AMD AthlonTM Processor
 Trademarks
 Contents
 Instruction Decoding Optimizations
 Cache and Memory Optimizations
 Scheduling Optimizations
 Floating-Point Optimizations
 General x86 Optimization Guidelines 127
 Appendix B Pipeline and Execution Unit Resources Overview
 Appendix E Programming the Mtrr and PAT
 List of Figures
 Xii
 List of Tables
 Xiv
 Revision History
 Xvi
 About this Document
Introduction
 Source Level Optimizations. Describes optimizations that
 AMD Athlon Processor Family
 AMD Athlon Processor Microarchitecture Summary
 AMD Athlon Processor Microarchitecture Summary
 AMD Athlon Processor x86 Code Optimization
 Top Optimizations
 Optimization Star
Memory Size and Alignment Issues
Group I Optimizations Essential Optimizations
Use the 3DNow! Prefetch and Prefetchw Instructions
 Select DirectPath Over VectorPath Instructions
Group II Optimizations-Secondary Optimizations
Load-Execute Instruction Usage
Use Load-Execute Instructions
 Take Advantage of Write Combining
Use 3DNow! Instructions
Avoid Branches Dependent on Random Data
 Avoid Placing Code and Data in the Same 64-Byte Cache Line
 22007E/0 November
 Use 32-Bit Data Types for Integer Code
Source Level Optimizations
 Consider the Sign of Integer Operands
Example 1 Avoid
Example Preferred
 Example Avoid
Use Array Style Instead of Pointer Style Code
Use unsigned types for
Use signed types for
 Vertex
 Example 2 Preferred
 Avoid Unnecessary Store-to-Load Dependencies
Completely Unroll Small Loops
 Avoid Unnecessary Store-to-Load Dependencies
 Consider Expression Order in Compound Branch Conditions
 Switch Statement Usage
Optimize Switch Statements
Use Prototypes for All Functions
 Use Const Type Qualifier
Generic Loop Hoisting
Example
 Generalization for Multiple Constant Control Code
 Declare Local Functions as Static
 Introduce Explicit Parallelism into Code
Dynamic Memory Allocation Consideration
 Explicitly Extract Common Subexpressions
 Example
Language Structure Component Considerations
Avoid
Preferred
 Sort Local Variables According to Base Type Size
Original ordering Avoid
New ordering, with padding Preferred
 Improved ordering Preferred
Accelerating Floating-Point Divides and Square Roots
 Accelerating Floating-Point Divides and Square Roots
 Avoid Unnecessary Integer Division
 AMD Athlon Processor x86 Code Optimization
 Overview
Instruction Decoding Optimizations
 Select DirectPath Over VectorPath Instructions
Load-Execute Instruction Usage
Use Load-Execute Integer Instructions
 TOP
 Use Short Instruction Lengths
Align Branch Targets in Program Hot Spots
 Example 2 Avoid
Avoid Partial Register Reads and Writes
 Replace Certain Shld Instructions with Alternative Code
Use 8-Bit Sign-Extended Immediates
 Code Padding Using Neutral Code Fillers
Use 8-Bit Sign-Extended Displacements
 Recommendations for the AMD Athlon Processor
 Code Padding Using Neutral Code Fillers
 AMD Athlon Processor x86 Code Optimization
 NOP6EDI
 AMD Athlon Processor x86 Code Optimization
 Memory Size and Alignment Issues
Cache and Memory Optimizations
Avoid Memory Size Mismatches
 Use the 3DNow! Prefetch and Prefetchw Instructions
Align Data Where Possible
 Code
Example Multiple Prefetches
 MOV ECX, -LARGENUM
 Prefetch Distance = 200 DS/C bytes
Determining Prefetch Distance
 Avoid Placing Code and Data in the Same 64-Byte Cache Line
Take Advantage of Write Combining
 Store-to-Load Forwarding Pitfalls -True Dependencies
Store-to-Load Forwarding Restrictions
 Example 4 Avoid
Example 3 Avoid
 Example 5 Preferred
Example 6 Avoid
Example 7 Avoid
 Summary of Store-to-Load Forwarding Pitfalls to Avoid
Stack Alignment Considerations
 Align Tbyte Variables on Quadword Aligned Addresses
 Sort Variables According to Base Type Size
 Avoid Branches Dependent on Random Data
Branch Optimizations
 Blended AMD-K6and AMD Athlon Processor Code
AMD Athlon Processor Specific Code
 Always Pair Call and Return
Example 6 Increment Ring Buffer Offset
Example 7 Integer Signum Function
 Muxing Constructs
Replace Branches with Computation in 3DNow! Code
 Sample Code Translated into 3DNow! Code
Code
3DNow! code
 MM5
 Pfsub
 Psrad
 Avoid Far Control Transfer Instructions
Avoid the Loop Instruction
 Avoid Recursive Functions
 Schedule Instructions According to their Latency
Scheduling Optimizations
Unrolling Loops
Complete Loop Unrolling
 Partial Loop Unrolling
 With Partial Loop Unrolling
Without Loop Unrolling
 Control For Partially
Deriving Loop
Unrolled Loops
Example 1 rolled loop
 Overview
Use Function Inlining
 Always Inline Functions if Called from One Site
Avoid Address Generation Interlocks
 Minimize Pointer Arithmetic in Loops
Use Movzx and Movsx
 MOV ECX, Maxsize
 Example 3 Preferred
Push Memory Data Carefully
 Push Memory Data Carefully
 Integer Optimizations
Replace Divides with Multiplies
Multiplication by Reciprocal Division Utility
 Unsigned Division by Multiplication of Constant
 Signed Division by Multiplication of Constant
Simpler Code for
Restricted Dividend
 Signed Division By 2n
Signed Division By
Remainder of Signed
Integer 2 or
 Integer 2n or -2n
Use Alternative Code When Multiplying by a Constant
 ADD REG1, REG1 REG1, REG2 SHL
 Use MMX Instructions for Integer-Only Work
 Repeated String Instruction Usage
Latency of Repeated String Instructions
Guidelines for Repeated String Instructions
 Ensure DF=0 UP
Using Movq
Align Source
Destination with
 Efficient 64-Bit Integer Arithmetic
Use XOR Instruction to Clear Integer Registers
 Example 4 Left shift
Example 5 Right shift
Example 6 Multiplication
 EBX, ESP+12 Dividendlo
Example 7 Division
 Example 8 Remainder
 SHR EDX
 Step
Efficient Implementation of Population Count Function
 Bit field. Thus the following computation is performed
 MOV EDX, EDX SHR
 Derivation of Multiplier Used for Integer Division by
 Utility sdiv.exe was compiled using the following code
 MOV ECX EDX Imul ADD SHR SAR
 Floating-Point Optimizations
Ensure All FPU Data is Aligned
Use Multiplies Rather than Divides
 Use Ffreep Macro to Pop One Register from the FPU Stack
Floating-Point Compare Instructions
 Use the Fxch Instruction Rather than FST/FLD Pairs
Avoid Using Extended-Precision Data
 Example 1 Fast
Minimize Floating-Point-to-Integer Conversions
 Example 2 Potentially faster
 Example 4 Fastest
Example 3 Potentially faster
 Floating-Point Subexpression Elimination
 104
 Take Advantage of the Fsincos Instruction
 106
 3DNow! and MMX Optimizations
Use 3DNow! Instructions
Use Femms Instruction
 Use 3DNow! Instructions for Fast Division
Optimized 14-Bit Precision Divide
Optimized Full 24-Bit Precision Divide
 Newton-Raphson Reciprocal
Pipelined Pair of 24-Bit Precision Divides
 Optimized 24-Bit Precision Square Root
Optimized 15-Bit Precision Square Root
 Newton-Raphson Reciprocal Square Root
 AMD Athlon
3DNow! and MMX Intra-Operand Swapping
Specific Code
Blended Code
 Use MMX Pxor to Negate 3DNow! Data
Fast Conversion of Signed Words to Floating-Point
 Both Numbers
Use MMX Pcmp Instead of 3DNow! Pfcmp
Positive One Negative, One
Positive
 AMD-K6and AMD Athlon Processor Blended Code
Use MMX Instructions for Block Copies and Block Fills
 116
 Processor Specific
 Use MMX Pxor to Clear All Bits in an MMX Register
 Use MMX Pcmpeqd to Set All Bits in an MMX Register
Optimized Matrix Multiplication
 MOV EBX, RES
 Optimized Matrix Multiplication 121
 Data
 Use 3DNow! Pavgusb for MPEG-2 Motion Compensation
 MM0=QWORD1
 Stream of Packed Unsigned Bytes
 Complex Number Arithmetic
 Short Forms
General x86 Optimization Guidelines
 Dependencies
Register Operands
Stack Allocation
 Introduction
AMD Athlon Processor Microarchitecture
 Superscalar Processor
AMD Athlon Processor Microarchitecture
 AMD Athlon Processor Microarchitecture 131
 Branch Prediction
Predecode
 Early Decoding
 Data Cache
Instruction Control Unit
 Integer Execution Unit
Integer Scheduler
 Floating-Point Scheduler
 12 to
Floating-Point Execution Unit
 Load/Store Unit
Load-Store Unit LSU
 L2 Cache Controller
Write Combining
AMD Athlon System Bus
 140 AMD Athlon Processor Microarchitecture
 Fetch and Decode Pipeline Stages
Pipeline and Execution Unit Resources Overview
 C T L R O M
 Cycle 2-SCAN
Cycle 1-FETCH
Cycle 3 DirectPath
Cycle 3 VectorPath
 Integer Pipeline Stages
Integer Pipeline Stages
 Cycle 8-EXEC
Cycle 7-SCHED
Cycle 9-ADDGEN
Cycle 10 -DCACC
 Floating-Point Pipeline Stages
Floating-Point Pipeline Stages
 Cycle 8-REGREN
Cycle 7-STKREN
Cycle 9-SCHEDW
Cycle 10 -SCHED
 Terminology
Execution Unit Resources
Operands
Results
 Integer Pipeline Operations
Integer Pipeline Operation Types
Integer Decode Types
 Floating-Point Pipeline Operations
Floating-Point Pipeline Operation Types
Floating-Point Decode Types
 Load/Store Pipeline Operations
Load/Store Unit Stages
Stage 1 Cycle Stage 2 Cycle Stage 3 Cycle
 Code Sample Analysis
 Imul EAX, ECX INC ESI MOV
ADD EDI, EBX SHL
INC EBX ADD ESI, EDX
 Sample 2 Integer Register and Memory Load Operations
DEC EDX MOV EDI, ECX SUB
SAR
 Implementation Write Combining
Appendix C
 What is Write Combining?
Write-Combining Definitions and Abbreviations
Programming Details
 Write-Combining Operations
 INIT, Halt
Write Combining Completion Events
 Sending Write-Buffer Data to the System
AMD Athlon System Bus Commands Generation Rules
 160 Write-Combining Operations
 Performance Counter Usage
Performance-Monitoring Counters
 PerfEvtSel30 Registers
PerfEvtSel30 MSRs MSR Addresses C0010000h-C0010003h
 Performance Counter Usage 163
 Performance-Monitoring Counters
 73h
65h
Snoop hits
74h
 Waited to use the L2
Event Source Event Description
Instruction cache fetches
Instruction cache misses
 PerfCtr30 MSRs MSR Addresses C0010004h-C0010007h
 Starting and Stopping the Performance-Monitoring Counters
Event and Time-Stamp Monitoring Software
 Monitoring Counter Overflow
 170 Monitoring Counter Overflow
 Memory Type Range Register Mtrr Mechanism
Programming the Mtrr
 172 Memory Type Range Register Mtrr Mechanism
 Fixed Ranges
FFFFFFFFh
100000h Kbytes each Fixed Ranges C0000h 80000h
 Memory Type Encodings
Memory Types
Mtrr Capability
Register Format
 Memory Type Range Register Mtrr Mechanism 175
 Standard Mtrr Types and Properties
 Attribute Table MSR 277h
Attribute Table PAT
 PATi 3-Bit Encodings
PAT Entry Reset Value
MTRRs and PAT
PATi
 PAT Memory Type Mtrr Memory Type
Effective Memory Type Based on PAT and MTRRs
 Input Memory Type
Final Output Memory Types
 Attribute Table PAT 181
 9FFFF 9BFFF 97FFF 93FFF 8FFFF 8BFFF 87FFF 83FFF
7FFFF 6FFFF 5FFFF 4FFFF 3FFFF 2FFFF 1FFFF 0FFFF
Bffff Bbfff B7FFF B3FFF Affff Abfff A7FFF A3FFF
C7FFF C6FFF C5FFF C4FFF C3FFF C2FFF C1FFF C0FFF
 Attribute Table PAT 183
 MTRRphysMaskn Register Format
 MTRR-Related Model-Specific Register MSR Map
 186
 Instruction Dispatch Execution Resources
Appendix F
 AAA
Integer Instructions
AAD
AAM
 ADC mreg8, reg8
ModR/M Decode Byte
ADC mem8, reg8
ADC mreg16/32, reg16/32
 Bswap EAX
Bound
Bswap ECX
Bswap EDX
 CLC
CBW/CWDE
CLD
CLI
 CMOVE/CMOVZ reg16/32, mem16/32 0Fh
CMOVE/CMOVZ reg16/32, reg16/32 0Fh
CMOVG/CMOVNLE reg16/32, reg16/32 0Fh
CMOVG/CMOVNLE reg16/32, mem16/32 0Fh
 CWD/CDQ
Cpuid
DAA
DAS
 AL, DX
Enter
AX, DX
EAX, DX
 Invlpg
Invd
 Leave
Lahf
 LOOPNE/LOOPNZ disp8 E0h
LOOPE/LOOPZ disp8 E1h
LSL reg16/32, mreg16/32 0Fh 03h
LSL reg16/32, mem16/32 0Fh 03h
 NOP Xchg EAX, EAX
 OUT DX, AX
OUT DX, AL
OUT DX, EAX
POP ES
 POP ESP
POP EBX
POP EBP
POP ESI
 Rdmsr
Rdpmc
Rdtsc
 Sahf
 SBB mem16/32, reg16/32
SBB mreg16/32, reg16/32
SBB reg8, mreg8
SBB reg8, mem8
 Sets mem8
Sets mreg8
Setns mreg8
Setns mem8
 STC
STD
STI
 Sysenter
Syscall
Sysexit
Sysret
 Xchg EAX, ECX
Xchg EAX, EAX
Xchg EAX, EDX
Xchg EAX, EBX
 Emms
MMX Instructions
 DFh
Pandn mmreg1, mmreg2
Pandn mmreg, mem64
Pcmpeqb mmreg1, mmreg2
 FADD/FMUL
 FPU
MMX Extensions
 Floating-Point Instructions
 Fcompp
Fcos
Fdecstp
 Fincstp
Finit
FLD1
 FLDL2T
FLDL2E
FLDLG2
FLDLN2
 Ftst
Fstsw AX
Fucom
Fucomp
 Femms
DNow! Instructions
 DNow! Extensions
 DirectPath Instructions
DirectPath versus VectorPath Instructions
 DirectPath Integer Instructions
BT mreg16/32, reg16/32 BT mreg16/32, imm8 BT mem16/32, imm8
CBW/CWDE CLC CMC
 INC mreg8 INC mem8 INC mreg16/32 INC mem16/32 JO short disp8
DEC mreg8 DEC mem8 DEC mreg16/32 DEC mem16/32
 222 DirectPath Instructions
 DirectPath Instructions 223
 224 DirectPath Instructions
 Wait Xchg EAX, EAX
 226 DirectPath Instructions
 DirectPath MMX Instructions
 DirectPath MMX Extensions
 Fcompp Fdecstp
DirectPath Floating-Point Instructions
Fist mem16int
FLD1 FLDL2E FLDL2T FLDLG2 FLDLN2 Fldpi Fldz
 Ftst Fucom Fucomp Fucompp Fwait Fxch
 VectorPath Integer Instructions
VectorPath Instructions
AAA AAD AAM AAS
CLD CLI Clts
 AL, DX AX, DX EAX, DX Invd Invlpg
Instruction Mnemonic DIV EAX, mem16/32
 Push mreg16/32 Push mem16/32
POP mreg 16/32 POP mem 16/32
PUSHA/PUSHAD PUSHF/PUSHFD
Rdmsr Rdpmc Rdtsc
 VectorPath MMX Extensions
VectorPath MMX Instructions
Syscall Sysenter Sysexit Sysret
Wbinvd Wrmsr
 Fptan Fpatan Frndint
VectorPath Floating-Point Instructions
Fscale Fsin Fsincos
Fxam Fxtract FYL2X FYL2XP1
 236
 Index
 238 Index
 Index 239
 240 Index