The Ups and Downs of Chip Manufacturing

Introduction

Previously, we blogged about a number of successes in the ARM world: being adopted for the next generation Macs, moving into the server and supercomputer markets and of course continuing to dominate the mobile world. ARM is owned by the Japanese conglomerate holding company Softbank. ARM is Softbank’s big success, balanced with a number of major failures such as WeWork. With ARM’s current success, Softbank is considering whether this is a good time to sell off ARM at a big profit.

Meanwhile, Intel just reported their quarterly earnings and along with those, announced their 7nm next generation manufacturing process has been delayed until 2022. As a result Intel’s stock price took a major haircut and it seems Intel is even considering outsourcing their manufacturing.

In this article, we’ll look at the ramifications that we might see over the next year or so.

Who Might Buy ARM?

Softbank paid $32 billion to acquire ARM in 2016 and it is suspected that Softbank is trying to get in excess of $40 billion from the sale. Softbank is considering spawning ARM off as a separate company via an IPO, or selling it to either nVidia or Apple.

It is reported that Apple has already said that it isn’t interested in buying ARM. The main reason is that Apple only licenses the ARM ISA (Instruction Set Architecture) and not the CPU circuitry designs, so it doesn’t gain that much and will bring on anti-trust attention if it buys the company that designs the processors for all its competitors. Even if Apple has good intentions to its competitors, it doesn’t want to deal with them, as buying ARM would force it to.

nVidia is the main interested party. nVidia develops graphics cards that are used for AI applications and playing video games. The explosion in AI has greatly benefited nVidia, but nVidia faces a struggle as its main competitors in the graphics/AI world, namely Intel and AMD both make CPUs and have been including more and more graphics processing on the core CPU chips. nVidia would dearly like to enter the CPU market and be able to compete with newer AMD CPU/GPU chips. Intel has struggled of late, but even their built in Intel graphics are good enough for most people, meaning they don’t feel like they need an nVidia product. nVidia already has a lot of experience with ARM, we’ve blogged about their nVidia Jetson Nano, which is just one in a line of processor boards with integrated nVidia SIMD cores.

nVidia is large enough that they can afford to buy ARM, but the question is whether nVidia will be a good steward of the ARM technology portfolio? At least Softbank, being a holding company has largely left ARM alone to do its thing. One question will be how hands-on nVidia is if they do acquire ARM, or will they allow it independence. Will they try to milk more revenue from ARM, raising prices for everyone? Will they force the inclusion of nVidia technology. For instance ARM designs their own GPU called Mali, will nVidia mandate this be replaced by nVidia GPU technology? Personally, I feel that GPU is a weak spot for ARM and that a migration to the excellent nVidia graphics cores will be a big benefit. But this will take time, since most software expects Mali or one of its competitors.

If this deal does pass all the complicated regulatory and financial hurdles, only time will tell if this turns out to be a good thing for ARM.

Intel’s Manufacturing Problems

Intel has been struggling to release its 10nm based chips and they are just starting to come out. Meanwhile, AMD, Apple and others have been having their chips manufactured by TSMC using 7nm technology for almost a year now. Intel claims their 10nm technology is as good as TSMC’s 7nm process, but independent analysis shows that TSMC is beating Intel in the number of transistors per square millimeter (hence denser chips with more transistors), while using less power and generating less heat. Add to that, Intel announcing their 7nm technology has been deleted to 2022, and that TSMC is starting to produce 5nm based chips now.

These problems caused Apple to hurry up their switch from Intel to ARM for their Mac computers. It has also resulted in tremendous growth for AMD which produces Intel compatible chips using TSMC technology.

With my first job after University, they sent me on a 2 week course at Intel in Santa Clara on using their embedded processors (at that time the 80186). The course started with an Intel marketing video on how Intel was centered on their chip manufacturing process technology, how this was their crown jewel and the core of everything they did. Everything else was based on their excellence in manufacturing chips. This certainly remained true for many years, but recently a chink has appeared in Intel’s armour as TSMC has passed Intel in processing technology.

At Intel’s earnings call, Bob Swan, CEO said the unthinkable that Intel was considering outsourcing their manufacturing to TSMC as well. Would this work for Intel? Will their chip designs which are optimized for their process technology work on TSMC’s? Is it in TSMC’s interest to ramp up for Intel, when Intel is likely to take the manufacturing back in-house down the road? None of these questions were answered by Bob Swan on the call. Another question is whether Intel would exit the chip manufacturing business forever? How would this affect Intel long term? Is Intel’s chip design capability competitive, without a process technology advantage to help them? These are all hard questions and Intel is going to have to find some answers to all these or face an accelerating decline over the next few years.

Summary

Just when ARM is on a roll, Softbank has thrown it a curved ball by offering it up for sale. Whether anything comes of this is yet to be seen, if it does happen, I think nVidia would be the best choice to acquire ARM and that long term it would be a good thing. I think nVidia has shown how to do excellent SoCs based on ARM processors and nVidia GPU cores with products like the Jetson Nano and that hopefully nVidia can be a good steward for ARM.

Intel certainly faces some challenges in the coming months. AMD is eating away at their market share and getting their new chips to market seems to be getting more and more challenging. Hopefully Intel can find a solution to their problems, but these things can take several years and billions in investment to turn around.

To learn more about the internal architecture of the ARM Processor, consider my book: Programming with 64-Bit ARM Assembly Language.