Language Selection

English French German Italian Portuguese Spanish

Intel cripples programs on AMD chips

Filed under
Hardware
Legal

Intel's compilers recognise when they're running on an AMD processor, and generates code that either degrades performance or causes it to crash. That's one of the many accusations in AMD's lengthy document of complaints against Intel in its recent lawsuit against the chip giant.

The paragraph in question, number 123, reads:

"Intel has designed its compiler purposely to degrade performance when a program is run on an AMD platform. To achieve this, Intel designed the compiler to compile code along several alternate code paths. Some paths are executed when the program runs on an Intel platform and others are executed when the program is operated on a computer with an AMD microprocessor. (The choice of code path is determined when the program is started, using a feature known as "CPUID" which identifies the computer's microprocessor.) By design, the code paths were not created equally. If the program detects a "Genuine Intel" microprocessor, it executes a fully optimized code path and operates with the maximum efficiency. However, if the program detects an "Authentic AMD" microprocessor, it executes a different code path that will degrade the program's performance or cause it to crash."

Among the other issues raised by AMD were:

- That Intel used illegal subsidies to win sales and, in some cases, threatened companies with "severe consequences" for using or selling AMD products.

- That Intel has allegedly abused its dominate market position by forcing major customers into exclusive deals in return for outright cash payments, discriminatory pricing or marketing subsidies.

Following AMD's accusations, representatives of the European Commission and of national competition authorities carried out on-site inspections of several Intel offices and of the offices of an undisclosed number of PC manufacturers, as part of "an ongoing competition investigation", according to an EC spokeswoman.

By Manek Dubash
Techworld

More in Tux Machines

How Linux became my job

I've been using open source since what seems like prehistoric times. Back then, there was nothing called social media. There was no Firefox, no Google Chrome (not even a Google), no Amazon, barely an internet. In fact, the hot topic of the day was the new Linux 2.0 kernel. The big technical challenges in those days? Well, the ELF format was replacing the old a.out format in binary Linux distributions, and the upgrade could be tricky on some installs of Linux. Read more

Linux 4.16-rc2

It's been a quiet week, and rc2 is out. I take the fairly quiet rc be a good sign for 4.16, but honestly, rc2 is often fairly calm. That's probably because people are taking a breather after the merge window, but also simply because it might take a while to find any issues. But let's be optimistic, and just assume - at least for now - that it's because all is well. The diffstat is fairly odd, but that often happens with small rc's just because then just a couple of pulls will skew things easily in one or two directions. This time the patch is about one third architecture updates (arm64, x86, powerpc), one third tooling (mostly 'perf') and one third "rest". And yes, the bulk of that rest is drivers (gpu, nvme, sound, misc), but those drivers are still distinctly *not* the bulk of the whole patch. Go out and test, it all looks fine. Read more Also: Linux 4.16-rc2 Kernel Released

OpenStreetMap in IkiWiki and Why OpenStreetMap is in Serious Trouble

  • OSM in IkiWiki
    Since about 15 years ago, I have been thinking of creating a geo-referenced wiki of pubs, with loads of structured data to help searching. I don't know if that would be useful for anybody else, but I know I would use it! Sadly, the many times I started coding something towards that goal, I ended blocked by something, and I keep postponing my dream project.
  • Why OpenStreetMap is in Serious Trouble
    That said, while I still believe in the goals of OpenStreetMap, I feel the OpenStreetMap project is currently unable to fulfill that mission due to poor technical decisions, poor political decisions, and a general malaise in the project. I'm going to outline in this article what I think OpenStreetMap has gotten wrong. It's entirely possible that OSM will reform and address the impediments to its success- and I hope it does. We need a Free as in Freedom geographic dataset.

Linux KPI-Based DRM Modules Now Working On FreeBSD 11

Thanks to work done by Hans Petter Selasky and others, this drm-next-kmod port is working on FreeBSD 11 stable. What's different with this package from the ports collection versus the ported-from-Linux Direct Rendering Modules found within the FreeBSD 11 kernel is that these DRM modules are using the linuxkpi interface. Read more