- NVIDIA expa ds NVIDIA Age t Toolkit with e-a chitected NVIDIA PhysicsNeMo lib a ies a d updated NVIDIA CUDA-X lib a ies, e abli g softwa e develope s to build auto omous AI e gi ee s with AI physics skills, accele ated solve s a d qua tum chemist y capabilities.
- NVIDIA Nemot o 3 Ult a leads amo g ope models i age tic egiste -t a sfe level codi g with the ACE-RTL age t f om NVIDIA Resea ch, helpi g e te p ises build customizable AI age ts fo chip desig a d ve ificatio .
- Cade ce, Sieme s, Sy opsys a d othe i dust y leade s a e usi g NVIDIA accele ated computi g a d age tic AI tech ologies to adva ce auto omous e gi ee i g wo kflows ac oss chip desig , ve ificatio , packagi g a d systems.
LONG BEACH, Calif., July 26, 2026 (GLOBE NEWSWIRE) — NVIDIA today a ou ced a expa sio of NVIDIA Age t Toolkit fo e gi ee i g, ow addi g NVIDIA PhysicsNeMo™ a d CUDA-X™ lib a ies as age t- eady tools a d skills built to t a sfo m how the wo ld desig s a d develops p oducts.
Buildi g the ext ge e atio of chips a d systems equi es teams to co ect physics, simulatio a d pe fo ma ce a alysis ac oss i c easi gly complex desig cycles. A ew class of auto omous AI e gi ee s is eme gi g to help take o that complexity — usi g specialized tools, u i g simulatio s a d ge e ati g high-fidelity data to help scale chip desig , ve ificatio , packagi g a d systems.
Now i cluded i NVIDIA Age t Toolkit, NVIDIA has e-a chitected PhysicsNeMo i to a set of age t-f ie dly lib a ies a d added ew a d updated CUDA-X lib a ies to suppo t complex e gi ee i g wo k. PhysicsNeMo p ovides AI physics skills fo t ai i g a d deployi g models, while CUDA-X lib a ies b i g accele ated solve s a d qua tum chemist y capabilities i to age tic e gi ee i g wo kflows.
“E gi ee i g has eached a i flectio poi t. AI ca ow wo k with tools of physics, simulatio a d desig ,” said Timothy Costa, vice p eside t a d ge e al ma age of computatio al e gi ee i g at NVIDIA. “With NVIDIA Age t Toolkit, develope s ca build age tic e gi ee s that easo usi g physics, u complex simulatio s a d ge e ate high-fidelity data to become a ew e gi e fo i ovatio i chip a d system desig .”
Key capabilities i clude:
AI physics skills : NVIDIA PhysicsNeMo lib a ies help age ts t ai a d deploy customizable AI physics models fo complex desig a d simulatio tasks, tu i g model a chitectu es i to callable tools fo e gi ee i g wo kflows.Ite ative spa se solve s: New NVIDIA cuISS (CUDA Ite ative Spa se Solve s) lib a y accele ates la ge spa se li ea systems i physics-based a d e gi ee i g simulatio s. Desig ed fo flexibility a d pe fo ma ce o GPUs, its mode , composable solve s a d p eco ditio e s help develope s build scalable, p oductio simulatio e gi es fo age tic e gi ee i g wo kflows.Di ect spa se solve s : NVIDIA cuDSS (CUDA Di ect Spa se Solve s) accele ates la ge, complex spa se li ea systems ce t al to elect o ic desig automatio (EDA) a d scie tific simulatio . It delive s high pe fo ma ce a d ume ical obust ess fo c itical wo kloads like device, ci cuit a d system simulatio s with scalability to multi-GPU a d multi- ode deployme ts i p oductio e vi o me ts.Qua tum chemist y : NVIDIA cuEST (CUDA Elect o ic St uctu e Theo y) b i gs high-accu acy qua tum chemist y simulatio s to device- eleva t scales, e abli g de sity fu ctio al theo y (DFT) a d post-DFT methods to be i teg ated i to p oductio wo kflows at scale. cuEST b i gs p oductio value to custome s by suppo ti g a wide a ge of mode fu ctio als a d maki g i c easi gly la ge g ou d-state a d excited-state simulatio s ma ageable o NVIDIA GPUs.
With ACE-RTL — a age t fo desig i g ha dwa e f om NVIDIA Resea ch — NVIDIA Nemot o ™ 3 Ult a leads amo g ope models i age tic RTL codi g o the comp ehe sive ve ilog desig p oblems be chma k ac oss RTL codi g tasks.
This ep ese ts how Nemot o 3 Ult a offe s i dust y-leadi g accu acy a d efficie cy a d ca be post-t ai ed o p op ieta y data — deployed locally o o p emises — givi g e te p ises g eate co t ol, customizatio a d data p ivacy as they build AI age ts fo chip desig .
Develope s ca get sta ted with Nemot o 3 Ult a usi g Cade ce’s ha ess; Sy opsys’ fully auto omous, lo g- u i g age ts fo desig ve ificatio a d a alog a d mixed-sig al wo kflows; Sieme s’ Questa O e sma t ve ificatio age tic toolkit; as well as o Huggi g Face.
Cade ce is usi g NVIDIA Nemot o , accele ated computi g a d CUDA-X lib a ies with the ece tly lau ched Cade ce Au aStack AI Supe Age t a d the Cade ce Mille ium M2000 platfo m to auto omously d ive adva ced packagi g a d p i ted ci cuit boa d (PCB) desig f om explo atio th ough sig off, delive i g up to 20x faste multiphysics pe fo ma ce. This joi s Cade ce’s complete po tfolio of silico desig supe age ts which collectively cove the chip desig wo kflow e d to e d, f om a chitectu e th ough ma ufactu i g sig off.
I additio , the collabo atio exte ds f om age tic desig to the u de lyi g compute as Cade ce’s po tfolio of EDA a d system desig automatio tools, i cludi g Cade ce Jaspe , a fo mal ve ificatio platfo m, is bei g optimized fo the NVIDIA Ve a CPU to help e gi ee i g teams validate adva ced chip desig s faste .
Sy opsys is usi g the NVIDIA Age t Toolkit, NVIDIA NIM™ mic ose vices, Nemot o ope models, the NVIDIA NeMo™ Gym lib a y a d NVIDIA NemoClaw™ bluep i ts with Sy opsys Age tE gi ee to build secu e, accele ated age tic wo kflows ac oss chip a d system desig . Leve agi g A sys Icepak, Sy opsys’ age tic wo kflow auto omously executes simulatio setup, a d p e- a d post-p ocessi g fo complex GPU cooli g desig optimizatio . Sy opsys is developi g NVIDIA cuISS use cases to accele ate simulatio wo kloads.
The collabo atio exte ds f om age tic wo kflows to the u de lyi g compute platfo m as Sy opsys VCS, a high-pe fo ma ce fu ctio al ve ificatio solutio used to simulate a d validate complex chip desig s befo e fab icatio , is bei g optimized fo the NVIDIA Ve a CPU to help imp ove ve ificatio th oughput.
Sieme s is usi g NVIDIA NeMo Gym, Nemot o ope models a d CUDA-X lib a ies with the Sieme s Fuse EDA AI Age t to o chest ate multi-tool a d multi-age t wo kflows ac oss semico ducto , 3D-IC, PCB a d system desig , f om co ceptio th ough sig off. I Sieme s Solido Cha acte izatio Suite, these age tic AI wo kflows a e delive i g mo e tha 10x faste lib a y cha acte izatio while educi g toke costs by mo e tha 10x.
Samsu g is usi g NVIDIA cuLitho a d CUDA-X lib a ies to achieve up to 20x g eate pe fo ma ce fo computatio al lithog aphy a d applyi g NVIDIA PhysicsNeMo to pe fo m chip-scale the mal-st ess a alysis with ume ical solve -level accu acy ac oss domai s co tai i g up to 10 billio cells.
ChipAge ts is usi g NVIDIA Age t Toolkit to build domai -specific AI age ts fo chip desig a d ve ificatio . The team is fi e-tu i g NVIDIA Nemot o models fo complex e d-to-e d semico ducto desig a d ve ificatio wo kflows i cludi g debug, fo mal ve ificatio , cove age a d mo e.
Silvaco is usi g NVIDIA accele ated computi g to scale high-accu acy 3D optical simulatio i the Silvaco Victo y Device. Ru i g o 32 NVIDIA GPUs i te co ected by NVIDIA NVLi k™ tech ology, it completed a 3.2-billio -mesh- ode photo ic edge couple simulatio i u de fou hou s, a wo kload beyo d the p actical limits of CPU-based simulatio .
Keysight is ha essi g NVIDIA cuDSS to accele ate elect omag etic simulatio s by up to 10x, while Samsu g, Sy opsys a d TSMC a e i teg ati g NVIDIA cuEST i to its GPU-accele ated pipeli e to achieve up to a 50x speedup fo key qua tum-chemist y wo kloads.
Lea mo e by joi i g NVIDIA at DAC.
Ce tai stateme ts i this p ess elease i cludi g, but ot limited to, stateme ts as to: With NVIDIA Age t Toolkit, develope s bei g able to build age tic e gi ee s that easo usi g physics, u complex simulatio s a d ge e ate high-fidelity data to become a ew e gi e fo i ovatio i chip a d system desig ; expectatio s with espect to g owth, pe fo ma ce, availability, a d be efits of NVIDIA’s p oducts, se vices a d tech ologies, a d elated t e ds a d d ive s; expectatio s with espect to NVIDIA’s thi d pa ty a a geme ts, i cludi g with its collabo ato s a d pa t e s; expectatio s with espect to tech ology developme ts, a d elated t e ds a d d ive s; p ojected ma ket g owth a d t e ds; expectatio s with espect to AI a d elated i dust ies; a d othe stateme ts that a e ot histo ical facts a e fo wa d-looki g stateme ts withi the mea i g of Sectio 27A of the Secu ities Act of 1933, as ame ded, a d Sectio 21E of the Secu ities Excha ge Act of 1934, as ame ded, which a e subject to the “safe ha bo ” c eated by those sectio s based o ma ageme t’s beliefs a d assumptio s a d o i fo matio cu e tly available to ma ageme t a d a e subject to isks a d u ce tai ties that could cause esults to be mate ially diffe e t tha expectatio s. Impo ta t facto s that could cause actual esults to diffe mate ially i clude: global eco omic a d political co ditio s; NVIDIA’s elia ce o thi d pa ties to ma ufactu e, assemble, package a d test NVIDIA’s p oducts; the impact of tech ological developme t a d competitio ; developme t of ew p oducts a d tech ologies o e ha ceme ts to NVIDIA’s existi g p oducts a d tech ologies; ma ket accepta ce of NVIDIA’s p oducts o NVIDIA’s pa t e s’ p oducts; desig , ma ufactu i g o softwa e defects; cha ges i co sume p efe e ces o dema ds; cha ges i i dust y sta da ds a d i te faces; u expected loss of pe fo ma ce of NVIDIA’s p oducts o tech ologies whe i teg ated i to systems; NVIDIA’s ability to ealize the pote tial be efits of busi ess i vestme ts o acquisitio s; a d cha ges i applicable laws a d egulatio s, as well as othe facto s detailed f om time to time i the most ece t epo ts NVIDIA files with the Secu ities a d Excha ge Commissio , o SEC, i cludi g, but ot limited to, its A ual Repo t o Fo m 10-K a d Qua te ly Repo ts o Fo m 10-Q. Copies of epo ts filed with the SEC a e posted o the compa y’s website a d a e available f om NVIDIA without cha ge. These fo wa d-looki g stateme ts a e ot gua a tees of futu e pe fo ma ce a d speak o ly as of the date he eof, a d, except as equi ed by law, NVIDIA disclaims a y obligatio to update these fo wa d-looki g stateme ts to eflect futu e eve ts o ci cumsta ces.
Ma y of the p oducts a d featu es desc ibed he ei emai i va ious stages a d will be offe ed o a whe -a d-if-available basis. The stateme ts above a e ot i te ded to be, a d should ot be i te p eted as a commitme t, p omise, o legal obligatio , a d the developme t, elease, a d timi g of a y featu es o fu ctio alities desc ibed fo ou p oducts is subject to cha ge a d emai s at the sole disc etio of NVIDIA. NVIDIA will have o liability fo failu e to delive o delay i the delive y of a y of the p oducts, featu es o fu ctio s set fo th he ei .
© 2026 NVIDIA Co po atio . All ights ese ved. NVIDIA, the NVIDIA logo, CUDA-X, NemoClaw, Nemot o , NVIDIA NeMo, NVIDIA NIM, NVLi k a d PhysicsNeMo a e t adema ks a d/o egiste ed t adema ks of NVIDIA Co po atio i the U.S. a d othe cou t ies. Othe compa y a d p oduct ames may be t adema ks of the espective compa ies with which they a e associated. Featu es, p ici g, availability a d specificatio s a e subject to cha ge without otice.
A photo accompa yi g this a ou ceme t is available at https://www.globe ewswi e.com/NewsRoom/Attachme tNg/8cc7fd5d-80e0-4960-9176-41e04d3909a0
