Reply to thread

Message: <blockquote data-quote="ibnanv" data-source="post: 21808482" data-attributes="member: 218596">GlobalFoundries Announces Early 7nm Availability, Huge Gains Over 14nm FinFET<img src="https://www.extremetech.com/wp-content/uploads/2013/11/Silicon-640x353.jpg" alt="" class="fr-fic fr-dii fr-draggable " style="" />       Over the past few years, we’ve seen the foundry  business evolve from a single-horse race that TSMC effectively “won”  each and every cycle to a two-way competition with Samsung. Now,  GlobalFoundries is making a serious push of its own with early 7nm  technology availability and volume production currently planned for the  back half of 2018.That’s the news  from Saratoga today, where GF announced that its 7nm LP node (LP =  Leading Performance) is ready for partners to begin planning their  designs. The first customer launches on 7nm LP are expected 12-18 months  from now, and GF is promising that it can deliver up to 40 percent  improved performance compared with 14nm. The company claims that its 7nm  work is exceeding its performance and power targets, and is on track to  deliver up to 2x area scaling compared with previous 14nm technology.  The company has also been hard at work on 5nm in partnership with IBM.                                <img src="https://www.extremetech.com/wp-content/uploads/2017/06/GF-7nm-640x330.jpg" alt="" class="fr-fic fr-dii fr-draggable " style="" />“Our  7nm FinFET technology development is on track and we are seeing strong  customer traction, with multiple product tapeouts planned in 2018,” said  Gregg Bartlett, senior vice president of the CMOS Business Unit at GF.  “And, while driving to commercialize 7nm, we are actively developing next-generation technologies at 5nm and beyond to ensure our customers  have access to a world-class roadmap at the leading edge.”GlobalFoundries will also have the option to integrate some EUV  manufacturing at this node, if its customers want to use it, but we’d  be surprised if many do. EUV may be slowly moving into commercial  production, but it isn’t expected to see broad availability for the next  few years and may be reserved for critical masks where other forms of  multi-patterning can’t be used for some time after that.                                  What’s  interesting about GF’s announcement is that it’s also claiming up to 60  percent reduced power with 40 percent improved performance, using the  word and. That didn’t used to be significant, but in recent years it’s become common to see semiconductor manufacturers using or  instead. You can have higher performance at the same power or you get  lower power at the same performance, but delivering both simultaneously  has become increasingly difficult as the benefits of each successive  process node grow smaller.GF also seems to be leading with a  process node that’s better suited to higher power silicon designs like  GPUs and CPUs, rather than the mobile-first approach TSMC has taken to  better suit the needs of Qualcomm and Apple. There’s nothing  intrinsically wrong with each option, but it reflects how different  companies now drive the semiconductor market compared with a decade ago,  when GPUs were major drivers of each new node. Now, we see companies  like AMD and NV sitting out some process nodes that are explicitly  designed for mobile SoCs, and taking a staggered approach to process  node deployment.When GlobalFoundries first spun off from AMD, it  had a great deal of difficulty finding its sea legs. The company’s  original roadmap called for aggressive competition with TSMC across a  range of nodes, but it was unable to deliver on that vision. Later, it  was forced to license Samsung’s 14nm technology due to problems with its  own 14nm XM. GF seems to be on much more stable footing now, and is  pushing hard to turn the two-way race between TSMC and Samsung into a  three-way competition with itself in the lead.</blockquote>

Verification: Nawa warak dahaya keeyada? (Namaya wadi kireema dahaya)

Top Bottom