Parallel accelerators such as GPUs are notoriously hard to program; exploiting their full performance potential is a job best left for ninja programmers. High-level programming languages coupled with optimizing compilers have been proposed to attempt to address this issue. However, they rely on device-specific heuristics or hard-coded library implementations to achieve good performance resulting in non-portable solutions that need to be re-optimized for every new device. Achieving performance portability is the holy grail of high-performance computing and has so far remained an open problem even for well studied applications like matrix multiplication. We argue that what is needed is a way to describe applications at a high-level without committing to particular implementations. To this end, we developed in a previous paper a functional data-parallel language which allows applications to be expressed in a device neutral way. We use a set of well-defined rewrite rules to automatically transform programs into semantically equivalent devicespecific forms, from which OpenCL code is generated. In this paper, we demonstrate how this approach produces high-performance OpenCL code for GPUs with a wellstudied, well-understood application: matrix multiplication. Starting from a single high-level program, our compiler automatically generate highly optimized and specialized implementations. We group simple rewrite rules into more complex macro-rules, each describing a well-known optimization like tiling and register blocking in a composable way. Using an exploration strategy our compiler automatically generates 50,000 OpenCL kernels, each providing a differently optimized – but provably correct – implementation of matrix multiplication. The automatically generated code offers competitive performance compared to the manually tuned MAGMA library implementations of matrix multiplication on Nvidia and even outperforms AMD’s clBLAS library.<\/p>\n","protected":false},"excerpt":{"rendered":"
Parallel accelerators such as GPUs are notoriously hard to program; exploiting their full performance potential is a job best left for ninja programmers. High-level programming languages coupled with optimizing compilers have been proposed to attempt to address this issue. However, they rely on device-specific heuristics or hard-coded library implementations to achieve good performance resulting in […]<\/p>\n","protected":false},"author":351,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_jetpack_memberships_contains_paid_content":false,"footnotes":"","jetpack_publicize_message":"","jetpack_publicize_feature_enabled":true,"jetpack_social_post_already_shared":true,"jetpack_social_options":{"image_generator_settings":{"template":"highway","default_image_id":0,"font":"","enabled":false},"version":2}},"categories":[11,90,3],"tags":[7,1307,215,955,1782,324,20,379,1766,1793],"class_list":["post-15449","post","type-post","status-publish","format-standard","hentry","category-computer-science","category-opencl","category-paper","tag-ati","tag-ati-radeon-hd-7970","tag-code-generation","tag-compilers","tag-computer-science","tag-matrix-multiplication","tag-nvidia","tag-nvidia-geforce-gtx-480","tag-nvidia-geforce-gtx-titan-black","tag-opencl"],"views":2281,"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/15449","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/users\/351"}],"replies":[{"embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=15449"}],"version-history":[{"count":0,"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/15449\/revisions"}],"wp:attachment":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=15449"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=15449"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=15449"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}