{"id":18708,"date":"2019-01-13T11:00:01","date_gmt":"2019-01-13T09:00:01","guid":{"rendered":"https:\/\/hgpu.org\/?p=18708"},"modified":"2019-01-13T11:00:01","modified_gmt":"2019-01-13T09:00:01","slug":"hg-caffe-mobile-and-embedded-neural-network-gpu-opencl-inference-engine-with-fp16-supporting","status":"publish","type":"post","link":"https:\/\/hgpu.org\/?p=18708","title":{"rendered":"HG-Caffe: Mobile and Embedded Neural Network GPU (OpenCL) Inference Engine with FP16 Supporting"},"content":{"rendered":"<p>Breakthroughs in the fields of deep learning and mobile system-on-chips are radically changing the way we use our smartphones. However, deep neural networks inference is still a challenging task for edge AI devices due to the computational overhead on mobile CPUs and a severe drain on the batteries. In this paper, we present a deep neural network inference engine named HG-Caffe, which supports GPUs with half precision. HG-Caffe provides up to 20 times speedup with GPUs compared to the original implementations. In addition to the speedup, the peak memory usage is also reduced to about 80%. With HG-Caffe, more innovative and fascinating mobile applications will be turned into reality.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Breakthroughs in the fields of deep learning and mobile system-on-chips are radically changing the way we use our smartphones. However, deep neural networks inference is still a challenging task for edge AI devices due to the computational overhead on mobile CPUs and a severe drain on the batteries. In this paper, we present a deep [&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":[11,90,3],"tags":[1777,1782,1673,1025,34,1793,176],"class_list":["post-18708","post","type-post","status-publish","format-standard","hentry","category-computer-science","category-opencl","category-paper","tag-caffe","tag-computer-science","tag-deep-learning","tag-machine-learning","tag-neural-networks","tag-opencl","tag-package"],"views":2272,"jetpack_publicize_connections":[],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/18708","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=18708"}],"version-history":[{"count":0,"href":"https:\/\/hgpu.org\/index.php?rest_route=\/wp\/v2\/posts\/18708\/revisions"}],"wp:attachment":[{"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=18708"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=18708"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/hgpu.org\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=18708"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}