Single Instruction, Multiple Data (SIMD) technology enhances performance through parallel data processing on CPUs. SIMD platforms are widely adopted across domains ranging from high-performance computing to AI inference. As modern AI workloads increasingly rely on Python-based kernel frameworks to maintain usability and benefit from automatic tuning, Triton has emerged as a representative solution. However, Triton\u2019s autotuning mechanism, designed primarily for NVIDIA GPUs, fails to effectively exploit the architectural features of SIMD CPUs, creating a significant performance gap on these platforms. To address this problem, we introduce a human\u2013machine collaborative design tailored for Triton kernel tuning on SIMD platforms. This design improves both development efficiency and performance by capturing high-level SIMD optimization intent from human users and integrating it seamlessly into machine framework tuning. Based on this collaborative design, we develop a tuning framework composed of a front-end for user intent recognition and a back-end for user-guided, SIMD-aware tuning. Experiments on x86 and RISC-V platforms show an average performance improvement of 31.7% over native Triton tuning, with tuning cost reduced by up to 75.0%.<\/p>\n","protected":false},"excerpt":{"rendered":"
Single Instruction, Multiple Data (SIMD) technology enhances performance through parallel data processing on CPUs. SIMD platforms are widely adopted across domains ranging from high-performance computing to AI inference. As modern AI workloads increasingly rely on Python-based kernel frameworks to maintain usability and benefit from automatic tuning, Triton has emerged as a representative solution. However, Triton\u2019s […]<\/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":[1856,1782,613,2182],"class_list":["post-30762","post","type-post","status-publish","format-standard","hentry","category-computer-science","category-paper","tag-auto-tuning","tag-computer-science","tag-evolutionary-computations","tag-triton"],"views":316,"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/30762","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=30762"}],"version-history":[{"count":1,"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/30762\/revisions"}],"predecessor-version":[{"id":30765,"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/30762\/revisions\/30765"}],"wp:attachment":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=30762"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=30762"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=30762"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}