SSE5 Instruction Set Architecture (ISA) Extension

128 bit instructions to be added with the Bulldozer processors:

• COMPD
  Compare Vector Double-Precision Floating-Point
• COMPS
  Compare Vector Single-Precision Floating-Point
• COMSD
  Compare Scalar Double-Precision Floating-Point
• COMSS
  Compare Scalar Single-Precision Floating-Point
• CVTPH2PS
  Convert 16-Bit Floating-Point to Single-Precision Floating-Point
• CVTPS2PH
  Convert Single-Precision Floating-Point to 16-Bit Floating-Point
• FMADDPD
  Multiply and Add Packed Double-Precision Floating-Point
• FMADDPS
  Multiply and Add Packed Single-Precision Floating-Point
• FMADDSD
  Multiply and Accumulate Scalar Double-Precision Floating-Point
• FMADDSS
  Multiply and Add Scalar Single-Precision Floating-Point
• FMSUBPD
  Multiply and Subtract Packed Double-Precision Floating-Point
• FMSUBPS
  Multiply and Subtract Packed Single-Precision Floating-Point
• FMSUBSD
  Multiply and Subtract Scalar Double-Precision Floating-Point
• FMSUBSS
  Multiply and Subtract Scalar Single-Precision Floating-Point
• FNMADDPD
  Negative Multiply and Add Packed Double-Precision Floating-Point
• FNMADDPS
  Negative Multiply and Add Packed Single-Precision Floating-Point
• FNMADDSD
  Negate Multiply and Add Scalar Double-Precision Floating-Point
• FNMADDSS
  Negative Multiply and Add Scalar Single-Precision Floating-Point
• FNMSUBPD
  Negative Multiply and Subtract Packed Double-Precision Floating-Point
• FNMSUBPS
  Negative Multiply and Subtract Packed Single-Precision Floating-Point
• FNMSUBSD
  Negative Multiply and Subtract Scalar Double-Precision Floating-Point
• FNMSUBSS
  Negative Multiply and Subtract Scalar Single-Precision Floating-Point
• FRCZPD
  Extract Fraction Packed Double-Precision Floating-Point
• FRCZPS
  Extract Fraction Packed Single-Precision Floating-Point
• FRCZSD
  Extract Fraction Scalar Double-Precision Floating-Point
• FRCZSS
  Extract Fraction Scalar Single-Precision Floating Point
• PCMOV
  Vector Conditional Moves
• PCOMB
  Compare Vector Signed Bytes
• PCOMD
  Compare Vector Signed Doublewords
• PCOMQ
  Compare Vector Signed Quadwords
• PCOMUB
  Compare Vector Unsigned Bytes
• PCOMUD
  Compare Vector Unsigned Doublewords
• PCOMUQ
  Compare Vector Unsigned Quadwords
• PCOMUW
  Compare Vector Unsigned Words
• PCOMW
  Compare Vector Signed Words
• PERMPD
  Permute Double-Precision Floating-Point
• PERMPS
  Permute and Modify Single-Precision Floating Point
• PHADDBD
  Packed Horizontal Add Signed Byte to Signed Doubleword
• PHADDBQ
  Packed Horizontal Add Signed Byte to Signed Quadword
• PHADDBW
  Packed Horizontal Add Signed Byte to Signed Word
• PHADDDQ
  Packed Horizontal Add Signed Doubleword to Signed Quadword
• PHADDUBD
  Packed Horizontal Add Unsigned Byte to Doubleword
• PHADDUBQ
  Packed Horizontal Add Unsigned Byte to Quadword
• PHADDUBW
  Packed Horizontal Add Unsigned Byte to Word
• PHADDUDQ
  Packed Horizontal Add Unsigned Doubleword to Quadword
• PHADDUWD
  Packed Horizontal Add Unsigned Word to Doubleword
• PHADDUWQ
  Packed Horizontal Add Unsigned Word to Quadword
• PHADDWD
  Packed Horizontal Add Signed Word to Signed Doubleword
• PHADDWQ
  Packed Horizontal Add Signed Word to Signed Quadword
• PHSUBBW
  Packed Horizontal Subtract Signed Byte to Signed Word
• PHSUBDQ
  Packed Horizontal Subtract Signed Doubleword to Signed Quadword
• PHSUBWD
  Packed Horizontal Subtract Signed Word to Signed Doubleword
• PMACSDD
  Packed Multiply Accumulate Signed Doubleword to Signed Doubleword
• PMACSDQH
  Packed Multiply Accumulate Signed High Doubleword to Signed Quadword
• PMACSDQL
  Packed Multiply Accumulate Signed Low Doubleword to Signed Quadword
• PMACSSDD
  Packed Multiply Accumulate Signed Doubleword to Signed Doubleword with Saturation
• PMACSSDQH
  Packed Multiply Accumulate Signed High Doubleword to Signed Quadword with Saturation
• PMACSSDQL
  Packed Multiply Accumulate Signed Low Doubleword to Signed Quadword with Saturation
• PMACSSWD
  Packed Multiply Accumulate Signed Word to Signed Doubleword with Saturation
• PMACSSWW
  Packed Multiply Accumulate Signed Word to Signed Word with Saturation
• PMACSWD
  Packed Multiply Accumulate Signed Word to Signed Doubleword
• PMACSWW
  Packed Multiply Accumulate Signed Word to Signed Word
• PMADCSSWD
  Packed Multiply, Add and Accumulate Signed Word to Signed Doubleword with Saturation
• PMADCSWD
  Packed Multiply Add and Accumulate Signed Word to Signed Doubleword
• PPERM
  Packed Permute Bytes
• PROTB
  Packed Rotate Bytes
• PROTD
  Packed Rotate Doublewords
• PROTQ
  Packed Rotate Quadwords
• PROTW
  Packed Rotate Words
• PSHAB
  Packed Shift Arithmetic Bytes
• PSHAD
  Packed Shift Arithmetic Doublewords
• PSHAQ
  Packed Shift Arithmetic Quadwords
• PSHAW
  Packed Shift Arithmetic Words
• PSHLB
  Packed Shift Logical Bytes
• PSHLD
  Packed Shift Logical Doublewords
• PSHLQ
  Packed Shift Logical Quadwords
• PSHLW
  Packed Shift Logical Words
• PTEST
  Predicate Test Register
• ROUNDPD
  Round Packed Double-Precision Floating-Point
• ROUNDPS
  Round Packed Single-Precision Floating-Point
• ROUNDSD
  Round Scalar Double-Precision Floating-Point
• ROUNDSS
  Round Scalar Single-Precision Floating-Point