It seems a shortcoming in AMD's processor QA testing has allowed a "very small number" of AMD CPU's to slip through the cracks with an annoying problem. Affected processors can't properly render JPEG images or MPEG audio or video in certain applications. Since JPEG and MPEG decompression can be done with either the ALU or the FPU, I'm not sure which functional unit contains the error. Since the problem is application specific, it probably only involves one of those units.
Van Smith has confirmed with AMD that the issue is real. This site has been detailing the issue since late 1998. The site also contains the necessary resources to determine if your AMD chip is affected.
Judging by the AMD statement, this QA shortcoming may have existed for quite some time, since the K6-2, Athlon, and Duron are all named. Oddly, the K6-3 isn't mentioned. It's also pecuilar that this problem has gone unnoticed for so long. I suppose if a problem is small enough, it's hard to notice the trend. After all, everything mass produced typically has a lemon batch here or there.
Thanks for the heads up, Rand.
|1. BIF - $340||2. Ryu Connor - $250||3. mbutrovich - $250|
|4. YetAnotherGeek2 - $200||5. End User - $150||6. Captain Ned - $100|
|7. Anonymous Gerbil - $100||8. Bill Door - $100||9. ericfulmer - $100|
|10. dkanter - $100|
|AMD drops prices on the Radeon RX 460 and RX 470||36|
|Reports: Radeon RX 470D is a budget Polaris card for China||6|
|Examining reports of slow write speeds on the 32GB iPhone 7||23|
|Cellular Insights dissects iPhone 7 Plus modem performance||11|
|Deals of the week: scads of high-performance storage and more||9|
|Tobii's Eye Tracker 4C knows where your head is||2|
|GeForce driver 375.57 is prepared for Titanfall 2||7|
|Phanteks Eclipse P400 gets a tempered glass option||0|
|Radeon 16.10.2 drivers add support for October's big games||10|
|A real "console monitor" would be 720p @ 30 Hz ;P||+58|