AMD Athlon: Processor
AMD Athlon: Processor
AMD Athlon: Processor
TM
Processor
Technical Brief
AMD’s products are not designed, intended, authorized or warranted for use
as components in systems intended for surgical implant into the body, or in
other applications intended to support or sustain life, or in any other applica-
tion in which the failure of AMD’s product could create a situation where per-
sonal injury, death, or severe property or environmental damage may occur.
AMD reserves the right to discontinue or make changes to its products at any
time without notice.
Trademarks
AMD, the AMD logo, AMD Athlon, and combinations thereof, and 3DNow! are trademarks of Advanced Micro
Devices, Inc.
Other product names used in this publication are for identification purposes only and may be trademarks of
their respective companies.
22054D/0—December 1999 AMD Athlon™ Processor Technical Brief
Revision History
Date Rev Description
August 1999 C Initial public release.
Added information about AMD's new 0.18-micron process technology to “Process Technology”
December 1999 D
on page 7
Technical Brief
Introduction
Introduction 1
AMD Athlon™ Processor Technical Brief 22054D/0—December 1999
2 Introduction
22054D/0—December 1999 AMD Athlon™ Processor Technical Brief
Fetch/Decode
Control
3-Way x86 Instruction Decoders
Multiple Decoders
The AMD Athlon processor includes three full x86 instruction
decoders. These decoders translate x86 instructions into
fixed-length MacroOPs for higher instruction throughput and
increased proc essing power. Inst ead of exec ut ing x86
instruct ions, which have lengths of 1 to 15 bytes, the
AMD Athlon processor executes the fixed-length MacroOPs,
while maintaining the instruction coding efficiencies found in
x86 programs.
Execution Pipelines
T h e A M D A t h l o n p ro c e s s o r c o n t a i n s a n 1 8 -e n t ry
integer/address generation MacroOP scheduler and a 36-entry
floating-point unit (FPU)/multimedia scheduler. These
schedulers issue MacroOPs to the nine independent execution
pipelines — three for integer calculations, three for address
calculations, and three for execution of MMX, 3DNow!, and x87
floating-point instructions.
The AM D Athlon pro ce sso r o f fe rs the mo st powe rful,
architecturally advanced floating-point engine ever delivered
in an x86 microprocessor. The AMD Athlon processor's
three-issue, superscalar floating-point capability is based on
three pipelined, out-of-order floating-point execution units,
each with a one-cycle throughput. These three execution units
(FMUL, FADD, and FSTORE) execute all x87 (floating-point)
instructions, MMX instructions, and enhanced 3DNow!
instructions. Using a data format and single-instruction
multiple-data (SIMD) operations based on the MMX instruction
model, the AMD Athlon processor can deliver as many as four
32-bit, single-precision floating-point results per clock cycle,
resulting in a peak performance of 2.4 Gflops at 600 MHz.
4 AMD Athlon™ Processor Microarchitecture
22054D/0—December 1999 AMD Athlon™ Processor Technical Brief
Branch Prediction
The AMD Athlon processor offers sophisticated dynamic
branch prediction logic to minimize or eliminate the delays due
to the branch instructions (jumps, calls, returns) common in x86
software. The processor includes the following:
■ Branch prediction table
■ Branch target address table
■ Return address stack
Cache Architecture
The A MD At hlon processor’ s hig h-perfo rma nce cache
architecture includes an integrated, 64-bit, dual-ported
128-Kbyte split-L1 cache with separate snoop port, multi-level
translation lookaside buffers (TLBs), a scalable L2 cache
controller with a 72-bit (64-bit data + 8-bit ECC) interface to as
much as 8-Mbyte of industry-standard SDR or DDR SRAMs, and
an integrated tag for the most cost-effective 512-Kbyte L2
configurations.
Process Technology
The AMD Athlon processor is manufactured on AMD's six-layer
metal, 0.25-micron process technology and AMD's new
0.18-micron process technology. In 0.25-micron technology, the
approximately 22-million-transistor AMD Athlon processor has
a d i e si z e o f 1 8 4 m m 2 . I n 0 . 1 8 -m i c ro n t e chn o l ogy, t h e
AMD Athlon processor has a die siz e of 102 mm 2 . The
AMD Athlon processor is inc luded in a cost-eff ective,
industry-standard module form factor — Slot A, which is
mechanically compatible with the existing Slot 1 infrastructure,
and therefore, leverages commonly available chassis, power
supply, and thermal solutions.
Summary
T h e A M D A t h l o n p ro c e s s o r ' s s e ve n t h -g e n e ra t i o n
microarchitecture and high-bandwidth system bus enable it to
attain performance levels never before achieved by an x86
processor. The AMD Athlon significantly outperforms
previous-generation x86 processors and delivers the highest
integer, floating-point, and 3D multimedia performance
available for x86 platforms, as measured by industry-standard
benchmarks.
The AMD Athlon provides industry-leading processing power
for cutting-edge software applications, including digital
content creation, digital photo editing, digital video, image
compression, video encoding for streaming over the internet,
sof t DVD, c ommerc ial 3D modeling, workstation-class
computer-aided design (CAD), commercial desktop publishing,
and speech recognition.
AMD Athlon™ Processor Microarchitecture 7