Delphi 用于将8位扩展为8个布尔字节（0或1）的英特尔x86汇编优化技术

我学习汇编程序已经有一段时间了，我正在尝试将一些简单的过程\函数重写到汇编程序中，以查看性能优势（如果有的话）。我的主要开发工具是Delphi2007，第一个示例将使用该语言，但也可以轻松地翻译成其他语言

问题是：

我们给出了一个无符号字节值，其中八位中的每一位表示屏幕一行中的一个像素。每个像素可以是实心（1）或透明（0）。换句话说，我们在一个字节值中有8个像素。 我想将这些像素解压成一个8字节的数组，以使最年轻的像素（位）位于数组的最低索引之下，以此类推。以下是一个例子：

One byte value -----------> eight byte array

10011011 -----------------> [1][1][0][1][1][0][0][1]

Array index number ------->  0  1  2  3  4  5  6  7

下面我将介绍解决这个问题的五种方法。接下来，我将展示他们的时间比较，以及我是如何测量这些时间的

我的问题包括两部分：

1. 我要求您提供有关方法

DecodePixels4a

和

DecodePixels4b

的详细回答。为什么方法

4b

比

4a

慢一些

例如，如果因为我的代码没有正确对齐而速度较慢，那么请向我展示给定方法中的哪些指令可以更好地对齐，以及如何这样做以不破坏该方法

我想看到理论背后的真实例子。请记住，我正在学习汇编，我想从你的答案中获得知识，这使我将来能够编写更好的优化代码

2. 你能写出比解码像素更快的例程吗？如果是这样，请介绍并描述您所采取的优化步骤。 所谓更快的例程，我指的是在这里介绍的所有例程中，在测试环境中运行时间最短的例程

允许使用所有英特尔系列处理器以及与之兼容的处理器

以下是我编写的例程：

procedure DecodePixels1(EncPixels: Byte; var DecPixels: TDecodedPixels);
var
  i3: Integer;
begin
  DecPixels[0] := EncPixels and $01;
  for i3 := 1 to 7 do
  begin
    EncPixels := EncPixels shr 1;
    DecPixels[i3] := EncPixels and $01;
    //DecPixels[i3] := (EncPixels shr i3) and $01;  //this is even slower if you replace above 2 lines with it
  end;
end;


//Lets unroll the loop and see if it will be faster.
procedure DecodePixels2(EncPixels: Byte; var DecPixels: TDecodedPixels);
begin
  DecPixels[0] := EncPixels and $01;
  EncPixels := EncPixels shr 1;
  DecPixels[1] := EncPixels and $01;
  EncPixels := EncPixels shr 1;
  DecPixels[2] := EncPixels and $01;
  EncPixels := EncPixels shr 1;
  DecPixels[3] := EncPixels and $01;
  EncPixels := EncPixels shr 1;
  DecPixels[4] := EncPixels and $01;
  EncPixels := EncPixels shr 1;
  DecPixels[5] := EncPixels and $01;
  EncPixels := EncPixels shr 1;
  DecPixels[6] := EncPixels and $01;
  EncPixels := EncPixels shr 1;
  DecPixels[7] := EncPixels and $01;
end;


procedure DecodePixels3(EncPixels: Byte; var DecPixels: TDecodedPixels);
begin
  asm
    push eax;
    push ebx;
    push ecx;
    mov bl, al;
    and bl, $01;
    mov [edx], bl;
    mov ecx, $00;
@@Decode:
    inc ecx;
    shr al, $01;
    mov bl, al;
    and bl, $01;
    mov [edx + ecx], bl;
    cmp ecx, $07;
    jnz @@Decode;
    pop ecx;
    pop ebx;
    pop eax;
  end;
end;


//Unrolled assembly loop
procedure DecodePixels4a(EncPixels: Byte; var DecPixels: TDecodedPixels);
begin
  asm
    push eax;
    push ebx;
    mov bl, al;
    and bl, $01;
    mov  [edx], bl;
    shr al, $01;
    mov bl, al;
    and bl, $01;
    mov [edx + $01], bl;
    shr al, $01;
    mov bl, al;
    and bl, $01;
    mov [edx + $02], bl;
    shr al, $01;
    mov bl, al;
    and bl, $01;
    mov [edx + $03], bl;
    shr al, $01;
    mov bl, al;
    and bl, $01;
    mov [edx + $04], bl;
    shr al, $01;
    mov bl, al;
    and bl, $01;
    mov [edx + $05], bl;
    shr al, $01;
    mov bl, al;
    and bl, $01;
    mov [edx + $06], bl;
    shr al, $01;
    mov bl, al;
    and bl, $01;
    mov [edx + $07], bl;
    pop ebx;
    pop eax;
  end;
end;


// it differs compared to 4a only in switching two instructions (but seven times)
procedure DecodePixels4b(EncPixels: Byte; var DecPixels: TDecodedPixels);
begin
  asm
    push eax;
    push ebx;
    mov bl, al;
    and bl, $01;
    shr al, $01;          //
    mov [edx], bl;        //
    mov bl, al;
    and bl, $01;
    shr al, $01;          //
    mov [edx + $01], bl;  //
    mov bl, al;
    and bl, $01;
    shr al, $01;          //
    mov [edx + $02], bl;  //
    mov bl, al;
    and bl, $01;
    shr al, $01;          //
    mov [edx + $03], bl;  //
    mov bl, al;
    and bl, $01;
    shr al, $01;          //
    mov [edx + $04], bl;  //
    mov bl, al;
    and bl, $01;
    shr al, $01;          //
    mov [edx + $05], bl;  //
    mov bl, al;
    and bl, $01;
    shr al, $01;          //
    mov [edx + $06], bl;  //
    mov bl, al;
    and bl, $01;
    mov [edx + $07], bl;
    pop ebx;
    pop eax;
  end;
end;

下面是如何测试它们：

program Test;

{$APPTYPE CONSOLE}

uses
  SysUtils, Windows;

type
  TDecodedPixels = array[0..7] of Byte;
var
  Pixels: TDecodedPixels;
  Freq, TimeStart, TimeEnd :Int64;
  Time1, Time2, Time3, Time4a, Time4b: Extended;
  i, i2: Integer;

begin
  if QueryPerformanceFrequency(Freq) then
  begin
    for i2 := 1 to 100 do
    begin
      QueryPerformanceCounter(TimeStart);
      for i := 1 to 100000 do
        DecodePixels1(155, Pixels);
      QueryPerformanceCounter(TimeEnd);
      Time1 := Time1 + ((TimeEnd - TimeStart) / Freq * 1000);

      QueryPerformanceCounter(TimeStart);
      for i := 1 to 100000 do
        DecodePixels2(155, Pixels);
      QueryPerformanceCounter(TimeEnd);
      Time2 := Time2 + ((TimeEnd - TimeStart) / Freq * 1000);

      QueryPerformanceCounter(TimeStart);
      for i := 1 to 100000 do
        DecodePixels3(155, Pixels);
      QueryPerformanceCounter(TimeEnd);
      Time3 := Time3 + ((TimeEnd - TimeStart) / Freq * 1000);

      QueryPerformanceCounter(TimeStart);
      for i := 1 to 100000 do
        DecodePixels4a(155, Pixels);
      QueryPerformanceCounter(TimeEnd);
      Time4a := Time4a + ((TimeEnd - TimeStart) / Freq * 1000);

      QueryPerformanceCounter(TimeStart);
      for i := 1 to 100000 do
        DecodePixels4b(155, Pixels);
      QueryPerformanceCounter(TimeEnd);
      Time4b := Time4b + ((TimeEnd - TimeStart) / Freq * 1000);

    end;
    Writeln('Time1 : ' + FloatToStr(Time1 / 100) + ' ms.    <- Delphi loop.');
    Writeln('Time2 : ' + FloatToStr(Time2 / 100) + ' ms.    <- Delphi unrolled loop.');
    Writeln('Time3 : ' + FloatToStr(Time3/ 100) + ' ms.    <- BASM loop.');
    Writeln('Time4a : ' + FloatToStr(Time4a / 100) + ' ms.    <- BASM unrolled loop.');
    Writeln('Time4b : ' + FloatToStr(Time4b / 100) + ' ms.    <- BASM unrolled loop instruction switch.');
  end;
  Readln;
end.

看看Time5的结果，很奇怪吧？ 我想我有不同的Delphi版本，因为我生成的汇编代码与Wouter提供的不同

第二次主要编辑：

---

我知道为什么常规

5

在我的机器上运行得较慢。我在编译器选项中选中了“范围检查”和“溢出检查”。我在例程

9

中添加了

assembler

指令，看看它是否有用。似乎这个指令的汇编程序和Delphi内联变量一样好，甚至稍好

以下是最终结果：

Time1  : 1,22508325749317 ms.     <- Delphi loop.
Time2  : 1,33004145373084 ms.     <- Delphi unrolled loop.
Time3  : 1,1473583622526 ms.      <- BASM loop.
Time4a : 0,77322594033463 ms.     <- BASM unrolled loop.
Time4b : 0,846033593023372 ms.    <- BASM unrolled loop instruction switch.
Time5  : 0,688689382044384 ms.    <- Wouter van Nifterick, Delphi unrolled
Time6  : 0,503233741036693 ms.    <- PhiS, table lookup Delphi
Time7  : 0,385254722925063 ms.    <- PhiS, table lookup Delphi inline
Time8  : 0,432993919452751 ms.    <- PhiS, table lookup BASM
Time9  : 0,362680491244212 ms.    <- PhiS, table lookup BASM with assembler directive

我想说，这相当依赖于数据

下面是测试和结果。我做了四次测试以确保没有事故。 我还为GJ建议的例程添加了新的时间（Time10a，Time10b）

test1test2test3test4
时间1:12112101201201201213
时间二:1280 1258 1253 1332
时间3:1129 1138 1130 1160
时间4A:0690068206170635
时间4b:07070698 07060659
时间4C:0679068506260625
时间5:0715 0682 0686 0679
时间6:0490048505220514
时间7:0323 0333 0336 0318
时间8:0407 0403 0373 0354
时间9:0352 0378 0355 0355
时间10A:1823 1812 1807 1813
时间10B:11131120 11151118
时间10C:0652063006530633
Time10d:0156 0155 0172 0160编译器在优化小例程方面做得非常好

我将使用查找表优化您的代码。

由于对单个字节（256种不同的状态）进行解码，所以可以使用未打包的值预先计算256个数组

编辑：请注意，奔腾处理器可以并行执行特定指令（），这称为配对
 我想是写入内存（实际上是缓存）比使用寄存器慢

所以

在再次需要
bl
寄存器之前，给处理器一些时间将
bl
写入内存，而

shr al, $01;
mov [edx], bl;
mov bl, al;

需要立即
bl
，因此处理器必须停止并等待内存写入完成

这让我很惊讶。现代英特尔处理器进行疯狂的流水线和寄存器重命名，因此在我看来，如果有什么不同的话，解码像素4B应该更快，因为每条指令的依赖关系都更靠前。除此之外，以上是我能提供的所有解释：

x86是一个糟糕的指令集，Intel做了惊人的、非常先进的hocus pocus来提高效率。如果我是你，我会调查别的事情。如今，PC机对MegaMcOptimized软件的需求非常少。我的友好建议是研究用于移动设备（主要是ARM）的处理器，因为在移动设备中，处理器速度、功耗和电池寿命问题意味着微优化软件更为重要。ARM的指令集优于x86。
4b比4a快的可能原因是它的并行性更好。从4a开始：

mov bl, al;
and bl, $01;          // data dep (bl)
mov  [edx], bl;       // data dep (bl)
shr al, $01;
mov bl, al;           // data dep (al)
and bl, $01;          // data dep (bl)
mov [edx + $01], bl;  // data dep (bl)

标记为“data dep”的指令在前一条指令完成之前无法开始执行，我已经编写了导致此数据依赖性的寄存器。如果没有依赖关系，现代CPU能够在最后一条指令完成之前启动指令。但你命令这些行动的方式阻止了这一切

在4b中，数据依赖性更少：

mov bl, al;
and bl, $01;          // data dep (bl)
shr al, $01;
mov [edx], bl;
mov bl, al;
and bl, $01;          // data dep (bl)
shr al, $01;
mov [edx + $01], bl;

使用这种指令顺序，依赖于前一条指令的指令更少，因此有更多的并行机会

我不能保证这是造成速度差异的原因，但这很可能是一个候选因素。不幸的是，很难找到像你所寻找的那样绝对的答案；现代处理器有分支预测器、多级缓存、硬件预取器和各种其他协同处理器
          Test1  Test2  Test3  Test4

Time1   : 1,211  1,210  1,220  1,213
Time2   : 1,280  1,258  1,253  1,332
Time3   : 1,129  1,138  1,130  1,160

Time4a  : 0,690  0,682  0,617  0,635
Time4b  : 0,707  0,698  0,706  0,659
Time4c  : 0,679  0,685  0,626  0,625
Time5   : 0,715  0,682  0,686  0,679

Time6   : 0,490  0,485  0,522  0,514
Time7   : 0,323  0,333  0,336  0,318
Time8   : 0,407  0,403  0,373  0,354
Time9   : 0,352  0,378  0,355  0,355
Time10a : 1,823  1,812  1,807  1,813
Time10b : 1,113  1,120  1,115  1,118
Time10c : 0,652  0,630  0,653  0,633
Time10d : 0,156  0,155  0,172  0,160  <-- current winner!

mov [edx+...], bl
shr al, $01;
mov bl, al;

shr al, $01;
mov [edx], bl;
mov bl, al;

mov bl, al;
and bl, $01;          // data dep (bl)
mov  [edx], bl;       // data dep (bl)
shr al, $01;
mov bl, al;           // data dep (al)
and bl, $01;          // data dep (bl)
mov [edx + $01], bl;  // data dep (bl)

mov bl, al;
and bl, $01;          // data dep (bl)
shr al, $01;
mov [edx], bl;
mov bl, al;
and bl, $01;          // data dep (bl)
shr al, $01;
mov [edx + $01], bl;

BT ax,1
SETC [dx]
inc dx

BT ax,2
SETC [dx]
inc dx

procedure DecodePixels5(EncPixels: Byte; var DecPixels: TDecodedPixels);
begin
  DecPixels[0] := (EncPixels shr 0) and $01;
  DecPixels[1] := (EncPixels shr 1) and $01;
  DecPixels[2] := (EncPixels shr 2) and $01;
  DecPixels[3] := (EncPixels shr 3) and $01;
  DecPixels[4] := (EncPixels shr 4) and $01;
  DecPixels[5] := (EncPixels shr 5) and $01;
  DecPixels[6] := (EncPixels shr 6) and $01;
  DecPixels[7] := (EncPixels shr 7) and $01;
end;


Results:

Time1  : 1,03096806151283 ms.    <- Delphi loop.
Time2  : 0,740308641141395 ms.   <- Delphi unrolled loop.
Time3  : 0,996602425688886 ms.   <- BASM loop.
Time4a : 0,608267951561275 ms.   <- BASM unrolled loop.
Time4b : 0,574162510648039 ms.   <- BASM unrolled loop instruction switch.
Time5  : 0,499628206138524 ms. !!!  <- Delphi unrolled loop 5.

  push ebx;
  // DecPixels[0] := (EncPixels shr 0) and 1;
  movzx ecx,al
  mov ebx,ecx
  //  shr ebx,$00
  and bl,$01
  mov [edx],bl
  // DecPixels[1] := (EncPixels shr 1) and 1;
  mov ebx,ecx
  shr ebx,1
  and bl,$01
  mov [edx+$01],bl
  // DecPixels[2] := (EncPixels shr 2) and 1;
  mov ebx,ecx
  shr ebx,$02
  and bl,$01
  mov [edx+$02],bl
  // DecPixels[3] := (EncPixels shr 3) and 1;
  mov ebx,ecx
  shr ebx,$03
  and bl,$01
  mov [edx+$03],bl
  // DecPixels[4] := (EncPixels shr 4) and 1;
  mov ebx,ecx
  shr ebx,$04
  and bl,$01
  mov [edx+$04],bl
  // DecPixels[5] := (EncPixels shr 5) and 1;
  mov ebx,ecx
  shr ebx,$05
  and bl,$01
  mov [edx+$05],bl
  // DecPixels[6] := (EncPixels shr 6) and 1;
  mov ebx,ecx
  shr ebx,$06
  and bl,$01
  mov [edx+$06],bl
  // DecPixels[7] := (EncPixels shr 7) and 1;
  shr ecx,$07
  and cl,$01
  mov [edx+$07],cl
  pop ebx;

var
  PixelLookup:Array[byte] of TDecodedPixels;

// You could precalculate, but the performance gain would hardly be worth it because you call this once only.
for I := 0 to 255 do
  DecodePixels5b(I, PixelLookup[I]);


procedure DecodePixels7(EncPixels: Byte; var DecPixels: TDecodedPixels);
begin
  DecPixels := PixelLookup[EncPixels];
end;

Results:

Time1  : 1,03096806151283 ms.    <- Delphi loop.
Time2  : 0,740308641141395 ms.   <- Delphi unrolled loop.
Time3  : 0,996602425688886 ms.   <- BASM loop.
Time4a : 0,608267951561275 ms.   <- BASM unrolled loop.
Time4b : 0,574162510648039 ms.   <- BASM unrolled loop instruction switch.
Time5  : 0,499628206138524 ms. !!!  <- Delphi unrolled loop 5.
Time7 : 0,251533475182096 ms.    <- simple table lookup


      const Uint64DecPix : PACKED ARRAY [0..255] OF UINT64 =
  ( $0000000000000000, $0000000000000001, $0000000000000100, $0000000000000101, $0000000000010000, $0000000000010001, $0000000000010100, $0000000000010101, $0000000001000000, $0000000001000001, $0000000001000100, $0000000001000101, $0000000001010000, $0000000001010001, $0000000001010100, $0000000001010101,
    $0000000100000000, $0000000100000001, $0000000100000100, $0000000100000101, $0000000100010000, $0000000100010001, $0000000100010100, $0000000100010101, $0000000101000000, $0000000101000001, $0000000101000100, $0000000101000101, $0000000101010000, $0000000101010001, $0000000101010100, $0000000101010101,
    $0000010000000000, $0000010000000001, $0000010000000100, $0000010000000101, $0000010000010000, $0000010000010001, $0000010000010100, $0000010000010101, $0000010001000000, $0000010001000001, $0000010001000100, $0000010001000101, $0000010001010000, $0000010001010001, $0000010001010100, $0000010001010101,
    $0000010100000000, $0000010100000001, $0000010100000100, $0000010100000101, $0000010100010000, $0000010100010001, $0000010100010100, $0000010100010101, $0000010101000000, $0000010101000001, $0000010101000100, $0000010101000101, $0000010101010000, $0000010101010001, $0000010101010100, $0000010101010101,
    $0001000000000000, $0001000000000001, $0001000000000100, $0001000000000101, $0001000000010000, $0001000000010001, $0001000000010100, $0001000000010101, $0001000001000000, $0001000001000001, $0001000001000100, $0001000001000101, $0001000001010000, $0001000001010001, $0001000001010100, $0001000001010101,
    $0001000100000000, $0001000100000001, $0001000100000100, $0001000100000101, $0001000100010000, $0001000100010001, $0001000100010100, $0001000100010101, $0001000101000000, $0001000101000001, $0001000101000100, $0001000101000101, $0001000101010000, $0001000101010001, $0001000101010100, $0001000101010101,
    $0001010000000000, $0001010000000001, $0001010000000100, $0001010000000101, $0001010000010000, $0001010000010001, $0001010000010100, $0001010000010101, $0001010001000000, $0001010001000001, $0001010001000100, $0001010001000101, $0001010001010000, $0001010001010001, $0001010001010100, $0001010001010101,
    $0001010100000000, $0001010100000001, $0001010100000100, $0001010100000101, $0001010100010000, $0001010100010001, $0001010100010100, $0001010100010101, $0001010101000000, $0001010101000001, $0001010101000100, $0001010101000101, $0001010101010000, $0001010101010001, $0001010101010100, $0001010101010101,
    $0100000000000000, $0100000000000001, $0100000000000100, $0100000000000101, $0100000000010000, $0100000000010001, $0100000000010100, $0100000000010101, $0100000001000000, $0100000001000001, $0100000001000100, $0100000001000101, $0100000001010000, $0100000001010001, $0100000001010100, $0100000001010101,
    $0100000100000000, $0100000100000001, $0100000100000100, $0100000100000101, $0100000100010000, $0100000100010001, $0100000100010100, $0100000100010101, $0100000101000000, $0100000101000001, $0100000101000100, $0100000101000101, $0100000101010000, $0100000101010001, $0100000101010100, $0100000101010101,
    $0100010000000000, $0100010000000001, $0100010000000100, $0100010000000101, $0100010000010000, $0100010000010001, $0100010000010100, $0100010000010101, $0100010001000000, $0100010001000001, $0100010001000100, $0100010001000101, $0100010001010000, $0100010001010001, $0100010001010100, $0100010001010101,
    $0100010100000000, $0100010100000001, $0100010100000100, $0100010100000101, $0100010100010000, $0100010100010001, $0100010100010100, $0100010100010101, $0100010101000000, $0100010101000001, $0100010101000100, $0100010101000101, $0100010101010000, $0100010101010001, $0100010101010100, $0100010101010101,
    $0101000000000000, $0101000000000001, $0101000000000100, $0101000000000101, $0101000000010000, $0101000000010001, $0101000000010100, $0101000000010101, $0101000001000000, $0101000001000001, $0101000001000100, $0101000001000101, $0101000001010000, $0101000001010001, $0101000001010100, $0101000001010101,
    $0101000100000000, $0101000100000001, $0101000100000100, $0101000100000101, $0101000100010000, $0101000100010001, $0101000100010100, $0101000100010101, $0101000101000000, $0101000101000001, $0101000101000100, $0101000101000101, $0101000101010000, $0101000101010001, $0101000101010100, $0101000101010101,
    $0101010000000000, $0101010000000001, $0101010000000100, $0101010000000101, $0101010000010000, $0101010000010001, $0101010000010100, $0101010000010101, $0101010001000000, $0101010001000001, $0101010001000100, $0101010001000101, $0101010001010000, $0101010001010001, $0101010001010100, $0101010001010101,
    $0101010100000000, $0101010100000001, $0101010100000100, $0101010100000101, $0101010100010000, $0101010100010001, $0101010100010100, $0101010100010101, $0101010101000000, $0101010101000001, $0101010101000100, $0101010101000101, $0101010101010000, $0101010101010001, $0101010101010100, $0101010101010101);
PUint64DecPix : pointer = @Uint64DecPix;

procedure DecodePixelsPS1Pas (EncPixels: Byte; var DecPixels: TDecodedPixels);
begin
  DecPixels := TDecodedPixels(Uint64DecPix[EncPixels]);
end;


procedure DecodePixelsPS1PasInline (EncPixels: Byte; var DecPixels: TDecodedPixels);
inline;
begin
  DecPixels := TDecodedPixels(Uint64DecPix[EncPixels]);
end;


procedure DecodePixelsPS1Asm (EncPixels: Byte; var DecPixels: TDecodedPixels);
asm
  lea ecx, Uint64DecPix //[<-Added in EDIT 3] 
  //mov ecx, dword ptr PUint64DecPix - alternative to the above line (slower for me)
  movzx eax, al
  movq xmm0, [8*eax+ecx]  //Using XMM rather than MMX so we don't have to issue emms at the end
  movq [edx], xmm0        //use MOVQ because it doesn't need mem alignment
end;

PACKED ARRAY [0..7] of byte

Time1 : 2.51638266874701 ms.    <- Delphi loop.
Time2 : 2.11277620479698 ms.    <- Delphi unrolled loop.
Time3 : 2.21972066282167 ms.    <- BASM loop.
Time4a : 1.34093090043567 ms.    <- BASM unrolled loop.
Time4b : 1.52222070123437 ms.    <- BASM unrolled loop instruction switch.
Time5 : 1.17106364076999 ms.    <- Wouter van Nifterick
TimePS1 : 0.633099318488802 ms.    <- PS.Pas
TimePS2 : 0.551617593856202 ms.    <- PS.Pas Inline
TimePS3 : 0.70921094720139 ms.    <- PS.Asm (speed for version before 3rd EDIT)
procedure DecodePixels(EncPixels: Byte; var DecPixels: TDecodedPixels);
asm
  xor   ecx, ecx
  add   al, al
  rcl   ecx, 8
  add   al, al
  rcl   ecx, 8
  add   al, al
  rcl   ecx, 8
  add   al, al
  rcl   ecx, 1
  mov   [DecPixels + 4], ecx
  xor   ecx, ecx
  add   al, al
  rcl   ecx, 8
  add   al, al
  rcl   ecx, 8
  add   al, al
  rcl   ecx, 8
  add   al, al
  rcl   ecx, 1
  mov   [DecPixels], ecx
end;

procedure DecodePixelsI(EncPixels: Byte; var DecPixels: TDecodedPixels);
asm
  mov   ecx, 0    //Faster than: xor   ecx, ecx
  add   al, al
  rcl   ch, 1
  add   al, al
  rcl   cl, 1
  ror   ecx, 16
  add   al, al
  rcl   ch, 1
  add   al, al
  rcl   cl, 1
  mov   [DecPixels + 4], ecx
  mov   ecx, 0    //Faster than: xor   ecx, ecx
  add   al, al
  rcl   ch, 1
  add   al, al
  rcl   cl, 1
  ror   ecx, 16
  add   al, al
  rcl   ch, 1
  add   al, al
  rcl   cl, 1
  mov   [DecPixels], ecx
end;

procedure DecodePixelsX(EncPixels: Byte; var DecPixels: TDecodedPixels);
asm
  add   al, al
  setc  byte ptr[DecPixels + 7]
  add   al, al
  setc  byte ptr[DecPixels + 6]
  add   al, al
  setc  byte ptr[DecPixels + 5]
  add   al, al
  setc  byte ptr[DecPixels + 4]
  add   al, al
  setc  byte ptr[DecPixels + 3]
  add   al, al
  setc  byte ptr[DecPixels + 2]
  add   al, al
  setc  byte ptr[DecPixels + 1]
  setnz byte ptr[DecPixels]
end;

const Uint32DecPix : array [0..15] of cardinal = (
  $00000000, $00000001, $00000100, $00000101,
  $00010000, $00010001, $00010100, $00010101,
  $01000000, $01000001, $01000100, $01000101,
  $01010000, $01010001, $01010100, $01010101
  );

procedure DecodePixelsY(EncPixels: byte; var DecPixels: TDecodedPixels); inline;
begin
  pcardinal(@DecPixels)^ := Uint32DecPix[EncPixels and $0F];
  pcardinal(cardinal(@DecPixels) + 4)^ := Uint32DecPix[(EncPixels and $F0) shr 4];
end;

int main ()
{
  const int
    size = 0x100000;

  unsigned char
    *source = new unsigned char [size],
    *dest,
    *dest1 = new unsigned char [size * 32],
    *dest2 = new unsigned char [size * 32];

  for (int i = 0 ; i < size ; ++i)
  {
    source [i] = rand () & 0xff;
  }

  LARGE_INTEGER
    start,
    middle,
    end;

  QueryPerformanceCounter (&start);
  dest = dest1;
  for (int i = 0 ; i < size ; ++i)
  {
    unsigned char
      v = source [i];

    for (int b = 0 ; b < 8 ; ++b)
    {
      *(dest++) = (v >> b) & 1;
    }
  }
  unsigned char
    bits [] = {1,2,4,8,16,32,64,128,1,2,4,8,16,32,64,128},
    zero [] = {0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0},
    ones [] = {1,1,1,1,1,1,1,1,1,1,1,1,1,1,1,1};

  QueryPerformanceCounter (&middle);
  __asm
  {
    movdqu xmm1,bits
    movdqu xmm2,zero
    movdqu xmm3,ones
    mov ecx,0x100000/4
    mov esi,source
    mov edi,dest2
l1:
    lodsd
    movd xmm0,eax
    movd xmm4,eax
    punpcklbw xmm0,xmm0
    punpcklbw xmm4,xmm4
    punpcklwd xmm0,xmm0
    punpcklwd xmm4,xmm4
    punpckldq xmm0,xmm0
    punpckhdq xmm4,xmm4
    pand xmm0,xmm1
    pand xmm4,xmm1
    pcmpeqb xmm0,xmm2
    pcmpeqb xmm4,xmm2
    paddb xmm0,xmm3
    paddb xmm4,xmm3
    movdqu [edi],xmm0
    movdqu [edi+16],xmm4
    add edi,32
    dec ecx
    jnz l1
  }
  QueryPerformanceCounter (&end);

  cout << "Time taken = " << (middle.QuadPart - start.QuadPart) << endl;
  cout << "Time taken = " << (end.QuadPart - middle.QuadPart) << endl;
  cout << "memcmp = " << memcmp (dest1, dest2, size * 32) << endl;

  return 0;
}

/* input byte in eax, address to store result in edx */
and eax, 0xff    /* may not be needed */
mov ebx, eax
shl ebx, 7
or  eax, ebx
mov ebx, eax
shl ebx, 14
or  eax, ebx
mov ebx, eax
and eax, 0x01010101
mov [edx], eax
shr ebx, 4
and ebx, 0x01010101
mov [edx+4], ebx

BtBld PROC Array:DWORD, Pixels:DWORD
  mov  eax, [Array]
  add  eax, 7
  mov  edx, [Pixels]

  mov  bx, 0

  mov  ecx, 8
rpt:  or  bx, [eax]
  dec  eax
  shl  bx, 1
  loop rpt
  shr  bx, 1
  mov  [edx], bl
  ret
BtBld ENDP

4a Instruction Sequence:
AND - MOV - SHR

4b Instruction Sequence:
AND - SHR - MOV

4a: AND (piped) MOV (piped) SHR
4b: AND (WAIT) SHR (piped) MOV

mov bl, al;
and bl, $01;          // data dep (bl)

mov bl, al -> (A:) read al (B:) write bl  => (2 clocks in i386)
and bl, 01 -> (C:) read 01 (D:) write bl  => idem

[--A--][--B--]
 [--C--]<wait>[---D--]

type TPackedDecodedPixels = record
case integer of
  0: (a: TDecodedPixels);
  1: (v: Int64);
end;

procedure DecodePixels(EncPixels: byte; var DecPixels: TDecodedPixels); inline;
const
  magic = $8040201008040201;
  mask  = $8080808080808080;
begin
  TPackedDecodedPixels(DecPixels).v := SwapEndian(((EncPixels*magic) and mask) shr 7);
end;

0000000a 0000000b 0000000c 0000000d 0000000e 0000000f 0000000g 0000000h (1)

  |  b7  ||  b6  ||  b4  ||  b4  ||  b3  ||  b2  ||  b1  ||  b0  |
                                                          abcdefgh (1-byte value)
x 1000000001000000001000000001000000001000000001000000001000000001
  ────────────────────────────────────────────────────────────────
= h0abcdefgh0abcdefgh0abcdefgh0abcdefgh0abcdefgh0abcdefgh0abcdefgh

  |  b7  ||  b6  ||  b4  ||  b4  ||  b3  ||  b2  ||  b1  ||  b0  |
  h0abcdefgh0abcdefgh0abcdefgh0abcdefgh0abcdefgh0abcdefgh0abcdefgh
& 1000000010000000100000001000000010000000100000001000000010000000
  ────────────────────────────────────────────────────────────────
= h0000000g0000000f0000000e0000000d0000000c0000000b0000000a0000000 (8-byte array)

                                                          0abcdefg
x 0000000000000010000001000000100000010000001000000100000010000001
  ────────────────────────────────────────────────────────────────
= 00000000abcdefgabcdefgabcdefgabcdefgabcdefgabcdefgabcdefgabcdefg
& 0000000000000001000000010000000100000001000000010000000100000001
  ────────────────────────────────────────────────────────────────    
= 000000000000000a0000000b0000000c0000000d0000000e0000000f0000000g

TPackedDecodedPixels(DecPixels).v := _pext_u64(EncPixels, $0101010101010101);

mov al, dil
mov rbx, rsi
movzx edi, al
movabs rax, 0x8040201008040201
imul rdi, rax
movabs rax, 0x8080808080808080
and rdi, rax
shr rdi, 0x7
call 4016a0 <SYSTEM_$$_SWAPENDIAN$INT64$$INT64>
mov QWORD PTR [rbx], rax