NVIDIA Grace–Blackwell systems make CPU–GPU memory increasingly unified at the programming level, but unified addressability does not make the memory system uniform. A CUDA managed allocation on GB200 may be served from GPU-local HBM, accessed through host\/system memory, demand-migrated, prefetched, reused after GPU access, or evicted and reloaded under capacity pressure. The problem is that these states share a programming interface while exercising different hardware paths and runtime mechanisms, making a single “Unified Memory bandwidth'' number misleading. This paper presents a placement-controlled microbenchmark study of CUDA Unified Memory on NVIDIA GB200, using GH200 as a Grace–Hopper baseline and GB10\/DGX Spark as a validation platform. Our methodology separates local HBM access, host\/system-memory access, explicit movement, managed first touch, prefetch, reuse, access-pattern sensitivity, oversubscription, and CPU–GPU handoff, then summarizes the observations with a measurement-calibrated model of compute, access, migration, eviction, synchronization, and handoff costs. On GB200, a 1 GB STREAM-style triad reaches 3963 GB\/s from local HBM but 304 GB\/s through host-mapped CPU\/system memory; for a 256 MB streaming kernel, cold CPU-initialized managed memory reaches 14.1 GB\/s, while managed prefetch and reuse reach 4606 GB\/s and 4504 GB\/s. Below the capacity boundary, prefetched and reused managed memory remain above 4.6 TB\/s, but at 125% of CUDA-visible memory they fall to 968 GB\/s and 1214 GB\/s, showing that Grace–Blackwell unified memory must be understood through placement, access history, locality, reuse, and capacity pressure.<\/p>\n","protected":false},"excerpt":{"rendered":"
NVIDIA Grace–Blackwell systems make CPU–GPU memory increasingly unified at the programming level, but unified addressability does not make the memory system uniform. A CUDA managed allocation on GB200 may be served from GPU-local HBM, accessed through host\/system memory, demand-migrated, prefetched, reused after GPU access, or evicted and reloaded under capacity pressure. The problem is that […]<\/p>\n","protected":false},"author":351,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"_jetpack_newsletter_access":"","_jetpack_dont_email_post_to_subs":false,"_jetpack_newsletter_tier_id":0,"_jetpack_memberships_contains_paywalled_content":false,"_jetpack_feature_clip_id":0,"_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},"jetpack_post_was_ever_published":false},"categories":[11,89,3],"tags":[451,1782,14,884,20,2195,2201,2151,546],"class_list":["post-31407","post","type-post","status-publish","format-standard","hentry","category-computer-science","category-nvidia-cuda","category-paper","tag-benchmarking","tag-computer-science","tag-cuda","tag-memory","tag-nvidia","tag-nvidia-gb10","tag-nvidia-gb200","tag-nvidia-gh200","tag-prefetch"],"views":469,"jetpack_publicize_connections":[],"jetpack_sharing_enabled":true,"jetpack_featured_media_url":"","_links":{"self":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/31407","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=31407"}],"version-history":[{"count":0,"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/31407\/revisions"}],"wp:attachment":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=31407"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=31407"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=31407"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}