Front Page All Articles Recent Changes Random Article

Contents

Concatenative language

  • ACL
  • Ait
  • Aocla
  • Breeze
  • Callisto
  • Cat
  • Cognate
  • colorForth
  • Concata
  • CoSy
  • Deque
  • DSSP
  • dt
  • Elymas
  • Enchilada
  • ETAC
  • F
  • Factor
  • Fiveth
  • Forth
  • Fourth
  • Freelang
  • Gershwin
  • hex
  • iNet
  • Joy
  • Joy of Postfix App
  • kcats
  • Kitten
  • lang5
  • Listack
  • LSE64
  • Lviv
  • Meow5
  • min
  • Mirth
  • mjoy
  • Mlatu
  • Ode
  • OForth
  • Om
  • Onyx
  • Plorth
  • Popr
  • Porth
  • PostScript
  • Prowl
  • Quest32
  • Quackery
  • r3
  • Raven
  • Retro
  • RPL
  • SPL
  • Staapl
  • Stabel
  • Tal
  • Titan
  • Trith
  • Uiua
  • Worst
  • xs
  • XY
  • 5th
  • 8th

Concatenative topics

  • Compilers
  • Interpreters
  • Type systems
  • Object systems
  • Quotations
  • Variables
  • Garbage collection
  • Example programs

Concatenative meta

  • People
  • Communities

Other languages

  • APL
  • C++
  • Erlang
  • FP trivia
  • Haskell
  • Io
  • Java
  • JavaScript
  • Lisp
  • ML
  • Oberon
  • RPL
  • Self
  • Slate
  • Smalltalk

Meta

  • Search
  • Farkup wiki format
  • Etiquette
  • Sandbox

SSE

This is a quick reference for Intel's Streaming SIMD Extensions. Feel free to make additions or corrections!

Vector types

The vector types here are named with the same convention as in Factor's SIMD library. It should be obvious what they mean:

  • char-16
  • uchar-16
  • short-8
  • ushort-8
  • int-4
  • uint-4
  • float-4
  • double-2

Instruction set

The number next to each instruction is the SSE version:

  • 1: SSE
  • 2: SSE2
  • 3: SSE3
  • 3.3: SSSE3
  • 4.1: SSE4.1
  • 4.2: SSE4.2
char-16 uchar-16short-8 ushort-8int-4 uint-4 float-4 double-2
move MOVDQ[AU] 2 MOVDQ[AU] 2 MOVDQ[AU] 2 MOVDQ[AU] 2 MOVDQ[AU] 2 MOVDQ[AU] 2 MOV[AU]PS 1 MOV[AU]PD 2
add PADDB 2 PADDB 2 PADDW 2 PADDW 2 PADDD 2 PADDD 2 ADDPS 1 ADDPD 2
subtractPSUBB 2 PSUBB 2 PSUBW 2 PSUBW 2 PSUBD 2 PSUBD 2 SUBPS 1 SUBPD 2
add with saturation PADDSB 2 PADDUSB 2 PADDSW 2 PADDUSW 2
subtract with saturation PSUBSB 2 PSUBUSB 2 PSUBSW 2 PSUBUSW 2
add-subtract ADDSUBPS 3 ADDSUBPD 3
horizontal addPHADDW 3.3PHADDW 3.3PHADDD 3.3PHADDW 3.3HADDPS 3HADDPS 3
multiply PMULLW 2 PMULLW 2 PMULLD 2 PMULLD 2 MULPS 1 MULPD 2
divide DIVPS 1 DIVPD 2
absolute value PABSB 3.3 PABSW 3.3 PABSD 3.3
minimum PMINUB 2 PMINSW 2 MINPS 1 MINPD 2
maximum PMAXUB 2 PMAXSW 2 MAXPS 1 MAXPD 2
approximate reciprocalRCPPS 1
square rootSQRTSS 1SQRTSD 2

Notes:

  • There are many more instructions that do not fit in this grid, but these are the most important ones to know.
  • Every move instruction has an aligned and unaligned form. Aligned is faster, but will trap if your address is not a multiple of 16 bytes.

Idioms

int-4

Select nth component

Gather four integers into a vector

float-4

Select nth component

Gather four floats into a vector

Broadcast float into four components

Absolute value

Horizontal add with SSE2

double-2

Select nth component

Gather two doubles into a vector

Broadcast double into two components

Absolute value

Horizontal add with SSE2

References

For full details, consult Intel's or AMD's instruction set reference documentation.

This revision created on Wed, 23 Sep 2009 01:35:51 by jckarter

Latest Revisions Edit

All content is © 2008-2024 by its respective authors. By adding content to this wiki, you agree to release it under the BSD license.