Lossless data compression is a promising software approach for reducing the bandwidth requirements of scientific applications on accelerator clusters without introducing approximation errors. Suitable compressors must be able to effectively compact floating-point data while saturating the system interconnect to avoid introducing unnecessary latencies. We present ndzip-gpu, a novel, highly-efficient GPU parallelization scheme for the block compressor ndzip, which has recently set a new milestone in CPU floating-point compression speeds. Through the combination of intra-block parallelism and efficient memory access patterns, ndzip-gpu achieves high resource utilization in decorrelating multi-dimensional data via the Integer Lorenzo Transform. We further introduce a novel, efficient warp-cooperative primitive for vertical bit packing, providing a high-throughput data reduction and expansion step. Using a representative set of scientific data, we compare the performance of ndzip-gpu against five other, existing GPU compressors. While observing that effectiveness of any compressor strongly depends on characteristics of the dataset, we demonstrate that ndzip-gpu offers the best average compression ratio for the examined data. On Nvidia Turing, Volta and Ampere hardware, it achieves the highest single-precision throughput by a significant margin while maintaining a favorable trade-off between data reduction and throughput in the double-precision case.<\/p>\n","protected":false},"excerpt":{"rendered":"
Lossless data compression is a promising software approach for reducing the bandwidth requirements of scientific applications on accelerator clusters without introducing approximation errors. Suitable compressors must be able to effectively compact floating-point data while saturating the system interconnect to avoid introducing unnecessary latencies. We present ndzip-gpu, a novel, highly-efficient GPU parallelization scheme for the block […]<\/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":[11,89,3],"tags":[832,1782,14,20,2029,2082,176,1845,1963],"class_list":["post-25401","post","type-post","status-publish","format-standard","hentry","category-computer-science","category-nvidia-cuda","category-paper","tag-compression","tag-computer-science","tag-cuda","tag-nvidia","tag-nvidia-geforce-rtx-2070","tag-nvidia-geforce-rtx-3090","tag-package","tag-sycl","tag-tesla-v100"],"views":2137,"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/25401","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=25401"}],"version-history":[{"count":0,"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/25401\/revisions"}],"wp:attachment":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=25401"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=25401"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=25401"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}