date":"2023-10-16T02:14:29","date_gmt":"2023-10-16T09:14:29","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/?post_type=msr-project&p=967329"},"modified":"2026-06-24T12:15:52","modified_gmt":"2026-06-24T19:15:52","slug":"domain-specialization","status":"publish","type":"msr-project","link":"https:\/\/www.microsoft.com\/en-us\/research\/project\/domain-specialization\/","title":{"rendered":"Domain Specialization"},"content":{"rendered":"
\n\t
\n\t\t
\n\t\t\t\t\t<\/div>\n\t\t\n\t\t
\n\t\t\t\n\t\t\t
\n\t\t\t\t\n\t\t\t\t
\n\t\t\t\t\t\n\t\t\t\t\t
\n\t\t\t\t\t\t
\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t\t\t<\/span>\n\t\t\t\t\t\t\t\t\tMicrosoft Research India\t\t\t\t\t\t\t\t<\/a>\n\t\t\t\t\t\t\t\n\t\t\t\t\t\t\t\n\n

Domain Specialization<\/h1>\n\n\n\n

Scaling performance beyond Moore’s law<\/p>\n\n\t\t\t\t\t\t<\/div>\n\t\t\t\t\t<\/div>\n\t\t\t\t<\/div>\n\t\t\t<\/div>\n\t\t<\/div>\n\t<\/div>\n<\/section>\n\n\n\n\n\n

Note<\/em><\/strong>: This research project has reached its conclusion. These pages are maintained for reference and archival purposes.<\/em><\/p>\n\n\n\n

Domain\u00a0specialization\u00a0is\u00a0expected\u00a0to\u00a0play\u00a0a\u00a0big\u00a0role\u00a0in\u00a0how\u00a0computer\u00a0systems\u00a0evolve\u00a0in\u00a0future. With\u00a0the\u00a0end\u00a0of\u00a0Moore’s Law, we\u00a0are\u00a0already\u00a0seeing\u00a0CPU,\u00a0GPU\u00a0and domain specific\u00a0hardware\u00a0evolving\u00a0rapidly. The next decade\u00a0is\u00a0therefore expected\u00a0to see\u00a0big\u00a0changes\u00a0in\u00a0how\u00a0we\u00a0develop,\u00a0compile\u00a0and\u00a0run\u00a0software. This project focuses on data systems, a class of systems where, as the data sizes grow, performance scaling is going to be of importance.

First,\u00a0we\u00a0believe\u00a0that domain-specific\u00a0compilers\u00a0will\u00a0play\u00a0a\u00a0crucial\u00a0strategic\u00a0role\u00a0in\u00a0helping\u00a0software\u00a0leverage\u00a0the changing hardware landscape. Such compilers will be multi-layered and will progressively lower computation through multiple intermediate abstractions, performing domain specific optimizations at the higher layers and specializing code to the hardware in lower layers. We\u00a0have\u00a0been\u00a0working\u00a0on\u00a0two\u00a0such\u00a0domain\u00a0specific\u00a0compilers\u00a0in\u00a0the\u00a0data\u00a0domain. Second, new hardware specific algorithms need to be designed to harness the hardware’s capabilities. To this end, we are designing new algorithms that can effectively harness the raw capabilities of a GPU irrespective of its architecture.<\/p>\n\n\n\n

\"diagram\"
The landscape of domain specialization.<\/strong><\/figcaption><\/figure>\n\n\n","protected":false},"excerpt":{"rendered":"

Scaling performance beyond Moore’s law Note: This research project has reached its conclusion. These pages are maintained for reference and archival purposes. Domain\u00a0specialization\u00a0is\u00a0expected\u00a0to\u00a0play\u00a0a\u00a0big\u00a0role\u00a0in\u00a0how\u00a0computer\u00a0systems\u00a0evolve\u00a0in\u00a0future. With\u00a0the\u00a0end\u00a0of\u00a0Moore’s Law, we\u00a0are\u00a0already\u00a0seeing\u00a0CPU,\u00a0GPU\u00a0and domain specific\u00a0hardware\u00a0evolving\u00a0rapidly. The next decade\u00a0is\u00a0therefore expected\u00a0to see\u00a0big\u00a0changes\u00a0in\u00a0how\u00a0we\u00a0develop,\u00a0compile\u00a0and\u00a0run\u00a0software. This project focuses on data systems, a class of systems where, as the data sizes grow, performance scaling is going to be […]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"_classifai_error":"","footnotes":""},"research-area":[13547],"msr-locale":[268875],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-967329","msr-project","type-msr-project","status-publish","hentry","msr-research-area-systems-and-networking","msr-locale-en_us","msr-archive-status-complete"],"msr_project_start":"","related-publications":[976416,980577,980586,1082997],"related-downloads":[],"related-videos":[],"related-groups":[144939],"related-events":[],"related-opportunities":[],"related-posts":[],"related-articles":[],"tab-content":[],"related-researchers":[{"type":"user_nicename","display_name":"Harish Doraiswamy","user_id":41051,"people_section":"Related people","alias":"hdoraiswamy"},{"type":"user_nicename","display_name":"Akash Lal","user_id":30905,"people_section":"Related people","alias":"akashl"},{"type":"user_nicename","display_name":"Sampath Rajendra","user_id":43107,"people_section":"Related people","alias":"srajendra"},{"type":"user_nicename","display_name":"Aseem Rastogi","user_id":36021,"people_section":"Related people","alias":"aseemr"}],"msr_research_lab":[199562],"msr_impact_theme":[],"_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/967329","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-project"}],"version-history":[{"count":16,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/967329\/revisions"}],"predecessor-version":[{"id":1176875,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-project\/967329\/revisions\/1176875"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=967329"}],"wp:term":[{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=967329"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=967329"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=967329"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=967329"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}