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... ;)
I accidentally bent some of the pins on mine but I was able to carefully bend them back and luckily it booted. Computer building on those days was much more unfriendly. I remember hearing tons of horror stories of water cooling including leaks and the cpu overheating and dying that kept me far away from it until more recently.
> Computer building on those days was much more unfriendly.
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.
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.
I think yes - everything was just more breakable. It feels today's heatsink, CPUs, motherboards, can handle the load and installation they're designed for (rtx 5xxx power connectors notwithstanding). I started building PCs in early 1990s and it was also just easy fun. Early 2000s were this weird time where even doing mainstream things you were absolutely supposed to, such as installing HSF on a CPU, was ridiculously perilous.
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 :)
I vaguely remember some builds where setting the DIP switches wrong came with large all-caps text about how it would kill the CPU. Also some Pentium 2 CPUs with cooling shrouds that required duct work the rivaled my house's central HVAC. And yes I remember memory slots on the motherboard that needed to be feathering in or something would snap, and anti-static gloves being critical.
These days I slap the CPU to the motherboard and a giant heatsink with two huge fans and call it a day.
> even the cases themselves are somewhat less likely to slot your wrists
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.
Yup, I killed an Athlon XP in a ridiculously (over-)expensive Voodoo Gaming computer in a similar fashion while updating the HSF, as careful as I was. I've been nervous and anxious every time I update a chip or hear sink ever since even though it's a MUCH quieter affair nowadays...
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.
Heh, one of my most prized posessions in my teens was a GlobalWin FOP38 with that PAL6035 you mentioned mounted. An absolutely CRAZY fan that had no objective right to exist, much less in a teenager's Socket A Celeron rig.
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...
Hardcore builders will remove the lid of their CPU to get the best possible thermal contact. The performance improvement is very small and not worth it but the bragging rights are fun. Unless you destroy the chip while delidding it, that is.
The article mentions this, but this was before CPUs had lids. When delidding a CPU, you have to be very careful not to crack the silicon die that you are applying force directly to. In the case of this Athlon, even care wasn't enough.
Interestingly, AMD's previous gen processors, the K6/K6-2/K6-III, were all lidded flip chips. A delidded K6-era CPU looks remarkably similar to the early Athlons which did away with the lid.
Your comment reminded me of my K6 (or was it a K7) based PC I had assembled as a high schooler of modest means.
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.
Table fan was the way to go in our first LAN party during the summer of the year 2000 in the south of Spain. These computer case side panels were all piled against the wall.
as a kid I once had a PC that would make a very loud siren noise when it was overheating. I don't know why they thought that was a good idea but I did solve it by pointing a fan at it. Somehow my parents never came and asked what's that noise.
The article is mistaken, all the lidded chips (discussed here) are also flip chip/C4. Just with a metal plate on top. That would be in contrast to the earlier lidded chips (like a 68k or i486) with ceramic packages, where the chip is mounted right side up on the ceramic package and then wire bonded, the lid just covers the bond wires.
I learned (can't remember where) that I should try to rotate the cooler a little bit, with the mounting clamp still on, before undoing the clamp and removing it.
I still have a working Athlon XP / KT133A with ISA under my desk.
I've been assembling my own desktop PCs since I was about 15, but I have never gotten comfortable with just how much pressure it takes to affix some heat sinks. I think it was my Thunderbird 1200 where you had to press a slotted-head screwdriver on the lever to force it down and under the clasp.
Is that actually the silicon that's on top of a cpu?
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.
Chips are made from silicon wafers that are ~0.8mm thick. The transistor layer is built on one side of the wafer (because the transistors need to be built from epitaxial silicon, that is, where all the atoms are neatly arranged, and you cannot deposit a perfect epitaxial layer). Then the metal layers are built on top, by depositing copper and dielectric (traditionally silicon dioxide, that is, glass, but these days some more exotic stuff is used too).
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.
I would guess that the effective layers are super thin. But such super thin parts do not have much structural integrity. So you leave material under it so that you can handle it. And then just drill to those parts as needed.
On the bottom [0], youtuber/cooling specialist/tuner der8auer did an interview with an intel engineer a few years ago. One of the points they bring up is that it's not a pure gain to have less silicon between the logic and the next interface to another material conducting heat away as the silicon itself acts as a conductor/spreader, i.e. sideways as well as upwards, so there's a balance.
No, that’s the die sawed out of a wafer. Those are wafer-thin, i.e. about 0.8mm. On some newer CPUs the wafer is ground down to improve thermals. In normal C4 packaging like here the active layer is sandwiched between the metal layers (which sit on the interposer PCB) and the bulk silicon (95% of the thickness upwards, to the camera). Silicon is not a great heat conductor.
There was just this video [0] yesterday showing the whole process for a GaN LED, it's fascinating how crude the post processing can be in contrast with the ultra precise etching and layering.
The first time I built a PC, and the first time I mounted a heatsink, was to one of these bare die AMD CPUs. I heard about the fragility of these, and must have read the directions about ten times, and paused and checked each step about five times while doing it. It came out fine, but it was nerve wracking as hell.
Overclocking an Athlon XP 2500+ to a 3200+ was pretty cool. Easiest overclock ever.
Even as a naive teen, I always found the mechanical forces required to clamp cpu heatsinks and fans brutally high considering the small ceramic package underneath.
No. AMD was taking 3200+ chips and binning/selling them as 2500+ chips. All it took was increasing the FSB speed in the BIOS, and a bit of luck from the silicon lottery. No hardware mods.
This happened to me several times with Athlons in 2000, the die on these would break exceptionally easily such that it was a known issue at the time. You had to be quite careful.
Oh man, the nostalgia. I had an Athlon XP too, and I still remember that fear when installing the heatsink. One wrong move and you're basically screwed...
I've got one sitting next to me that I'm in the process of rejuvenating. The north bridge has a small fan with integrated heatsink/boat that I'm searching for. The CPU fan is still okay. It's a pre-PCIe system, and has a VGA output (no DVI or HDMI).
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.
the fan is likely a 12vdc 40x40mm, relatively shallow one (not very high airflow and not loud) one so you should be able to get a replacement from mouser or digikey. it's basically the same thing as a 80mm case fan from the same era scaled down.
Socket 370 and Socket A were very easy to break. You needed a flat head screwdriver to pry off the metal bracket which held the cooler in place. Apply a little too much force (or just repeat the process a few times) and watch the plastic nook break off of the socket, rendering the entire mainboard useless. Zip-ties or super glue might save you, if just for a while. But good luck moving/transporting the computer then.
You'd need unlimited money and hyperadvanced future technology. There's just no way to get things lined up and no way to reconnect any of it and no way to reclaim or reattach any of the tiny bits of silicon that preferred to become dust rather than take sides.
If you had enough money to convince AMD to sell you the tapeout, and if you could hire a fab using a similar process, you could make a new CPU. Other than that... probably not.
The next best thing would be buying a replacement.
Maybe, you would have to buy AMD or make them sell you the schema/chip masks for this chip, then buy ASML and ask them to spend the next 10 years figuring out how to regrow silicon on the broken chip layer by layer while also re-exposing the missing part. You would probably also need to buy a chunk of TSMC since this would require advanced chemical processing such that you can re-grow and re-expose a part of the chip without destroying the existing part. You would also need a lot of investment in scanning technology, to measure exactly what the current state of the chip is and what needs rebuilding and where.
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?
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... ;)
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.
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.
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 :)
These days I slap the CPU to the motherboard and a giant heatsink with two huge fans and call it a day.
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.
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.
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...
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!
Thanks for the nostalgia trip.
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.
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.
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.
[0] https://youtu.be/ljZt_TQegHE?t=120
[0] https://www.youtube.com/watch?v=VHyoz8fFpUM
Overclocking an Athlon XP 2500+ to a 3200+ was pretty cool. Easiest overclock ever.
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.
The next best thing would be buying a replacement.
My last desktop multimedia PC was powered by Athlon XP.
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?