Hag*_*ble 30 c arm performancecounter time-measurement cortex-a8
我正在使用一个名为i.MX515的基于ARM Cortex-A8的处理器.有Linux Ubuntu 9.10发行版.我正在运行一个用C编写的非常大的应用程序,我正在利用gettimeofday();函数来衡量我的应用程序所需的时间.
main()
{
gettimeofday(start);
....
....
....
gettimeofday(end);
}
这个方法足以让我看看我的应用程序块占用了多少时间.但是,现在,我正在尝试使用gettimeofday()计算时间的方法彻底优化我的代码,我看到连续运行之间有很多波动(在我的优化之前和之后运行),所以我不能确定实际执行时间,从而影响我的改进.
谁能告诉我应该怎么做？
如果通过访问循环计数器(在ARM网站上为Cortex-M3建议的想法),任何人都可以向我指出一些代码,它给出了我在Cortex-A8上访问定时器寄存器时必须遵循的步骤吗？
如果这种方法不是很准确,那么请提出一些替代方案.
谢谢
跟进1:在Code Sorcery上编写了以下程序,生成了可执行文件,当我尝试在主板上运行时,我得到了 - 非法指令消息:(
static inline unsigned int get_cyclecount (void)
{
unsigned int value;
// Read CCNT Register
asm volatile ("MRC p15, 0, %0, c9, c13, 0\t\n": "=r"(value));
return value;
}
static inline void init_perfcounters (int32_t do_reset, int32_t enable_divider)
{
// in general enable all counters (including cycle counter)
int32_t value = 1;
// peform reset:
if (do_reset)
{
value |= 2; // reset all counters to zero.
value |= 4; // reset cycle counter to zero.
}
if (enable_divider)
value |= 8; // enable "by 64" divider for CCNT.
value |= 16;
// program the performance-counter control-register:
asm volatile ("MCR p15, 0, %0, c9, c12, 0\t\n" :: "r"(value));
// enable all counters:
asm volatile ("MCR p15, 0, %0, c9, c12, 1\t\n" :: "r"(0x8000000f));
// clear overflows:
asm volatile ("MCR p15, 0, %0, c9, c12, 3\t\n" :: "r"(0x8000000f));
}
int main()
{
/* enable user-mode access to the performance counter*/
asm ("MCR p15, 0, %0, C9, C14, 0\n\t" :: "r"(1));
/* disable counter overflow interrupts (just in case)*/
asm ("MCR p15, 0, %0, C9, C14, 2\n\t" :: "r"(0x8000000f));
init_perfcounters (1, 0);
// measure the counting overhead:
unsigned int overhead = get_cyclecount();
overhead = get_cyclecount() - overhead;
unsigned int t = get_cyclecount();
// do some stuff here..
printf("\nHello World!!");
t = get_cyclecount() - t;
printf ("function took exactly %d cycles (including function call) ", t - overhead);
get_cyclecount();
return 0;
}
跟进2:我已经写信给飞思卡尔寻求支持,他们已经给我发回了以下回复和一个程序(我对此并不太了解)
以下是我们现在可以帮助您的内容:我发送给您附上一个代码示例,它使用UART发送一个流,从您的代码,您似乎没有正确初始化MPU.
(hash)include <stdio.h>
(hash)include <stdlib.h>
(hash)define BIT13 0x02000
(hash)define R32 volatile unsigned long *
(hash)define R16 volatile unsigned short *
(hash)define R8 volatile unsigned char *
(hash)define reg32_UART1_USR1 (*(R32)(0x73FBC094))
(hash)define reg32_UART1_UTXD (*(R32)(0x73FBC040))
(hash)define reg16_WMCR (*(R16)(0x73F98008))
(hash)define reg16_WSR (*(R16)(0x73F98002))
(hash)define AIPS_TZ1_BASE_ADDR 0x70000000
(hash)define IOMUXC_BASE_ADDR AIPS_TZ1_BASE_ADDR+0x03FA8000
typedef unsigned long U32;
typedef unsigned short U16;
typedef unsigned char U8;
void serv_WDOG()
{
reg16_WSR = 0x5555;
reg16_WSR = 0xAAAA;
}
void outbyte(char ch)
{
while( !(reg32_UART1_USR1 & BIT13) );
reg32_UART1_UTXD = ch ;
}
void _init()
{
}
void pause(int time)
{
int i;
for ( i=0 ; i < time ; i++);
}
void led()
{
//Write to Data register [DR]
*(R32)(0x73F88000) = 0x00000040; // 1 --> GPIO 2_6
pause(500000);
*(R32)(0x73F88000) = 0x00000000; // 0 --> GPIO 2_6
pause(500000);
}
void init_port_for_led()
{
//GPIO 2_6 [73F8_8000] EIM_D22 (AC11) DIAG_LED_GPIO
//ALT1 mode
//IOMUXC_SW_MUX_CTL_PAD_EIM_D22 [+0x0074]
//MUX_MODE [2:0] = 001: Select mux mode: ALT1 mux port: GPIO[6] of instance: gpio2.
// IOMUXC control for GPIO2_6
*(R32)(IOMUXC_BASE_ADDR + 0x74) = 0x00000001;
//Write to DIR register [DIR]
*(R32)(0x73F88004) = 0x00000040; // 1 : GPIO 2_6 - output
*(R32)(0x83FDA090) = 0x00003001;
*(R32)(0x83FDA090) = 0x00000007;
}
int main ()
{
int k = 0x12345678 ;
reg16_WMCR = 0 ; // disable watchdog
init_port_for_led() ;
while(1)
{
printf("Hello word %x\n\r", k ) ;
serv_WDOG() ;
led() ;
}
return(1) ;
}
Nil*_*nck 50
访问性能计数器并不困难,但您必须从内核模式启用它们.默认情况下,计数器被禁用.
简而言之,您必须在内核中执行以下两行.无论是作为可加载模块还是只是在board-init中的某处添加两条线都可以:
/* enable user-mode access to the performance counter*/
asm ("MCR p15, 0, %0, C9, C14, 0\n\t" :: "r"(1));
/* disable counter overflow interrupts (just in case)*/
asm ("MCR p15, 0, %0, C9, C14, 2\n\t" :: "r"(0x8000000f));
一旦你这样做,循环计数器将开始递增每个循环.寄存器的溢出将被忽视并且不会引起任何问题(除非它们可能弄乱您的测量).
现在您想要从用户模式访问循环计数器:
我们从一个读取寄存器的函数开始:
static inline unsigned int get_cyclecount (void)
{
unsigned int value;
// Read CCNT Register
asm volatile ("MRC p15, 0, %0, c9, c13, 0\t\n": "=r"(value));
return value;
}
你很可能也希望重置并设置分隔符:
static inline void init_perfcounters (int32_t do_reset, int32_t enable_divider)
{
// in general enable all counters (including cycle counter)
int32_t value = 1;
// peform reset:
if (do_reset)
{
value |= 2; // reset all counters to zero.
value |= 4; // reset cycle counter to zero.
}
if (enable_divider)
value |= 8; // enable "by 64" divider for CCNT.
value |= 16;
// program the performance-counter control-register:
asm volatile ("MCR p15, 0, %0, c9, c12, 0\t\n" :: "r"(value));
// enable all counters:
asm volatile ("MCR p15, 0, %0, c9, c12, 1\t\n" :: "r"(0x8000000f));
// clear overflows:
asm volatile ("MCR p15, 0, %0, c9, c12, 3\t\n" :: "r"(0x8000000f));
}
do_reset将循环计数器设置为零.很简单.
enable_diver将启用1/64循环分频器.如果没有这个标志,你将测量每个循环.启用它后,计数器每64个周期增加一次.如果要测量否则会导致计数器溢出的长时间,这非常有用.
如何使用它:
// init counters:
init_perfcounters (1, 0);
// measure the counting overhead:
unsigned int overhead = get_cyclecount();
overhead = get_cyclecount() - overhead;
unsigned int t = get_cyclecount();
// do some stuff here..
call_my_function();
t = get_cyclecount() - t;
printf ("function took exactly %d cycles (including function call) ", t - overhead);
应该适用于所有Cortex-A8 CPU ..
哦 - 还有一些说明:
使用这些计数器,您将测量两次调用之间的确切时间,get_cyclecount()包括在其他进程或内核中花费的所有内容.没有办法将测量限制在您的过程或单个线程中.
打电话get_cyclecount()也不是免费的.它将编译为单个asm指令,但从协处理器移动将停止整个ARM管道.开销很高,可能会使您的测量偏差.幸运的是,开销也是固定的,因此您可以测量它并从您的时间中减去它.
在我的例子中,我为每次测量都做了.不要在实践中这样做.两次呼叫之间迟早会发生中断,甚至会进一步扭曲您的测量值.我建议您在空闲系统上测量几次开销,忽略所有局外人并使用固定常量.