Dmi*_*try 1 delphi 64-bit assembly inline-assembly
我有以下功能,需要使其与64位平台兼容:
procedure ExecuteAsm(Tab, Buf: Pointer; Len: DWORD);
asm
mov ebx, Tab
mov ecx, Len
mov edx, Buf
@1: mov al, [edx]
xlat
mov [edx], al
inc edx
dec ecx
jnz @1
end;
Run Code Online (Sandbox Code Playgroud)
Delphi XE5 [dcc64 Error] E2107 Operand size mismatch在带有Tab和Len参数的行上引起错误.
不幸的是,我不知道汇编程序是否足以自行解决问题.成功编译函数应该更改什么?
该汇编代码基本上只是执行以下操作,它可以在32位和64位工作:
procedure ExecuteAsm(Tab, Buf: Pointer; Len: DWORD);
var
pBuf: PByte;
begin
pBuf := PByte(Buf);
repeat
pBuf^ := PByte(Tab)[pBuf^];
Inc(pBuf);
Dec(Len);
until Len = 0;
end;
Run Code Online (Sandbox Code Playgroud)
那么为什么不使用普通的Delphi代码并让编译器处理程序集呢?
你为什么使用汇编程序?
没有充分的理由!
这是你的asm代码直接转换为Delphi pascal:
procedure ExecuteAsm(Tab, Buf: PByte; Len: DWORD);
repeat
Buf^ := Tab[Buf^];
inc(Buf);
dec(Len);
until Len = 0;
end;
Run Code Online (Sandbox Code Playgroud)
但正如您现在所看到的,如果值为Len0,那么程序应该纠正程序备忘录.
...
这段代码看起来更好,因为while循环测试0值并且永远不会执行循环.
procedure ExecuteAsm(Tab, Buf: PByte; Len: cardinal);
begin
while Len > 0 do
begin
Buf^ := Tab[Buf^];
inc(Buf);
dec(Len);
end;
end;
Run Code Online (Sandbox Code Playgroud)
但是,如果您仍然喜欢汇编程序,则必须保留ebx/rbx寄存器,如...
procedure ExecuteAsm(Tab, Buf: Pointer; Len: DWORD);
asm
push ebx //rbx
//... your code
pop ebx //rbx
end;
Run Code Online (Sandbox Code Playgroud)
编辑:添加了32位和64位测试
因为HeartWare没有做David Heffernan的作业,所以我做到了.最初的测试让David Heffernan看了看HeartWares的评论.我做了一些改动,又增加了两个测试用例.该指令很重要:{$ O +} //打开编译器优化...... :)
{$APPTYPE CONSOLE}
uses
Diagnostics;
{$O+} //Turn on compiler optimisation... :)
procedure _asm_GJ(Tab, Buf : PByte; Len : Cardinal);
// 32-bit eax edx ecx
// 64-bit rcx rdx r8
asm
{$IFDEF CPUX64 }
test Len, Len
jz @exit
@loop:
movzx rax, [Buf]
mov al, byte ptr[Tab + rax]
mov [Buf],al
inc Buf
dec Len
jnz @loop
{$ELSE }
test Len, Len
jz @exit
push ebx
@loop:
movzx ebx, [Buf]
mov bl,byte ptr[Tab + ebx]
mov [Buf], bl
inc Buf
dec Len
jnz @loop
pop ebx
{$ENDIF }
@exit:
end;
procedure _asm_HeartWare(Tab, Buf : PByte; Len : Cardinal);
// 32-bit EAX EDX ECX
// 64-bit RCX RDX R8
asm
{$IFDEF CPUX64 }
XCHG R8,RCX
JECXZ @OUT
XOR RAX,RAX
@LOOP:
MOV AL,[RDX]
MOV AL,[R8+RAX]
MOV [RDX],AL
INC RDX
DEC ECX
JNZ @LOOP
// LOOP @LOOP
{$ELSE }
JECXZ @OUT
PUSH EBX
XCHG EAX,EBX
XOR EAX,EAX
@LOOP:
MOV AL,[EDX+ECX-1]
MOV AL,[EBX+EAX]
MOV [EDX+ECX-1],AL
DEC ECX
JNZ @LOOP
// LOOP @LOOP
POP EBX
{$ENDIF }
@OUT:
end;
procedure _pas_normal(Tab, Buf: PByte; Len: Cardinal);
begin
while Len > 0 do begin
Buf^ := Tab[Buf^];
inc(Buf);
dec(Len);
end;
end;
procedure _pas_inline(Tab, Buf: PByte; Len: Cardinal); inline;
begin
while Len > 0 do begin
Buf^ := Tab[Buf^];
inc(Buf);
dec(Len);
end;
end;
var
Stopwatch: TStopwatch;
i: Integer;
x, y: array [0 .. 1023] of Byte;
procedure refresh;
begin
for i := low(x) to high(x) do
begin
x[i] := i mod 256;
y[i] := (i + 20) mod 256;
end;
end;
begin
{$IFDEF CPUX64 }
Writeln('64 bit mode');
{$ELSE }
Writeln('32 bit mode');
{$ENDIF }
refresh;
Stopwatch := TStopwatch.StartNew;
for i := 1 to 1000000 do
begin
_asm_HeartWare(PByte(@x), PByte(@y), SizeOf(x));
end;
Writeln('asm HeartWare : ', Stopwatch.ElapsedMilliseconds, 'ms');
refresh;
Stopwatch := TStopwatch.StartNew;
for i := 1 to 1000000 do
begin
_asm_GJ(PByte(@x), PByte(@y), SizeOf(x));
end;
Writeln('asm GJ : ', Stopwatch.ElapsedMilliseconds, 'ms');
refresh;
Stopwatch := TStopwatch.StartNew;
for i := 1 to 1000000 do
begin
_pas_normal(PByte(@x), PByte(@y), SizeOf(x));
end;
Writeln('pas normal : ', Stopwatch.ElapsedMilliseconds, 'ms');
refresh;
Stopwatch := TStopwatch.StartNew;
for i := 1 to 1000000 do
begin
_pas_inline(PByte(@x), PByte(@y), SizeOf(x));
end;
Writeln('pas inline : ', Stopwatch.ElapsedMilliseconds, 'ms');
Readln;
end.
Run Code Online (Sandbox Code Playgroud)
结果......

Cunclusion ...
几乎无话可说!数字谈...
Delphi编译好,嗯非常好!
我已经内置了另一个asm优化程序,因为HeartWare asm优化并不是真正的优化.
| 归档时间: |
|
| 查看次数: |
1621 次 |
| 最近记录: |