Intel processors have been with us in our PCs since the first model on the market, and the company Gordon Moore founded in his day continues to create new processors that are always faster and more efficient. That’s why we decided to take a quick tour of the history of Intel processors.
Once upon a time there was a PC with an Intel 8088
The first PC was sold by IBM with the 8088 processor, which was a shortened version of Intel’s 8086 which differed only in an 8-bit bus. The processor was not originally designed for the PC, because when Intel created it, the PC as such did not exist but rather as an evolution of the Intel 8080 without backward compatibility with it, but from which it was easy to port the programs.
It is a 16-bit CPU with the particularity of having a redirection of up to 20 bits, which allowed to have up to 1 MB of memory in total, which in 1981 was scandalous.
The Intel 80286, the biggest leap in CPU of the x86
In the early 1980s, the quintessential processor in terms of power was the Motorola 68K, which found its way into various workstations as well as Apple Macintosh computers, Commodore Amiga, Atari ST and a host of other systems. Given the huge success of the IBM PC and the large amount of software from Intel, they designed a new 16-bit processor that released the IBM PC AT in 1984, although Intel completed the design in 1982. .
The 80286 was the biggest IPC leap in Intel processor history, achieving more than double the performance per clock cycle of the 8086 and 8088. Their buses were upgraded and were no longer multiplexed, recovering instructions from memory has been sped up, more buffers have been created in the processor, and the capabilities of jump instructions have been improved.
The first 32-bit x86 processor, the Intel 80386
One of the problems the PC encountered was that it couldn’t run complex operating systems because it didn’t have any mode that allowed the operating system to run in isolation. These were added in the 80386 and thanks to that processor we were able to have much more complex operating systems than MS-DOS, making things like Windows 3 and Linux possible on a PC.
It was also the first 32-bit x86 processor and it did so by extending the length of the various registers, maintaining backward compatibility. It was also the first processor with a segmented pipeline, which was in three stages. Without a doubt one of the most important processors in the history of computing.
The 80386 was not licensed to AMD, which had to reverse-engineer and release an approximate clone of the 80386, the am386 which ran at higher clock speeds and consumed less using a more advanced manufacturing node. than the original 80386.
Integration of the FPU in the CPU with the 80486
The floating point unit, formerly known as the math coprocessor, was once sold as a component, but starting with the 80486, Intel decided to build it into the processor. But the changes based on the 80386 weren’t limited to it, but also nearly doubled the CPI, with the move to the 80486 being the second biggest jump in Intel processor history.
Other improvements made by this processor include the inclusion for the first time of the first level cache, split between data and instructions since, as well as improvements in the interface with memory and in pipelining, which has gone from 3 to 5 cycles.
As with the am386, AMD went back to reverse engineering, again going beyond Intel’s design. Of course, again with the benefit of a newer, more efficient manufacturing node.
Intel Pentium, the first superscalar processor for PC
The Intel Pentium was the first superscalar processor under ISA x86, which brought with it the ability to execute 2 instructions in parallel and at the same time. As a result, the CPI of 80486 improved by 40% in the process.
Years later, Intel released the Pentium MMX, which made a change in the FPU, as it implemented SIMD on record in it to speed up nascent multimedia programs of the time. But the Pentium MMX’s life was short.
Intel’s P6 architecture
The Pentium Pro was released in 1995 and resulted in out-of-order execution and speculative execution. Besides increasing the number of stages in the pipeline from 5 to 14, which allowed Intel to release multiple processors with this architecture.
- The Pentium Pro was the first processor to have the L2 cache built into the processor, until then it was included on the board near the processor.
- The Pentium II was based on the Pentium Pro, but moved the L2 cache, although I left it in the same package.
- The Pentium III, on the other hand, included the SSE instructions and I ended up putting the L2 cache back into the processor.
Since Intel’s P6 generation, all PC processors have run out of order.
Pentium 4, the end of a road for Intel processors
For the Pentium 4, Intel created a new architecture called Netburst, which followed the trend of the day to add a large number of stages to achieve high clock speed. It was with this processor that Intel hit the ceiling of clock speeds and it was discovered that racing based on this metric had no future, due to the high consumption of processors and temperature. they had.
It was from the Pentium 4 experience that power per metric watt became important and they began to design
Intel Pentium M, a processor designed for laptops
The Pentium 4s were so hot and consumed so much that they were not viable in a laptop, hence the creation of the first Intel Core, which was based on the P6 philosophy, but with a shorter pipeline. They added improvements that would later be adopted by other processors such as micro-operation merge, a dedicated stack for managing registers and new SSE instructions.
Intel put the Centrino platform together with them and thanks to their specs, laptops started to stop being niche computers with poor specs so they could start competing with you-to-you desktops.
Intel Core 2, the rebirth of Intel processors
The Core 2 is one of the milestones in Intel history and a paradigm shift, since it was the first multi-core processors from Intel where they also adopted for the first time the 64-bit extension of the ISA that AMD had previously offered. .
They managed to almost double the IPC over the Pentium 4, improved out-of-order execution, made the processor capable of handling more instructions in parallel, and added Smart Cache for the first time in Intel processors.
The saga of the Intel Core i3, i5 and i7 processors
Although the Intel Core 2 can be considered the first Intel Core for desktop, Intel started using Nehalem’s Intel Core i3, i5, and i7 brands which was a design improvement on the Core 2. Since then Nehalem Intel adopted AMD’s idea of integrating the Northbridge into the processor and with it the memory controller. In addition, they improved the cache, the hop prediction unit and brought back Hyperthreading after years of absence.
From this moment the changes in Intel processors have been quite modest compared to what happened before, little by little there is less to improve.
- Sand / ivy bridge: Once again, Intel has improved the Hop Prediction Unit, aside from those improved things like micro-op cache, integer and floating point units, and the performance of some instructions for capturing data from memory.
- Haswell / Broadwell: Intel again increased the number of instructions the processor can execute per cycle, in addition to increasing the bandwidth of the processor internal caches and improving the memory controller.
- SkyLake Generation: Intel has improved the number of instructions the CPU can decode, but has not increased the number of instructions it can execute in parallel. The changes compared to previous generations are very small.
- Current generation: This is the current Rocket Lake-S and Tiger Lake, after years with slight improvements in the CPI, Intel decided to follow AMD’s path not to be outdone.
This year we will see Alder Lake, the twelfth generation of Intel Core i3, i5 and i7. Will this be a minor change like what we’ve had so far or will Intel change its brand to Core 2?