I find it highly ironic that this link has appeared on Hacker News literally hours after Meltdown and Spectre vulnerabilities have been officially announced and described.
If this bug is really present in all chips since 1995, then where have all these people been for the last 22 years? If they're so competent about CPU design, why haven't we seen literally tens of Intel competitor startups pop up and succeed?
It's only natural that you get some articles like these posted. For many of us, we've read a few details about the bugs raised this week and thought to ourselves — "man, CPUs are so complicated, how do they even managed to make them work at all?"
An article like this helps to answer some of the questions for those of us interested in finding out more.
Hardware is a long and tedious process. CPU design is an extra level of difficult on top.
In my field, it is routine to hire people in late 40s/50s to make CPUs. I'm in my late 20s, and viewed as a weird specimen. In my career I've made a armv8 CPU and now work RV64.
It takes a couple of years to get a guy from uni into working shape. And that's just to teach him how to do 1-2 tasks in his field. If verification, this usually is coverage specification and test writing. Combine this with a cpu project duration average of 5ish years and it's quickly evident that you won't beat someone with a startup.
In my office today, in a team of 10, no one, other than me is under 40.
Yes, FPGA's exist but they are not even relevant when you are talking about the skillset/engineering discipline to make the FPGA itself and actually producing the physical thing.
ARM-based startups have conquered 95% of the smartphone market and significant chunks of TV's, set-top boxes, cars, tablets, etc since 1995, totaling at about 15 billion ARM-based chips a year (compared to Intel's 500ish million / year). That's pretty successful, right?
The specific chips I know of have ARM cores in them.
https://en.wikipedia.org/wiki/Intel_i860
I'd also look at the market of the time. Itanium was in the tech press everywhere. HP-RISC and Alpha were abandoned. MIPS moved into the low-power market. Resources for SPARC and POWER seem to have been cut. Everyone making the top-level decisions was convinced that Itanium and a sufficiently smart compiler were the solution (hint: the halting problem prevents general static analysis as Turing discovered in the 1930s).
Everyone that is, except AMD and Intel. AMD had no alternatives, so they pulled the x64 rabbit out of their hat. Meanwhile, Intel hadn't slowed down their x86 work. When Itanium fell through (like history indicated it would), Intel was out some R&D and some marketing, but had effectively killed off all their RISC competition (it took a decade or more to catch up). Intel then proceeded to Monopolize AMD almost out of existence (and only paid a couple billion in return for their hundreds of billions in profit).
It all works out way too conveniently for Intel.