mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/chenhuacai/linux-loongson
synced 2025-09-04 10:33:13 +00:00
drm/format-helper: Optimize 32-to-16-bpp conversion
For ease of implementation, existing line-conversion functions for 16-bit formats write each pixel individually. Optimize the performance by writing multiple pixels in single 64-bit and 32-bit stores. v2: - simplify address calculation (Jani) - fix typo in commit message (Jocelyn) Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de> Reviewed-by: Jocelyn Falempe <jfalempe@redhat.com> Link: https://lore.kernel.org/r/20250328141709.217283-8-tzimmermann@suse.de
This commit is contained in:
parent
58523a25cb
commit
3f31a017dd
@ -265,10 +265,45 @@ static __always_inline void drm_fb_xfrm_line_32to16(void *dbuf, const void *sbuf
|
|||||||
unsigned int pixels,
|
unsigned int pixels,
|
||||||
u32 (*xfrm_pixel)(u32))
|
u32 (*xfrm_pixel)(u32))
|
||||||
{
|
{
|
||||||
__le16 *dbuf16 = dbuf;
|
__le64 *dbuf64 = dbuf;
|
||||||
|
__le32 *dbuf32;
|
||||||
|
__le16 *dbuf16;
|
||||||
const __le32 *sbuf32 = sbuf;
|
const __le32 *sbuf32 = sbuf;
|
||||||
const __le32 *send32 = sbuf32 + pixels;
|
const __le32 *send32 = sbuf32 + pixels;
|
||||||
|
|
||||||
|
#if defined(CONFIG_64BIT)
|
||||||
|
/* write 4 pixels at once */
|
||||||
|
while (sbuf32 < ALIGN_DOWN_PIXELS(send32, pixels, 4)) {
|
||||||
|
u32 pix[4] = {
|
||||||
|
le32_to_cpup(sbuf32++),
|
||||||
|
le32_to_cpup(sbuf32++),
|
||||||
|
le32_to_cpup(sbuf32++),
|
||||||
|
le32_to_cpup(sbuf32++),
|
||||||
|
};
|
||||||
|
/* write output bytes in reverse order for little endianness */
|
||||||
|
u64 val64 = ((u64)xfrm_pixel(pix[0])) |
|
||||||
|
((u64)xfrm_pixel(pix[1]) << 16) |
|
||||||
|
((u64)xfrm_pixel(pix[2]) << 32) |
|
||||||
|
((u64)xfrm_pixel(pix[3]) << 48);
|
||||||
|
*dbuf64++ = cpu_to_le64(val64);
|
||||||
|
}
|
||||||
|
#endif
|
||||||
|
|
||||||
|
/* write 2 pixels at once */
|
||||||
|
dbuf32 = (__le32 __force *)dbuf64;
|
||||||
|
while (sbuf32 < ALIGN_DOWN_PIXELS(send32, pixels, 2)) {
|
||||||
|
u32 pix[2] = {
|
||||||
|
le32_to_cpup(sbuf32++),
|
||||||
|
le32_to_cpup(sbuf32++),
|
||||||
|
};
|
||||||
|
/* write output bytes in reverse order for little endianness */
|
||||||
|
u32 val32 = xfrm_pixel(pix[0]) |
|
||||||
|
(xfrm_pixel(pix[1]) << 16);
|
||||||
|
*dbuf32++ = cpu_to_le32(val32);
|
||||||
|
}
|
||||||
|
|
||||||
|
/* write trailing pixel */
|
||||||
|
dbuf16 = (__le16 __force *)dbuf32;
|
||||||
while (sbuf32 < send32)
|
while (sbuf32 < send32)
|
||||||
*dbuf16++ = cpu_to_le16(xfrm_pixel(le32_to_cpup(sbuf32++)));
|
*dbuf16++ = cpu_to_le16(xfrm_pixel(le32_to_cpup(sbuf32++)));
|
||||||
}
|
}
|
||||||
|
Loading…
Reference in New Issue
Block a user