This week Samsung Electronics and Synopsys launched that Samsung has taped out its first mobile system-on-chip on Samsung Foundry’s 3nm gate-all-around (GAA) course of know-how. The announcement, coming from digital design automation Synopsys, further notes that Samsung used the Synopsys.ai EDA suite to place-n-route the construction and ensure design of the SoC, which in flip enabled better effectivity.
Samsung’s unnamed high-performance mobile SoC will depend on ‘flagship’ general-purpose CPU and GPU architectures along with quite a few IP blocks from Synopsys. SoC designers used Synopsys.ai EDA software program program, along with the Synopsys DSO.ai to fine-tune design and maximize yields along with Synopsys Fusion Compiler RTL-to-GDSII decision to realize better effectivity, lower vitality, and optimize house (PPA).
And whereas the knowledge that Samsung has developed a high-performance SoC using the Synopsys.ai suite is significant, there could also be one different, way more important dimension to this announcement: due to this Samsung has lastly taped out an advanced smartphone software program processor on its cutting-edge 3nm GAAFET course of.
Although Samsung Foundry has been producing chips on its GAA-equipped SF3E (3 nm-class, ‘early’ node) course of for almost two years now, Samsung Electronics has certainly not used this know-how for its private system-on-chips for smartphones or totally different superior devices. So far, SF3E has been used primarily for cryptocurrency mining chips, presumably on account of inevitable early teething and yield factors that embrace being the commerce’s first enterprise GAAFET course of.
For now, Samsung is just not disclosing what specific course of node is getting used for the SoC; the official Samsung/Synposys announcement solely notes that it’s for a GAA course of node. Along with their first-generation 3nm-class SF3E, Samsung Foundry has a considerably additional refined SF3 manufacturing know-how that gives fairly a number of enhancements over SF3E, and is due to be used for mass manufacturing throughout the coming quarters. Given the timing of the announcement, a budget wager is that they’re using SF3.
As for Samsung’s tooling partnership with Synopsys, the latter’s devices are being credited for delivering some essential effectivity enhancements to the chip’s design. Notably, the two firms are crediting these devices for enhancing the chip’s peak clockspeed by 300MHz whereas chopping down on dynamic vitality utilization by 10%. To carry out that, Samsung Electronics’ SoC builders used design partitioning optimization, multi-source clock tree synthesis (MSCTS), and wise wire optimization to reduce signal interference, along with a easier hierarchical technique. And thru the usage of Synopsys Fusion Compiler, they did all this whereas being able to skip weeks of ‘information’ design work, in accordance with the joint press launch.
“Our longstanding collaboration has delivered fashionable SoC designs,” acknowledged Kijoon Hong, vice chairman of SLSI at Samsung Electronics. “It’s a distinctive milestone to effectively acquire the very best effectivity, vitality and house on basically probably the most superior mobile CPU cores and SoC designs in collaboration with Synopsys. Not solely have we demonstrated that AI-driven choices may additionally assist us acquire PPA targets for even basically probably the most superior GAA course of utilized sciences, nonetheless by the use of our partnership we now have established an ultra-high-productivity design system that is continually delivering spectacular outcomes.”