When we have to change the CPU of our PC, unless it is compatible with the socket of our motherboard, we have to change almost the entire PC. Wouldn’t it be ideal to have in a expansion card for the processor? Well then, we are going to explain the reasons why it has not been done since those Intel Socket 1 of the Pentium III and it will not be done in the future either (surely).
For any central processor, the biggest bottleneck is the communication with the RAM memory, there is no more. It is about the universal limitation that for physical reasons will always be there and that at the same time makes certain scenarios impossible. The case at hand is that of having the processor as an expansion card, so we would really be talking about a scenario like that of graphics cards, in which main memory and CPU would be on the same PCI Express card.
Can another processor be added through an expansion card?
Imagine for a moment the following scenario: instead of using a socket to plug the central processor to the motherboard, Intel and AMD decide that their PC CPUs are going to come in the form of an expansion card that can be plugged into a PCI Express port.
At first glance, this would be ideal, it would allow us to have universal motherboards for both Intel and AMD. What’s more, at the same time, the chipsets on the board would be universal and we wouldn’t have a huge number of motherboard models for different processors. It would be ideal, don’t you think? Well, this has never been done on the PC and the reasons are not, as many may believe, economic, but technical. Although if it were done, it would not be a novelty either.
A bit of historical perspective
Before the PC became standardized as we know it now, a standard based on the MITS Altair called S-100 appeared, in which all components communicated through a common board that was a series of card slots. totally symmetrical expansion. Even the central processor was on a separate expansion card. Of course, they were systems for a minority at a time when the users themselves had to know both programming and soldering to create their own boards or sell them to third parties.
The image above corresponds to an Intel 8086, as a curiosity, the three largest chips are not the CPU, but also the memory controller that was not integrated at that time and the peripheral manager. The rest? RAM. Notice how even with a processor clocked below 5 MHz, the system RAM is not found on another board. This is because if the distance between a processor and a memory is too high, this is detrimental because the signal transmission slows down. In theory the idea would be none other than to place the RAM and the CPU on the board itself, but this leads us to the next question.
Could two cards of this type intercommunicate with each other?
The fact that we have two memory pools at a great distance from each other presents a series of problems, since we not only have to make sure that there are coherence mechanisms in a non-unified system, which is a nightmare for hardware. In addition to the fact that when a data or instruction is found in the memory of another board, the latency would be too high.
What times would we be talking about? The PCI Express interface can add, if we’re generous, 200 nanoseconds per access to what we’d already get with a direct connection to memory, so instructions would take much longer to complete and overall performance would drop dramatically for the time it takes. it would take the CPU to receive the instructions. What has been done, instead, is to use a general purpose processor as a central accelerator, but this is not done due to the fact that it was discovered long ago that GPUs for certain tasks are more efficient than adding additional cores.
So no, you can’t add more cores to the CPU as an expansion card, would it be ideal to be able to? There is no doubt, but we hope that you have understood the reasons that make it totally impossible.
