Re: [Cbe-oss-dev] [RFC 0/3] powerpc: memory copy routines tweaked for Cell

[syokazuliao@yahoo.com.tw]

[-- Attachment #1.1: Type: text/plain, Size: 74 bytes --]

Sorry, I was send wrong files.
I send my three files again.


      

[-- Attachment #1.2: Type: text/html, Size: 312 bytes --]

[-- Attachment #2: main1.C --]
[-- Type: text/plain, Size: 1204 bytes --]

#include <stdlib.h>
#include <stdio.h>
#include <ppu_intrinsics.h>

extern void *memcpy(void *, const void *, size_t);

int main() {
	unsigned char *s, *d;
	register unsigned long long start, finish,  i;
	if(posix_memalign((void *)&s, 128, 16384)) {
		printf("failed\n");
		goto end;
	}
	for(i = 128, j = 0; i > 0; i--, j += 128) {		/* clear s from cache */
		__dcbf(s+j);
	}
	if(posix_memalign((void *)&d, 128, 16384)) {
		printf("failed\n");
		goto end;
	}
	for(i = 128, j = 0; i > 0; i--, j += 128) {		/* clear d from cache */
		__dcbf(s+j);
	}

	__dcbt(memcpy);		/* prefetch memcpy */
	__dcbt(memcpy+128);
	__dcbt(memcpy+256);
	__dcbt(memcpy+384);
	__dcbt(memcpy+512);
	__dcbt(memcpy+640);
	__dcbt(memcpy+768);
	__dcbt(memcpy+896);
	__dcbt(memcpy+1024);
	__dcbt(memcpy+1152);
	__dcbt(memcpy+1280);
	__dcbt(memcpy+1408);
	__dcbt(memcpy+1536);
	__dcbt(memcpy+1664);
	__dcbt(memcpy+1792);
	__dcbt(memcpy+1920);
	__dcbt(memcpy+2048);
	__dcbt(memcpy+2176);
	__dcbt(memcpy+2304);
	__dcbt(memcpy+2432);
	__sync();

	start = __mftb();
	memcpy(d, s, 4096);
	finish = __mftb();

	printf("%lld\n", finish - start);

	free(s);
	free(d);
end:
	return 0;
}

[-- Attachment #3: main2.C --]
[-- Type: text/plain, Size: 1200 bytes --]

#include <stdlib.h>
#include <stdio.h>
#include <ppu_intrinsics.h>

extern void *memcpy(void *, const void *, size_t);

int main() {
	unsigned char *s, *d;
	register unsigned long long start, finish,  i;
	if(posix_memalign((void *)&s, 128, 4096)) {
		printf("failed\n");
		goto end;
	}
	for(i = 32, j = 0; i > 0; i--, j += 128) {		/* clear s from cache */
		__dcbf(s+j);
	}
	if(posix_memalign((void *)&d, 128, 4096)) {
		printf("failed\n");
		goto end;
	}
	for(i = 32, j = 0; i > 0; i--, j += 128) {		/* clear d from cache */
		__dcbf(s+j);
	}

	__dcbt(cpymem);		/* prefetch memcpy */
	__dcbt(cpymem+128);
	__dcbt(cpymem+256);
	__dcbt(cpymem+384);
	__dcbt(cpymem+512);
	__dcbt(cpymem+640);
	__dcbt(cpymem+768);
	__dcbt(cpymem+896);
	__dcbt(cpymem+1024);
	__dcbt(cpymem+1152);
	__dcbt(cpymem+1280);
	__dcbt(cpymem+1408);
	__dcbt(cpymem+1536);
	__dcbt(cpymem+1664);
	__dcbt(cpymem+1792);
	__dcbt(cpymem+1920);
	__dcbt(cpymem+2048);
	__dcbt(cpymem+2176);
	__dcbt(cpymem+2304);
	__dcbt(cpymem+2432);
	__sync();

	start = __mftb();
	memcpy(d, s, 4096);
	finish = __mftb();

	printf("%lld\n", finish - start);

	free(s);
	free(d);
end:
	return 0;
}

[-- Attachment #4: test_result.TXT --]
[-- Type: text/plain, Size: 449 bytes --]

Copy Memory-to-Memory, results are in ticks.

             16KB        4KB     2KB    1KB    512B     256B     128B    64B     32B     16B 
-----------------------------------------------------------------------------------------------------------------------------------
main1.C   2063~2466	   669~879	60~63	 33~36	 22~24	  19~21		17~21		17~19		15~17		15~16
main2.C                110~114	60~62	 33~36	 21~24		19~21		17~18		17~18		15~16		15~16