Streaming SIMD Extensions: diferenças entre revisões

Origem: Wikipédia, a enciclopédia livre.
Conteúdo apagado Conteúdo adicionado
Leandromartinez (discussão | contribs)
Hgfernan (discussão | contribs)
m Referência a artigo em inglês
Linha 30: Linha 30:
[[bg:SSE]]
[[bg:SSE]]
[[de:Internet Streaming SIMD Extensions]]
[[de:Internet Streaming SIMD Extensions]]
[[en:SSE]]
[[en:Streaming SIMD Extensions]]
[[es:SSE]]
[[es:SSE]]
[[eo:SSE]]
[[eo:SSE]]

Revisão das 01h46min de 18 de julho de 2007

SSE (Streaming SIMD Extensions, inicialmente chamado de ISSE, Internet Streaming SIMD Extensions) é um SIMD (Single Instruction, Multiple Data) conjuntos de instruções desenvolvido pela Intel e introduzido no mercado em 1999 no processador Pentium III como resposta à tecnologia 3DNow! da AMD (que foi lançada um ano antes).

O SSE contém 70 novas instruções.

Ele foi originalmente conhecido como KNI (Katmai era o apelido para o primeiro Pentium III (com núcleo revisto). Durante o projeto Katmai a Intel procurava distingui-lo da sua linha anterior de produtos, particularmente do projeto Pentium II. A AMD rapidamente aproveitou do projeto da Intel e adicionou suporte às instruções SSEs, começando assim a era do famoso processador Athlon XP.

A Intel desapontou-se com seu primeiro esforço de desenvolvimento SIMD o IA-32 e o MMX. MMX possuía dois grandes problemas: ele re-utilizava pontos de flutuação registrados, fazendo com que a CPU ficasse impossibilitada de trabalhar em ambos Ponto de flutuação e instruções SIMD ao mesmo tempo, só funcionava com intruções simples.

SSE adds eight new 128-bit registers known as XMM0 through XMM7. Each register packs together four 32-bit single-precision floating point numbers.

Because these 128-bit registers are additional program states that the operating system must preserve across task switches, they are disabled by default until the operating system explicitly enables them. This means that the OS must know how to use the FXSAVE and FXRSTR instructions, which is the extended pair of instructions which can save all x87 and SSE register states all at once. This support was quickly added to all major IA-32 operating systems.

Because SSE adds floating point support, it sees much more use than MMX now that the graphics cards all handle integer calculations internally. Integer SIMD operations may still be performed with the eight 64-bit MMX registers. The MMX registers are "aliased" on top of the eight FPU registers. Later, Intel augmented SSE with the SSE2 instruction set, which added support for integer math. While redundant, MMX operations can be executed in parallel with SSE operations; offering great performance in limited situations.

The first CPU to support SSE, the Pentium III, shared execution resources between SSE and the FPU. While a compiled application can interleave FPU and SSE instructions side-by-side, the Pentium III will not issue a FPU and a SSE instruction in the same clock-cycle. This limitation reduces the effectiveness of pipelining, but the separate XMM registers do allow SIMD and scalar floating point operations to be mixed without the performance hit from explicit MMX/floating point mode switching.

Versões posteriores

  • SSE2, introduced with the Pentium 4, is a major enhancement to SSE (which some programmers renamed "SSE1"). SSE2 adds new math instructions for double-precision (64-bit) floating point and 8/16/32-bit integer data types, all operating on the same 128-bit XMM vector register-file previously introduced with SSE. SSE2 enables the programmer to perform SIMD math of virtually any type (from 8-bit integer to 64-bit float) entirely with the XMM vector-register file, without the need to touch the (legacy) MMX/FPU registers. Many programmers consider SSE2 to be "everything SSE should have been", as SSE2 offers an orthogonal set of instructions for dealing with common datatypes.
  • SSE3 called Prescott New Instructions, is an incremental upgrade to SSE2, adding a handful of DSP-oriented math instructions and some process (thread) management instructions.
  • SSSE3 is an incremental upgrade to SSE3, adding 16 new opcodes which include permuting the bytes in a word, multiplying 16-bit fixed-point numbers with correct rounding, and within-word accumulate instructions.

pt:SSE