svn commit: r252032 - head/sys/amd64/include

[Bruce Evans]

On Fri, 21 Jun 2013, Bruce Evans wrote:

> On Fri, 21 Jun 2013, I wrote:
>
>> On Thu, 20 Jun 2013, Konstantin Belousov wrote:
>>> ...
>>> @@ -44,7 +44,7 @@ counter_u64_add(counter_u64_t c, int64_t
>>> ...
>> The i386 version of the counter asm doesn't support the immediate
>> constraint for technical reasons.  64 bit counters are too large and
>> slow to use on i386, especially when they are implemented as they are
>> without races.
>
> Actual testing showed that it is only about twice as slow as a direct
> increment.  With the enclosed test program (a userland version hacked
> on a bit to avoid pcpu), on ref10-i386 the times are:
> - loop overhead:                                        1 cycle
> - direct unlocked increment of a uint32_t:              6 cycles
> - direct unlocked increment of a uint64_t:              7 cycles
> - non-inline function unlocked increment of a uint64_t: 7.5 cycles
> - counter_u64_add():                                   14 cycles
> - non-inline counter_u64_add():                        18 cycles
> ...

Actually enclosing the test program:

% #include <stdint.h>
% #include <stdio.h>
% 
% static inline void
% counter_64_inc_8b(volatile uint64_t *p, int64_t inc)
% {
% 
% 	__asm __volatile(
% 	"movl	%%ds:(%%esi),%%eax\n\t"
% 	"movl	%%ds:4(%%esi),%%edx\n"
% "1:\n\t"
% 	"movl	%%eax,%%ebx\n\t"
% 	"movl	%%edx,%%ecx\n\t"
% 	"addl	(%%edi),%%ebx\n\t"
% 	"adcl	4(%%edi),%%ecx\n\t"
% 	"cmpxchg8b %%ds:(%%esi)\n\t"
% 	"jnz	1b"
% 	:
% 	: "S" (p), "D" (&inc)
% 	: "memory", "cc", "eax", "edx", "ebx", "ecx");
% }
% 
% uint32_t cpu_feature = 1;
% 
% typedef volatile uint64_t *counter_u64_t;
% 
% static void
% #if 1
% inline
% #else
% __noinline
% #endif
% counter_u64_add(counter_u64_t c, int64_t inc)
% {
% 
% #if 1
% 	if ((cpu_feature & 1) == 1) {
% 		counter_64_inc_8b(c, inc);
% 	}
% #elif 0
% 	if ((cpu_feature & 1) == 1) {
% 		*c += inc;
% 	}
% #else
% 	*c += inc;
% #endif
% }
% 
% uint64_t mycounter[1];
% 
% int
% main(void)
% {
% 	unsigned i;
% 
% 	for (i = 0; i < 1861955704; i++)	/* sysctl -n machdep.tsc_freq */
% 		counter_u64_add(mycounter, 1);
% 	printf("%ju\n", (uintmax_t)mycounter[0]);
% }

Bruce