The data revolution is fueled by advances in machine learning, databases, and hardware design. Programmable accelerators are making their way into each of these areas independently. As such, there is a void of solutions that enables hardware acceleration at the intersection of these disjoint fields. This paper sets out to be the initial step towards a unifying solution for in-Database Acceleration of Advanced Analytics (DAnA). Deploying specialized hardware, such as FPGAs, for in-database analytics currently requires hand-designing the hardware and manually routing the data. Instead, DAnA automatically maps a high-level specification of advanced analytics queries to an FPGA accelerator. The accelerator implementation is generated for a User Defined Function (UDF), expressed as a part of an SQL query using a Python-embedded Domain-Specific Language (DSL). To realize an efficient in-database integration, DAnA accelerators contain a novel hardware structure, Striders, that directly interface with the buffer pool of the database. Striders extract, cleanse, and process the training data tuples that are consumed by a multi-threaded FPGA engine that executes the analytics algorithm. We integrate DAnA with PostgreSQL to generate hardware accelerators for a range of real-world and synthetic datasets running diverse ML algorithms. Results show that DAnA-enhanced PostgreSQL provides, on average, 8.3\u00d7 end-to-end speedup for real datasets, with a maximum of 28.2\u00d7. Moreover, DAnA-enhanced PostgreSQL is, on average, 4.0\u00d7 faster than the multi-threaded Apache MADLib running on Greenplum. DAnA provides these benefits while hiding the complexity of hardware design from data scientists and allowing them to express the algorithm in \u224830-60 lines of Python.<\/p>\n","protected":false},"excerpt":{"rendered":"
The data revolution is fueled by advances in machine learning, databases, and hardware design. Programmable accelerators are making their way into each of these areas independently. As such, there is a void of solutions that enables hardware acceleration at the intersection of these disjoint fields. This paper sets out to be the initial step towards […]<\/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":"","msr-author-ordering":null,"msr_publishername":"VLDB Endowment","msr_publisher_other":"","msr_booktitle":"","msr_chapter":"","msr_edition":"","msr_editors":"","msr_how_published":"","msr_isbn":"","msr_issue":"","msr_journal":"","msr_number":"","msr_organization":"","msr_pages_string":"","msr_page_range_start":"1317","msr_page_range_end":"1331","msr_series":"","msr_volume":"","msr_copyright":"","msr_conference_name":"","msr_doi":"","msr_arxiv_id":"","msr_s2_paper_id":"","msr_mag_id":"3121313599","msr_pubmed_id":"","msr_other_authors":"","msr_other_contributors":"","msr_speaker":"","msr_award":"","msr_affiliation":"","msr_institution":"","msr_host":"","msr_version":"","msr_duration":"","msr_original_fields_of_study":null,"msr_release_tracker_id":"","msr_s2_match_type":"","msr_citation_count_updated":"","msr_published_date":"2018-6-30","msr_highlight_text":"","msr_notes":"","msr_longbiography":"","msr_publicationurl":"","msr_external_url":"","msr_secondary_video_url":"","msr_conference_url":"","msr_journal_url":"","msr_s2_pdf_url":"","msr_year":0,"msr_citation_count":0,"msr_influential_citations":0,"msr_reference_count":0,"msr_s2_match_confidence":0,"msr_microsoftintellectualproperty":false,"msr_s2_open_access":false,"msr_s2_author_ids":[],"msr_pub_ids":[],"msr_hide_image_in_river":0,"footnotes":""},"msr-research-highlight":[],"research-area":[13563,13552],"msr-publication-type":[193716],"msr-publisher":[],"msr-focus-area":[],"msr-locale":[268875],"msr-post-option":[],"msr-field-of-study":[246784,246691,252751,256702,246955,251902,251617,246802,252502],"msr-conference":[259156],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-772639","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-data-platform-analytics","msr-research-area-hardware-devices","msr-locale-en_us","msr-field-of-study-analytics","msr-field-of-study-computer-science","msr-field-of-study-field-programmable-gate-array","msr-field-of-study-interface-computing","msr-field-of-study-operating-system","msr-field-of-study-python-programming-language","msr-field-of-study-relational-database-management-system","msr-field-of-study-sql","msr-field-of-study-user-defined-function"],"msr_publishername":"VLDB Endowment","msr_edition":"","msr_affiliation":"","msr_published_date":"2018-6-30","msr_host":"","msr_duration":"","msr_version":"","msr_speaker":"","msr_other_contributors":"","msr_booktitle":"","msr_pages_string":"","msr_chapter":"","msr_isbn":"","msr_journal":"","msr_volume":"","msr_number":"","msr_editors":"","msr_series":"","msr_issue":"","msr_organization":"","msr_how_published":"","msr_notes":"","msr_highlight_text":"","msr_release_tracker_id":"","msr_original_fields_of_study":"","msr_download_urls":"","msr_external_url":"","msr_secondary_video_url":"","msr_longbiography":"","msr_microsoftintellectualproperty":0,"msr_main_download":"","msr_publicationurl":"","msr_doi":"","msr_publication_uploader":[{"type":"url","viewUrl":"false","id":"false","title":"http:\/\/www.vldb.org\/pvldb\/vol11\/p1317-mahajan.pdf","label_id":"243132","label":0},{"type":"url","viewUrl":"false","id":"false","title":"https:\/\/dblp.uni-trier.de\/db\/journals\/corr\/corr1801.html#abs-1801-06027","label_id":"243106","label":0},{"type":"url","viewUrl":"false","id":"false","title":"https:\/\/dl.acm.org\/doi\/10.14778\/3236187.3236188","label_id":"243109","label":0}],"msr_related_uploader":"","msr_citation_count":0,"msr_citation_count_updated":"","msr_s2_paper_id":"","msr_influential_citations":0,"msr_reference_count":0,"msr_arxiv_id":"","msr_s2_author_ids":[],"msr_s2_open_access":false,"msr_s2_pdf_url":null,"msr_attachments":[],"msr-author-ordering":[{"type":"user_nicename","value":"Divya Mahajan","user_id":40195,"rest_url":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=Divya Mahajan"},{"type":"guest","value":"joon-kyung-kim","user_id":772579,"rest_url":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=joon-kyung-kim"},{"type":"guest","value":"jacob-sacks","user_id":772630,"rest_url":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=jacob-sacks"},{"type":"guest","value":"adel-ardalan","user_id":772642,"rest_url":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=adel-ardalan"},{"type":"guest","value":"arun-kumar","user_id":772645,"rest_url":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=arun-kumar"},{"type":"guest","value":"hadi-esmaeilzadeh","user_id":772546,"rest_url":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/microsoft-research\/v1\/researchers?person=hadi-esmaeilzadeh"}],"msr_impact_theme":[],"msr_research_lab":[],"msr_event":[],"msr_group":[],"msr_project":[],"publication":[],"video":[],"msr-tool":[],"msr_publication_type":"inproceedings","related_content":[],"_links":{"self":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/772639","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item"}],"about":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-research-item"}],"version-history":[{"count":1,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/772639\/revisions"}],"predecessor-version":[{"id":772648,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/772639\/revisions\/772648"}],"wp:attachment":[{"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/media?parent=772639"}],"wp:term":[{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=772639"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=772639"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=772639"},{"taxonomy":"msr-publisher","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-publisher?post=772639"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=772639"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=772639"},{"taxonomy":"msr-post-option","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-post-option?post=772639"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=772639"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=772639"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=772639"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=772639"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/cm-edgetun.pages.dev\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=772639"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}