I still have a working Athlon XP / KT133A with ISA under my desk.
I've always assumed the silicon is super thin - "wafer" thin. And then some material is added where the bonding wires etc are embedded in and the pads or pins are attached to.
For sure it's like this on newer CPUs, where there is not a single piece of silicon bit rather multiple ones with interconnect between them.
Overclocking an Athlon XP 2500+ to a 3200+ was pretty cool. Easiest overclock ever.
I remember it well, back in the very early 2000s, when my own Athlon XP 1800+ (an AGOIA stepping, I do know that for sure :D) met its untimely end at the hands of a device that was designed to prevent the exact misfortune that killed its sister CPU as seen in this submission!
The fragile silicon was a problem the enthusiast/PC-builder community was very aware of, and the market responded with "spacer" kits you could buy for a few $$$ that were cut from solid sheets of thin copper. These spacers would carefully wrap around all the little bumps on the CPU's upper side, and provide a level plane for the heatsink to rest upon, while still establishing direct contact with the die that it was supposed to cool down. So there was, in theory, decidedly less of a chance of killing your CPU by having the heatsink meet it in an unfortunate angle, or something to that effect.
Unfortunately, the spacer that I had bought turned out to be just a wee little bit too thick, and, despite thermal paste (Arctic Silver!), the CPU did not in fact make contact with the heatsink (something shiny from Thermalright or Zalman, I think?) at all, which killed it instantly as soon as I powered up the rig for the first time. That's what it was like back in the days, when we got to school walking ten miles uphill (both ways) barefoot in deep snow.
I had to put in some overtime at the small PC shop I worked after school back then, to afford a measly Duron 800 as its replacement. And still they keep claiming that time heals all wounds... ;)
The main reason I'm keeping it around is that it's got 5-1/4" & 3-1/2" floppy drives, and T1000 and DDR4 tape drives.
My last desktop multimedia PC was powered by Athlon XP.
Then that chip is flipped around, so the transistors and metal layers face the pcb. Most of the chip on the upside is just bulk silicon, and there for structural and heat spreading purposes, it's not needed for operation.
When chips are built out of multiple stacked layers, typically they thin the chips that go below and leave a thick bulk layer on the topmost one. IIRC, for some AMD chips they needed to use a separate, unprocessed bulk heat spreader layer for bonding reasons.
Even modern silicon only has some 60 of them right?
Plus don't transformers work in layers, making it natural to put a bunch of layers on top of each other? Regarding cooling, couldn't there be liquid cooling through a plumbing network in the same die?
Our brain takes quite a large volume, and we want chips that have a similar level of parts count (achieved - 80 billion neurons) and interconnectedness (not yet, around 10k synapses per neuron). Why do it in 80 2D layers? Is there no way to etch silicon in 3D?
It's nice that modern CPUs self-overclock well, and my 9850X3D is by far the best CPU I've ever owned. But I miss the tweaking days a little. Fun hobby.
This must be what petrol heads fear about EVs. Sure, they're simpler and less maintenance and healthier. But you can't overbore it, or add a turbo, or change the cams.
Speaking of uphill every way, I also remember upgrading to a Alpha PAL screaming 6500rpm++ CPU fan+heatsink that sounded like a mix of jet engine or broken vacuum cleaner. Ridiculously loud - this was a few months before we as a society figured out that larger fans spinning more slowly were all around better for everyone :). I think it was something tiny like 60mm diameter industrial fan.
My goto testing protocol was to recompile the Linux kernel and make GNU chess play itself at the highest settings.
I was quite disheartened to find that my rig would crash out repeatedly. Not a single successful compilation of the kernel. Then on a whim I removed the case and pointed my table fan at it. Voila, everything worked.
I had planned to get some more thermal paste and redo the thermals and put the case back. But I never did.
Then one day the dialer of my landline got fried by a thunderstorm. No problem I used to dial using my modem and my skeletonic linux box.
Great setup when the money is tight. Good times.
The next best thing would be buying a replacement.
Now that is a name I have not heard in a long time
Much later I finally noticed that the PSU, that I had in this same case ever since the PC started out as a 486, was something ridiculous, like 75W or so. I got a new cheap PSU, and finally the spookiness stopped.
Has it? CPUs ran much cooler back then. And gpus didn’t need brackets and special power cables and all that. Water cooling was harder. But also way less common or necessary.
I remember the day it arrived in the mail and I installed it - my family had just recently moved into a new house where my own room was located directly above the living room. When I started my PC with the new cooler and fan for the first time, the noise (esp. the obscene vibrations through the floor/ceiling!) actually prompted my mother to visit and check what's up/wrong :D
I ended up rigging together two chopping boards and a few pristine cleaning sponges as a kind of pedestal for my big tower case to rest upon, and was allowed to operate that way for the months to come. If it weren't for the over-ear headphones I wore all day back then, I guess I would have had suffered hearing loss from the noise exposure rather sooner than later...
GPUs could be spooky hot. While the cards themselves didn't seem to care at all, the heat emanating from a 3dfx Voodoo3 card (I've had a 2000 and a 3500TV) could be enough to make other nearby cards stinky. Fan brackets and other hacks, from now long-defunct small companies like 3dfxcool, were pretty common.
We had PCI, then AGP, then PCI Express -- with overlaps. Woe be to those who errantly picked the older standard for their shiny new build; they would forever be stuck with their new hardware on the older bus, or with an even-deeper hole in their wallet.
There were other unfriendly things. RAM compatibility was weird; I remember a time around the turn of the century when double-sided RAM became inexpensive enough that was cheaper to buy 256MB of double-sided RAM that the PC may only use half of, than to buy 128MB of single-sided RAM.
Cables weren't always keyed, and when they were keyed it wasn't always in useful ways. Plugging a floppy drive in backwards was a common experience. A 40-pin IDE cable might have a key pin blocked off, while the hard drive had all 40 pins populated, and the two wouldn't fit together without modification.
Burning CDs was often a slow-moving disaster, involving feeding expensive blanks into an expensive drive installed in the machine every half-hour just to hope that things would work this time so you could finally listen to some of those MP3s in your Ford after you spent hours downloading them.
Unless you were foolish enough to buy an external drive, instead: As USB was attrociously-slow, those burners usually plugged into the printer port in what could be most-charitably described as an awful fucking mess.
And even if we weren't burning CDs, we had that pesky analog cable to deal with -- neither end of which was necessarily standardized -- so we could play Total Annihilation and listen to its (rather excellent) soundtrack at the same time.
We still had things like sound cards and modems and IRQs to deal with. NICs were often separate from motherboards. BIOS flashing felt like a dark and dangerous art. The fan headers often had different shapes, and usually only some of them were capable of ramping fan speeds.
At one point around that time, we rather quietly shifted the main power draw for new motherboards from the 5v rail to the 12v rail. Existing power supplies weren't always ready for this and it lead some down expensive and unexpected paths.
I enjoyed working with PC hardware back then. But it was all pretty unfriendly, and I haven't even mentioned yet how much fun SCSI was to deal with.
Nowadays: We buy a fish tank and install a motherboard and power supply into it. The smart builder has already got the NVMe drive, CPU, and cooler fastened down into place in their purposeful mounts before this point. The fan headers all work. If we saved enough pennies, we add a GPU -- and it slots into the same x16 PCI Express socket that we've been using for over 20 years now. The NICs (often a plurality of them!) are built-in. There are no dip switches or configuration jumpers.
All that's left is to plug it in and install an OS. Easy.
Mobos and cases also seem better designed these days. Yes some components need more stuff than before but it all seems to plug in and slot and wrap and screw in nicely if you're patient and methodical. Heck even the cases themselves are somewhat less likely to slot your wrists :).
I feel ~2003 or so was the cusp when I started seeing less builds that were just maddeningly messy and sharp and hyper loud and crazy, and started getting more predictable and sane and workable.
All anecdotal and based on personal perception of course :)
CPUs now throttle to keep their temp in check. Back then, if the temp got too high they’d be permanently damaged like in the example above.
> Water cooling was harder. But also way less common or necessary.
Water cooling isn’t necessary today, either. The heat pipe heatsinks we have available are so good that you can cool every consumer CPU with a good air cooler. The automatic throttling means it won’t be a disaster if the temp gets high. Water cooling might get a few 100 more MHz during sustained all core workloads but it’s not necessary.
First, the NexGen Nx686 prototype... that became the K6 after AMD bought NexGen.
https://web.archive.org/web/19990901212245/http://www.sandpi...
https://web.archive.org/web/20000831030211/http://www.sandpi...
https://web.archive.org/web/20000831030227/http://www.sandpi...
Second, the AMD K6 prototype... which came in a small footprint ceramic package.
https://www.cpushack.com/chippics/AMD/K6/AMDK6-Processor-CA-...
Third, the AMD K7... which also came in that small footprint ceramic package, on a Slot A PCB, with L2 cache chips.
http://www.cpu-galerie.de/html/amdk7athlonslot.html
Enjoy!
Fair. I have a scar on the knuckle of my index finger from breaking off the cover on a 5 1/4” drive bay. I was trying to push it out and it suddenly gave. My finger slammed into sharp tin and cut deep.
I’m glad they don’t make them like that anymore.
Slap on a 256K stick of Winbond cache and boy did that thing scream for its time.
These days I slap the CPU to the motherboard and a giant heatsink with two huge fans and call it a day.
Well, it kinda depended on the CPU. And then sometimes the motherboard.
On the Intel side, P3s had a pin on Socket 370 to signal an immediate halt/shutdown. You could probably still damage the CPU, and I'm willing to bet a lot of the cheaper motherboards wouldn't respect it. But plenty did, since S370 needed other changes to support Coppermine anyway.
On the AMD Side, Athlon XPs and Morgan Durons did add a safety mechanism similar to the Pentium 3, but since the Thunderbird and Spitfire Durons did not, it was far far less supported.
My Athlon 1100 was barely a third tdp at 60watts, yet was perilous to install, broke one (almost $1k, in 2001 money!), and then on the replacement had a 6500rpm screamer jet engine under my desk sitting on mobo that barely supported it and which could fail and kill my 1core cpu at any point :0
Thanks for the nostalgia trip.
When I was researching the mess related to strange and poorly documented CPUID bits in the Athlon MP and XP processors, I had to swap a lot of CPUs. This was uneventful in most cases… but only most.
When I removed the heatsink from one unlucky Athlon XP, the processor looked like this:

A chunk of AMD Athlon silicon is just gone
And this is what the heatsink looked like, with a piece of the CPU glued to it:

A piece of an Athlon CPU stuck to a heatsink
There are two interesting things about this. One is that the CPU worked just fine until a good chunk of it came off. The other is that removing the heatsink did not need any particularly excessive force, although some heatsinks do have a tendency to get stuck on.
Based on the shape of the “extracted” piece of silicon, I suspect there was a relatively long and straight micro-crack in the silicon which did not noticeably impact the operation. But when force was applied, the micro-crack gave way, and then a whole big chunk of silicon came off.

A close-up of the damaged CPU
Notice how the right-hand side of the gouge in the CPU is very straight, whereas the left-hand side shows typical fracture marks.
It is notable that around 2000, both Intel and AMD used flip-chip PGA packaging in an effort to provide better cooling (something both companies struggled with as the TDP of the processors quickly shot past 50W and approached 70-80W).
Both companies, especially Intel, gave up on this type of packaging relatively quickly. Intel only used it for some PIII models and switched to lidded CPUs for the P4 line, as well as the PIII-S processors. AMD used flip-chip packaging for PGA Athlons but not for Opterons.
The exposed silicon was a little bit too fragile and required assemblers to install heatsinks very very carefully—if installing a heatsink applied pressure that was too uneven, the silicon would crack. Many vintage flip-chip CPUs have chipped corners, although that usually does not affect operation.
Processors with lidded packaging still provided very good cooling, but compared to CPUs with exposed silicon they proved much sturdier and far less susceptible to mechanical damage. Especially Intel’s pin-less LGA processors are quite sturdy and not at all prone to mechanical damage, although the weak spot simply moved to the motherboard socket instead.
This entry was posted in AMD, K7, PC hardware. Bookmark the permalink.