AMD x86 manual AMD Athlon Processor Microarchitecture Summary

22007E/0 — November 1999 AMD Athlon™ Processor x86 Code Optimization

AMD Athlon execution core to achieve and sustain maximum performance.

As a decoupled decode/execution processor, the AMD Athlon processor makes use of a proprietary microarchitecture, which defines the heart of the AMD Athlon processor. With the inclusion of all these features, the AMD Athlon processor is capable of decoding, issuing, executing, and retiring multiple x86 instructions per cycle, resulting in superior scaleable performance.

The AMD Athlon processor includes both the industry-standard MMX SIMD integer instructions and the 3DNow! SIMD floating-point instructions that were first introduced in the AMD-K6®-2 processor. The design of 3DNow! technology was based on suggestions from leading graphics and independent software vendors (ISVs). Using SIMD format, the AMD Athlon processor can generate up to four 32-bit, single-precision floating-point results per clock cycle.

The 3DNow! execution units allow for high-performance floating-point vector operations, which can replace x87 instructions and enhance the performance of 3D graphics and other floating-point-intensive applications. Because the 3DNow! architecture uses the same registers as the MMX instructions, switching between MMX and 3DNow! has no penalty.

The AMD Athlon processor designers took another innovative step by carefully integrating the traditional x87 floating-point, MMX, and 3DNow! execution units into one operational engine. With the introduction of the AMD Athlon processor, the switching overhead between x87, MMX, and 3DNow! technology is virtually eliminated. The AMD Athlon processor combined with 3DNow! technology brings a better multimedia experience to mainstream PC users while maintaining backwards compatibility with all existing x86 software.

Although the AMD Athlon processor can extract code parallelism on-the-fly from off-the-shelf, commercially available x86 software, specific code optimization for the AMD Athlon processor can result in even higher delivered performance. This document describes the proprietary microarchitecture in the AMD Athlon processor and makes recommendations for optimizing execution of x86 software on the processor.

AMD Athlon™ Processor Microarchitecture Summary 5