Posts by expat_abroad 4 publicly visible posts • joined 4 May 2018
The key problem with this and similar chip designs is not the hardware, but having a working compiler that will actually let one do all the great things this chip is supposed to do. If Tachyum can demonstrate an early version of a compiler that at least sort-of works, they have a chance. For example, Tachyum wants to implement out-of-order execution on their in-order design through the compiler - far from a trivial task, and that's just one of many.
One thing I simply don't get is why HDD manufacturers are still sticking to the 3.5" disk format. I mean, let's face it - spinning rust lost the speed race to SSDs years ago. It's main and key advantage is capacity/price, which SSDs simply can't touch for now. I don't buy drives like these 10 TB here for speed, but for lot's of cheap space, and I can always use more. So, why not go back to, let's say, 5.25 inch format platters, which offer an ~ 80% larger area (3.5 inch disks are actually a bit over 3.7 inches, and 5.25 disks are about 5.1 inch in diameter). These larger disks fell into disfavor due to higher loads on the motors and spindles and worse thermals many years ago, BUT, that was long before we had current disk materials and He-filled drives that enable thinner, lighter disks and reduced friction. Plus, current bays for 3.5 inch drives (except laptops) are 5.25 inch bays, after all, so they would fit in my existing racks or NASs. So, Toshiba, WD, Seagate & Co., how about it? Instead of a 10 TB capacity, we'd instantly go to 18 TB, sticking to PMR. Thoughts, Comments?
The key one of this new Spectre-spawn actually does have a lot of potential - for damage, that is. Apparently, targeting this primo variant can allow an attacker to access several, possibly even all VMs running on a server, harvesting user names and passwords along whatever files are to be had. With AWS, Azure &Co. running a lot of government services these days, there is plenty of yummy secrets to be slurped (and for once, not by Facebook or Google) . Intel's statement is remarkable, as it doesn't dispute any of this.
As a question: is current Big Iron immune to any or all of this?
Actually, switching to an ARM architecture likely would not fix it. ARM had "no comments " on these vulnerabilities, but it looks like everything with predictive branching is vulnerable. So, looks like pretty much everybody fell into the crapper on these, and they all stink alike.
The Register 
Biting the hand that feeds IT
Copyright. All rights reserved © 1998–2025
