对于VM /间preTER性能改进策略？ [英] Performance improvement strategies for VM / interpreter?
问题描述
我已经用C语言编写一个简单的虚拟机，使用指令一个简单的开关，不用任何指令译码，但性能是可怕的。
对于简单的aritmetic操作虚拟机比本地C code为相同的操作慢约4000倍。我与一组长度为10亿阵列的测试中，第一自由以下组成的程序指令，随机+ - * /运算，2阵列保持随机整数，且第三阵列是操作对象存储。
我期待看到3-4次降算术性能，使'4000X真的把我吓倒了。即使是最慢的跨preTED语言似乎提供更高的性能。那么，我与我的方法去错了，我怎么能提高，而不诉诸JIT编译机器code性能？
的实施是...基本上是最简单的我能想出：
开始：
{
开关（*（OP +（C ++）））
{
情况下0：
添加（IN1 + C，IN2 + C，OUT + C）;转到开始; 情况1：
子（IN1 + C，IN2 + C，OUT + C）;转到开始; 案例2：
MUL（IN1 + C，IN2 + C，OUT + C）;转到开始; 案例3：
DIV（IN1 + C，IN2 + C，OUT + C）;转到开始; 情况4：
COUT＆LT;＆LT; ＆LT节目结束;＆LT; ENDL;
转到结束; 默认：
COUT＆LT;＆LT; 错误！！！ ＆LT;＆LT; ENDL; }
}结束：
更新：
我是用程序的长度玩弄时，我注意到我使用个人资料，实际上打破了QElapsedTimer。现在，我使用从时钟（）函数，并根据其计算goto实际上看齐运行与本地code，也许一点点降低。是合法的结果？下面是完整的源代码（它是丑陋的，我知道，这只是因为毕竟测试）：
的#include＆LT; QtGlobal＆GT;
＃包括LT＆;＆iostream的GT;
＃包括LT＆;＆stdio.h中GT;
＃包括LT＆;＆的ctime GT;使用命名空间std;＃定义长度7000无效添加（INT和放大器;一，INT和b，诠释和再现性）{R = A * B;}
无效子（INT和放大器;一，INT和b，诠释和再现性）{R = A - B;}
MUL无效（INT和放大器;一，INT和b，诠释和再现性）{R = A * B;}
无效格（INT和放大器;一，INT和b，诠释和再现性）{R = A / B;}诠释的main（）
{
字符* OP =新的char [长度];
为int * IN1 =新INT [长度];
为int * IN2 =新INT [长度];
为int *出新= INT [长度]; 的for（int i = 0; I＆LT;长度+ I）
{
*（OP + I）= I％4;
*（IN1 + I）= qrand（）;
*（IN2 + I）= qrand（）+ 1;
} *（OP +长度-1）= 4; //程序结束
长长的SCLOCK，且fCLOCK;
unsigned int类型C = 0;
SCLOCK =时钟（）; COUT＆LT;＆LT; 程序开始＆LT;＆LT; ENDL; 静态无效*表[] = {
＆功放;＆安培; do_add，
＆功放;＆安培; do_sub，
＆功放;＆安培; do_mul，
＆功放;＆安培; do_div，
＆功放;＆安培; do_end，
＆功放;＆安培; do_err，
＆功放;＆安培; do_fin};＃定义跳转（）转到*表[OP [C ++] 跳（）;
do_add：
添加（IN1 [C]，IN2 [C]，走出[C]）;跳（）;
do_sub：
子（IN1 [C]，IN2 [C]，走出[C]）;跳（）;
do_mul：
MUL（IN1 [C]，IN2 [C]，走出[C]）;跳（）;
do_div：
DIV（IN1 [C]，IN2 [C]，走出[C]）;跳（）;
do_end：
COUT＆LT;＆LT; ＆LT节目结束;＆LT; ENDL;转到*表[6];
do_err：
COUT＆LT;＆LT; 错误！！！ ＆LT;＆LT; ENDL;转到*表[6];
do_fin： 且fCLOCK =时钟（）;
COUT＆LT;＆LT;且fCLOCK - SCLOCK＆LT;＆LT; ENDL; 删除[]运算;
删除[] IN1;
删除[]平方英寸;
删除[]的; IN1 =新INT [长度];
IN2 =新INT [长度];
OUT =新INT [长度]; 的for（int i = 0; I＆LT;长度+ I）
{
*（IN1 + I）= qrand（）;
*（IN2 + I）= qrand（）+ 1;
} COUT＆LT;＆LT; 本土开始＆LT;＆LT; ENDL; SCLOCK =时钟（）; 的for（int i = 0; I＆LT;长度，I + = 4）
{ *（OUT + I）= *（IN1 + I）+ *（IN2 + I）;
*（OUT + I + 1）= *（IN1 + I + 1） - *（IN2 + I + 1）;
*（OUT + I + 2）= *（IN1 + I + 2）*（IN2 + I + 2）;
*（OUT + I + 3）= *（IN1 + I + 3）/ *（IN2 + I + 3）;
} 且fCLOCK =时钟（）;
COUT＆LT;＆LT;且fCLOCK - SCLOCK＆LT;＆LT; ENDL; 删除[] IN1;
删除[]平方英寸;
删除[]的; 返回0;
}
Darek Mihocka对创造可移植的C快间preters一个良好而深入的新手必看：<一href=\"http://www.emulators.com/docs/nx25_nostradamus.htm\">http://www.emulators.com/docs/nx25_nostradamus.htm
I have written a simple VM in C, using a simple switch of instructions, without any instruction decoding whatsoever, but performance is terrible.
For simple aritmetic operations the VM is about 4000 times slower than native C code for the same operations. I tested with a group of arrays of length 10 million, the first consisting of the program instructions, random + - * / operations, 2 arrays holding random integers and the third array being the operation target storage.
I was expecting to see 3-4 times drop in arithmetic performance, so that `4000x really blew me away. Even the slowest interpreted languages seem to offer higher performance. So where I am going wrong with my approach and how can I improve performance without resorting to JIT compilation to machine code?
The implementation is... basically the simplest I could come up with:
begin:
{
switch (*(op+(c++)))
{
case 0:
add(in1+c, in2+c, out+c); goto begin;
case 1:
sub(in1+c, in2+c, out+c); goto begin;
case 2:
mul(in1+c, in2+c, out+c); goto begin;
case 3:
div(in1+c, in2+c, out+c); goto begin;
case 4:
cout << "end of program" << endl;
goto end;
default:
cout << "ERROR!!!" << endl;
}
}
end:
UPDATE: I was toying with the length of the program when I noticed the QElapsedTimer I was using to profile was actually broken. Now I am using the clock() function from and according to it the computed goto is actually running on par with the native code, maybe a tad lower. Is that result legit??? Here is the full source (it is ugly I know, it's just for testing after all):
#include <QtGlobal>
#include <iostream>
#include <stdio.h>
#include <ctime>
using namespace std;
#define LENGTH 70000000
void add(int & a, int & b, int & r) {r = a * b;}
void sub(int & a, int & b, int & r) {r = a - b;}
void mul(int & a, int & b, int & r) {r = a * b;}
void div(int & a, int & b, int & r) {r = a / b;}
int main()
{
char * op = new char[LENGTH];
int * in1 = new int[LENGTH];
int * in2 = new int[LENGTH];
int * out = new int[LENGTH];
for (int i = 0; i < LENGTH; ++i)
{
*(op+i) = i % 4;
*(in1+i) = qrand();
*(in2+i) = qrand()+1;
}
*(op+LENGTH-1) = 4; // end of program
long long sClock, fClock;
unsigned int c = 0;
sClock = clock();
cout << "Program begins" << endl;
static void* table[] = {
&&do_add,
&&do_sub,
&&do_mul,
&&do_div,
&&do_end,
&&do_err,
&&do_fin};
#define jump() goto *table[op[c++]]
jump();
do_add:
add(in1[c], in2[c], out[c]); jump();
do_sub:
sub(in1[c], in2[c], out[c]); jump();
do_mul:
mul(in1[c], in2[c], out[c]); jump();
do_div:
div(in1[c], in2[c], out[c]); jump();
do_end:
cout << "end of program" << endl; goto *table[6];
do_err:
cout << "ERROR!!!" << endl; goto *table[6];
do_fin:
fClock = clock();
cout << fClock - sClock << endl;
delete [] op;
delete [] in1;
delete [] in2;
delete [] out;
in1 = new int[LENGTH];
in2 = new int[LENGTH];
out = new int[LENGTH];
for (int i = 0; i < LENGTH; ++i)
{
*(in1+i) = qrand();
*(in2+i) = qrand()+1;
}
cout << "Native begins" << endl;
sClock = clock();
for (int i = 0; i < LENGTH; i += 4)
{
*(out+i) = *(in1+i) + *(in2+i);
*(out+i+1) = *(in1+i+1) - *(in2+i+1);
*(out+i+2) = *(in1+i+2) * *(in2+i+2);
*(out+i+3) = *(in1+i+3) / *(in2+i+3);
}
fClock = clock();
cout << fClock - sClock << endl;
delete [] in1;
delete [] in2;
delete [] out;
return 0;
}
Darek Mihocka has a good and in-depth writeup on creating fast interpreters in portable C: http://www.emulators.com/docs/nx25_nostradamus.htm
这篇关于对于VM /间preTER性能改进策略？的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！
