[Mesa3d-dev] dynamic code generation with gcc

[Josh V. <ho...@na...>]

Keith Whitwell <ke...@va...> writes:

> You may want to avoid sharing the nv-specific stuff, but any progress on otf
> codegen has lots of application beyond that extension -- I can think of a
> dozen uses for something like this.

What would you guys think of putting stuff like this in Mesa?

#include <dlfcn.h>
#include <stdio.h>
#include <stdlib.h>
#include <unistd.h>

void *
compile_function(const char *name, const char *source, void **r_handle)
{
	char name_c[256], name_so[256], cmdline[768];
	FILE *fp;
	size_t len = strlen(source);
	pid_t pid = getpid();
	void *handle, *sym;

	sprintf(name_c, "/tmp/%ld_%.200s.c", (long)pid, name);
	sprintf(name_so, "/tmp/%ld_%.200s.so", (long)pid, name);

	fp = fopen(name_c, "w");

	if (fp == NULL)
		return NULL;

	if (fwrite(source, len, 1, fp) != 1) {
		fclose(fp);
		remove(name_c);
		return NULL;
	}

	fclose(fp);

	sprintf(cmdline, "gcc -O2 -fomit-frame-pointer -shared %s -o %s",
	 name_c, name_so);

	if (system(cmdline) != 0) {
		remove(name_c);
		return NULL;
	}

	remove(name_c);

	handle = dlopen(name_so, RTLD_NOW);

	remove(name_so);

	if (handle == NULL)
		return NULL;

	sym = dlsym(handle, name);

	if (sym == NULL) {
		dlclose(handle);
		return NULL;
	}

	*r_handle = handle;

	return sym;
}

void
free_function(void *handle)
{
	dlclose(handle);
}

static const char *convert_template =
"
void
NAME(void *vsrc, void *vdst, int count)
{
	SRC_TYPE *src = vsrc;
	DST_TYPE *dst = vdst;
	int i;
	unsigned int s, d, r, g, b, a;

	for (i = 0; i < count; i++) {
		s = src[i];

		r = s >> SRC_RPOS;
		r &= (1 << SRC_RSZ) - 1;
		#if SRC_RSZ < DST_RSZ
		r = r * ((1 << DST_RSZ) - 1) / ((1 << SRC_RSZ - 1));
		#else
		r >>= SRC_RSZ - DST_RSZ;
		#endif
		r <<= DST_RPOS;

		g = s >> SRC_GPOS;
		g &= (1 << SRC_GSZ) - 1;
		#if SRC_GSZ < DST_GSZ
		g = g * ((1 << DST_GSZ) - 1) / ((1 << SRC_GSZ - 1));
		#else
		g >>= SRC_GSZ - DST_GSZ;
		#endif
		g <<= DST_GPOS;

		b = s >> SRC_BPOS;
		b &= (1 << SRC_BSZ) - 1;
		#if SRC_BSZ < DST_BSZ
		b = b * ((1 << DST_BSZ) - 1) / ((1 << SRC_BSZ - 1));
		#else
		b >>= SRC_BSZ - DST_BSZ;
		#endif
		b <<= DST_BPOS;

		a = s >> SRC_APOS;
		a &= (1 << SRC_ASZ) - 1;
		#if SRC_ASZ < DST_ASZ
		a = a * ((1 << DST_ASZ) - 1) / ((1 << SRC_ASZ - 1));
		#else
		a >>= SRC_ASZ - DST_ASZ;
		#endif
		a <<= DST_APOS;

		d = r | g | b | a;

		dst[i] = d;
	}
}
";

int
convert_pixels(void *src, int src_pixel_size,
 int src_rpos, int src_gpos, int src_bpos, int src_apos,
 int src_rsz, int src_gsz, int src_bsz, int src_asz,
 void *dst, int dst_pixel_size,
 int dst_rpos, int dst_gpos, int dst_bpos, int dst_apos,
 int dst_rsz, int dst_gsz, int dst_bsz, int dst_asz,
 int count)
{
	char buf[10000], name[200];
	char *p = buf;
	void (*fn)(void *src, void *dst, int count);
	void *handle;

	switch (dst_pixel_size) {
		case 1:
		case 2:
		case 4:
			break;
		default:
			return 0;
	}

	sprintf(name, "convert_%d%d%d%d_%d%d%d%d",
	 src_rsz, src_gsz, src_bsz, src_asz,
	 dst_rsz, dst_gsz, dst_bsz, dst_asz);

	p += sprintf(p, "#define NAME %s\n", name);

	p += sprintf(p, "#define SRC_TYPE ");
	switch (src_pixel_size) {
		case 1:
			p += sprintf(p, "unsigned char\n");
			break;
		case 2:
			p += sprintf(p, "unsigned short\n");
			break;
		case 4:
			p += sprintf(p, "unsigned int\n");
			break;
		default:
			return 0;
	}

	p += sprintf(p, "#define SRC_RPOS %d\n", src_rpos);
	p += sprintf(p, "#define SRC_GPOS %d\n", src_gpos);
	p += sprintf(p, "#define SRC_BPOS %d\n", src_bpos);
	p += sprintf(p, "#define SRC_APOS %d\n", src_apos);

	p += sprintf(p, "#define SRC_RSZ %d\n", src_rsz);
	p += sprintf(p, "#define SRC_GSZ %d\n", src_gsz);
	p += sprintf(p, "#define SRC_BSZ %d\n", src_bsz);
	p += sprintf(p, "#define SRC_ASZ %d\n", src_asz);

	p += sprintf(p, "#define DST_TYPE ");
	switch (dst_pixel_size) {
		case 1:
			p += sprintf(p, "unsigned char\n");
			break;
		case 2:
			p += sprintf(p, "unsigned short\n");
			break;
		case 4:
			p += sprintf(p, "unsigned int\n");
			break;
		default:
			return 0;
	}

	p += sprintf(p, "#define DST_RPOS %d\n", dst_rpos);
	p += sprintf(p, "#define DST_GPOS %d\n", dst_gpos);
	p += sprintf(p, "#define DST_BPOS %d\n", dst_bpos);
	p += sprintf(p, "#define DST_APOS %d\n", dst_apos);

	p += sprintf(p, "#define DST_RSZ %d\n", dst_rsz);
	p += sprintf(p, "#define DST_GSZ %d\n", dst_gsz);
	p += sprintf(p, "#define DST_BSZ %d\n", dst_bsz);
	p += sprintf(p, "#define DST_ASZ %d\n", dst_asz);

	strcpy(p, convert_template);

	fn = compile_function(name, buf, &handle);

	if (fn != NULL)
		fn(src, dst, count);
	else
		return 0;

	free_function(handle);
	return 1;
}

int
main(void)
{
	unsigned int src[8] = {
		0xff555555,
		0x55ff5555,
		0x5555ff55,
		0x555555ff,
		0x00555555,
		0x55005555,
		0x55550055,
		0x55555500
	};
	unsigned short dst[8];
	int i;

	i = convert_pixels(
	 src,
	 4, 		/* pixel size */
	 16, 8, 0, 24, 	/* offsets for r, g, b, a */
	 8, 8, 8, 8, 	/* sizes for r, g, b, a */
	 dst,
	 2,
	 8, 4, 0, 12,
	 4, 4, 4, 4,
	 8); 		/* count */

	if (i == 0)
		return 1;

	for (i = 0; i < 8; i++)
		printf("%08x %04x\n", src[i], dst[i]);

	return 0;
}