Writing mixed-precision kernels allows to achieve higher throughput together with outputs whose precision remain within given limits. The recent introduction of native half-precision arithmetic capabilities in several GPUs, such as NVIDIA P100 and AMD Vega 10, contributes to make precision-tuning even more relevant as of late. However, it is not trivial to manually find which variables are to be represented as half-precision instead of single- or double-precision. Although the use of half-precision arithmetic can speed up kernel execution considerably, it can also result in providing non-usable kernel outputs, whenever the wrong variables are declared using the half-precision data-type. In this paper we present an automatic approach for precision tuning. Given an OpenCL kernel with a set of inputs declared by a user (i.e., the person responsible for programming and\/or tuning the kernel), our approach is capable of deriving the mixed-precision versions of the kernel that are better improve upon the original with respect to a given metric (e.g., time-to-solution, energy-to-solution). We allow the user to declare and\/or select a metric to measure and to filter solutions based on the quality of the output. We implement a proof-of-concept of our approach using an aspect-oriented programming language called LARA. It is capable of generating mixed-precision kernels that result in considerably higher performance when compared with the original single-precision floating-point versions, while generating outputs that can be acceptable in some scenarios.<\/p>\n","protected":false},"excerpt":{"rendered":"
Writing mixed-precision kernels allows to achieve higher throughput together with outputs whose precision remain within given limits. The recent introduction of native half-precision arithmetic capabilities in several GPUs, such as NVIDIA P100 and AMD Vega 10, contributes to make precision-tuning even more relevant as of late. However, it is not trivial to manually find which […]<\/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":[2005,7,215,1782,625,20,1793,176],"class_list":["post-18270","post","type-post","status-publish","format-standard","hentry","category-computer-science","category-opencl","category-paper","tag-amd-vega-10-xt","tag-ati","tag-code-generation","tag-computer-science","tag-mixed-precision","tag-nvidia","tag-opencl","tag-package"],"views":2249,"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/18270","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=18270"}],"version-history":[{"count":0,"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/18270\/revisions"}],"wp:attachment":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=18270"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=18270"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=18270"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}