Manuals / Compaq / Computer Equipment / Laptop

Compaq ECQD2KCTE Denormal, Dirty zero, Infinity, Non-finite number, Not-a-Number, Trap shadow

Models: ECQD2KCTE

1 371

Download 371 pages 20.35 Kb

Page 120

For VAX floating-point, finites do not include reserved operands or dirty zeros (this differs from the usual VAX interpretation of dirty zeros as finite). For IEEE floating-point, finites do not include infinites, NaNs, or denormals, but do include minus zero.

denormal

An IEEE floating-point bit pattern that represents a number whose magnitude lies between zero and the smallest finite number.

dirty zero

A VAX floating-point bit pattern that represents a zero value, but not in true-zero form.

infinity

An IEEE floating-point bit pattern that represents plus or minus infinity.

LSB

The least significant bit. For a positive finite representable number A, A + 1 LSB is the next larger representative number, and A + ½ LSB is exactly halfway between A and the next larger representable number. For a positive representable number A whose fraction field is not all zeros, A – 1 LSB is the next smaller representable number, and A – ½ LSB is exactly halfway between A and the next smaller representable number.

non-finite number

An IEEE infinity, NaN, denormal number, or a VAX dirty zero or reserved operand.

Not-a-Number

An IEEE floating-point bit pattern that represents something other than a number. This comes in two forms: signaling NaNs (for Alpha, those with an initial fraction bit of 0) and quiet NaNs (for Alpha , those with initial fraction bit of 1).

representable result

A real number that can be represented exactly as a VAX or IEEE floating-point number, with finite precision and bounded exponent range.

reserved operand

A VAX floating-point bit pattern that represents an illegal value.

trap shadow

The set of instructions potentially executed after an instruction that signals an arithmetic trap but before the trap is actually taken.

true result

The mathematically correct result of an operation, assuming that the input operand values are exact. The true result is typically rounded to the nearest representable result.

4–64Alpha Architecture Handbook

Image 120

Compaq ECQD2KCTE Denormal, Dirty zero, Infinity, Non-finite number, Not-a-Number, Representable result, Reserved operand

Contents

Alpha Architecture Handbook October Table of Contents Instruction Formats Page 10.19 Integer Register to Floating-Point Register Move System Architecture and Programming Implications Digital Unix Ieee Floating-Point Conformance Index Figures Tables Xiii Xiv Preface Page Chapter Alpha Approach to Risc ArchitectureAlpha Is a True 64-Bit Architecture Alpha Is Designed for Very High-Speed ImplementationsAlpha Approach to Byte Manipulation Alpha Approach to Multiprocessor Shared MemoryAlpha Instructions Include Hints for Achieving Higher Speed PALcode Alpha’s Very Flexible Privileged Software LibraryData Format Overview Alpha and Programming LanguagesInstruction Format Overview Instruction OverviewPALcode Instructions Branch Instructions Load/Store InstructionsInteger Operate Instructions Instruction Set Characteristics Terminology and ConventionsFloating-Point Operate Instructions Numbering Security HolesUnpredictable and Undefined Ranges and Extents Aligned and UnalignedUnaligned Must Be Zero MBZ Read As Zero RAZShould Be Zero SBZ Ignore IGNPage Addressing Data TypesByte WordLongword QuadwordVAX Floating-Point Formats FfloatingFfloating Load Exponent Mapping Mapf GfloatingGfloating Register Format DfloatingIeee Floating-Point Formats SFloating Sfloating Load Exponent Mapping Maps Memory RegisterTfloating 13 Tfloating Datum14 Tfloating Register Format XFloating15 Xfloating Datum XFloating Big-Endian FormatsLongword Integer Format in Floating-Point Unit 17 Xfloating Big-Endian DatumQuadword Integer Format in Floating-Point Unit Data Types with No Hardware SupportBig-Endian Addressing Support 23 Little-Endian Byte Addressing14Alpha Architecture Handbook Alpha Registers Program CounterInteger Registers Implementation noteFloating-Point Registers Lock RegistersNotation Processor Cycle Counter PCC RegisterOptional Registers Memory Prefetch RegistersOperand Notation Operand Notation MeaningOperand Value Notation Meaning Expression Operand Notation MeaningOperand Access Type Notation Operand Access Type Notation MeaningInstruction Operand Notation Operand Name NotationOperators Operand Data Type NotationOperand Data Type Notation Meaning Operators MeaningBit concatenation Case DIVLoadlocked Not PhysicaladdressPriorityencode LTUInstruction Formats Notation ConventionsSoftware Note XORMemory Instruction Format Memory Format Instructions with a Function CodeBranch Instruction Format Operate Instruction FormatMemory Format Jump Instructions Floating-Point Operate Instruction Format Floating-Point Operate Instruction FormatPALcode Instruction Format Floating-Point Convert InstructionsFloating-Point/Integer Register Moves PALcode Instruction Format Page Instruction Set Overview Instruction Type SectionSubsetting Rules Floating-Point SubsetsSoftware Emulation Rules Opcode QualifiersOpcode Qualifiers Meaning Memory Integer Load/Store Instructions Memory Integer Load/Store Instructions Mnemonic OperationLoad Address Load Memory Data into Integer Register LDLImplementation Notes Load Unaligned Memory Data into Integer Register Load Memory Data into Integer Register Locked 10Alpha Architecture Handbook Implementation Notes Store Integer Register Data into Memory Conditional Stqc BEQ Hardware/Software Implementation Note Store Integer Register Data into Memory 16Alpha Architecture Handbook Store Unaligned Integer Register Data into Memory Control Instructions Control Instructions Summary Mnemonic OperationBNE BSRJMP JSRConditional Branch Unconditional Branch Jumps Encoding Meaning Integer Arithmetic Instructions Count instruction CIX extension implementation noteInteger Arithmetic Instructions Summary Mnemonic Operation Longword Add AddlScaled Longword Add S4ADDLS8ADDL Quadword Add AddqScaled Quadword Add S4ADDQS8ADDQ Integer Signed Compare Integer Unsigned Compare Count Leading Zero Count Population Count Trailing Zero Longword Multiply MullQuadword Multiply MulqUnsigned Quadword Multiply High Longword Subtract SublScaled Longword Subtract S4SUBLS8SUBL Quadword Subtract SubqScaled Quadword Subtract S4SUBQS8SUBQ Logical and Shift Instructions Logical and Shift Instructions Summary Mnemonic OperationLogical Functions Conditional Move Integer Is exactly equivalent to Shift Logical Shift Arithmetic Byte Manipulation Instructions Instruction Meaning Described in SectionInswh InslhInsqh MskblCompare Byte BEQ LoopTo compare two character strings for greater/equal/less Extract Byte Ldqu Optimized examples Big-endian examples Byte Insert 56Alpha Architecture Handbook Byte Mask Insqh Inswh Sign Extend Zero Bytes Subsets and Faults Floating-Point InstructionsSingle-Precision Operations Definitions Alpha finite numberDenormal Dirty zeroInfinity Non-finite numberEncodings True zeroSign Exponent Fraction Vax Meaning FiniteRounding Modes VAX Rounding ModesIeee Rounding Modes VAX Rounding Mode Instruction Notation Ieee Rounding Mode Instruction NotationComputational Models VAX-Format Arithmetic with Precise ExceptionsHigh-Performance VAX-Format Arithmetic IEEE-Compliant ArithmeticIEEE-Compliant Arithmetic Without Inexact Exception Trapping Modes High-Performance IEEE-Format ArithmeticVAX Trapping Modes When /U or /V mode is specified VAX Trapping Modes Summary Trap Mode Notation Meaning Ieee Trapping ModesSummary of Ieee Trapping Modes Trap Mode Notation Meaning SUIArithmetic Trap Completion SVITrap Shadow Length Rules Page Invalid Operation INV Arithmetic Trap Division by Zero DZE Arithmetic Trap Overflow OVF Arithmetic TrapIeee Floating-Point Trap Disable Bits Underflow UNF Arithmetic TrapInexact Result INE Arithmetic Trap Integer Overflow IOV Arithmetic TrapFloating-Point Control Register Fpcr Ieee Denormal Control BitsIeee Rounding Mode Selected Floating-Point Control Register Fpcr FormatPage Accessing the Fpcr Default Values of the Fpcr Saving and Restoring the FpcrSoftware Notes Floating-Point Instruction Function Field Format Floating-Point Instruction Function FieldContents Meaning for Opcodes 1616 FNC ITOFS/ITOFTSQRTS/SQRTT Unpredictable Ieee Standard Conversion of NaN and Infinity ValuesCopying NaN Values Generating NaN ValuesPropagating NaN Values Memory Format Floating-Point Instructions Load Ffloating Load Gfloating Load Sfloating Load Tfloating Store Ffloating Store Gfloating Store Sfloating Store Tfloating Branch Format Floating-Point Instructions FBxx Fa.rq,disp.al Branch format Page Floating-Point Operate Format Instructions Addf AddgAdds IeeeMulf MulgMuls MultCopy Sign Convert Integer to Integer Floating-Point Conditional Move Fcmovne F3,F2,F1 Move from/to Floating-Point Control Register VAX Floating Add Ieee Floating Add VAX Floating Compare CmpgeqCmpgle CmpgltIeee Floating Compare CmpteqCmptle CmptltConvert VAX Floating to Integer Convert Integer to VAX Floating Convert VAX Floating to VAX Floating Convert Ieee Floating to Integer Convert Integer to Ieee Floating Convert Ieee SFloating to Ieee TFloating Convert Ieee TFloating to Ieee SFloating VAX Floating Divide Ieee Floating Divide Floating-Point Register to Integer Register Move Integer Register to Floating-Point Register Move Itofs is exactly equivalent to the sequence VAX Floating Multiply Ieee Floating Multiply VAX Floating Square Root Ieee Floating Square Root VAX Floating Subtract Ieee Floating Subtract Miscellaneous Instructions 17 Miscellaneous Instructions Summary Mnemonic OperationArchitecture Mask 134Alpha Architecture Handbook Call Privileged Architecture Library Evict Data Cache Block Implementation Note Exception Barrier Prefetch Data 140Alpha Architecture Handbook Implementation Version Memory Barrier Read Processor Cycle Counter Trap Barrier Write Hint Implementation Note Write Memory Barrier Processor Processor j VAX Compatibility Instructions 18 VAX Compatibility Instructions Summary Mnemonic OperationVAX Compatibility Instructions Multimedia Graphics and Video Support Mnemonic OperationByte and Word Minimum and Maximum Instruction mnemonics Pixel Error Pack Bytes Unpack Bytes Physical Address Space Characteristics Coherency of Memory AccessIntroduction Granularity of Memory Access Software/Hardware NoteWidth of Memory Access Memory-Like and Non-Memory-Like BehaviorTranslation Buffers and Virtual Caches Caches and Write BuffersHardware/Software Coordination Note Page Atomic Update of a Single Datum Data SharingAtomic Change of a Single Datum Atomic Update of Data Structures STQ8Alpha Architecture Handbook Ordering Considerations for Shared Data Structures Read/Write Ordering Alpha Shared Memory ModelImplementation Note Architectural Definition of Processor Issue Sequence Definition of Processor Issue ConstraintsDefinition of Before and After Processor Issue Constraints 1st↓ 2nd → PiIn=4y,b PiRny,b PiWny,b PiMB PiIMBDefinition of Location Access Constraints Definition of VisibilityDefinition of Storage Definition of Dependence Constraint Definition of Load-Locked and Store-Conditional Litmus Tests TimelinessLitmus Test 1 Impossible Sequence PiPjLitmus Test 2 Impossible Sequence Litmus Test 3 Impossible SequenceLitmus Test 4 Sequence Okay Litmus Test 5 Sequence OkayLitmus Test 6 Sequence Okay Litmus Test 7 Impossible Sequence Litmus Test 8 Impossible SequenceLitmus Test 9 Impossible Sequence Litmus Test 10 Sequence OkayLitmus Test 11 Impossible Sequence Implied Barriers Implications for SoftwareSingle Processor Data Stream Single Processor Instruction StreamSee Footnote 1 on Multiprocessor Context Switch First Processor Second ProcessorPage Multiprocessor Send/Receive Interrupt Implications for Memory Mapped I/O Multiple Processors Writing to a Single I/O Device Implications for Hardware Arithmetic Traps DictablePALcode PALcode Instructions and FunctionsPALcode Environment Special Functions Required for PALcodePALcode Replacement PALcode Effects on System CodeRequired PALcode Instructions PALcode Instructions that Require Recognition Mnemonic NameRequired PALcode Instructions Mnemonic Type Operation DrainaHalt IMBDrain Aborts Callpal DrainaHalt Callpal HaltInstruction Memory Barrier Callpal IMBConsole Subsystem Overview Page Input/Output Overview Page OpenVMS Alpha Unprivileged OpenVMS Alpha PALcodeChme ChmkChms ChmuInsqhil InsqhilrInsqhiq InsqhiqrInsqtilr InsqtiqInsqtiqr InsquelRdps ReadunqREI RemqhilRemqhiqr RemqtilRemqtilr RemqtiqRemquel RemqueqRscc SwastenPrivileged OpenVMS Alpha Palcode CflushLdqp MfprStqp SwpctxWtint Page Unprivileged Digital Unix PALcode Mnemonic Operation and DescriptionPrivileged Digital Unix PALcode 10-3 10-4Alpha Architecture Handbook Unprivileged Windows NT Alpha PALcode Unprivileged Windows NT Alpha PALcode Instruction SummaryPrivileged Windows NT Alpha PALcode 11-3 11-4Alpha Architecture Handbook 11-5 Page Appendix a Hardware-Software CompactInstruction-Stream Considerations Instruction AlignmentBranch Prediction and Minimizing Branch-Taken Factor Figure A-1 Branch-Format BSR and BR Opcodes Data-Stream Considerations Improving I-Stream Density FactorInstruction Scheduling Factor Data Alignment FactorShared Data in Multiple Processors Factor Avoiding Cache/TB Conflicts Factor Figure A-3 Bad Allocation in Cache Sequential Read/Write Factor Prefetching FactorAligned Byte/Word Within Register Memory Accesses Code SequencesDivision Byte Swap Stylized Code Forms4.1 NOP Clear a Register Load LiteralRegister-to-Register Move Negate4.6 not BooleansExceptions and Trap Barriers Pseudo-Operations Stylized Code FormsSoftware Considerations A-15 Timing Considerations Atomic Sequences Appendix B Alpha Choices for Ieee Options2Alpha Architecture Handbook Alpha Support for OS Completion Handlers Ieee Floating-Point Control FPC Quadword Figure B-1 Ieee Floating-Point Control FPC QuadwordPage Mapping to Ieee Standard Figure B-2 Ieee Trap Handling Behavior Completion Signal Alpha Instructions Code Handler Table B-2 Ieee Floating-Point Trap Handling User Hardware1MULx Output Exceptions CVTff Output Exceptions Cmptlt Cmptle Input ExceptionsSQRTx Output Exceptions Division by Zero OverflowUnderflow InexactAppendix C Common Architecture Instruction SummaryTable C-2 Common Architecture Instructions ADDL/VADDQ/V 15.0AF Convert Gfloating to quadword MULL/V MULQ/VSUBL/V SUBQ/VIeee Floating-Point Instructions Table C-3 Ieee Floating-Point Instruction Function CodesVAX Floating-Point Instructions Programming NoteIndependent Floating-Point Instructions Opcode SummaryTable C-7 Key to Opcode Summary Symbol Meaning Table C-6 Opcode SummaryCommon Architecture Opcodes in Numerical Order Table C-8 Common Architecture Opcodes in Numerical OrderInstruction Summary C-11 Addt Instruction Summary C-13 OpenVMS Alpha PALcode Instruction Summary Mfprasn MfprespMfprfen MfpriplDigital Unix PALcode Instruction Summary Table C-12 Digital Unix Privileged PALcode InstructionsMnemonic Opcode Description Windows NT Alpha Instruction Summary Table C-14 Windows NT Alpha Privileged PALcode instructionsPALcode Opcodes in Numerical Order Table C-15 PALcode Opcodes in Numerical OrderWindows NT OpenVMS AlphaWtint 00.003F 00.0063 Required PALcode Opcodes Opcodes Reserved to PALcodeTable C-16 Required PALcode Opcodes Mnemonic Type Table C-17 Opcodes Reserved for PALcode MnemonicOpcodes Reserved to Compaq Unused Function Code BehaviorTable C-18 Opcodes Reserved for Compaq Mnemonic OPC01 OPC02 OPC03 OPC04 OPC05 OPC06 OPC07Ascii Character Set Table C-19 Ascii Character Set Hex CodeAppendix D Processor Type AssignmentsTable D-1 Processor Type Assignments Major Type Minor Type EV3PALcode Variation Assignments Architecture Mask and Implementation Values Table D-3 Amask Bit Assignments Bit MeaningTable D-4 Implver Value Assignments Meaning Digital UnixPage Appendix E WaiversDECchip 21264 LDxL/STxC with WH64 Violation Implementation-Specific Functionality DECchip 21064/21066/21068 Performance MonitoringFor the OpenVMS Alpha Operating System Disable performance monitoring Functions and Arguments for the DECchip 21064/21066/21068Select desired events muxctl Select performance monitoring options= PCMUX0 = PCMUX1Value Description PC0 PC1DECchip 21164/21164PC Performance Monitoring Performance Monitor Interrupt MechanismInput Contents Register Bits Meaning Windows NT Alpha Functions and ArgumentCTR0 CTR1PCSEL0 OpenVMS Alpha and Digital Unix Functions and Arguments ModeselectPCSEL1 PCSEL2Disable performance monitoring do not reset counters Select desired events MuxselectSelect interrupt frequencies Read the countersOperate on counter MBZ PCSEL0 MBZMBZ PCSEL1 Counters Operate Under These Modes When Bits Set Bits MeaningS U P 6310 Table E-13 21164/21164PC Counter 1 PCSEL1 Event Selection Table E-14 21164/21164PC Counter 2 PCSEL2 Event Selection Table E-15 21164 CBOX1 Event Selection Value MeaningTable E-16 21164 CBOX2 Event Selection Table E-17 21164PC PM0MUX Event Selection Table E-18 21164PC PM1MUX Event Selection3 21264 Performance Monitoring SEXTPCTR0CTL47 PCTR0IERCMPCEN0 PCTR1SL1 Bit value MeaningSelect logging options Enable and write selected counters R17/a1 Bits Meaning Table E-26 21264 Enable and Write Counters for OpenVMS Alpha Page Index Index-2 Index-3 Index-4 Index-5 Index-6 Index-7 Index-8 Index-9 Index-10 Index-11 Index-12 Index-13