SSE3

Source: Wikipedia, the free encyclopedia.

SSE3, Streaming SIMD Extensions 3, also known by its

SIMD instruction sets on the x86 platform, from oldest to newest, are MMX, 3DNow! (developed by AMD, no longer supported on newer CPUs), SSE, and SSE2
.

SSE3 contains 13 new instructions over SSE2.[3]

Changes

The most notable change is the capability to work horizontally in a register, as opposed to the more or less strictly vertical operation of all previous SSE instructions. More specifically, instructions to add and subtract the multiple values stored within a single register have been added.

pipeline stalls. Finally, the extension adds LDDQU, an alternative misaligned integer vector load that has better performance on NetBurst based platforms for loads that cross cacheline boundaries.[5]

CPUs with SSE3

New instructions

Common instructions

Arithmetic

ADDSUBPD
Add-Subtract-Packed-Double[8]
  • Input: { A0, A1 }, { B0, B1 }
  • Output: { A0 − B0, A1 + B1 }
ADDSUBPS
Add-Subtract-Packed-Single[8]
  • Input: { A0, A1, A2, A3 }, { B0, B1, B2, B3 }
  • Output: { A0 − B0, A1 + B1, A2 − B2, A3 + B3 }

AOS ( Array Of Structures )

HADDPD
Horizontal-Add-Packed-Double[8]
  • Input: { A0, A1 }, { B0, B1 }
  • Output: { A0 + A1, B0 + B1 }
HADDPS
Horizontal-Add-Packed-Single[8]
  • Input: { A0, A1, A2, A3 }, { B0, B1, B2, B3 }
  • Output: { A0 + A1, A2 + A3, B0 + B1, B2 + B3 }
HSUBPD
Horizontal-Subtract-Packed-Double[8]
  • Input: { A0, A1 }, { B0, B1 }
  • Output: { A0 − A1, B0 − B1 }
HSUBPS
Horizontal-Subtract-Packed-Single[8]
  • Input: { A0, A1, A2, A3 }, { B0, B1, B2, B3 }
  • Output: { A0 − A1, A2 − A3, B0 − B1, B2 − B3 }
LDDQU
As stated above, this is an alternative misaligned integer vector load.[8] It can be helpful for video compression tasks.
MOVDDUP, MOVSHDUP, MOVSLDUP[4]
These are useful for complex numbers and wave calculation like sound.
FISTTP
Like the older x87 FISTP instruction, but ignores the floating point control register's rounding mode settings and uses the "chop" (truncate) mode instead.[4] Allows omission of the expensive loading and re-loading of the control register in languages such as C where float-to-int conversion requires truncate behaviour by standard.

Other instructions

MONITOR, MWAIT
The MONITOR instruction is used to specify a memory address for monitoring, while the MWAIT instruction puts the processor into a low-power state and waits for a write event to the monitored address.[4]

References

  1. ^ a b Wilson, Anand Lal Shimpi & Derek. "Intel's Pentium 4 E: Prescott Arrives with Luggage". www.anandtech.com. Retrieved 2023-04-10.
  2. ^ Shimpi, Anand Lal. "Industry Update - Q4-2004: AMD adds SSE3 Support, Intel's 925/915 not selling and more". www.anandtech.com. Retrieved 2023-04-10.
  3. ^ "Intel Instruction Set Extensions Technology". Intel. Retrieved 2023-04-10.
  4. ^ a b c d Wright, Christopher. "SSE3 Instruction Set". softpixel.com. Retrieved 2023-04-10.
  5. ^ "LDDQU — Load Unaligned Integer 128 Bits". www.felixcloutier.com. Retrieved 2023-04-10.
  6. ^ Wilson, Derek. "AMD K8 E4 Stepping: SSE3 Performance". www.anandtech.com. Retrieved 2023-04-10.
  7. ^ "Intel Xeon 3.4GHz ['Nocona' core]". HEXUS. 2004-08-18. Retrieved 2023-04-10.
  8. ^ a b c d e f g "SSE3 Instructions - x86 Assembly Language Reference Manual". docs.oracle.com. Retrieved 2023-04-10.

External links

This page is based on the copyrighted Wikipedia article: SSE3. Articles is available under the CC BY-SA 3.0 license; additional terms may apply.Privacy Policy