When vectorizing programs for modern processors with SIMD extensions, IF-statements pose a challenge: existing vectorization approaches often introduce redundant computations or they resort to inefficient masked instructions. In this paper, we introduce a new notion of warp-coherence for conditions that exhibit coherent run-time behavior on different lanes of a vector register. We demonstrate that warp-coherent conditions appear frequently in practice. We present Warp-Coherent Condition Vectorization (WCCV) – an approach to detecting and optimizing IF-statements with warp-coherent conditions – to efficiently vectorize programs with IF-statements while avoiding the overhead of existing methods. WCCV detects warp-coherent conditions via the affine analysis of conditional boolean expressions and branch predication of IF-statements; the runtime code generated by WCCV avoids redundant computations and masked instructions. We employ auto-tuning to find the optimal benefit-overhead ratio for WCCV. We implement WCCV on top of Region Vectorizer (RV) – an LLVM-based vectorizing compiler, and we conduct experiments on the Rodinia benchmark suite, achieving a mean speedup of 1.14x over the original vectorized and optimized code, and speedup between 0.98x and 7.02x over the scalar code on Skylake with AVX512.<\/p>\n","protected":false},"excerpt":{"rendered":"
When vectorizing programs for modern processors with SIMD extensions, IF-statements pose a challenge: existing vectorization approaches often introduce redundant computations or they resort to inefficient masked instructions. In this paper, we introduce a new notion of warp-coherence for conditions that exhibit coherent run-time behavior on different lanes of a vector register. We demonstrate that warp-coherent […]<\/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":[451,215,1782,1814,1793,176,67],"class_list":["post-18975","post","type-post","status-publish","format-standard","hentry","category-computer-science","category-opencl","category-paper","tag-benchmarking","tag-code-generation","tag-computer-science","tag-llvm","tag-opencl","tag-package","tag-performance"],"views":2169,"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/18975","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=18975"}],"version-history":[{"count":0,"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/18975\/revisions"}],"wp:attachment":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=18975"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=18975"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=18975"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}