improvements over i486

improvements over i486
Pentium Overdrive for i486 systems

* Superscalar architecture - The Pentium has two datapaths (pipelines) that allow it to complete more than one instruction per clock cycle. One pipe (called U) can handle any instruction, while the other (called V) can handle the simplest, most common instructions. Some RISC-proponents argued that the "complicated" x86 instruction set would probably never be implemented by a tightly pipelined microarchitecture, much less by a dual pipeline design. The 486 and the Pentium demonstrated that this was indeed possible and feasible.
* 64-bit external databus width - This doubles the amount of information read or written on each memory access. This doesn't mean that the Pentium can execute 64-bit applications; its main registers are still 32 bits wide.
* Faster floating point unit.
* MMX instructions (later models only) - A basic SIMD instruction set extension designed for use in multimedia applications.

Pentium architecture chips offered just under twice the performance of a 486 processor per clock cycle. The fastest Intel 486 parts were almost as powerful as a first-generation Pentium, and the AMD Am5x86 was roughly equal to the Pentium 75.

The Pentium ("Classic") series were designed to run at over 100 million instructions per second (MIPS), with the 75 MHz model running at 126.5 MIPS.

No comments:

Post a Comment