\u201cWith cuLitho, TSMC can reduce prototype cycle time, increase throughput and reduce the carbon footprint of their manufacturing, and prepare for 2nm and beyond,\u201d he said.<\/p>\n\n\n\n
Nvidia partnered with some of the biggest names in the industry on the work. TSMC, the largest chip foundry in the world, plans to qualify the approach in production this summer. Meanwhile, chip designer, Synopsis, and equipment maker, ASML, said in a press release<\/a> they will integrate cuLitho into their chip design and lithography software.<\/p>\n\n\n\n To fabricate a modern computer chip, makers shine ultraviolet light through intricate \u201cstencils\u201d to etch billions of patterns\u2014like wires and transistors\u2014onto smooth silicon wafers at near-atomic resolutions. This step, called photolithography, is how every new chip design, from Nvidia to Apple to Intel, is manifested physically in silicon.<\/p>\n\n\n\n The machines that make it happen, built by ASML, cost hundreds of millions of dollars<\/a> and can produce near-flawless works of nanoscale art on chips. The end product, an example of which is humming away near your fingertips as you read this, is probably the most complex commodity in history. (TSMC churns out a quintillion transistors every six months<\/a>\u2014for Apple alone.)<\/p>\n\n\n\n To make more powerful chips, with ever-more, ever-smaller transistors<\/a>, engineers have had to get creative.<\/p>\n\n\n\n Remember that stencil mentioned above? It\u2019s the weirdest stencil you\u2019ve ever seen. Today\u2019s transistors are smaller than the wavelength of light used to etch them. Chipmakers have to use some extremely clever tricks to design stencils\u2014or technically, photomasks\u2014that can bend light into interference patterns whose features are smaller than the light\u2019s wavelength and<\/em> perfectly match the chip\u2019s design.<\/p>\n\n\n\n Whereas photomasks once had a more one-to-one shape\u2014a rectangle projected a rectangle\u2014they\u2019ve necessarily become more and more complicated over the years. The most advanced masks these days are more like mandalas than simple polygons.<\/p>\n\n\n\n To design these advanced photomask patterns, engineers reverse the process.<\/p>\n\n\n\n They start with the design they want, then stuff it through a wicked mess of equations describing the physics involved to design a suitable pattern. This step is called inverse lithography, and as the gap between light wavelength and feature size has increased, it\u2019s become increasingly crucial to the whole process. But as the complexity of photomasks increases, so too does the computing<\/a> power, time, and cost required to design them.<\/p>\n\n\n\n \u201cComputational lithography is the largest computation workload in chip design and manufacturing, consuming tens of billions of CPU hours annually,\u201d Huang said. \u201cMassive data centers run 24\/7 to create reticles used in lithography systems.\u201d<\/p>\n\n\n\n In the broader category of computational lithography\u2014the methods used to design photomasks\u2014inverse lithography is one of the newer, more advanced approaches. Its advantages include greater depth of field and resolution and should benefit the entire chip, but due its heavy computational lift, it\u2019s currently only used sparingly.<\/p>\n\n\n\n Nvidia aims to reduce that lift by making the computation more amenable to graphics processing units, or GPUs. These powerful chips are used for tasks with lots of simple computations that can be completed in parallel, like video games and machine learning. So it isn\u2019t just about running existing processes on GPUs, which only yields a modest improvement, but modifying those processes specifically<\/em> for GPUs.<\/p>\n\n\n\n That\u2019s what the new software, cuLitho, is designed to do. The product, developed over the last four years, is a library of algorithms for the basic operations used in inverse lithography. By breaking inverse lithography down into these smaller, more repetitive computations, the whole process can now be split and parallelized on GPUs. And that, according to Nvidia, significantly speeds everything up.<\/p>\n\n\n\n \u201cIf [inverse lithography] was sped up 40x, would many more people and companies use full-chip ILT on many more layers? I am sure of it,\u201d said Vivek Singh, VP of Nvidia\u2019s Advanced Technology Group, in a talk at GTC<\/a>.<\/p>\n\n\n\n With a speedier, less computationally hungry process, makers can more rapidly iterate on experimental designs, tweak existing designs, make more photomasks per day, and generally, expand the use of inverse lithography to more of the chip, he said.<\/p>\n\n\n\n This last detail is critical. Wider use of inverse lithography should reduce print errors by sharpening the projected image\u2014meaning chipmakers can churn out more working chips per silicon wafer\u2014and be precise enough to make features at 2 nanometers and beyond.<\/p>\n\n\n\n It turns out making better chips isn\u2019t all<\/em> about the hardware. Software improvements, like cuLitho or the increased use of machine learning in design<\/a>, can have a big impact too.<\/p>\n\n\n\n Image Credit:\u00a0Nvidia<\/a><\/em><\/p>\n\n\n\n Author:<\/strong> Jason Dorrier<\/a><\/p>\n\n\n\n Jason is editorial director of Singularity Hub. He researched and wrote about finance and economics before moving on to science and technology. He’s curious about pretty much everything, but especially loves learning about and sharing big ideas and advances in artificial intelligence, computing, robotics, biotech, neuroscience, and space.<\/p>\n\n\n\n Original Article<\/a><\/strong><\/p>\n","protected":false},"excerpt":{"rendered":" If computer chips make the modern world go around, then Nvidia and TSMC are flywheels keeping it spinning. It\u2019s worth paying attention when the former says they\u2019ve made a chipmaking breakthrough, and the latter confirms they\u2019re about to put it into practice. At Nvidia\u2019s GTC developer conference this week, CEO Jensen Huang saidNvidia has developed software […]\n","protected":false},"author":1,"featured_media":4943,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"episode_type":"","audio_file":"","podmotor_file_id":"","podmotor_episode_id":"","cover_image":"","cover_image_id":"","duration":"","filesize":"","filesize_raw":"","date_recorded":"","explicit":"","block":"","footnotes":""},"categories":[13],"tags":[238,162],"series":[],"class_list":["post-4940","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-articulos-ingles","tag-chips","tag-computing"],"episode_featured_image":"https:\/\/singularityumexico.com\/wp-content\/uploads\/2023\/05\/IMG_0299.jpeg","episode_player_image":"https:\/\/singularityumexico.com\/wp-content\/uploads\/2023\/05\/11711533-1673157178559-89a95be153719-4-scaled.jpg","download_link":"","player_link":"","audio_player":false,"episode_data":{"playerMode":"dark","subscribeUrls":{"apple_podcasts":{"key":"apple_podcasts","url":"","label":"Apple Podcasts","class":"apple_podcasts","icon":"apple-podcasts.png"},"stitcher":{"key":"stitcher","url":"","label":"Stitcher","class":"stitcher","icon":"stitcher.png"},"google_podcasts":{"key":"google_podcasts","url":"","label":"Google Podcasts","class":"google_podcasts","icon":"google-podcasts.png"},"spotify":{"key":"spotify","url":"","label":"Spotify","class":"spotify","icon":"spotify.png"}},"rssFeedUrl":"https:\/\/singularityumexico.com\/en\/feed\/podcast\/the-feedback-loop-by-singularity","embedCode":"What Is Inverse Lithography?<\/strong><\/h2>\n\n\n\n
![\"\"](\"https:\/\/singularityumexico.com\/wp-content\/uploads\/2023\/05\/IMG_0300-1024x570.jpeg\")
A Library in Parallel<\/strong><\/h2>\n\n\n\n
![\"\"](\"https:\/\/singularityumexico.com\/wp-content\/uploads\/2023\/05\/IMG_0301-1024x579.jpeg\")
\n\n\n\nThis Chipmaking Step Is Crucial to the Future of Computing\u2014and Just Got 40x Faster Thanks to Nvidia<\/a><\/blockquote>