{"id":12297,"date":"2014-06-17T09:36:22","date_gmt":"2014-06-17T06:36:22","guid":{"rendered":"http:\/\/hgpu.org\/?p=12297"},"modified":"2014-06-17T09:36:22","modified_gmt":"2014-06-17T06:36:22","slug":"synergia-cuda-gpu-accelerated-accelerator-modeling-package","status":"publish","type":"post","link":"https:\/\/hgpu.org\/?p=12297","title":{"rendered":"Synergia CUDA: GPU-accelerated accelerator modeling package"},"content":{"rendered":"<p>Synergia is a parallel, 3-dimensional space-charge particle-in-cell accelerator modeling code. We present our work porting the purely MPI-based version of the code to a hybrid of CPU and GPU computing kernels. The hybrid code uses the CUDA platform in the same framework as the pure MPI solution. We have implemented a lock-free collaborative charge-deposition algorithm for the GPU, as well as other optimizations, including local communication avoidance for GPUs, a customized FFT, and fine-tuned memory access patterns. On a small GPU cluster (up to 4 Tesla C1070 GPUs), our benchmarks exhibit both superior peak performance and better scaling than a CPU cluster with 16 nodes and 128 cores. We also compare the code performance on different GPU architectures, including C1070 Tesla and K20 Kepler.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Synergia is a parallel, 3-dimensional space-charge particle-in-cell accelerator modeling code. We present our work porting the purely MPI-based version of the code to a hybrid of CPU and GPU computing kernels. The hybrid code uses the CUDA platform in the same framework as the pure MPI solution. We have implemented a lock-free collaborative charge-deposition algorithm [&hellip;]<\/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":[89,3,12],"tags":[14,207,106,242,20,176,299,1783,410,1390],"class_list":["post-12297","post","type-post","status-publish","format-standard","hentry","category-nvidia-cuda","category-paper","category-physics","tag-cuda","tag-fft","tag-gpu-cluster","tag-mpi","tag-nvidia","tag-package","tag-particle-in-cell-methods","tag-physics","tag-tesla-c1070","tag-tesla-k20"],"views":3406,"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/12297","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=12297"}],"version-history":[{"count":0,"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/12297\/revisions"}],"wp:attachment":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=12297"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=12297"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=12297"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}