OpenACC provides a high-productivity API for programming GPUs and similar accelerator devices. One of the last steps in tuning OpenACC programs is selecting values for the num_gangs and vector length clauses, which control how a parallel workload is distributed to an accelerator’s processing units. In this paper, we present OptACC, an autotuner that can assist the programmer in selecting high-quality values for these parameters, and we evaluate the effectiveness of two direct search methods in finding solutions. We assess the quality of the the num_gangs and vector_length values found by our autotuner by comparing them to the values found by a bounded exhaustive search; we also compare the kernel execution times to those of the untuned kernel. On a suite of 36 OpenACC kernels, one or both of our autotuner’s direct search methods identified values within the top 5% for 29 of the kernels, within the top 10% for five kernels, and within the top 25% for the remaining two. Eleven of the kernels achieved a speedup greater than 2x over the compiler’s defaults, and the autotuner required only 7-11 runs of the target program, on average.<\/p>\n","protected":false},"excerpt":{"rendered":"
OpenACC provides a high-productivity API for programming GPUs and similar accelerator devices. One of the last steps in tuning OpenACC programs is selecting values for the num_gangs and vector length clauses, which control how a parallel workload is distributed to an accelerator’s processing units. In this paper, we present OptACC, an autotuner that can assist […]<\/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":[11,3],"tags":[1782,242,20,1321,176,67,513,1390],"class_list":["post-14244","post","type-post","status-publish","format-standard","hentry","category-computer-science","category-paper","tag-computer-science","tag-mpi","tag-nvidia","tag-openacc","tag-package","tag-performance","tag-python","tag-tesla-k20"],"views":2021,"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/14244","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=14244"}],"version-history":[{"count":0,"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/14244\/revisions"}],"wp:attachment":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=14244"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=14244"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=14244"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}