On Wednesday 08 September 2010 10:45:07 Siarhei Siamashka wrote:
> +/* A variant of 'core_combine_over_u_sse2' with minor tweaks */
> +static force_inline void
> +scaled_nearest_scanline_sse2_8888_8888_none_OVER (uint32_t* pd,
> + const uint32_t* ps,
> + int32_t w,
> + pixman_fixed_t vx,
> + pixman_fixed_t unit_x,
> + pixman_fixed_t max_vx)
> +{
> + uint32_t s, d;
> + const uint32_t* pm = NULL;
> +
> + __m128i xmm_dst_lo, xmm_dst_hi;
> + __m128i xmm_src_lo, xmm_src_hi;
> + __m128i xmm_alpha_lo, xmm_alpha_hi;
> +
> + /* Align dst on a 16-byte boundary */
> + while (w && ((unsigned long)pd & 15))
> + {
> + d = *pd;
> + s = combine1 (ps + (vx >> 16), pm);
> + vx += unit_x;
> +
> + *pd++ = core_combine_over_u_pixel_sse2 (s, d);
> + if (pm)
> + pm++;
> + w--;
> + }
> +
> + while (w >= 4)
> + {
> + __m128i tmp;
> + uint32_t tmp1, tmp2, tmp3, tmp4;
> +
> + tmp1 = ps[vx >> 16];
> + vx += unit_x;
> + tmp2 = ps[vx >> 16];
> + vx += unit_x;
> + tmp3 = ps[vx >> 16];
> + vx += unit_x;
> + tmp4 = ps[vx >> 16];
> + vx += unit_x;
> +
> + tmp = _mm_set_epi32 (tmp4, tmp3, tmp2, tmp1);
> +
> + xmm_src_hi = combine4 ((__m128i*)&tmp, (__m128i*)pm);
> +
> + if (is_opaque (xmm_src_hi))
> + {
> + save_128_aligned ((__m128i*)pd, xmm_src_hi);
> + }
> + else if (!is_zero (xmm_src_hi))
> + {
> + xmm_dst_hi = load_128_aligned ((__m128i*) pd);
> +
> + unpack_128_2x128 (xmm_src_hi, &xmm_src_lo, &xmm_src_hi);
> + unpack_128_2x128 (xmm_dst_hi, &xmm_dst_lo, &xmm_dst_hi);
> +
> + expand_alpha_2x128 (
> + xmm_src_lo, xmm_src_hi, &xmm_alpha_lo, &xmm_alpha_hi);
> +
> + over_2x128 (&xmm_src_lo, &xmm_src_hi,
> + &xmm_alpha_lo, &xmm_alpha_hi,
> + &xmm_dst_lo, &xmm_dst_hi);
> +
> + /* rebuid the 4 pixel data and save*/
> + save_128_aligned ((__m128i*)pd,
> + pack_2x128_128 (xmm_dst_lo, xmm_dst_hi));
> + }
> +
> + w -= 4;
> + pd += 4;
> + if (pm)
> + pm += 4;
> + }
> +
> + while (w)
> + {
> + d = *pd;
> + s = combine1 (ps + (vx >> 16), pm);
> + vx += unit_x;
> +
> + *pd++ = core_combine_over_u_pixel_sse2 (s, d);
> + if (pm)
> + pm++;
> +
> + w--;
> + }
> +}
Actually there is a problem here which I discovered after also trying the
patch on a 32-bit x86 system. The floating point registers may become corrupted
unless _mm_empty() is added somewhere at the end of this scaling fast path
code.
I have sent a patch which can help to detect such issues automatically by just
running pixman test suite (maybe not totally bulletproof, but still quite
useful):
http://lists.freedesktop.org/archives/pixman/2010-September/000486.html
--
Best regards,
Siarhei Siamashka
_______________________________________________
Pixman mailing list
[email protected]
http://lists.freedesktop.org/mailman/listinfo/pixman
