{"id":61554,"date":"2024-10-23T02:37:06","date_gmt":"2024-10-23T06:37:06","guid":{"rendered":"https:\/\/blogs.sw.siemens.com\/simcenter\/?p=61554"},"modified":"2026-03-26T06:51:23","modified_gmt":"2026-03-26T10:51:23","slug":"faster-sph-on-gpus-windows-support","status":"publish","type":"post","link":"https:\/\/blogs.sw.siemens.com\/simcenter\/faster-sph-on-gpus-windows-support\/","title":{"rendered":"Unlock faster SPH on GPUs, higher fidelity with surface tension, stronger on any operating system"},"content":{"rendered":"\n<blockquote class=\"wp-block-quote is-layout-flow wp-block-quote-is-layout-flow\">\n<p>\u201c<em>Citius, Altius, Fortius<\/em>\u201d \u2013 Faster, Higher, Stronger. <\/p>\n<cite>Or: SPH on GPUs on Windows<\/cite><\/blockquote>\n\n\n\n<p>As we both live in France, we are slowly coming down from the exhilarating vibe of the big sports games on this planet that recently took place in Paris, exactly one hundred years after the last edition in France. Watching all these athletes from so many nations who worked tirelessly to go faster, jump higher and be stronger was truly inspiring.<\/p>\n\n\n\n<div class=\"wp-block-media-text is-stacked-on-mobile\"><figure class=\"wp-block-media-text__media\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"668\" src=\"https:\/\/blogs.sw.siemens.com\/wp-content\/uploads\/sites\/6\/2024\/10\/GettyImages-2149936871-1024x668.jpg\" alt=\"\" class=\"wp-image-61575 size-full\" srcset=\"https:\/\/blogs.sw.siemens.com\/wp-content\/uploads\/sites\/6\/2024\/10\/GettyImages-2149936871-1024x668.jpg 1024w, https:\/\/blogs.sw.siemens.com\/wp-content\/uploads\/sites\/6\/2024\/10\/GettyImages-2149936871-600x392.jpg 600w, https:\/\/blogs.sw.siemens.com\/wp-content\/uploads\/sites\/6\/2024\/10\/GettyImages-2149936871-768x501.jpg 768w, https:\/\/blogs.sw.siemens.com\/wp-content\/uploads\/sites\/6\/2024\/10\/GettyImages-2149936871-1536x1003.jpg 1536w, https:\/\/blogs.sw.siemens.com\/wp-content\/uploads\/sites\/6\/2024\/10\/GettyImages-2149936871-2048x1337.jpg 2048w, https:\/\/blogs.sw.siemens.com\/wp-content\/uploads\/sites\/6\/2024\/10\/GettyImages-2149936871-900x588.jpg 900w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><\/figure><div class=\"wp-block-media-text__content\">\n<p>What better example than that of L\u00e9on Marchand dazzling the whole world, and magnificent in his smooth, fast swimming to win 4 gold medals for France? Or Armand Duplantis pole-vaulting ever higher to reach the skies and beat his own world record for the 9th time in a row! Sweden at the top! And one more for the road: probably the greatest wrestler of all time, Mija\u00edn L\u00f3pez N\u00fa\u00f1ez from Cuba, putting the finishing touches to his masterpiece with a 5th gold medal in the Greco-Roman event. Simply the strongest!<\/p>\n<\/div><\/div>\n\n\n\n<h2 class=\"wp-block-heading\"><br>The everlasting development marathon<\/h2>\n\n\n\n<p>With Simcenter STAR-CCM+ 2410, you\u2019ll notice some parallels: developers, product managers, quality engineers and many more CFD athletes from all across the globe worked hard to excel in their respective discipline. But there is one difference to the athletes at the big games. Our software engineers did not do this for their nation, their teams or themselves. They did this for you, the user of our software: to make you go faster to market, create products that perform higher and be stronger in a competitive world!<br>In keeping with the scrupulous, intense efforts over the years, this release is the result of dedicated hard work aimed at making your simulations faster and stronger. And all that without breaking a sweat, we promise!<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">\u201cCitius\u201d, go faster with SPH on GPUs<\/h2>\n\n\n\n<figure class=\"wp-block-video\"><video controls poster=\"https:\/\/blogs.sw.siemens.com\/wp-content\/uploads\/sites\/6\/2024\/10\/Untitled-Project-Time-0_00_0801.png\" src=\"https:\/\/videos.mentor-cdn.com\/mgc\/videos\/5400\/585e68f0-9f23-41a9-ba75-0035648e0ed6-en-US-video.mp4\"><\/video><\/figure>\n\n\n\n<p>Back at the beginning of this year, <a href=\"https:\/\/blogs.sw.siemens.com\/simcenter\/simcenter-star-ccm-2402-released\/\" target=\"_blank\" rel=\"noreferrer noopener\">Simcenter STAR-CCM+ 2402 marked an important milestone<\/a> with the introduction of the Smoothed Particle Hydrodynamics (SPH) solver, designed to simulate highly dynamic free surface flow applications in a faster manner. Since then and like L\u00e9on Marchand, we have continuously ridden the wave of the SPH solver to enhance it and add new capabilities with each release.<br>In parallel, our GPU journey has evolved similarly. With version 2410, we celebrate the 9th release and over two years since the introduction of <a href=\"https:\/\/blogs.sw.siemens.com\/simcenter\/gpu-acceleration-for-cfd-simulation\/\" target=\"_blank\" rel=\"noreferrer noopener\">our original GPU-accelerated CFD functionality<\/a>.<\/p>\n\n\n\n<figure class=\"wp-block-embed is-type-video is-provider-youtube wp-block-embed-youtube wp-embed-aspect-16-9 wp-has-aspect-ratio\"><div class=\"wp-block-embed__wrapper\">\n<iframe loading=\"lazy\" title=\"GPU enabled acceleration of CFD simulation | Simcenter STAR-CCM+ #SimcenterCFD #SimcenterVehicle\" width=\"640\" height=\"360\" src=\"https:\/\/www.youtube.com\/embed\/1FiDLliDSkc?feature=oembed\" frameborder=\"0\" allow=\"accelerometer; autoplay; clipboard-write; encrypted-media; gyroscope; picture-in-picture; web-share\" referrerpolicy=\"strict-origin-when-cross-origin\" allowfullscreen><\/iframe>\n<\/div><\/figure>\n\n\n\n<p>Now, with Simcenter STAR-CCM+ 2410, these two streams converge to achieve another significant milestone: SPH on GPUs. In this new release, you can now significantly accelerate your powertrain lubrication simulations on single GPUs, thanks to the GPU-native implementation of the SPH solver.<br><\/p>\n\n\n\n<h3 class=\"wp-block-heading\">Faster gearbox lubrication simulations <\/h3>\n\n\n\n<p>To understand the benefits of running SPH on GPUs let&#8217;s look at the industrial gearbox lubrication example below, the GPU-native SPH solver running on a single <a href=\"https:\/\/www.nvidia.com\/en-us\/data-center\/a100\/\" target=\"_blank\" rel=\"noreferrer noopener\">NVIDIA A100 GPU<\/a> can deliver up to a 9x speed up compared to a 64-core CPU. All currently available models for the SPH solver have been ported to GPU, reducing the simulation time of this industrial gearbox lubrication application to less than an hour.<\/p>\n\n\n\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"550\" src=\"https:\/\/blogs.sw.siemens.com\/wp-content\/uploads\/sites\/6\/2024\/10\/GPU_SPH_Gearbox_CFD_2-1024x550.png\" alt=\"\" class=\"wp-image-61562\" srcset=\"https:\/\/blogs.sw.siemens.com\/wp-content\/uploads\/sites\/6\/2024\/10\/GPU_SPH_Gearbox_CFD_2-1024x550.png 1024w, https:\/\/blogs.sw.siemens.com\/wp-content\/uploads\/sites\/6\/2024\/10\/GPU_SPH_Gearbox_CFD_2-600x322.png 600w, https:\/\/blogs.sw.siemens.com\/wp-content\/uploads\/sites\/6\/2024\/10\/GPU_SPH_Gearbox_CFD_2-768x412.png 768w, https:\/\/blogs.sw.siemens.com\/wp-content\/uploads\/sites\/6\/2024\/10\/GPU_SPH_Gearbox_CFD_2-1536x824.png 1536w, https:\/\/blogs.sw.siemens.com\/wp-content\/uploads\/sites\/6\/2024\/10\/GPU_SPH_Gearbox_CFD_2-2048x1099.png 2048w, https:\/\/blogs.sw.siemens.com\/wp-content\/uploads\/sites\/6\/2024\/10\/GPU_SPH_Gearbox_CFD_2-900x483.png 900w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><figcaption class=\"wp-element-caption\">Simcenter STAR-CCM+ 2410 is bringing SPH on GPUs &#8211; with significant performance opportunities<\/figcaption><\/figure>\n\n\n\n<p>Another example is a 2-gear case lubricated by an injector. In that case, a single NVIDIA A100 GPU can achieve up to a 17x speedup compared to a 64-core CPU, while maintaining excellent consistency in results thanks to a unified code base.<\/p>\n\n\n\n<figure class=\"wp-block-gallery has-nested-images columns-1 is-cropped wp-block-gallery-1 is-layout-flex wp-block-gallery-is-layout-flex\">\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"572\" data-id=\"61565\" src=\"https:\/\/blogs.sw.siemens.com\/wp-content\/uploads\/sites\/6\/2024\/10\/GPU_SPH_InjectorGear_CFD2-1024x572.png\" alt=\"\" class=\"wp-image-61565\" srcset=\"https:\/\/blogs.sw.siemens.com\/wp-content\/uploads\/sites\/6\/2024\/10\/GPU_SPH_InjectorGear_CFD2-1024x572.png 1024w, https:\/\/blogs.sw.siemens.com\/wp-content\/uploads\/sites\/6\/2024\/10\/GPU_SPH_InjectorGear_CFD2-600x335.png 600w, https:\/\/blogs.sw.siemens.com\/wp-content\/uploads\/sites\/6\/2024\/10\/GPU_SPH_InjectorGear_CFD2-768x429.png 768w, https:\/\/blogs.sw.siemens.com\/wp-content\/uploads\/sites\/6\/2024\/10\/GPU_SPH_InjectorGear_CFD2-1536x858.png 1536w, https:\/\/blogs.sw.siemens.com\/wp-content\/uploads\/sites\/6\/2024\/10\/GPU_SPH_InjectorGear_CFD2-2048x1144.png 2048w, https:\/\/blogs.sw.siemens.com\/wp-content\/uploads\/sites\/6\/2024\/10\/GPU_SPH_InjectorGear_CFD2-395x222.png 395w, https:\/\/blogs.sw.siemens.com\/wp-content\/uploads\/sites\/6\/2024\/10\/GPU_SPH_InjectorGear_CFD2-900x503.png 900w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><\/figure>\n\n\n\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"589\" data-id=\"61564\" src=\"https:\/\/blogs.sw.siemens.com\/wp-content\/uploads\/sites\/6\/2024\/10\/CPU-GPU_TorqueComp-1024x589.png\" alt=\"\" class=\"wp-image-61564\" srcset=\"https:\/\/blogs.sw.siemens.com\/wp-content\/uploads\/sites\/6\/2024\/10\/CPU-GPU_TorqueComp-1024x589.png 1024w, https:\/\/blogs.sw.siemens.com\/wp-content\/uploads\/sites\/6\/2024\/10\/CPU-GPU_TorqueComp-600x345.png 600w, https:\/\/blogs.sw.siemens.com\/wp-content\/uploads\/sites\/6\/2024\/10\/CPU-GPU_TorqueComp-768x442.png 768w, https:\/\/blogs.sw.siemens.com\/wp-content\/uploads\/sites\/6\/2024\/10\/CPU-GPU_TorqueComp-900x518.png 900w, https:\/\/blogs.sw.siemens.com\/wp-content\/uploads\/sites\/6\/2024\/10\/CPU-GPU_TorqueComp.png 1263w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><\/figure>\n<figcaption class=\"blocks-gallery-caption wp-element-caption\">Faster SPH simulations: Now possible thanks to Simcenter STAR-CCM+ 2410 featuring SPH on GPUs. Consistency between GPU and CPU-enabled results guaranteed through a common unified physics code base<\/figcaption><\/figure>\n\n\n\n<p>Besides the types and generations of CPU and GPU which can significantly impact performance, the speedup for SPH on GPUs depends on the nature of the case and the number of particles in your simulation. As demonstrated above, applications with inlets such as lubrication by injectors typically benefit from greater acceleration for SPH on GPUs.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">\u201cAltius\u201d, higher fidelity for SPH<\/h2>\n\n\n\n<p>In Simcenter STAR-CCM+ 2410, further enhancements that come with the SPH solver will take you to hit higher limits, following the example of Armand Duplantis. Those improvements are automatically compatible with GPU acceleration.<\/p>\n\n\n\n<h3 class=\"wp-block-heading\">Surface tension modeling for SPH<\/h3>\n\n\n\n<p>Firstly, we have introduced the surface tension model to increase the accuracy of your highly dynamic free surface flows. This model allows you to model with higher fidelity the fluid forming droplets and flow behavior on walls. You can set up a surface contact angle for each solid boundary to model either hydrophilic or hydrophobic surfaces.<\/p>\n\n\n\n<figure class=\"wp-block-video\"><video controls poster=\"https:\/\/blogs.sw.siemens.com\/wp-content\/uploads\/sites\/6\/2024\/10\/vlcsnap-2024-10-22-17h42m31s960.png\" src=\"https:\/\/videos.mentor-cdn.com\/mgc\/videos\/5400\/6290f235-45f5-47d1-96fb-15eb794b796f-en-US-video.mp4\"><\/video><figcaption class=\"wp-element-caption\">SPH in Simcenter STAR-CCM+ 2410 will enable higher fidelity simulations thanks to state of the art surface tensions modeling for SPH on GPUs and CPUs alike<\/figcaption><\/figure>\n\n\n\n<h3 class=\"wp-block-heading\">Enhancements to the core of the SPH solver<\/h3>\n\n\n\n<p>Secondly, we\u2019ve added a few enhancements to the core of the SPH solver. One notable improvement is a revision of the criteria for the adaptive time step. This enhancement boosts robustness and convergence rates for all applications across the board. By improving the convergence rate, you need fewer iterations for convergence which leads to saving up to 40% of total simulation time.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\">\u201cFortius\u201d, stronger with GPU solvers on any operating system<\/h2>\n\n\n\n<p>So, in the end, how does Simcenter STAR-CCM+ make you even stronger, just as strong as Mija\u00edn L\u00f3pez N\u00fa\u00f1ez\u2019 longevity with 16 years at the top of the Olympus?  <\/p>\n\n\n\n<p>Well, for those who are fueled by Windows, SPH naturally benefits from the new support for GPU acceleration on Windows operating systems. This means that it is now possible to use your personal Windows laptop or workstation to achieve faster solving time, leveraging the embedded graphic card, not just for SPH on GPUs but for any GPU-enabled solver in Simcenter STAR-CCM+. Well, not to be outdone, simulations on <em>Windows clusters<\/em> can also be accelerated with GPUs. As an illustration with the industrial gearbox lubrication example below, the GPU-native SPH solver running on a single NVIDIA RTX 6000 GPU can deliver up to a 2.8x speed up compared to a 40-core CPU on Windows.<\/p>\n\n\n\n<figure class=\"wp-block-image size-large\"><img loading=\"lazy\" decoding=\"async\" width=\"1024\" height=\"550\" src=\"https:\/\/blogs.sw.siemens.com\/wp-content\/uploads\/sites\/6\/2024\/10\/GPU_SPH_Gearbox_CFD_Windows2-1024x550.png\" alt=\"\" class=\"wp-image-61566\" srcset=\"https:\/\/blogs.sw.siemens.com\/wp-content\/uploads\/sites\/6\/2024\/10\/GPU_SPH_Gearbox_CFD_Windows2-1024x550.png 1024w, https:\/\/blogs.sw.siemens.com\/wp-content\/uploads\/sites\/6\/2024\/10\/GPU_SPH_Gearbox_CFD_Windows2-600x322.png 600w, https:\/\/blogs.sw.siemens.com\/wp-content\/uploads\/sites\/6\/2024\/10\/GPU_SPH_Gearbox_CFD_Windows2-768x413.png 768w, https:\/\/blogs.sw.siemens.com\/wp-content\/uploads\/sites\/6\/2024\/10\/GPU_SPH_Gearbox_CFD_Windows2-1536x825.png 1536w, https:\/\/blogs.sw.siemens.com\/wp-content\/uploads\/sites\/6\/2024\/10\/GPU_SPH_Gearbox_CFD_Windows2-2048x1100.png 2048w, https:\/\/blogs.sw.siemens.com\/wp-content\/uploads\/sites\/6\/2024\/10\/GPU_SPH_Gearbox_CFD_Windows2-900x483.png 900w\" sizes=\"auto, (max-width: 1024px) 100vw, 1024px\" \/><figcaption class=\"wp-element-caption\">SPH on GPUs now also on Windows Operating Systems. Simcenter STAR-CCM+  2410 enables you to leverage all GPU-native solvers on Windows and Linux alike. With consistent simulation results across hardware and operating systems<\/figcaption><\/figure>\n\n\n\n<h2 class=\"wp-block-heading\">\u201c<em>Citius, Altius, Fortius<\/em>\u201d with Simcenter STAR-CCM+ 2410<\/h2>\n\n\n\n<p>Simcenter STAR-CCM+ is a multiphysics CFD software targeting a wide range of applications. And the experience gathered over the years by experimented and dedicated teams took it to converge to multiple streams of technology. The 2410 release perfectly illustrates this, with the continuous integration of various technologies, starting with SPH and GPU, coming together to enable the GPU-native SPH solver on the Windows platform. With this approach, all the building blocks are combined together to strengthen your simulation experience with a more complete solution.<br>Join us on our journey to grow stronger, higher and faster with each release of Simcenter STAR-CCM+ and to unlock the key to success!<\/p>\n\n\n\n<div style=\"height:30px\" aria-hidden=\"true\" class=\"wp-block-spacer\"><\/div>\n\n\n\n<hr class=\"wp-block-separator has-alpha-channel-opacity is-style-dots\"\/>\n\n\n\n<div style=\"height:30px\" aria-hidden=\"true\" class=\"wp-block-spacer\"><\/div>\n\n\n\n<div class=\"wp-block-buttons is-content-justification-center is-layout-flex wp-container-core-buttons-is-layout-16018d1d wp-block-buttons-is-layout-flex\">\n<div class=\"wp-block-button\"><a class=\"wp-block-button__link wp-element-button\" href=\"https:\/\/blogs.sw.siemens.com\/simcenter\/simcenter-star-ccm-2410-released\/\" target=\"_blank\" rel=\"noreferrer noopener\">Explore more exciting new features in Simcenter STAR-CCM+ 2410<\/a><\/div>\n<\/div>\n\n\n\n<a href=\"https:\/\/www.g2.com\/products\/simcenter-star-ccm\/reviews?utm_source=review-widget\" title=\"Read reviews of Simcenter STAR-CCM+ on G2\" target=\"_blank\" rel=\"noopener\"><img decoding=\"async\" class=\"full-width\" style=\"max-width: 200px\" alt=\"Read Simcenter STAR-CCM+ reviews on G2\" src=\"https:\/\/www.g2.com\/products\/simcenter-star-ccm\/widgets\/stars?color=gray&amp;type=read\" \/><\/a><script>(function(a,b,c,d){window.fetch(\"https:\/\/www.g2.com\/products\/simcenter-star-ccm\/rating_schema.json\").then(e=>e.json()).then(f=>{c=a.createElement(b);c.type=\"application\/ld+json\";c.text=JSON.stringify(f);d=a.getElementsByTagName(b)[0];d.parentNode.insertBefore(c,d);});})(document,\"script\");<\/script>\n","protected":false},"excerpt":{"rendered":"<p>Simcenter STAR-CCM+ 2410 enables SPH on GPUs, and any GPU-native solver on the Windows platform.<\/p>\n","protected":false},"author":81034,"featured_media":61569,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"spanish_translation":"","french_translation":"","german_translation":"","italian_translation":"","polish_translation":"","japanese_translation":"","chinese_translation":"","footnotes":""},"categories":[179,1],"tags":[242],"industry":[],"product":[513],"coauthors":[18425,4511],"class_list":["post-61554","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-product-updates","category-news","tag-computational-fluid-dynamics-cfd","product-simcenter-star-ccm"],"featured_image_url":"https:\/\/blogs.sw.siemens.com\/wp-content\/uploads\/sites\/6\/2024\/10\/vlcsnap-2024-10-22-17h42m31s960.png","_links":{"self":[{"href":"https:\/\/blogs.sw.siemens.com\/simcenter\/wp-json\/wp\/v2\/posts\/61554","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/blogs.sw.siemens.com\/simcenter\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/blogs.sw.siemens.com\/simcenter\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/blogs.sw.siemens.com\/simcenter\/wp-json\/wp\/v2\/users\/81034"}],"replies":[{"embeddable":true,"href":"https:\/\/blogs.sw.siemens.com\/simcenter\/wp-json\/wp\/v2\/comments?post=61554"}],"version-history":[{"count":5,"href":"https:\/\/blogs.sw.siemens.com\/simcenter\/wp-json\/wp\/v2\/posts\/61554\/revisions"}],"predecessor-version":[{"id":70512,"href":"https:\/\/blogs.sw.siemens.com\/simcenter\/wp-json\/wp\/v2\/posts\/61554\/revisions\/70512"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/blogs.sw.siemens.com\/simcenter\/wp-json\/wp\/v2\/media\/61569"}],"wp:attachment":[{"href":"https:\/\/blogs.sw.siemens.com\/simcenter\/wp-json\/wp\/v2\/media?parent=61554"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/blogs.sw.siemens.com\/simcenter\/wp-json\/wp\/v2\/categories?post=61554"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/blogs.sw.siemens.com\/simcenter\/wp-json\/wp\/v2\/tags?post=61554"},{"taxonomy":"industry","embeddable":true,"href":"https:\/\/blogs.sw.siemens.com\/simcenter\/wp-json\/wp\/v2\/industry?post=61554"},{"taxonomy":"product","embeddable":true,"href":"https:\/\/blogs.sw.siemens.com\/simcenter\/wp-json\/wp\/v2\/product?post=61554"},{"taxonomy":"author","embeddable":true,"href":"https:\/\/blogs.sw.siemens.com\/simcenter\/wp-json\/wp\/v2\/coauthors?post=61554"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}