{"id":3149,"date":"2024-09-24T08:00:00","date_gmt":"2024-09-23T23:00:00","guid":{"rendered":"https:\/\/www.xlsoft.com\/jp\/blog\/intel\/?p=3149"},"modified":"2024-09-21T01:16:51","modified_gmt":"2024-09-20T16:16:51","slug":"migrating-high-performance-flood-modelling-software-from-cuda-to-sycl","status":"publish","type":"post","link":"https:\/\/www.xlsoft.com\/jp\/blog\/intel\/2024\/09\/24\/migrating-high-performance-flood-modelling-software-from-cuda-to-sycl\/","title":{"rendered":"oneAPI \u3092\u4f7f\u7528\u3057\u3066\u9ad8\u6027\u80fd\u6d2a\u6c34\u30e2\u30c7\u30ea\u30f3\u30b0\u30fb\u30bd\u30d5\u30c8\u30a6\u30a7\u30a2\u3092 CUDA* \u304b\u3089 SYCL* \u3078\u79fb\u884c"},"content":{"rendered":"\n<hr class=\"wp-block-separator has-text-color has-cyan-bluish-gray-color has-alpha-channel-opacity has-cyan-bluish-gray-background-color has-background\" \/>\n\n\n\n<p class=\"wp-block-paragraph\">\u3053\u306e\u8a18\u4e8b\u306f\u3001\u30a4\u30f3\u30c6\u30eb\u306e\u30d6\u30ed\u30b0\u3067\u516c\u958b\u3055\u308c\u3066\u3044\u308b\u300c<a href=\"https:\/\/community.intel.com\/t5\/Blogs\/Tech-Innovation\/Tools\/Migrating-High-performance-Flood-Modelling-Software-from-CUDA-to\/post\/1630530\" target=\"_blank\" rel=\"noreferrer noopener\">Migrating High-performance Flood Modelling Software from CUDA* to SYCL* with oneAPI<\/a>\u300d\u306e\u65e5\u672c\u8a9e\u53c2\u8003\u8a33\u3067\u3059\u3002\u539f\u6587\u306f\u66f4\u65b0\u3055\u308c\u308b\u53ef\u80fd\u6027\u304c\u3042\u308a\u307e\u3059\u3002\u539f\u6587\u3068\u7ffb\u8a33\u6587\u306e\u5185\u5bb9\u304c\u7570\u306a\u308b\u5834\u5408\u306f\u539f\u6587\u3092\u512a\u5148\u3057\u3066\u304f\u3060\u3055\u3044\u3002<\/p>\n\n\n\n<hr class=\"wp-block-separator has-text-color has-cyan-bluish-gray-color has-alpha-channel-opacity has-cyan-bluish-gray-background-color has-background\" \/>\n\n\n\n<figure class=\"wp-block-image size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"999\" height=\"664\" src=\"https:\/\/www.xlsoft.com\/jp\/blog\/intel\/wp-content\/uploads\/sites\/5\/2024\/09\/12_unsplash-anastasia-taioglou-ctivhyitbfw.jpg\" alt=\"\" class=\"wp-image-3153\" srcset=\"https:\/\/www.xlsoft.com\/jp\/blog\/intel\/wp-content\/uploads\/sites\/5\/2024\/09\/12_unsplash-anastasia-taioglou-ctivhyitbfw.jpg 999w, https:\/\/www.xlsoft.com\/jp\/blog\/intel\/wp-content\/uploads\/sites\/5\/2024\/09\/12_unsplash-anastasia-taioglou-ctivhyitbfw-300x199.jpg 300w, https:\/\/www.xlsoft.com\/jp\/blog\/intel\/wp-content\/uploads\/sites\/5\/2024\/09\/12_unsplash-anastasia-taioglou-ctivhyitbfw-768x510.jpg 768w\" sizes=\"auto, (max-width: 999px) 100vw, 999px\" \/><\/figure>\n\n\n\n<h3 class=\"wp-block-heading\">SYCL* \u30b3\u30fc\u30c9\u30d9\u30fc\u30b9\u306e\u6d2a\u6c34\u30b7\u30df\u30e5\u30ec\u30fc\u30b7\u30e7\u30f3\u306f\u3001\u540c\u3058 NVIDIA* GPU \u4e0a\u3067\u5143\u306e CUDA* \u30b3\u30fc\u30c9\u3088\u308a\u3082 10% \u4ee5\u4e0a\u9ad8\u901f<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">\u6d2a\u6c34\u306f\u6bce\u5e74\u5927\u304d\u306a\u88ab\u5bb3\u3092\u3082\u305f\u3089\u3057\u3001\u4eba\u3005\u3084\u30a4\u30f3\u30d5\u30e9\u306b\u5927\u304d\u306a\u8105\u5a01\u3092\u3082\u305f\u3089\u3057\u307e\u3059\u3002\u6c17\u5019\u5909\u52d5\u306b\u3088\u308a\u3001\u4e16\u754c\u4e2d\u3067\u6d2a\u6c34\u304c\u983b\u767a\u3057\u3001\u6df1\u523b\u5316\u3057\u3066\u3044\u307e\u3059\u3002\u6c34\u529b\u5b66\u7684\u6d2a\u6c34\u30e2\u30c7\u30eb\u306f\u3001\u6d2a\u6c34\u30ea\u30b9\u30af\u306e\u8efd\u6e1b\u306b\u5f79\u7acb\u3064\u5f37\u529b\u306a\u30c4\u30fc\u30eb\u3067\u3042\u308a\u3001\u6d2a\u6c34\u767a\u751f\u6642\u306e\u6c34\u306e\u6d41\u308c\u3068\u6d2a\u6c34\u306e\u7bc4\u56f2\u3092\u30b7\u30df\u30e5\u30ec\u30fc\u30c8\u3067\u304d\u307e\u3059\u3002\u3053\u308c\u3089\u306e\u30e2\u30c7\u30eb\u306f\u3001\u6d2a\u6c34\u3092\u4e88\u6e2c\u3057\u3001\u6d2a\u6c34\u30ea\u30b9\u30af\u3092\u7406\u89e3\u3059\u308b\u305f\u3081\u306b\u4e0d\u53ef\u6b20\u3067\u3042\u308b\u3068\u3068\u3082\u306b\u3001\u793e\u4f1a\u306e\u8010\u6027\u3092\u9ad8\u3081\u308b\u306e\u306b\u3082\u5f79\u7acb\u3061\u307e\u3059\u3002<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">SynxFlow \u30d7\u30ed\u30b8\u30a7\u30af\u30c8\u306b\u3064\u3044\u3066<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\"><a href=\"https:\/\/github.com\/SynxFlow\/SynxFlow\" target=\"_blank\" rel=\"noreferrer noopener\">SynxFlow<\/a>&nbsp;(\u82f1\u8a9e) \u306f\u3001\u30d0\u30fc\u30df\u30f3\u30ac\u30e0\u5927\u5b66\u306e Xilin Xia \u535a\u58eb\u3068\u305d\u306e\u540c\u50da\u304c CUDA*\u3001C++\u3001Python* \u3067\u958b\u767a\u3057\u305f\u3001\u30aa\u30fc\u30d7\u30f3\u30bd\u30fc\u30b9\u306e GPU \u30d9\u30fc\u30b9\u306e\u6c34\u529b\u5b66\u7684\u6d2a\u6c34\u30e2\u30c7\u30ea\u30f3\u30b0\u30fb\u30bd\u30d5\u30c8\u30a6\u30a7\u30a2\u3067\u3059\u3002\u30b7\u30df\u30e5\u30ec\u30fc\u30b7\u30e7\u30f3\u306e\u5b9f\u884c\u306b CUDA* \u30b3\u30fc\u30c9\u3092\u4f7f\u7528\u3057\u3001\u30c7\u30fc\u30bf\u306e\u524d\u51e6\u7406\u3068\u8996\u899a\u5316\u306b Python* \u30b3\u30fc\u30c9\u3092\u4f7f\u7528\u3057\u3066\u3044\u307e\u3059\u3002\u8907\u6570\u306e GPU \u3067\u52d5\u4f5c\u3059\u308b SynxFlow \u306f\u3001\u6570\u5104\u306e\u8a08\u7b97\u30bb\u30eb\u3068\u30e1\u30fc\u30c8\u30eb\u30ec\u30d9\u30eb\u306e\u89e3\u50cf\u5ea6\u3067\u3001\u30ea\u30a2\u30eb\u30bf\u30a4\u30e0\u3088\u308a\u3082\u9ad8\u901f\u306b\u6d2a\u6c34\u30b7\u30df\u30e5\u30ec\u30fc\u30b7\u30e7\u30f3\u3092\u5b9f\u884c\u3067\u304d\u307e\u3059\u3002\u30e6\u30fc\u30b6\u30fc\u30d5\u30ec\u30f3\u30c9\u30ea\u30fc\u306a Python* \u30a4\u30f3\u30bf\u30fc\u30d5\u30a7\u30a4\u30b9\u3092\u5099\u3048\u305f\u30aa\u30fc\u30d7\u30f3\u30bd\u30fc\u30b9\u30fb\u30bd\u30d5\u30c8\u30a6\u30a7\u30a2\u3067\u3042\u308b\u305f\u3081\u3001\u707d\u5bb3\u6642\u306e\u30ea\u30b9\u30af\u8a55\u4fa1\u3092\u884c\u3046\u30c7\u30fc\u30bf\u30b5\u30a4\u30a8\u30f3\u30b9\u30fb\u30ef\u30fc\u30af\u30d5\u30ed\u30fc\u306b\u7c21\u5358\u306b\u7d71\u5408\u3067\u304d\u307e\u3059\u3002\u305d\u306e\u305f\u3081\u3001\u3053\u306e\u30e2\u30c7\u30eb\u306f\u6d2a\u6c34\u65e9\u671f\u8b66\u5831\u30b7\u30b9\u30c6\u30e0\u306e\u30b5\u30dd\u30fc\u30c8\u3084\u3001(\u518d) \u4fdd\u967a\u4f1a\u793e\u5411\u3051\u306e\u6d2a\u6c34\u30de\u30c3\u30d7\u306e\u4f5c\u6210\u306a\u3069\u3001\u7814\u7a76\u3084\u7523\u696d\u754c\u3067\u5e83\u304f\u4f7f\u7528\u3055\u308c\u3066\u3044\u307e\u3059\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">SynxFlow \u30bd\u30d5\u30c8\u30a6\u30a7\u30a2\u306f\u3001\u6d2a\u6c34\u30b7\u30ca\u30ea\u30aa\u3084\u3001\u5730\u6ed1\u308a\u6d41\u51fa\u3084\u571f\u77f3\u6d41\u306a\u3069\u306e\u95a2\u9023\u3059\u308b\u5371\u967a\u3092\u30b7\u30df\u30e5\u30ec\u30fc\u30c8\u3067\u304d\u307e\u3059\u3002\u3053\u306e\u3088\u3046\u306a\u30b7\u30df\u30e5\u30ec\u30fc\u30b7\u30e7\u30f3\u306f\u3001\u7dca\u6025\u30b5\u30fc\u30d3\u30b9\u306e\u4e8b\u524d\u8a08\u753b\u3068\u7ba1\u7406\u306b\u304a\u3044\u3066\u91cd\u8981\u306a\u5f79\u5272\u3092\u679c\u305f\u3057\u307e\u3059\u3002\u81ea\u7136\u707d\u5bb3\u306e\u8a73\u7d30\u306a\u4e88\u6e2c\u306f\u3001\u707d\u5bb3\u306b\u3088\u308b\u793e\u4f1a\u7684\u3001\u7d4c\u6e08\u7684\u60aa\u5f71\u97ff\u3092\u8efd\u6e1b\u3059\u308b\u306e\u306b\u5f79\u7acb\u3061\u307e\u3059\u3002\u30ea\u30b9\u30af\u8a55\u4fa1\u3068\u707d\u5bb3\u5bfe\u7b56\u306e\u307b\u304b\u306b\u3082\u3001SynxFlow \u306b\u3088\u308b\u6d2a\u6c34\u30b7\u30df\u30e5\u30ec\u30fc\u30b7\u30e7\u30f3\u306f\u3001\u90fd\u5e02\u8a08\u753b\u3001\u74b0\u5883\u4fdd\u8b77\u3001\u6c17\u5019\u5909\u52d5\u3078\u306e\u9069\u5fdc\u3001\u4fdd\u967a\u304a\u3088\u3073\u8ca1\u52d9\u8a08\u753b\u3001\u30a4\u30f3\u30d5\u30e9\u30b9\u30c8\u30e9\u30af\u30c1\u30e3\u30fc\u306e\u8a2d\u8a08\u3068\u30a8\u30f3\u30b8\u30cb\u30a2\u30ea\u30f3\u30b0\u3001\u4e00\u822c\u306e\u610f\u8b58\u5411\u4e0a\u3068\u6559\u80b2\u306b\u3082\u5f79\u7acb\u3061\u307e\u3059\u3002<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">\u8ab2\u984c<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">\u65b0\u3057\u3044\u30a2\u30d7\u30ea\u30b1\u30fc\u30b7\u30e7\u30f3\u306b\u306f\u65b0\u3057\u3044\u8ab2\u984c\u304c\u751f\u3058\u307e\u3059\u3002<a href=\"https:\/\/www.ukri.org\/councils\/nerc\/\" target=\"_blank\" rel=\"noreferrer noopener\">\u81ea\u7136\u74b0\u5883\u7814\u7a76\u8a55\u8b70\u4f1a<\/a>&nbsp;(\u82f1\u8a9e) \u304c\u652f\u63f4\u3057\u3066\u3044\u308b<a href=\"https:\/\/www.birmingham.ac.uk\/schools\/engineering\" target=\"_blank\" rel=\"noreferrer noopener\">\u30d0\u30fc\u30df\u30f3\u30ac\u30e0\u5927\u5b66<\/a>&nbsp;(\u82f1\u8a9e) \u3068&nbsp;<a href=\"https:\/\/www.ceh.ac.uk\/\" target=\"_blank\" rel=\"noreferrer noopener\">\u82f1\u56fd\u751f\u614b\u6c34\u6587\u5b66\u7814\u7a76\u6240<\/a>&nbsp;(\u82f1\u8a9e) \u306e\u5171\u540c\u30d7\u30ed\u30b8\u30a7\u30af\u30c8\u306b\u304a\u3044\u3066\u3001Xilin \u535a\u58eb\u3068\u305d\u306e\u540c\u50da\u306f\u3001\u65b0\u4e16\u4ee3\u306e\u78ba\u7387\u7684\u6d2a\u6c34\u4e88\u6e2c\u30b7\u30b9\u30c6\u30e0\u3092\u958b\u767a\u3057\u3066\u3044\u307e\u3059\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u78ba\u7387\u7684\u6d2a\u6c34\u4e88\u6e2c\u306f\u3001\u6b21\u306e\u3088\u3046\u306a\u8981\u56e0\u306b\u3088\u308a\u3001\u8a08\u7b97\u304c\u56f0\u96e3\u306a\u30d7\u30ed\u30bb\u30b9\u3067\u3059\u3002<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>\u5927\u898f\u6a21\u306a\u30c7\u30fc\u30bf\u30bb\u30c3\u30c8\u306e\u4fdd\u5b58\u3001\u691c\u7d22\u3001\u7ba1\u7406<\/li>\n\n\n\n<li>\u8907\u96d1\u306a\u30ea\u30a2\u30eb\u30bf\u30a4\u30e0\u30fb\u30c7\u30fc\u30bf\u3092\u51e6\u7406\u3059\u308b\u30cf\u30a4\u30d1\u30d5\u30a9\u30fc\u30de\u30f3\u30b9\u30fb\u30b3\u30f3\u30d4\u30e5\u30fc\u30c6\u30a3\u30f3\u30b0\u8981\u4ef6<\/li>\n\n\n\n<li>\u5909\u5316\u3059\u308b\u73fe\u5b9f\u4e16\u754c\u306e\u72b6\u6cc1\u306b\u5fdc\u3058\u305f\u5fc5\u8981\u306a\u30e2\u30c7\u30eb\u306e\u8abf\u6574\u3068\u691c\u8a3c<\/li>\n\n\n\n<li>\u3055\u307e\u3056\u307e\u306a (\u6c34\u6587\u5b66\u3001\u6c34\u529b\u5b66\u3001\u6c17\u8c61) \u30e2\u30c7\u30eb\u306e\u52b9\u7387\u7684\u306a\u7d71\u5408\u3068\u30e2\u30c7\u30eb\u9593\u306e\u6b63\u78ba\u306a\u30c7\u30fc\u30bf\u8ee2\u9001\u3001\u306a\u3069<\/li>\n<\/ul>\n\n\n\n<p class=\"wp-block-paragraph\">\u6d2a\u6c34\u4e88\u6e2c\u30b7\u30b9\u30c6\u30e0\u306f\u540c\u6642\u306b\u591a\u304f\u306e\u8ab2\u984c\u306b\u5bfe\u51e6\u3057\u306a\u3051\u308c\u3070\u306a\u3089\u306a\u3044\u305f\u3081\u3001\u4e26\u5217\u30c7\u30fc\u30bf\u51e6\u7406\u3068\u8a08\u7b97\u8ca0\u8377\u306e\u9ad8\u3044\u30bf\u30b9\u30af\u3092\u30cf\u30fc\u30c9\u30a6\u30a7\u30a2\u30fb\u30a2\u30af\u30bb\u30e9\u30ec\u30fc\u30bf\u30fc\u306b\u30aa\u30d5\u30ed\u30fc\u30c9\u3059\u308b\u3053\u3068\u3067\u3001\u30b7\u30b9\u30c6\u30e0\u304b\u3089\u3088\u308a\u901f\u304f\u7d50\u679c\u3092\u5f97\u308b\u5fc5\u8981\u304c\u3042\u308a\u307e\u3059\u3002\u3057\u305f\u304c\u3063\u3066\u3001SynxFlow \u30c1\u30fc\u30e0\u306f\u3001\u3055\u3089\u306b\u5927\u304d\u306a\u30b9\u30fc\u30d1\u30fc\u30b3\u30f3\u30d4\u30e5\u30fc\u30bf\u30fc\u3092\u4f7f\u7528\u3059\u308b\u3053\u3068\u3067\u3001\u6d2a\u6c34\u30b7\u30df\u30e5\u30ec\u30fc\u30b7\u30e7\u30f3\u306e\u898f\u6a21\u3092\u62e1\u5927\u3057\u3001\u30b7\u30df\u30e5\u30ec\u30fc\u30b7\u30e7\u30f3\u6642\u9593\u3092\u5927\u5e45\u306b\u77ed\u7e2e\u3059\u308b\u5fc5\u8981\u304c\u3042\u308a\u307e\u3059\u3002\u3057\u304b\u3057\u3001\u82f1\u56fd\u306e\u6700\u65b0\u30b9\u30fc\u30d1\u30fc\u30b3\u30f3\u30d4\u30e5\u30fc\u30bf\u30fc\u3067\u3042\u308b&nbsp;<a href=\"https:\/\/www.hpc.cam.ac.uk\/d-w-n\" target=\"_blank\" rel=\"noreferrer noopener\">DAWN<\/a>&nbsp;(\u82f1\u8a9e) \u306f\u3001SynxFlow \u304c\u30b5\u30dd\u30fc\u30c8\u3057\u3066\u3044\u306a\u3044\u30a4\u30f3\u30c6\u30eb\u00ae GPU\u3092\u4f7f\u7528\u3057\u3066\u3044\u307e\u3059\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u3053\u308c\u3089\u306e\u8ab2\u984c\u306b\u5bfe\u51e6\u3059\u308b\u305f\u3081\u3001\u7814\u7a76\u8005\u306f SynxFlow \u30e2\u30c7\u30eb\u3092\u6539\u826f\u3057\u3001\u30b9\u30fc\u30d1\u30fc\u30b3\u30f3\u30d4\u30e5\u30fc\u30bf\u30fc\u4e0a\u306e\u30de\u30eb\u30c1\u30d9\u30f3\u30c0\u30fc GPU \u3067\u30d1\u30d5\u30a9\u30fc\u30de\u30f3\u30b9\u3092\u79fb\u690d\u53ef\u80fd\u304b\u3064\u30b9\u30b1\u30fc\u30e9\u30d6\u30eb\u306b\u3059\u308b\u3068\u3044\u3046\u65b0\u3057\u3044\u76ee\u6a19\u3092\u63b2\u3052\u307e\u3057\u305f\u3002\u3064\u307e\u308a\u3001SynxFlow \u30b3\u30fc\u30c9\u3092 CUDA* \u304b\u3089\u30de\u30eb\u30c1\u30d9\u30f3\u30c0\u30fc\u3092\u30b5\u30dd\u30fc\u30c8\u3059\u308b\u5225\u306e\u30d7\u30ed\u30b0\u30e9\u30df\u30f3\u30b0\u8a00\u8a9e\u306b\u3001\u73fe\u5b9f\u7684\u306a\u6642\u9593\u67a0\u5185 (\u6570\u5e74\u3067\u306f\u306a\u304f\u6570\u9031\u9593) \u3067\u79fb\u884c\u3059\u308b\u5fc5\u8981\u304c\u3042\u308a\u307e\u3059\u3002<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>oneAPI \u3092\u5229\u7528\u3057\u305f\u30bd\u30ea\u30e5\u30fc\u30b7\u30e7\u30f3<\/strong><\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">\u3055\u307e\u3056\u307e\u306a\u30aa\u30d7\u30b7\u30e7\u30f3\u3092\u691c\u8a0e\u3057\u305f\u7d50\u679c\u3001SynxFlow \u30d7\u30ed\u30b8\u30a7\u30af\u30c8\u30fb\u30c1\u30fc\u30e0\u306f\u3001Unified Acceleration Foundation (UXL) \u306e oneAPI \u4ed5\u69d8\u306e\u30a4\u30f3\u30c6\u30eb\u00ae oneAPI \u30d9\u30fc\u30b9\u30fb\u30c4\u30fc\u30eb\u30ad\u30c3\u30c8\u5b9f\u88c5\u3092\u5229\u7528\u3059\u308b\u3053\u3068\u306b\u3057\u307e\u3057\u305f\u3002oneAPI \u306f\u3001\u30de\u30eb\u30c1\u30a2\u30fc\u30ad\u30c6\u30af\u30c1\u30e3\u30fc\u3001\u30de\u30eb\u30c1\u30d9\u30f3\u30c0\u30fc\u5bfe\u5fdc\u306e SYCL* \u30d5\u30ec\u30fc\u30e0\u30ef\u30fc\u30af\u306b\u57fa\u3065\u3044\u3066\u3044\u307e\u3059\u3002\u30a4\u30f3\u30c6\u30eb\u3001NVIDIA*\u3001AMD* GPU \u3092\u30b5\u30dd\u30fc\u30c8\u3057\u3066\u304a\u308a\u3001<a href=\"https:\/\/www.isus.jp\/dpc-compatibility-tool\/\" target=\"_blank\" rel=\"noreferrer noopener\">\u30a4\u30f3\u30c6\u30eb\u00ae DPC++ \u4e92\u63db\u6027\u30c4\u30fc\u30eb (\u30a4\u30f3\u30c6\u30eb\u00ae DPCT)<\/a>&nbsp;\u306b\u3088\u308a\u3001CUDA* \u304b\u3089 SYCL* \u3078\u306e\u30b3\u30fc\u30c9\u79fb\u884c\u304c\u7c21\u5358\u304b\u3064\u81ea\u52d5\u5316\u3055\u308c\u307e\u3059\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">SynxFlow \u30b3\u30fc\u30c9\u306e\u79fb\u884c\u30d7\u30ed\u30bb\u30b9\u306f\u30b9\u30e0\u30fc\u30ba\u3067\u3057\u305f\u3002Microsoft* Visual Studio* \u3092\u4f7f\u7528\u3057\u3066\u30d7\u30ed\u30b8\u30a7\u30af\u30c8\u3092\u518d\u7de8\u6210\u3057\u305f\u5f8c\u3001Xilin \u535a\u58eb\u306f\u30a4\u30f3\u30c6\u30eb\u00ae DPC++ \u4e92\u63db\u6027\u30c4\u30fc\u30eb\u3092\u5b9f\u884c\u3057\u307e\u3057\u305f\u3002\u3053\u308c\u306b\u3088\u308a\u3001CUDA* \u30ab\u30fc\u30cd\u30eb\u3068 API \u547c\u3073\u51fa\u3057\u306e\u307b\u3068\u3093\u3069\u304c\u81ea\u52d5\u7684\u306b SYCL* \u306b\u5909\u63db\u3055\u308c\u305f\u30b3\u30fc\u30c9\u304c\u751f\u6210\u3055\u308c\u307e\u3057\u305f\u3002\u81ea\u52d5\u5909\u63db\u5f8c\u306b\u30b3\u30f3\u30d1\u30a4\u30eb\u3059\u308b\u3068\u3001\u3044\u304f\u3064\u304b\u306e\u30a8\u30e9\u30fc\u304c\u767a\u751f\u3057\u307e\u3057\u305f\u304c\u3001\u79fb\u884c\u30c4\u30fc\u30eb\u306e\u51fa\u529b\u306b\u542b\u307e\u308c\u308b\u30a8\u30e9\u30fc\u8a3a\u65ad\u306e\u30d2\u30f3\u30c8\u3068\u8b66\u544a\u306b\u57fa\u3065\u3044\u3066\u7c21\u5358\u306b\u4fee\u6b63\u3067\u304d\u307e\u3057\u305f\u3002\u3088\u308a\u6642\u9593\u304c\u304b\u304b\u3063\u305f\u306e\u306f\u3001NVIDIA* Collective Communications Library (NCCL) \u30d9\u30fc\u30b9\u306e GPU \u9593\u901a\u4fe1\u3092 GPU \u30c0\u30a4\u30ec\u30af\u30c8\u5bfe\u5fdc\u306e<a href=\"https:\/\/www.xlsoft.com\/jp\/products\/intel\/cluster\/mpi\/index.html\" target=\"_blank\" rel=\"noreferrer noopener\">\u30a4\u30f3\u30c6\u30eb\u00ae MPI \u30e9\u30a4\u30d6\u30e9\u30ea\u30fc<\/a>&nbsp;(\u82f1\u8a9e) \u547c\u3073\u51fa\u3057\u306b\u5909\u66f4\u3059\u308b\u3053\u3068\u3067\u3057\u305f\u3002\u3053\u308c\u306f\u81ea\u52d5\u7684\u306b\u884c\u308f\u308c\u307e\u305b\u3093\u3067\u3057\u305f\u3002<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">\u91cd\u8981\u306a\u7d50\u679c<\/h3>\n\n\n\n<figure class=\"wp-block-table\"><table><tbody><tr><td>\u300c\u751f\u6210\u3055\u308c\u305f\u30b3\u30fc\u30c9\u306f\u3001Codeplay* \u306e oneAPI \u30d7\u30e9\u30b0\u30a4\u30f3\u3092\u4f7f\u7528\u3059\u308b\u3053\u3068\u3067\u3001CPU\u3001\u30a4\u30f3\u30c6\u30eb\u00ae GPU\u3001NVIDIA* GPU \u4e0a\u3067\u5b9f\u884c\u3067\u304d\u307e\u3059\u3002\u30d1\u30d5\u30a9\u30fc\u30de\u30f3\u30b9\u306e\u6700\u9069\u5316\u3092\u884c\u3063\u3066\u3044\u306a\u3044\u72b6\u614b\u3067\u3082\u3001\u5927\u90fd\u5e02\u306e\u6d2a\u6c34\u306e\u30b7\u30df\u30e5\u30ec\u30fc\u30b7\u30e7\u30f3\u3067\u306f\u3001SYCL* \u30b3\u30fc\u30c9\u306e\u307b\u3046\u304c\u540c\u3058 NVIDIA* A100 GPU \u4e0a\u306e\u5143\u306e CUDA* \u30b3\u30fc\u30c9\u3088\u308a\u3082 10% \u4ee5\u4e0a\u9ad8\u901f\u3067\u3059<sup>[1]<\/sup>\u3002\u30a4\u30f3\u30c6\u30eb\u00ae \u30c7\u30fc\u30bf\u30bb\u30f3\u30bf\u30fc GPU Max 1550 \u3067\u3082\u30d1\u30d5\u30a9\u30fc\u30de\u30f3\u30b9\u306f\u540c\u7b49\u3067\u3059\u3002\u30a4\u30f3\u30c6\u30eb\u00ae \u30c7\u30fc\u30bf\u30bb\u30f3\u30bf\u30fc GPU Max 1550 \u3067\u306f\u3001\u540c\u3058\u30b7\u30df\u30e5\u30ec\u30fc\u30b7\u30e7\u30f3\u306b NVIDIA* A100 GPU \u3088\u308a\u3082\u7d04 40% \u9577\u304f\u304b\u304b\u308a\u307e\u3059\u3002\u30b9\u30b1\u30fc\u30e9\u30d3\u30ea\u30c6\u30a3\u30fc\u306b\u3064\u3044\u3066\u306f\u3001\u30b3\u30fc\u30c9\u306f NVIDIA* \u304a\u3088\u3073\u30a4\u30f3\u30c6\u30eb\u00ae GPU \u30d9\u30fc\u30b9\u306e\u30b9\u30fc\u30d1\u30fc\u30b3\u30f3\u30d4\u30e5\u30fc\u30bf\u30fc\u306e\u4e21\u65b9\u3067\u3001\u307b\u307c 90% \u306e\u5f37\u529b\u306a\u30b9\u30b1\u30fc\u30ea\u30f3\u30b0\u52b9\u7387\u3092\u9054\u6210\u3057\u307e\u3057\u305f\u3002\u300d<br><br>&#8212;\u00a0<em>\u30d0\u30fc\u30df\u30f3\u30ac\u30e0\u5927\u5b66\u52a9\u6559\u6388\u3001<\/em>Xilin Xia<em> \u535a\u58eb<\/em><\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n<p class=\"wp-block-paragraph\">\u8981\u7d04\u3059\u308b\u3068\u3001\u8907\u96d1\u306a CUDA* \u30d9\u30fc\u30b9\u306e\u6d2a\u6c34\u30b7\u30df\u30e5\u30ec\u30fc\u30b7\u30e7\u30f3\u30fb\u30b3\u30fc\u30c9\u3092 SYCL* \u306b\u79fb\u884c\u3059\u308b\u3053\u3068\u306f\u6709\u671b\u3067\u3042\u308a\u3001\u30d1\u30d5\u30a9\u30fc\u30de\u30f3\u30b9\u306e\u79fb\u690d\u6027\u3068\u30b9\u30b1\u30fc\u30e9\u30d3\u30ea\u30c6\u30a3\u30fc\u306e\u4e21\u65b9\u3092\u9054\u6210\u3057\u307e\u3057\u305f\u3002<a href=\"https:\/\/www.xlsoft.com\/jp\/products\/intel\/oneapi\/index.html\" target=\"_blank\" rel=\"noreferrer noopener\">\u30a4\u30f3\u30c6\u30eb\u00ae oneAPI \u30d9\u30fc\u30b9\u30fb\u30c4\u30fc\u30eb\u30ad\u30c3\u30c8<\/a>\u306f\u3001\u79fb\u884c\u3092\u30b9\u30e0\u30fc\u30ba\u304b\u3064\u5bb9\u6613\u306b\u7ba1\u7406\u3067\u304d\u308b\u3088\u3046\u306b\u3057\u3066\u304f\u308c\u307e\u3057\u305f\u3002<\/p>\n\n\n\n<p class=\"highlight wp-block-paragraph\">\u30a4\u30f3\u30c6\u30eb\u00ae \u30c7\u30fc\u30bf\u30bb\u30f3\u30bf\u30fc GPU Max 1550 \u306f\u3001<a href=\"https:\/\/www.xlsoft.com\/jp\/products\/intel\/devcloud\/index.html\">\u30a4\u30f3\u30c6\u30eb\u00ae Tiber&#x2122; \u30c7\u30d9\u30ed\u30c3\u30d1\u30fc\u30fb\u30af\u30e9\u30a6\u30c9<\/a>\u4e0a\u3067\u30a2\u30af\u30bb\u30b9\u3044\u305f\u3060\u3051\u307e\u3059\u3002\u30a8\u30af\u30bb\u30eb\u30bd\u30d5\u30c8\u3067\u306f\u3001\u30a4\u30f3\u30c6\u30eb\u00ae Tiber&#x2122; \u30c7\u30d9\u30ed\u30c3\u30d1\u30fc\u30fb\u30af\u30e9\u30a6\u30c9\u306e\u8a55\u4fa1\u7528\u30af\u30fc\u30dd\u30f3\u3092\u914d\u5e03\u3057\u3066\u3044\u307e\u3059\u3002\u3054\u8208\u5473\u306e\u3042\u308b\u65b9\u306f\u3001<a href=\"https:\/\/www.xlsoft.com\/jp\/services\/xlsoft_form.html?option2=Intel\" target=\"_blank\" rel=\"noopener\" title=\"\u3053\u3061\u3089\u306e\u30d5\u30a9\u30fc\u30e0\">\u3053\u3061\u3089\u306e\u30d5\u30a9\u30fc\u30e0<\/a>\u3088\u308a\u304a\u554f\u3044\u5408\u308f\u305b\u304f\u3060\u3055\u3044\u3002<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">\u8457\u8005\u306b\u3064\u3044\u3066<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">Xilin Xia \u535a\u58eb\u306f\u3001\u82f1\u56fd\u30d0\u30fc\u30df\u30f3\u30ac\u30e0\u5927\u5b66\u5de5\u5b66\u90e8\u30ec\u30b8\u30ea\u30a8\u30f3\u30b9\u5de5\u5b66\u79d1\u52a9\u6559\u6388\u3067\u3042\u308a\u3001\u30a2\u30e9\u30f3\u30fb\u30c1\u30e5\u30fc\u30ea\u30f3\u30b0\u7814\u7a76\u6240\u306e\u30c1\u30e5\u30fc\u30ea\u30f3\u30b0\u30fb\u30d5\u30a7\u30ed\u30fc\u3067\u3082\u3042\u308a\u307e\u3059\u3002\u6d2a\u6c34\u3001\u5730\u6ed1\u308a\u3001\u571f\u77f3\u6d41\/\u6ce5\u6d41\u306a\u3069\u306e\u81ea\u7136\u707d\u5bb3\u3068\u305d\u306e\u5f71\u97ff\u306e\u8a08\u7b97\u30e2\u30c7\u30ea\u30f3\u30b0\u3092\u7814\u7a76\u3057\u3066\u3044\u307e\u3059\u3002\u4e16\u754c\u4e2d\u3067\u4f7f\u7528\u3055\u308c\u3066\u3044\u308b\u6570\u5024\u89e3\u6790\u624b\u6cd5\u3068\u30aa\u30fc\u30d7\u30f3\u30bd\u30fc\u30b9\u30fb\u30b3\u30fc\u30c9\u306e\u958b\u767a\u8005\u3067\u3082\u3042\u308a\u307e\u3059\u3002\u30aa\u30fc\u30d7\u30f3\u30bd\u30fc\u30b9\u306e\u6d2a\u6c34\u30e2\u30c7\u30eb\u958b\u767a\u3078\u306e\u8ca2\u732e\u306b\u3088\u308a\u30012024\u5e74\u30b9\u30eb\u30bf\u30f3\u30fb\u30d3\u30f3\u30fb\u30a2\u30d6\u30c9\u30eb\u30a2\u30b8\u30fc\u30ba\u738b\u5b50\u56fd\u969b\u6c34\u8cde\u3092\u53d7\u8cde\u3057\u3066\u3044\u307e\u3059\u3002<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">\u6b21\u306e\u30b9\u30c6\u30c3\u30d7<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">\u30a4\u30f3\u30c6\u30eb\u00ae DPC++ \u4e92\u63db\u6027\u30c4\u30fc\u30eb\u3068\u3001\u305d\u306e\u30aa\u30fc\u30d7\u30f3\u30bd\u30fc\u30b9\u7248\u3067\u3042\u308b&nbsp;<a href=\"https:\/\/github.com\/oneapi-src\/SYCLomatic\" target=\"_blank\" rel=\"noreferrer noopener\">SYCLomatic<\/a>&nbsp;(\u82f1\u8a9e) \u3092\u4f7f\u7528\u3059\u308b\u3068\u3001CUDA* \u304b\u3089 SYCL* \u3078\u81ea\u52d5\u7684\u306b\u52b9\u7387\u826f\u304f\u30b3\u30fc\u30c9\u3092\u79fb\u884c\u3057\u3001\u3055\u307e\u3056\u307e\u306a\u30d9\u30f3\u30c0\u30fc\u306e\u30cf\u30fc\u30c9\u30a6\u30a7\u30a2\u3067\u30d8\u30c6\u30ed\u30b8\u30cb\u30a2\u30b9\u30fb\u30b3\u30f3\u30d4\u30e5\u30fc\u30c6\u30a3\u30f3\u30b0\u3092\u9ad8\u901f\u5316\u3067\u304d\u307e\u3059\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><a href=\"https:\/\/www.intel.com\/content\/www\/us\/en\/developer\/tools\/oneapi\/training\/migrate-cuda-to-sycl-library.html\" target=\"_blank\" rel=\"noreferrer noopener\">CUDA* \u304b\u3089 SYCL* \u3078\u306e\u30ab\u30bf\u30ed\u30b0<\/a>&nbsp;(\u82f1\u8a9e) \u3067\u5b9f\u7528\u7684\u306a\u30a2\u30d7\u30ea\u30b1\u30fc\u30b7\u30e7\u30f3\u306e\u30b3\u30fc\u30c9\u79fb\u884c\u4f8b\u3092\u78ba\u8a8d\u3067\u304d\u307e\u3059\u3002\u307e\u305f\u3001\u30a4\u30f3\u30c6\u30eb\u306e&nbsp;<a href=\"https:\/\/www.xlsoft.com\/jp\/products\/intel\/oneapi\/index.html\">oneAPI<\/a>&nbsp;\u642d\u8f09\u30bd\u30d5\u30c8\u30a6\u30a7\u30a2\u30fb\u30dd\u30fc\u30c8\u30d5\u30a9\u30ea\u30aa\u306b\u3042\u308b <a href=\"https:\/\/www.xlsoft.com\/jp\/products\/intel\/oneapi\/ai\/index.html\">AI<\/a>\u3001<a href=\"https:\/\/www.xlsoft.com\/jp\/products\/intel\/oneapi\/index.html?tab=1#features-hpc\" title=\"\">HPC<\/a>\u3001<a href=\"https:\/\/www.intel.com\/content\/www\/us\/en\/developer\/tools\/oneapi\/rendering-toolkit.html\" target=\"_blank\" rel=\"noopener\" title=\"\">Rendering<\/a> (\u82f1\u8a9e)&nbsp;\u30c4\u30fc\u30eb\u3082\u305c\u3072\u30c1\u30a7\u30c3\u30af\u3057\u3066\u307f\u3066\u304f\u3060\u3055\u3044\u3002<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>\u30bd\u30d5\u30c8\u30a6\u30a7\u30a2\u3092\u5165\u624b<\/strong><\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">\u30a4\u30f3\u30c6\u30eb\u00ae DPC++ \u4e92\u63db\u6027\u30c4\u30fc\u30eb\u306f\u3001\u30b9\u30bf\u30f3\u30c9\u30a2\u30ed\u30f3\u30fb\u30d0\u30fc\u30b8\u30e7\u30f3\u307e\u305f\u306f<a href=\"https:\/\/www.xlsoft.com\/jp\/products\/intel\/oneapi\/index.html\">\u30a4\u30f3\u30c6\u30eb\u00ae oneAPI \u30d9\u30fc\u30b9\u30fb\u30c4\u30fc\u30eb\u30ad\u30c3\u30c8<\/a>\u306e\u4e00\u90e8\u3068\u3057\u3066\u5229\u7528\u3067\u304d\u307e\u3059\u3002<\/p>\n\n\n\n<h3 class=\"wp-block-heading\"><strong>\u95a2\u9023\u8cc7\u6599<\/strong><\/h3>\n\n\n\n<ul class=\"wp-block-list\">\n<li><a href=\"https:\/\/www.xlsoft.com\/jp\/products\/intel\/oneapi\/index.html\">\u30a4\u30f3\u30c6\u30eb\u00ae oneAPI \u30d7\u30ed\u30b0\u30e9\u30df\u30f3\u30b0\u30fb\u30e2\u30c7\u30eb<\/a><\/li>\n\n\n\n<li><a href=\"https:\/\/www.isus.jp\/products\/oneapi\/dpct-dgr-released\/\">\u30a4\u30f3\u30c6\u30eb\u00ae DPC++ \u4e92\u63db\u6027\u30c4\u30fc\u30eb\u30fb\u30c9\u30ad\u30e5\u30e1\u30f3\u30c8<\/a><\/li>\n\n\n\n<li><a href=\"https:\/\/oneapi-src.github.io\/SYCLomatic\/get_started\/index.html\" target=\"_blank\" rel=\"noreferrer noopener\">SYCLomatic \u30c9\u30ad\u30e5\u30e1\u30f3\u30c8<\/a>&nbsp;(\u82f1\u8a9e)<\/li>\n\n\n\n<li><a href=\"https:\/\/www.xlsoft.com\/jp\/products\/intel\/oneapi\/cuda-to-sycl-migration.html\">CUDA* \u304b\u3089 C++ with SYCL* \u3078\u306e\u79fb\u884c<\/a><\/li>\n\n\n\n<li><a href=\"https:\/\/www.isus.jp\/products\/oneapi\/oneapi-for-nvidia-gpu-get-started\/\">Codeplay \u306e oneAPI for NVIDIA* GPU \u30d7\u30e9\u30b0\u30a4\u30f3<\/a><\/li>\n<\/ul>\n\n\n\n<h3 class=\"wp-block-heading\">\u6cd5\u52d9\u4e0a\u306e\u6ce8\u610f\u66f8\u304d<\/h3>\n\n\n\n<p class=\"wp-block-paragraph\">[1]<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>\u6e2c\u5b9a\u65e5:<\/strong>&nbsp;\u6027\u80fd\u306e\u6e2c\u5b9a\u7d50\u679c\u306f\u30012024\u5e745\u6708\u6642\u70b9\u306e\u30d0\u30fc\u30df\u30f3\u30ac\u30e0\u5927\u5b66\u3068\u82f1\u56fd\u751f\u614b\u6c34\u6587\u5b66\u7814\u7a76\u6240\u306b\u3088\u308b\u30c6\u30b9\u30c8\u306b\u57fa\u3065\u3044\u3066\u3044\u307e\u3059\u3002\u307e\u305f\u3001\u73fe\u5728\u516c\u958b\u4e2d\u306e\u3059\u3079\u3066\u306e\u30bb\u30ad\u30e5\u30ea\u30c6\u30a3\u30fc\u30fb\u30a2\u30c3\u30d7\u30c7\u30fc\u30c8\u304c\u9069\u7528\u3055\u308c\u3066\u3044\u308b\u3068\u306f\u9650\u308a\u307e\u305b\u3093\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>\u30b7\u30df\u30e5\u30ec\u30fc\u30b7\u30e7\u30f3\u30fb\u30b5\u30a4\u30ba:<\/strong>&nbsp;\u5408\u8a08 2.625 \u5104\u30b0\u30ea\u30c3\u30c9\u30bb\u30eb<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><strong>\u30cf\u30fc\u30c9\u30a6\u30a7\u30a2\u3068\u30bd\u30d5\u30c8\u30a6\u30a7\u30a2\u306e\u69cb\u6210:<\/strong><\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li>NVIDIA* \u30de\u30b7\u30f3 (Baskerville HPC): 16 \u307e\u305f\u306f 32 x NVIDIA* A100 GPU\u3001CUDA* Toolkit v11.1<\/li>\n\n\n\n<li>\u30a4\u30f3\u30c6\u30eb\u30fb\u30de\u30b7\u30f3 (DAWN HPC): 16\u300132\u3001\u307e\u305f\u306f 64 x \u30a4\u30f3\u30c6\u30eb\u00ae \u30c7\u30fc\u30bf\u30bb\u30f3\u30bf\u30fc GPU Max 1550\u3001\u30a4\u30f3\u30c6\u30eb\u00ae oneAPI \u30d9\u30fc\u30b9\u30fb\u30c4\u30fc\u30eb\u30ad\u30c3\u30c8 v2024.2.0<\/li>\n<\/ul>\n\n\n\n<p class=\"wp-block-paragraph\">\u6027\u80fd\u306e\u6e2c\u5b9a\u7d50\u679c\u306f\u30b7\u30b9\u30c6\u30e0\u69cb\u6210\u306e\u65e5\u4ed8\u6642\u70b9\u306e\u30c6\u30b9\u30c8\u306b\u57fa\u3065\u3044\u3066\u3044\u307e\u3059\u3002\u307e\u305f\u3001\u73fe\u5728\u516c\u958b\u4e2d\u306e\u3059\u3079\u3066\u306e\u30bb\u30ad\u30e5\u30ea\u30c6\u30a3\u30fc\u30fb\u30a2\u30c3\u30d7\u30c7\u30fc\u30c8\u304c\u9069\u7528\u3055\u308c\u3066\u3044\u308b\u3068\u306f\u9650\u308a\u307e\u305b\u3093\u3002\u8a73\u7d30\u306b\u3064\u3044\u3066\u306f\u3001\u516c\u958b\u3055\u308c\u3066\u3044\u308b\u69cb\u6210\u60c5\u5831\u3092\u53c2\u7167\u3057\u3066\u304f\u3060\u3055\u3044\u3002\u7d76\u5bfe\u7684\u306a\u30bb\u30ad\u30e5\u30ea\u30c6\u30a3\u30fc\u3092\u63d0\u4f9b\u3067\u304d\u308b\u88fd\u54c1\u307e\u305f\u306f\u30b3\u30f3\u30dd\u30fc\u30cd\u30f3\u30c8\u306f\u3042\u308a\u307e\u305b\u3093\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u6027\u80fd\u306f\u3001\u4f7f\u7528\u72b6\u6cc1\u3001\u69cb\u6210\u3001\u305d\u306e\u4ed6\u306e\u8981\u56e0\u306b\u3088\u3063\u3066\u7570\u306a\u308a\u307e\u3059\u3002\u5b9f\u969b\u306e\u8cbb\u7528\u3068\u7d50\u679c\u306f\u7570\u306a\u308b\u5834\u5408\u304c\u3042\u308a\u307e\u3059\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\">\u30a4\u30f3\u30c6\u30eb\u306e\u30c6\u30af\u30ce\u30ed\u30b8\u30fc\u3092\u4f7f\u7528\u3059\u308b\u306b\u306f\u3001\u5bfe\u5fdc\u3057\u305f\u30cf\u30fc\u30c9\u30a6\u30a7\u30a2\u3001\u30bd\u30d5\u30c8\u30a6\u30a7\u30a2\u3001\u307e\u305f\u306f\u30b5\u30fc\u30d3\u30b9\u306e\u6709\u52b9\u5316\u304c\u5fc5\u8981\u3068\u306a\u308b\u5834\u5408\u304c\u3042\u308a\u307e\u3059\u3002\u30a4\u30f3\u30c6\u30eb\u306f\u3001\u30b5\u30fc\u30c9\u30d1\u30fc\u30c6\u30a3\u30fc\u306e\u30c7\u30fc\u30bf\u306b\u3064\u3044\u3066\u7ba1\u7406\u3084\u76e3\u67fb\u3092\u884c\u3063\u3066\u3044\u307e\u305b\u3093\u3002\u307b\u304b\u306e\u60c5\u5831\u3082\u53c2\u8003\u306b\u3057\u3066\u3001\u6b63\u78ba\u304b\u3069\u3046\u304b\u3092\u8a55\u4fa1\u3057\u3066\u304f\u3060\u3055\u3044\u3002<\/p>\n\n\n\n<p class=\"wp-block-paragraph\"><\/p>\n\n\n\n<div class=\"wp-block-group gray-bg\"><div class=\"wp-block-group__inner-container is-layout-constrained wp-block-group-is-layout-constrained\">\n<h2 class=\"wp-block-heading\">\u65e5\u672c\u8a9e\u3067\u306e\u512a\u5148\u30b5\u30dd\u30fc\u30c8\u306e\u3054\u6848\u5185<\/h2>\n\n\n\n<p class=\"wp-block-paragraph\">\u30a8\u30af\u30bb\u30eb\u30bd\u30d5\u30c8\u306f\u3001\u30a4\u30f3\u30c6\u30eb<sup>\u00ae<\/sup>&nbsp;\u30bd\u30d5\u30c8\u30a6\u30a7\u30a2\u958b\u767a\u30c4\u30fc\u30eb\u306e\u6b63\u898f\u8ca9\u58f2\u4ee3\u7406\u5e97\u3068\u3057\u3066\u300125 \u5e74\u4ee5\u4e0a\u306b\u308f\u305f\u3063\u3066\u56fd\u5185\u306e\u958b\u767a\u8005\u5411\u3051\u306b\u65e5\u672c\u8a9e\u3067\u6280\u8853\u30b5\u30dd\u30fc\u30c8\u3084\u6700\u65b0\u60c5\u5831\u3092\u63d0\u4f9b\u3057\u3066\u304d\u307e\u3057\u305f\u3002\u30a4\u30f3\u30c6\u30eb\u3068\u306e\u9577\u5e74\u306e\u5f37\u56fa\u306a\u30d1\u30fc\u30c8\u30ca\u30fc\u30b7\u30c3\u30d7\u3092\u901a\u3057\u3066\u3001\u56fd\u5185\u306b\u5b58\u5728\u3059\u308b\u591a\u304f\u306e\u4f01\u696d\u3001\u7814\u7a76\u6a5f\u95a2\u3001\u5b66\u8853\u6a5f\u95a2\u3067\u306e\u30c4\u30fc\u30eb\u306e\u5c0e\u5165\u3084\u30d7\u30ed\u30b0\u30e9\u30e0\u306e\u6700\u9069\u5316\u306b\u643a\u308f\u3063\u3066\u304d\u305f\u7d4c\u9a13\u3092\u6d3b\u304b\u3057\u3001\u56fd\u5185\u306e\u958b\u767a\u8005\u3084\u4f01\u696d\u306b\u3088\u308b\u30af\u30e9\u30a6\u30c9\u306e\u5c0e\u5165\u3092\u4fc3\u9032\u3059\u308b\u3060\u3051\u3067\u306a\u304f\u3001\u30a4\u30f3\u30c6\u30eb\u958b\u767a\u30c4\u30fc\u30eb\u3092\u6d3b\u7528\u3057\u3066\u30af\u30e9\u30a6\u30c9\u74b0\u5883\u3067\u3082\u9ad8\u901f\u3067\u30aa\u30fc\u30d7\u30f3\u306a\u958b\u767a\u3092\u5b9f\u73fe\u3059\u308b\u305f\u3081\u306e\u304a\u624b\u4f1d\u3044\u3092\u3057\u307e\u3059\u3002<\/p>\n\n\n\n<div class=\"wp-block-columns is-layout-flex wp-container-core-columns-is-layout-8f761849 wp-block-columns-is-layout-flex\">\n<div class=\"wp-block-column is-layout-flow wp-block-column-is-layout-flow\">\n<div class=\"wp-block-buttons is-layout-flex wp-block-buttons-is-layout-flex\">\n<div class=\"wp-block-button has-custom-font-size\" style=\"font-size:15px\"><a class=\"wp-block-button__link has-white-color has-text-color has-background wp-element-button\" href=\"https:\/\/www.xlsoft.com\/jp\/products\/intel\/oneapi\/index.html\" style=\"border-radius:10px;background-color:#e64946\" target=\"_blank\" rel=\"noreferrer noopener\"><strong>\u958b\u767a\u30c4\u30fc\u30eb\u30b9\u30a4\u30fc\u30c8\u306e\u8a73\u7d30\u306f\u3053\u3061\u3089<\/strong><\/a><\/div>\n<\/div>\n<\/div>\n\n\n\n<div class=\"wp-block-column is-layout-flow wp-block-column-is-layout-flow\">\n<div class=\"wp-block-buttons is-layout-flex wp-block-buttons-is-layout-flex\">\n<div class=\"wp-block-button has-custom-font-size\" style=\"font-size:15px\"><a class=\"wp-block-button__link has-white-color has-text-color has-background wp-element-button\" href=\"https:\/\/www.xlsoft.com\/jp\/products\/intel\/purchase\/intel_license.html\" style=\"border-radius:10px;background-color:#e64946\" target=\"_blank\" rel=\"noreferrer noopener\"><strong>\u65e5\u672c\u8a9e\u30b5\u30dd\u30fc\u30c8\u306e\u5229\u7528\u306f\u3053\u3061\u3089<\/strong><\/a><\/div>\n<\/div>\n<\/div>\n<\/div>\n<\/div><\/div>\n","protected":false},"excerpt":{"rendered":"<div class=\"mh-excerpt\"><p>\u3053\u306e\u8a18\u4e8b\u306f\u3001\u30a4\u30f3\u30c6\u30eb\u306e\u30d6\u30ed\u30b0\u3067\u516c\u958b\u3055\u308c\u3066\u3044\u308b\u300cMi <a class=\"mh-excerpt-more\" href=\"https:\/\/www.xlsoft.com\/jp\/blog\/intel\/2024\/09\/24\/migrating-high-performance-flood-modelling-software-from-cuda-to-sycl\/\" title=\"oneAPI \u3092\u4f7f\u7528\u3057\u3066\u9ad8\u6027\u80fd\u6d2a\u6c34\u30e2\u30c7\u30ea\u30f3\u30b0\u30fb\u30bd\u30d5\u30c8\u30a6\u30a7\u30a2\u3092 CUDA* \u304b\u3089 SYCL* \u3078\u79fb\u884c\">[&#8230;]<\/a><\/p>\n<\/div>","protected":false},"author":1,"featured_media":3157,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[2],"tags":[14,33,131],"class_list":["post-3149","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-tech-tips","tag-oneapi","tag-sycl","tag--tiber-"],"aioseo_notices":[],"aioseo_head":"\n\t\t<!-- All in One SEO 5.0.0.1 - aioseo.com -->\n\t<meta name=\"description\" content=\"\u3053\u306e\u8a18\u4e8b\u306f\u3001\u30a4\u30f3\u30c6\u30eb\u306e\u30d6\u30ed\u30b0\u3067\u516c\u958b\u3055\u308c\u3066\u3044\u308b\u300cMigrating High-performance Flood\" \/>\n\t<meta name=\"robots\" content=\"max-image-preview:large\" \/>\n\t<meta name=\"author\" content=\"\u30a8\u30af\u30bb\u30eb\u30bd\u30d5\u30c8\"\/>\n\t<link rel=\"canonical\" href=\"https:\/\/www.xlsoft.com\/jp\/blog\/intel\/2024\/09\/24\/migrating-high-performance-flood-modelling-software-from-cuda-to-sycl\/\" \/>\n\t<meta name=\"generator\" content=\"All in One SEO (AIOSEO) 5.0.0.1\" \/>\n\n\t\t<script async src=\"https:\/\/www.googletagmanager.com\/gtag\/js?id=UA-2372005-1\"><\/script>\n<script>\n window.dataLayer = window.dataLayer || [];\n function gtag(){dataLayer.push(arguments);}\n gtag(\"js\", new Date());\n \n gtag('config', 'G-MH4P59ZD5Q');\n gtag(\"config\", \"UA-2372005-1\");\n gtag(\"config\", \"AW-1072573867\");\n<\/script>\n\t\t<meta property=\"og:locale\" content=\"ja_JP\" \/>\n\t\t<meta property=\"og:site_name\" content=\"\u30a4\u30f3\u30c6\u30eb\u30bd\u30d5\u30c8\u6700\u65b0\u60c5\u5831\u767a\u4fe1\u5c40 - \u30a4\u30f3\u30c6\u30eb\u00ae \u30bd\u30d5\u30c8\u30a6\u30a7\u30a2\u958b\u767a\u88fd\u54c1\u306e\u6700\u65b0\u60c5\u5831\u3092\u304a\u5c4a\u3051\u3057\u307e\u3059\u3002\" \/>\n\t\t<meta property=\"og:type\" content=\"article\" \/>\n\t\t<meta property=\"og:title\" content=\"oneAPI \u3092\u4f7f\u7528\u3057\u3066\u9ad8\u6027\u80fd\u6d2a\u6c34\u30e2\u30c7\u30ea\u30f3\u30b0\u30fb\u30bd\u30d5\u30c8\u30a6\u30a7\u30a2\u3092 CUDA* \u304b\u3089 SYCL* \u3078\u79fb\u884c - \u30a4\u30f3\u30c6\u30eb\u30bd\u30d5\u30c8\u6700\u65b0\u60c5\u5831\u767a\u4fe1\u5c40\" \/>\n\t\t<meta property=\"og:description\" content=\"\u3053\u306e\u8a18\u4e8b\u306f\u3001\u30a4\u30f3\u30c6\u30eb\u306e\u30d6\u30ed\u30b0\u3067\u516c\u958b\u3055\u308c\u3066\u3044\u308b\u300cMigrating High-performance Flood\" \/>\n\t\t<meta property=\"og:url\" content=\"https:\/\/www.xlsoft.com\/jp\/blog\/intel\/2024\/09\/24\/migrating-high-performance-flood-modelling-software-from-cuda-to-sycl\/\" \/>\n\t\t<meta property=\"article:published_time\" content=\"2024-09-23T23:00:00+00:00\" \/>\n\t\t<meta property=\"article:modified_time\" content=\"2024-09-20T16:16:51+00:00\" \/>\n\t\t<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n\t\t<meta name=\"twitter:title\" content=\"oneAPI \u3092\u4f7f\u7528\u3057\u3066\u9ad8\u6027\u80fd\u6d2a\u6c34\u30e2\u30c7\u30ea\u30f3\u30b0\u30fb\u30bd\u30d5\u30c8\u30a6\u30a7\u30a2\u3092 CUDA* \u304b\u3089 SYCL* \u3078\u79fb\u884c - \u30a4\u30f3\u30c6\u30eb\u30bd\u30d5\u30c8\u6700\u65b0\u60c5\u5831\u767a\u4fe1\u5c40\" \/>\n\t\t<meta name=\"twitter:description\" content=\"\u3053\u306e\u8a18\u4e8b\u306f\u3001\u30a4\u30f3\u30c6\u30eb\u306e\u30d6\u30ed\u30b0\u3067\u516c\u958b\u3055\u308c\u3066\u3044\u308b\u300cMigrating High-performance Flood\" \/>\n\t\t<script type=\"application\/ld+json\" class=\"aioseo-schema\">\n\t\t\t{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"BlogPosting\",\"@id\":\"https:\\\/\\\/www.xlsoft.com\\\/jp\\\/blog\\\/intel\\\/2024\\\/09\\\/24\\\/migrating-high-performance-flood-modelling-software-from-cuda-to-sycl\\\/#blogposting\",\"name\":\"oneAPI \\u3092\\u4f7f\\u7528\\u3057\\u3066\\u9ad8\\u6027\\u80fd\\u6d2a\\u6c34\\u30e2\\u30c7\\u30ea\\u30f3\\u30b0\\u30fb\\u30bd\\u30d5\\u30c8\\u30a6\\u30a7\\u30a2\\u3092 CUDA* \\u304b\\u3089 SYCL* \\u3078\\u79fb\\u884c - \\u30a4\\u30f3\\u30c6\\u30eb\\u30bd\\u30d5\\u30c8\\u6700\\u65b0\\u60c5\\u5831\\u767a\\u4fe1\\u5c40\",\"headline\":\"oneAPI \\u3092\\u4f7f\\u7528\\u3057\\u3066\\u9ad8\\u6027\\u80fd\\u6d2a\\u6c34\\u30e2\\u30c7\\u30ea\\u30f3\\u30b0\\u30fb\\u30bd\\u30d5\\u30c8\\u30a6\\u30a7\\u30a2\\u3092 CUDA* \\u304b\\u3089 SYCL* \\u3078\\u79fb\\u884c\",\"author\":{\"@id\":\"https:\\\/\\\/www.xlsoft.com\\\/jp\\\/blog\\\/intel\\\/author\\\/xlblog\\\/#author\"},\"publisher\":{\"@id\":\"https:\\\/\\\/www.xlsoft.com\\\/jp\\\/blog\\\/intel\\\/#organization\"},\"image\":{\"@type\":\"ImageObject\",\"url\":\"https:\\\/\\\/www.xlsoft.com\\\/jp\\\/blog\\\/intel\\\/wp-content\\\/uploads\\\/sites\\\/5\\\/2024\\\/09\\\/migrating-high-performance-Flood-modelling-software_thumbnail.png\",\"width\":310,\"height\":175},\"datePublished\":\"2024-09-24T08:00:00+09:00\",\"dateModified\":\"2024-09-21T01:16:51+09:00\",\"inLanguage\":\"ja\",\"mainEntityOfPage\":{\"@id\":\"https:\\\/\\\/www.xlsoft.com\\\/jp\\\/blog\\\/intel\\\/2024\\\/09\\\/24\\\/migrating-high-performance-flood-modelling-software-from-cuda-to-sycl\\\/#webpage\"},\"isPartOf\":{\"@id\":\"https:\\\/\\\/www.xlsoft.com\\\/jp\\\/blog\\\/intel\\\/2024\\\/09\\\/24\\\/migrating-high-performance-flood-modelling-software-from-cuda-to-sycl\\\/#webpage\"},\"articleSection\":\"Tech Tips, oneAPI, SYCL, \\u30a4\\u30f3\\u30c6\\u30eb Tiber \\u30c7\\u30d9\\u30ed\\u30c3\\u30d1\\u30fc\\u30fb\\u30af\\u30e9\\u30a6\\u30c9\"},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\\\/\\\/www.xlsoft.com\\\/jp\\\/blog\\\/intel\\\/2024\\\/09\\\/24\\\/migrating-high-performance-flood-modelling-software-from-cuda-to-sycl\\\/#breadcrumblist\",\"itemListElement\":[{\"@type\":\"ListItem\",\"@id\":\"https:\\\/\\\/www.xlsoft.com\\\/jp\\\/blog\\\/intel#listItem\",\"position\":1,\"name\":\"\\u30db\\u30fc\\u30e0\",\"item\":\"https:\\\/\\\/www.xlsoft.com\\\/jp\\\/blog\\\/intel\",\"nextItem\":{\"@type\":\"ListItem\",\"@id\":\"https:\\\/\\\/www.xlsoft.com\\\/jp\\\/blog\\\/intel\\\/category\\\/tech-tips\\\/#listItem\",\"name\":\"Tech Tips\"}},{\"@type\":\"ListItem\",\"@id\":\"https:\\\/\\\/www.xlsoft.com\\\/jp\\\/blog\\\/intel\\\/category\\\/tech-tips\\\/#listItem\",\"position\":2,\"name\":\"Tech Tips\",\"item\":\"https:\\\/\\\/www.xlsoft.com\\\/jp\\\/blog\\\/intel\\\/category\\\/tech-tips\\\/\",\"nextItem\":{\"@type\":\"ListItem\",\"@id\":\"https:\\\/\\\/www.xlsoft.com\\\/jp\\\/blog\\\/intel\\\/2024\\\/09\\\/24\\\/migrating-high-performance-flood-modelling-software-from-cuda-to-sycl\\\/#listItem\",\"name\":\"oneAPI \\u3092\\u4f7f\\u7528\\u3057\\u3066\\u9ad8\\u6027\\u80fd\\u6d2a\\u6c34\\u30e2\\u30c7\\u30ea\\u30f3\\u30b0\\u30fb\\u30bd\\u30d5\\u30c8\\u30a6\\u30a7\\u30a2\\u3092 CUDA* \\u304b\\u3089 SYCL* \\u3078\\u79fb\\u884c\"},\"previousItem\":{\"@type\":\"ListItem\",\"@id\":\"https:\\\/\\\/www.xlsoft.com\\\/jp\\\/blog\\\/intel#listItem\",\"name\":\"\\u30db\\u30fc\\u30e0\"}},{\"@type\":\"ListItem\",\"@id\":\"https:\\\/\\\/www.xlsoft.com\\\/jp\\\/blog\\\/intel\\\/2024\\\/09\\\/24\\\/migrating-high-performance-flood-modelling-software-from-cuda-to-sycl\\\/#listItem\",\"position\":3,\"name\":\"oneAPI \\u3092\\u4f7f\\u7528\\u3057\\u3066\\u9ad8\\u6027\\u80fd\\u6d2a\\u6c34\\u30e2\\u30c7\\u30ea\\u30f3\\u30b0\\u30fb\\u30bd\\u30d5\\u30c8\\u30a6\\u30a7\\u30a2\\u3092 CUDA* \\u304b\\u3089 SYCL* \\u3078\\u79fb\\u884c\",\"previousItem\":{\"@type\":\"ListItem\",\"@id\":\"https:\\\/\\\/www.xlsoft.com\\\/jp\\\/blog\\\/intel\\\/category\\\/tech-tips\\\/#listItem\",\"name\":\"Tech Tips\"}}]},{\"@type\":\"Organization\",\"@id\":\"https:\\\/\\\/www.xlsoft.com\\\/jp\\\/blog\\\/intel\\\/#organization\",\"name\":\"\\u30a4\\u30f3\\u30c6\\u30eb\\u30bd\\u30d5\\u30c8\\u6700\\u65b0\\u60c5\\u5831\\u767a\\u4fe1\\u5c40\",\"description\":\"\\u30a4\\u30f3\\u30c6\\u30eb\\u00ae \\u30bd\\u30d5\\u30c8\\u30a6\\u30a7\\u30a2\\u958b\\u767a\\u88fd\\u54c1\\u306e\\u6700\\u65b0\\u60c5\\u5831\\u3092\\u304a\\u5c4a\\u3051\\u3057\\u307e\\u3059\\u3002\",\"url\":\"https:\\\/\\\/www.xlsoft.com\\\/jp\\\/blog\\\/intel\\\/\"},{\"@type\":\"Person\",\"@id\":\"https:\\\/\\\/www.xlsoft.com\\\/jp\\\/blog\\\/intel\\\/author\\\/xlblog\\\/#author\",\"url\":\"https:\\\/\\\/www.xlsoft.com\\\/jp\\\/blog\\\/intel\\\/author\\\/xlblog\\\/\",\"name\":\"\\u30a8\\u30af\\u30bb\\u30eb\\u30bd\\u30d5\\u30c8\"},{\"@type\":\"WebPage\",\"@id\":\"https:\\\/\\\/www.xlsoft.com\\\/jp\\\/blog\\\/intel\\\/2024\\\/09\\\/24\\\/migrating-high-performance-flood-modelling-software-from-cuda-to-sycl\\\/#webpage\",\"url\":\"https:\\\/\\\/www.xlsoft.com\\\/jp\\\/blog\\\/intel\\\/2024\\\/09\\\/24\\\/migrating-high-performance-flood-modelling-software-from-cuda-to-sycl\\\/\",\"name\":\"oneAPI \\u3092\\u4f7f\\u7528\\u3057\\u3066\\u9ad8\\u6027\\u80fd\\u6d2a\\u6c34\\u30e2\\u30c7\\u30ea\\u30f3\\u30b0\\u30fb\\u30bd\\u30d5\\u30c8\\u30a6\\u30a7\\u30a2\\u3092 CUDA* \\u304b\\u3089 SYCL* \\u3078\\u79fb\\u884c - \\u30a4\\u30f3\\u30c6\\u30eb\\u30bd\\u30d5\\u30c8\\u6700\\u65b0\\u60c5\\u5831\\u767a\\u4fe1\\u5c40\",\"description\":\"\\u3053\\u306e\\u8a18\\u4e8b\\u306f\\u3001\\u30a4\\u30f3\\u30c6\\u30eb\\u306e\\u30d6\\u30ed\\u30b0\\u3067\\u516c\\u958b\\u3055\\u308c\\u3066\\u3044\\u308b\\u300cMigrating High-performance Flood\",\"inLanguage\":\"ja\",\"isPartOf\":{\"@id\":\"https:\\\/\\\/www.xlsoft.com\\\/jp\\\/blog\\\/intel\\\/#website\"},\"breadcrumb\":{\"@id\":\"https:\\\/\\\/www.xlsoft.com\\\/jp\\\/blog\\\/intel\\\/2024\\\/09\\\/24\\\/migrating-high-performance-flood-modelling-software-from-cuda-to-sycl\\\/#breadcrumblist\"},\"author\":{\"@id\":\"https:\\\/\\\/www.xlsoft.com\\\/jp\\\/blog\\\/intel\\\/author\\\/xlblog\\\/#author\"},\"creator\":{\"@id\":\"https:\\\/\\\/www.xlsoft.com\\\/jp\\\/blog\\\/intel\\\/author\\\/xlblog\\\/#author\"},\"image\":{\"@type\":\"ImageObject\",\"url\":\"https:\\\/\\\/www.xlsoft.com\\\/jp\\\/blog\\\/intel\\\/wp-content\\\/uploads\\\/sites\\\/5\\\/2024\\\/09\\\/migrating-high-performance-Flood-modelling-software_thumbnail.png\",\"@id\":\"https:\\\/\\\/www.xlsoft.com\\\/jp\\\/blog\\\/intel\\\/2024\\\/09\\\/24\\\/migrating-high-performance-flood-modelling-software-from-cuda-to-sycl\\\/#mainImage\",\"width\":310,\"height\":175},\"primaryImageOfPage\":{\"@id\":\"https:\\\/\\\/www.xlsoft.com\\\/jp\\\/blog\\\/intel\\\/2024\\\/09\\\/24\\\/migrating-high-performance-flood-modelling-software-from-cuda-to-sycl\\\/#mainImage\"},\"datePublished\":\"2024-09-24T08:00:00+09:00\",\"dateModified\":\"2024-09-21T01:16:51+09:00\"},{\"@type\":\"WebSite\",\"@id\":\"https:\\\/\\\/www.xlsoft.com\\\/jp\\\/blog\\\/intel\\\/#website\",\"url\":\"https:\\\/\\\/www.xlsoft.com\\\/jp\\\/blog\\\/intel\\\/\",\"name\":\"\\u30a4\\u30f3\\u30c6\\u30eb\\u30bd\\u30d5\\u30c8\\u6700\\u65b0\\u60c5\\u5831\\u767a\\u4fe1\\u5c40\",\"description\":\"\\u30a4\\u30f3\\u30c6\\u30eb\\u00ae \\u30bd\\u30d5\\u30c8\\u30a6\\u30a7\\u30a2\\u958b\\u767a\\u88fd\\u54c1\\u306e\\u6700\\u65b0\\u60c5\\u5831\\u3092\\u304a\\u5c4a\\u3051\\u3057\\u307e\\u3059\\u3002\",\"inLanguage\":\"ja\",\"publisher\":{\"@id\":\"https:\\\/\\\/www.xlsoft.com\\\/jp\\\/blog\\\/intel\\\/#organization\"}}]}\n\t\t<\/script>\n\t\t<!-- All in One SEO -->\n\n","aioseo_head_json":{"title":"oneAPI \u3092\u4f7f\u7528\u3057\u3066\u9ad8\u6027\u80fd\u6d2a\u6c34\u30e2\u30c7\u30ea\u30f3\u30b0\u30fb\u30bd\u30d5\u30c8\u30a6\u30a7\u30a2\u3092 CUDA* \u304b\u3089 SYCL* \u3078\u79fb\u884c - \u30a4\u30f3\u30c6\u30eb\u30bd\u30d5\u30c8\u6700\u65b0\u60c5\u5831\u767a\u4fe1\u5c40","description":"\u3053\u306e\u8a18\u4e8b\u306f\u3001\u30a4\u30f3\u30c6\u30eb\u306e\u30d6\u30ed\u30b0\u3067\u516c\u958b\u3055\u308c\u3066\u3044\u308b\u300cMigrating High-performance Flood","canonical_url":"https:\/\/www.xlsoft.com\/jp\/blog\/intel\/2024\/09\/24\/migrating-high-performance-flood-modelling-software-from-cuda-to-sycl\/","robots":"max-image-preview:large","keywords":"","webmasterTools":{"miscellaneous":"&lt;script async src=\"https:\/\/www.googletagmanager.com\/gtag\/js?id=UA-2372005-1\"&gt;&lt;\/script&gt;\n&lt;script&gt;\n window.dataLayer = window.dataLayer || [];\n function gtag(){dataLayer.push(arguments);}\n gtag(\"js\", new Date());\n \n gtag('config', 'G-MH4P59ZD5Q');\n gtag(\"config\", \"UA-2372005-1\");\n gtag(\"config\", \"AW-1072573867\");\n&lt;\/script&gt;"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"BlogPosting","@id":"https:\/\/www.xlsoft.com\/jp\/blog\/intel\/2024\/09\/24\/migrating-high-performance-flood-modelling-software-from-cuda-to-sycl\/#blogposting","name":"oneAPI \u3092\u4f7f\u7528\u3057\u3066\u9ad8\u6027\u80fd\u6d2a\u6c34\u30e2\u30c7\u30ea\u30f3\u30b0\u30fb\u30bd\u30d5\u30c8\u30a6\u30a7\u30a2\u3092 CUDA* \u304b\u3089 SYCL* \u3078\u79fb\u884c - \u30a4\u30f3\u30c6\u30eb\u30bd\u30d5\u30c8\u6700\u65b0\u60c5\u5831\u767a\u4fe1\u5c40","headline":"oneAPI \u3092\u4f7f\u7528\u3057\u3066\u9ad8\u6027\u80fd\u6d2a\u6c34\u30e2\u30c7\u30ea\u30f3\u30b0\u30fb\u30bd\u30d5\u30c8\u30a6\u30a7\u30a2\u3092 CUDA* \u304b\u3089 SYCL* \u3078\u79fb\u884c","author":{"@id":"https:\/\/www.xlsoft.com\/jp\/blog\/intel\/author\/xlblog\/#author"},"publisher":{"@id":"https:\/\/www.xlsoft.com\/jp\/blog\/intel\/#organization"},"image":{"@type":"ImageObject","url":"https:\/\/www.xlsoft.com\/jp\/blog\/intel\/wp-content\/uploads\/sites\/5\/2024\/09\/migrating-high-performance-Flood-modelling-software_thumbnail.png","width":310,"height":175},"datePublished":"2024-09-24T08:00:00+09:00","dateModified":"2024-09-21T01:16:51+09:00","inLanguage":"ja","mainEntityOfPage":{"@id":"https:\/\/www.xlsoft.com\/jp\/blog\/intel\/2024\/09\/24\/migrating-high-performance-flood-modelling-software-from-cuda-to-sycl\/#webpage"},"isPartOf":{"@id":"https:\/\/www.xlsoft.com\/jp\/blog\/intel\/2024\/09\/24\/migrating-high-performance-flood-modelling-software-from-cuda-to-sycl\/#webpage"},"articleSection":"Tech Tips, oneAPI, SYCL, \u30a4\u30f3\u30c6\u30eb Tiber \u30c7\u30d9\u30ed\u30c3\u30d1\u30fc\u30fb\u30af\u30e9\u30a6\u30c9"},{"@type":"BreadcrumbList","@id":"https:\/\/www.xlsoft.com\/jp\/blog\/intel\/2024\/09\/24\/migrating-high-performance-flood-modelling-software-from-cuda-to-sycl\/#breadcrumblist","itemListElement":[{"@type":"ListItem","@id":"https:\/\/www.xlsoft.com\/jp\/blog\/intel#listItem","position":1,"name":"\u30db\u30fc\u30e0","item":"https:\/\/www.xlsoft.com\/jp\/blog\/intel","nextItem":{"@type":"ListItem","@id":"https:\/\/www.xlsoft.com\/jp\/blog\/intel\/category\/tech-tips\/#listItem","name":"Tech Tips"}},{"@type":"ListItem","@id":"https:\/\/www.xlsoft.com\/jp\/blog\/intel\/category\/tech-tips\/#listItem","position":2,"name":"Tech Tips","item":"https:\/\/www.xlsoft.com\/jp\/blog\/intel\/category\/tech-tips\/","nextItem":{"@type":"ListItem","@id":"https:\/\/www.xlsoft.com\/jp\/blog\/intel\/2024\/09\/24\/migrating-high-performance-flood-modelling-software-from-cuda-to-sycl\/#listItem","name":"oneAPI \u3092\u4f7f\u7528\u3057\u3066\u9ad8\u6027\u80fd\u6d2a\u6c34\u30e2\u30c7\u30ea\u30f3\u30b0\u30fb\u30bd\u30d5\u30c8\u30a6\u30a7\u30a2\u3092 CUDA* \u304b\u3089 SYCL* \u3078\u79fb\u884c"},"previousItem":{"@type":"ListItem","@id":"https:\/\/www.xlsoft.com\/jp\/blog\/intel#listItem","name":"\u30db\u30fc\u30e0"}},{"@type":"ListItem","@id":"https:\/\/www.xlsoft.com\/jp\/blog\/intel\/2024\/09\/24\/migrating-high-performance-flood-modelling-software-from-cuda-to-sycl\/#listItem","position":3,"name":"oneAPI \u3092\u4f7f\u7528\u3057\u3066\u9ad8\u6027\u80fd\u6d2a\u6c34\u30e2\u30c7\u30ea\u30f3\u30b0\u30fb\u30bd\u30d5\u30c8\u30a6\u30a7\u30a2\u3092 CUDA* \u304b\u3089 SYCL* \u3078\u79fb\u884c","previousItem":{"@type":"ListItem","@id":"https:\/\/www.xlsoft.com\/jp\/blog\/intel\/category\/tech-tips\/#listItem","name":"Tech Tips"}}]},{"@type":"Organization","@id":"https:\/\/www.xlsoft.com\/jp\/blog\/intel\/#organization","name":"\u30a4\u30f3\u30c6\u30eb\u30bd\u30d5\u30c8\u6700\u65b0\u60c5\u5831\u767a\u4fe1\u5c40","description":"\u30a4\u30f3\u30c6\u30eb\u00ae \u30bd\u30d5\u30c8\u30a6\u30a7\u30a2\u958b\u767a\u88fd\u54c1\u306e\u6700\u65b0\u60c5\u5831\u3092\u304a\u5c4a\u3051\u3057\u307e\u3059\u3002","url":"https:\/\/www.xlsoft.com\/jp\/blog\/intel\/"},{"@type":"Person","@id":"https:\/\/www.xlsoft.com\/jp\/blog\/intel\/author\/xlblog\/#author","url":"https:\/\/www.xlsoft.com\/jp\/blog\/intel\/author\/xlblog\/","name":"\u30a8\u30af\u30bb\u30eb\u30bd\u30d5\u30c8"},{"@type":"WebPage","@id":"https:\/\/www.xlsoft.com\/jp\/blog\/intel\/2024\/09\/24\/migrating-high-performance-flood-modelling-software-from-cuda-to-sycl\/#webpage","url":"https:\/\/www.xlsoft.com\/jp\/blog\/intel\/2024\/09\/24\/migrating-high-performance-flood-modelling-software-from-cuda-to-sycl\/","name":"oneAPI \u3092\u4f7f\u7528\u3057\u3066\u9ad8\u6027\u80fd\u6d2a\u6c34\u30e2\u30c7\u30ea\u30f3\u30b0\u30fb\u30bd\u30d5\u30c8\u30a6\u30a7\u30a2\u3092 CUDA* \u304b\u3089 SYCL* \u3078\u79fb\u884c - \u30a4\u30f3\u30c6\u30eb\u30bd\u30d5\u30c8\u6700\u65b0\u60c5\u5831\u767a\u4fe1\u5c40","description":"\u3053\u306e\u8a18\u4e8b\u306f\u3001\u30a4\u30f3\u30c6\u30eb\u306e\u30d6\u30ed\u30b0\u3067\u516c\u958b\u3055\u308c\u3066\u3044\u308b\u300cMigrating High-performance Flood","inLanguage":"ja","isPartOf":{"@id":"https:\/\/www.xlsoft.com\/jp\/blog\/intel\/#website"},"breadcrumb":{"@id":"https:\/\/www.xlsoft.com\/jp\/blog\/intel\/2024\/09\/24\/migrating-high-performance-flood-modelling-software-from-cuda-to-sycl\/#breadcrumblist"},"author":{"@id":"https:\/\/www.xlsoft.com\/jp\/blog\/intel\/author\/xlblog\/#author"},"creator":{"@id":"https:\/\/www.xlsoft.com\/jp\/blog\/intel\/author\/xlblog\/#author"},"image":{"@type":"ImageObject","url":"https:\/\/www.xlsoft.com\/jp\/blog\/intel\/wp-content\/uploads\/sites\/5\/2024\/09\/migrating-high-performance-Flood-modelling-software_thumbnail.png","@id":"https:\/\/www.xlsoft.com\/jp\/blog\/intel\/2024\/09\/24\/migrating-high-performance-flood-modelling-software-from-cuda-to-sycl\/#mainImage","width":310,"height":175},"primaryImageOfPage":{"@id":"https:\/\/www.xlsoft.com\/jp\/blog\/intel\/2024\/09\/24\/migrating-high-performance-flood-modelling-software-from-cuda-to-sycl\/#mainImage"},"datePublished":"2024-09-24T08:00:00+09:00","dateModified":"2024-09-21T01:16:51+09:00"},{"@type":"WebSite","@id":"https:\/\/www.xlsoft.com\/jp\/blog\/intel\/#website","url":"https:\/\/www.xlsoft.com\/jp\/blog\/intel\/","name":"\u30a4\u30f3\u30c6\u30eb\u30bd\u30d5\u30c8\u6700\u65b0\u60c5\u5831\u767a\u4fe1\u5c40","description":"\u30a4\u30f3\u30c6\u30eb\u00ae \u30bd\u30d5\u30c8\u30a6\u30a7\u30a2\u958b\u767a\u88fd\u54c1\u306e\u6700\u65b0\u60c5\u5831\u3092\u304a\u5c4a\u3051\u3057\u307e\u3059\u3002","inLanguage":"ja","publisher":{"@id":"https:\/\/www.xlsoft.com\/jp\/blog\/intel\/#organization"}}]},"og:locale":"ja_JP","og:site_name":"\u30a4\u30f3\u30c6\u30eb\u30bd\u30d5\u30c8\u6700\u65b0\u60c5\u5831\u767a\u4fe1\u5c40 - \u30a4\u30f3\u30c6\u30eb\u00ae \u30bd\u30d5\u30c8\u30a6\u30a7\u30a2\u958b\u767a\u88fd\u54c1\u306e\u6700\u65b0\u60c5\u5831\u3092\u304a\u5c4a\u3051\u3057\u307e\u3059\u3002","og:type":"article","og:title":"oneAPI \u3092\u4f7f\u7528\u3057\u3066\u9ad8\u6027\u80fd\u6d2a\u6c34\u30e2\u30c7\u30ea\u30f3\u30b0\u30fb\u30bd\u30d5\u30c8\u30a6\u30a7\u30a2\u3092 CUDA* \u304b\u3089 SYCL* \u3078\u79fb\u884c - \u30a4\u30f3\u30c6\u30eb\u30bd\u30d5\u30c8\u6700\u65b0\u60c5\u5831\u767a\u4fe1\u5c40","og:description":"\u3053\u306e\u8a18\u4e8b\u306f\u3001\u30a4\u30f3\u30c6\u30eb\u306e\u30d6\u30ed\u30b0\u3067\u516c\u958b\u3055\u308c\u3066\u3044\u308b\u300cMigrating High-performance Flood","og:url":"https:\/\/www.xlsoft.com\/jp\/blog\/intel\/2024\/09\/24\/migrating-high-performance-flood-modelling-software-from-cuda-to-sycl\/","article:published_time":"2024-09-23T23:00:00+00:00","article:modified_time":"2024-09-20T16:16:51+00:00","twitter:card":"summary_large_image","twitter:title":"oneAPI \u3092\u4f7f\u7528\u3057\u3066\u9ad8\u6027\u80fd\u6d2a\u6c34\u30e2\u30c7\u30ea\u30f3\u30b0\u30fb\u30bd\u30d5\u30c8\u30a6\u30a7\u30a2\u3092 CUDA* \u304b\u3089 SYCL* \u3078\u79fb\u884c - \u30a4\u30f3\u30c6\u30eb\u30bd\u30d5\u30c8\u6700\u65b0\u60c5\u5831\u767a\u4fe1\u5c40","twitter:description":"\u3053\u306e\u8a18\u4e8b\u306f\u3001\u30a4\u30f3\u30c6\u30eb\u306e\u30d6\u30ed\u30b0\u3067\u516c\u958b\u3055\u308c\u3066\u3044\u308b\u300cMigrating High-performance Flood"},"aioseo_meta_data":{"post_id":"3149","title":null,"description":null,"keywords":[],"keyphrases":{"focus":{"keyphrase":"","score":0,"analysis":{"keyphraseInTitle":{"score":0,"maxScore":9,"error":1}}},"additional":[]},"primary_term":null,"canonical_url":null,"og_title":null,"og_description":null,"og_object_type":"default","og_image_type":"default","og_image_url":null,"og_image_width":null,"og_image_height":null,"og_image_custom_url":null,"og_image_custom_fields":null,"og_video":"","og_custom_url":null,"og_article_section":null,"og_article_tags":[],"twitter_use_og":false,"twitter_card":"default","twitter_image_type":"default","twitter_image_url":null,"twitter_image_custom_url":null,"twitter_image_custom_fields":null,"twitter_title":null,"twitter_description":null,"schema":{"blockGraphs":[],"customGraphs":[],"default":{"data":{"Article":[],"Course":[],"Dataset":[],"FAQPage":[],"Movie":[],"Person":[],"Product":[],"ProductReview":[],"Car":[],"Recipe":[],"Service":[],"SoftwareApplication":[],"WebPage":[]},"graphName":"BlogPosting","isEnabled":true},"graphs":[]},"schema_type":"default","schema_type_options":null,"pillar_content":false,"robots_default":true,"robots_noindex":false,"robots_noarchive":false,"robots_nosnippet":false,"robots_nofollow":false,"robots_noimageindex":false,"robots_noodp":false,"robots_notranslate":false,"robots_max_snippet":"-1","robots_max_videopreview":"-1","robots_max_imagepreview":"large","priority":null,"frequency":"default","local_seo":null,"breadcrumb_settings":null,"limit_modified_date":false,"ai":null,"created":"2024-09-19 18:07:29","updated":"2026-04-16 18:02:56","focus_keyword":null,"additional_keywords":null,"truseo_locale":null,"seo_analyzer_scan_date":null},"aioseo_breadcrumb":"<div class=\"aioseo-breadcrumbs\"><span class=\"aioseo-breadcrumb\">\n\t\t\t<a href=\"https:\/\/www.xlsoft.com\/jp\/blog\/intel\" title=\"\u30db\u30fc\u30e0\">\u30db\u30fc\u30e0<\/a>\n\t\t<\/span><span class=\"aioseo-breadcrumb-separator\">&raquo;<\/span><span class=\"aioseo-breadcrumb\">\n\t\t\t<a href=\"https:\/\/www.xlsoft.com\/jp\/blog\/intel\/category\/tech-tips\/\" title=\"Tech Tips\">Tech Tips<\/a>\n\t\t<\/span><span class=\"aioseo-breadcrumb-separator\">&raquo;<\/span><span class=\"aioseo-breadcrumb\">\n\t\t\toneAPI \u3092\u4f7f\u7528\u3057\u3066\u9ad8\u6027\u80fd\u6d2a\u6c34\u30e2\u30c7\u30ea\u30f3\u30b0\u30fb\u30bd\u30d5\u30c8\u30a6\u30a7\u30a2\u3092 CUDA* \u304b\u3089 SYCL* \u3078\u79fb\u884c\n\t\t<\/span><\/div>","aioseo_breadcrumb_json":[{"label":"\u30db\u30fc\u30e0","link":"https:\/\/www.xlsoft.com\/jp\/blog\/intel"},{"label":"Tech Tips","link":"https:\/\/www.xlsoft.com\/jp\/blog\/intel\/category\/tech-tips\/"},{"label":"oneAPI \u3092\u4f7f\u7528\u3057\u3066\u9ad8\u6027\u80fd\u6d2a\u6c34\u30e2\u30c7\u30ea\u30f3\u30b0\u30fb\u30bd\u30d5\u30c8\u30a6\u30a7\u30a2\u3092 CUDA* \u304b\u3089 SYCL* \u3078\u79fb\u884c","link":"https:\/\/www.xlsoft.com\/jp\/blog\/intel\/2024\/09\/24\/migrating-high-performance-flood-modelling-software-from-cuda-to-sycl\/"}],"_links":{"self":[{"href":"https:\/\/www.xlsoft.com\/jp\/blog\/intel\/wp-json\/wp\/v2\/posts\/3149","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.xlsoft.com\/jp\/blog\/intel\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.xlsoft.com\/jp\/blog\/intel\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.xlsoft.com\/jp\/blog\/intel\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.xlsoft.com\/jp\/blog\/intel\/wp-json\/wp\/v2\/comments?post=3149"}],"version-history":[{"count":6,"href":"https:\/\/www.xlsoft.com\/jp\/blog\/intel\/wp-json\/wp\/v2\/posts\/3149\/revisions"}],"predecessor-version":[{"id":3160,"href":"https:\/\/www.xlsoft.com\/jp\/blog\/intel\/wp-json\/wp\/v2\/posts\/3149\/revisions\/3160"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.xlsoft.com\/jp\/blog\/intel\/wp-json\/wp\/v2\/media\/3157"}],"wp:attachment":[{"href":"https:\/\/www.xlsoft.com\/jp\/blog\/intel\/wp-json\/wp\/v2\/media?parent=3149"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.xlsoft.com\/jp\/blog\/intel\/wp-json\/wp\/v2\/categories?post=3149"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.xlsoft.com\/jp\/blog\/intel\/wp-json\/wp\/v2\/tags?post=3149"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}