git update 12 sep 2011

6 files changed, 280 insertions, 47 deletions

diff --git a/pixman/configure.ac b/pixman/configure.ac
index 4c62102be..21613e135 100644
--- a/pixman/configure.ac
+++ b/pixman/configure.ac
@@ -54,7 +54,7 @@ AC_PREREQ([2.57])
 
 m4_define([pixman_major], 0)
 m4_define([pixman_minor], 23)
-m4_define([pixman_micro], 3)
+m4_define([pixman_micro], 5)
 
 m4_define([pixman_version],[pixman_major.pixman_minor.pixman_micro])
 
@@ -801,6 +801,17 @@ fi
 AC_MSG_RESULT($support_for_attribute_constructor)
 AC_SUBST(TOOLCHAIN_SUPPORTS_ATTRIBUTE_CONSTRUCTOR)
 
+dnl ==================
+dnl libpng
+
+AC_CHECK_LIB([png], [png_write_info], [have_libpng=yes], [have_libpng=no])
+
+if test x$have_libpng = xyes; then
+    AC_DEFINE([HAVE_LIBPNG], [1], [Whether we have libpng])
+fi
+
+AC_SUBST(HAVE_LIBPNG)
+
 AC_OUTPUT([pixman-1.pc
            pixman-1-uninstalled.pc
            Makefile
diff --git a/pixman/pixman/pixman-arm-neon-asm.S b/pixman/pixman/pixman-arm-neon-asm.S
index 3dc14d79d..3fcd07dc3 100644
--- a/pixman/pixman/pixman-arm-neon-asm.S
+++ b/pixman/pixman/pixman-arm-neon-asm.S
@@ -706,13 +706,55 @@ generate_composite_function_single_scanline \
 
 /******************************************************************************/
 
-/* TODO: expand macros and do better instructions scheduling */
+.macro pixman_composite_over_n_8888_process_pixblock_head
+    /* deinterleaved source pixels in {d0, d1, d2, d3} */
+    /* inverted alpha in {d24} */
+    /* destination pixels in {d4, d5, d6, d7} */
+    vmull.u8    q8, d24, d4
+    vmull.u8    q9, d24, d5
+    vmull.u8    q10, d24, d6
+    vmull.u8    q11, d24, d7
+.endm
+
+.macro pixman_composite_over_n_8888_process_pixblock_tail
+    vrshr.u16   q14, q8, #8
+    vrshr.u16   q15, q9, #8
+    vrshr.u16   q2, q10, #8
+    vrshr.u16   q3, q11, #8
+    vraddhn.u16 d28, q14, q8
+    vraddhn.u16 d29, q15, q9
+    vraddhn.u16 d30, q2, q10
+    vraddhn.u16 d31, q3, q11
+    vqadd.u8    q14, q0, q14
+    vqadd.u8    q15, q1, q15
+.endm
+
 .macro pixman_composite_over_n_8888_process_pixblock_tail_head
-    pixman_composite_over_8888_8888_process_pixblock_tail
+        vrshr.u16   q14, q8, #8
+        vrshr.u16   q15, q9, #8
+        vrshr.u16   q2, q10, #8
+        vrshr.u16   q3, q11, #8
+        vraddhn.u16 d28, q14, q8
+        vraddhn.u16 d29, q15, q9
+        vraddhn.u16 d30, q2, q10
+        vraddhn.u16 d31, q3, q11
     vld4.8      {d4, d5, d6, d7}, [DST_R, :128]!
-    vst4.8      {d28, d29, d30, d31}, [DST_W, :128]!
-    pixman_composite_over_8888_8888_process_pixblock_head
-    cache_preload 8, 8
+        vqadd.u8    q14, q0, q14
+                                    PF add PF_X, PF_X, #8
+                                    PF tst PF_CTL, #0x0F
+                                    PF addne PF_X, PF_X, #8
+                                    PF subne PF_CTL, PF_CTL, #1
+        vqadd.u8    q15, q1, q15
+                                    PF cmp PF_X, ORIG_W
+    vmull.u8    q8, d24, d4
+                                    PF pld, [PF_DST, PF_X, lsl #dst_bpp_shift]
+    vmull.u8    q9, d24, d5
+                                    PF subge PF_X, PF_X, ORIG_W
+    vmull.u8    q10, d24, d6
+                                    PF subges PF_CTL, PF_CTL, #0x10
+    vmull.u8    q11, d24, d7
+                                    PF ldrgeb DUMMY, [PF_DST, DST_STRIDE, lsl #dst_bpp_shift]!
+        vst4.8      {d28, d29, d30, d31}, [DST_W, :128]!
 .endm
 
 .macro pixman_composite_over_n_8888_init
@@ -722,6 +764,7 @@ generate_composite_function_single_scanline \
     vdup.8      d1, d3[1]
     vdup.8      d2, d3[2]
     vdup.8      d3, d3[3]
+    vmvn.8      d24, d3  /* get inverted alpha */
 .endm
 
 generate_composite_function \
@@ -1183,49 +1226,83 @@ generate_composite_function \
     /* mask is in d24 (d25, d26, d27 are unused) */
 
     /* in */
-    vmull.u8    q0, d24, d8
-    vmull.u8    q1, d24, d9
-    vmull.u8    q6, d24, d10
-    vmull.u8    q7, d24, d11
-    vrshr.u16   q10, q0, #8
-    vrshr.u16   q11, q1, #8
-    vrshr.u16   q12, q6, #8
-    vrshr.u16   q13, q7, #8
-    vraddhn.u16 d0, q0, q10
-    vraddhn.u16 d1, q1, q11
-    vraddhn.u16 d2, q6, q12
-    vraddhn.u16 d3, q7, q13
-    vmvn.8      d24, d3  /* get inverted alpha */
+    vmull.u8    q6, d24, d8
+    vmull.u8    q7, d24, d9
+    vmull.u8    q8, d24, d10
+    vmull.u8    q9, d24, d11
+    vrshr.u16   q10, q6, #8
+    vrshr.u16   q11, q7, #8
+    vrshr.u16   q12, q8, #8
+    vrshr.u16   q13, q9, #8
+    vraddhn.u16 d0, q6, q10
+    vraddhn.u16 d1, q7, q11
+    vraddhn.u16 d2, q8, q12
+    vraddhn.u16 d3, q9, q13
+    vmvn.8      d25, d3  /* get inverted alpha */
     /* source:      d0 - blue, d1 - green, d2 - red, d3 - alpha */
     /* destination: d4 - blue, d5 - green, d6 - red, d7 - alpha */
     /* now do alpha blending */
-    vmull.u8    q8, d24, d4
-    vmull.u8    q9, d24, d5
-    vmull.u8    q10, d24, d6
-    vmull.u8    q11, d24, d7
+    vmull.u8    q8, d25, d4
+    vmull.u8    q9, d25, d5
+    vmull.u8    q10, d25, d6
+    vmull.u8    q11, d25, d7
 .endm
 
 .macro pixman_composite_over_n_8_8888_process_pixblock_tail
     vrshr.u16   q14, q8, #8
     vrshr.u16   q15, q9, #8
-    vrshr.u16   q12, q10, #8
-    vrshr.u16   q13, q11, #8
+    vrshr.u16   q6, q10, #8
+    vrshr.u16   q7, q11, #8
     vraddhn.u16 d28, q14, q8
     vraddhn.u16 d29, q15, q9
-    vraddhn.u16 d30, q12, q10
-    vraddhn.u16 d31, q13, q11
+    vraddhn.u16 d30, q6, q10
+    vraddhn.u16 d31, q7, q11
     vqadd.u8    q14, q0, q14
     vqadd.u8    q15, q1, q15
 .endm
 
-/* TODO: expand macros and do better instructions scheduling */
 .macro pixman_composite_over_n_8_8888_process_pixblock_tail_head
-    pixman_composite_over_n_8_8888_process_pixblock_tail
-    vst4.8      {d28, d29, d30, d31}, [DST_W, :128]!
+        vrshr.u16   q14, q8, #8
     vld4.8      {d4, d5, d6, d7}, [DST_R, :128]!
+        vrshr.u16   q15, q9, #8
     fetch_mask_pixblock
-    cache_preload 8, 8
-    pixman_composite_over_n_8_8888_process_pixblock_head
+        vrshr.u16   q6, q10, #8
+                                    PF add PF_X, PF_X, #8
+        vrshr.u16   q7, q11, #8
+                                    PF tst PF_CTL, #0x0F
+        vraddhn.u16 d28, q14, q8
+                                    PF addne PF_X, PF_X, #8
+        vraddhn.u16 d29, q15, q9
+                                    PF subne PF_CTL, PF_CTL, #1
+        vraddhn.u16 d30, q6, q10
+                                    PF cmp PF_X, ORIG_W
+        vraddhn.u16 d31, q7, q11
+                                    PF pld, [PF_DST, PF_X, lsl #dst_bpp_shift]
+    vmull.u8    q6, d24, d8
+                                    PF pld, [PF_MASK, PF_X, lsl #mask_bpp_shift]
+    vmull.u8    q7, d24, d9
+                                    PF subge PF_X, PF_X, ORIG_W
+    vmull.u8    q8, d24, d10
+                                    PF subges PF_CTL, PF_CTL, #0x10
+    vmull.u8    q9, d24, d11
+                                    PF ldrgeb DUMMY, [PF_DST, DST_STRIDE, lsl #dst_bpp_shift]!
+        vqadd.u8    q14, q0, q14
+                                    PF ldrgeb DUMMY, [PF_MASK, MASK_STRIDE, lsl #mask_bpp_shift]!
+        vqadd.u8    q15, q1, q15
+    vrshr.u16   q10, q6, #8
+    vrshr.u16   q11, q7, #8
+    vrshr.u16   q12, q8, #8
+    vrshr.u16   q13, q9, #8
+    vraddhn.u16 d0, q6, q10
+    vraddhn.u16 d1, q7, q11
+    vraddhn.u16 d2, q8, q12
+    vraddhn.u16 d3, q9, q13
+        vst4.8      {d28, d29, d30, d31}, [DST_W, :128]!
+    vmvn.8      d25, d3
+    vmull.u8    q8, d25, d4
+    vmull.u8    q9, d25, d5
+    vmull.u8    q10, d25, d6
+    vmull.u8    q11, d25, d7
 .endm
 
 .macro pixman_composite_over_n_8_8888_init
diff --git a/pixman/pixman/pixman-bits-image.c b/pixman/pixman/pixman-bits-image.c
index f540c76e1..f382c65ad 100644
--- a/pixman/pixman/pixman-bits-image.c
+++ b/pixman/pixman/pixman-bits-image.c
@@ -935,17 +935,16 @@ MAKE_FETCHERS (reflect_r5g6b5,   r5g6b5,   PIXMAN_REPEAT_REFLECT)
 MAKE_FETCHERS (normal_r5g6b5,    r5g6b5,   PIXMAN_REPEAT_NORMAL)
 
 static void
-bits_image_fetch_solid_32 (pixman_image_t * image,
-                           int              x,
-                           int              y,
-                           int              width,
-                           uint32_t *       buffer,
-                           const uint32_t * mask)
+replicate_pixel_32 (bits_image_t *   bits,
+		    int              x,
+		    int              y,
+		    int              width,
+		    uint32_t *       buffer)
 {
     uint32_t color;
     uint32_t *end;
 
-    color = image->bits.fetch_pixel_32 (&image->bits, 0, 0);
+    color = bits->fetch_pixel_32 (bits, x, y);
 
     end = buffer + width;
     while (buffer < end)
@@ -953,18 +952,17 @@ bits_image_fetch_solid_32 (pixman_image_t * image,
 }
 
 static void
-bits_image_fetch_solid_64 (pixman_image_t * image,
-                           int              x,
-                           int              y,
-                           int              width,
-                           uint32_t *       b,
-                           const uint32_t * unused)
+replicate_pixel_64 (bits_image_t *   bits,
+		    int              x,
+		    int              y,
+		    int              width,
+		    uint32_t *       b)
 {
     uint64_t color;
     uint64_t *buffer = (uint64_t *)b;
     uint64_t *end;
 
-    color = image->bits.fetch_pixel_64 (&image->bits, 0, 0);
+    color = bits->fetch_pixel_64 (bits, x, y);
 
     end = buffer + width;
     while (buffer < end)
@@ -972,6 +970,28 @@ bits_image_fetch_solid_64 (pixman_image_t * image,
 }
 
 static void
+bits_image_fetch_solid_32 (pixman_image_t * image,
+                           int              x,
+                           int              y,
+                           int              width,
+                           uint32_t *       buffer,
+                           const uint32_t * mask)
+{
+    replicate_pixel_32 (&image->bits, 0, 0, width, buffer);
+}
+
+static void
+bits_image_fetch_solid_64 (pixman_image_t * image,
+                           int              x,
+                           int              y,
+                           int              width,
+                           uint32_t *       b,
+                           const uint32_t * unused)
+{
+    replicate_pixel_64 (&image->bits, 0, 0, width, b);
+}
+
+static void
 bits_image_fetch_untransformed_repeat_none (bits_image_t *image,
                                             pixman_bool_t wide,
                                             int           x,
@@ -1031,6 +1051,16 @@ bits_image_fetch_untransformed_repeat_normal (bits_image_t *image,
     while (y >= image->height)
 	y -= image->height;
 
+    if (image->width == 1)
+    {
+	if (wide)
+	    replicate_pixel_64 (image, 0, y, width, buffer);
+	else
+	    replicate_pixel_32 (image, 0, y, width, buffer);
+
+	return;
+    }
+
     while (width)
     {
 	while (x < 0)
diff --git a/pixman/test/Makefile.am b/pixman/test/Makefile.am
index 9f61fc9e4..52ef8ad96 100644
--- a/pixman/test/Makefile.am
+++ b/pixman/test/Makefile.am
@@ -1,6 +1,6 @@
 AM_CFLAGS = @OPENMP_CFLAGS@
 AM_LDFLAGS = @OPENMP_CFLAGS@ @TESTPROGS_EXTRA_LDFLAGS@
-LDADD = $(top_builddir)/pixman/libpixman-1.la -lm
+LDADD = $(top_builddir)/pixman/libpixman-1.la -lm -lpng
 INCLUDES = -I$(top_srcdir)/pixman -I$(top_builddir)/pixman
 
 TESTPROGRAMS =			\
diff --git a/pixman/test/utils.c b/pixman/test/utils.c
index 44188ea90..adabd75dd 100644
--- a/pixman/test/utils.c
+++ b/pixman/test/utils.c
@@ -21,6 +21,10 @@
 #include <fenv.h>
 #endif
 
+#ifdef HAVE_LIBPNG
+#include <png.h>
+#endif
+
 /* Random number seed
  */
 
@@ -335,6 +339,114 @@ make_random_bytes (int n_bytes)
     return bytes;
 }
 
+#ifdef HAVE_LIBPNG
+
+static void
+pngify_pixels (uint32_t *pixels, int n_pixels)
+{
+    int i;
+
+    for (i = 0; i < n_pixels; ++i)
+    {
+	uint32_t p = pixels[i];
+	uint8_t *out = (uint8_t *)&(pixels[i]);
+	uint8_t a, r, g, b;
+
+	a = (p & 0xff000000) >> 24;
+	r = (p & 0x00ff0000) >> 16;
+	g = (p & 0x0000ff00) >> 8;
+	b = (p & 0x000000ff) >> 0;
+
+	if (a != 0)
+	{
+	    r = (r * 255) / a;
+	    g = (g * 255) / a;
+	    b = (b * 255) / a;
+	}
+
+	*out++ = r;
+	*out++ = g;
+	*out++ = b;
+	*out++ = a;
+    }
+}
+
+pixman_bool_t
+write_png (pixman_image_t *image, const char *filename)
+{
+    int width = pixman_image_get_width (image);
+    int height = pixman_image_get_height (image);
+    int stride = width * 4;
+    uint32_t *data = malloc (height * stride);
+    pixman_image_t *copy;
+    png_struct *write_struct;
+    png_info *info_struct;
+    pixman_bool_t result = FALSE;
+    FILE *f = fopen (filename, "wb");
+    png_bytep *row_pointers;
+    int i;
+
+    if (!f)
+	return FALSE;
+
+    row_pointers = malloc (height * sizeof (png_bytep));
+
+    copy = pixman_image_create_bits (
+	PIXMAN_a8r8g8b8, width, height, data, stride);
+
+    pixman_image_composite32 (
+	PIXMAN_OP_SRC, image, NULL, copy, 0, 0, 0, 0, 0, 0, width, height);
+
+    pngify_pixels (data, height * width);
+
+    for (i = 0; i < height; ++i)
+	row_pointers[i] = (png_bytep)(data + i * width);
+
+    if (!(write_struct = png_create_write_struct (
+	      PNG_LIBPNG_VER_STRING, NULL, NULL, NULL)))
+	goto out1;
+
+    if (!(info_struct = png_create_info_struct (write_struct)))
+	goto out2;
+
+    png_init_io (write_struct, f);
+
+    png_set_IHDR (write_struct, info_struct, width, height,
+		  8, PNG_COLOR_TYPE_RGB_ALPHA,
+		  PNG_INTERLACE_NONE, PNG_COMPRESSION_TYPE_BASE,
+		  PNG_FILTER_TYPE_BASE);
+
+    png_write_info (write_struct, info_struct);
+
+    png_write_image (write_struct, row_pointers);
+
+    png_write_end (write_struct, NULL);
+
+    result = TRUE;
+
+out2:
+    png_destroy_write_struct (&write_struct, &info_struct);
+
+out1:
+    if (fclose (f) != 0)
+	result = FALSE;
+
+    pixman_image_unref (copy);
+    free (row_pointers);
+    free (data);
+    return result;
+}
+
+#else /* no libpng */
+
+pixman_bool_t
+write_png (pixman_image_t *image, const char *filename)
+{
+    return FALSE;
+}
+
+#endif
+
 /*
  * A function, which can be used as a core part of the test programs,
  * intended to detect various problems with the help of fuzzing input
diff --git a/pixman/test/utils.h b/pixman/test/utils.h
index f0c9c300c..3790483db 100644
--- a/pixman/test/utils.h
+++ b/pixman/test/utils.h
@@ -105,6 +105,9 @@ fail_after (int seconds, const char *msg);
 /* If possible, enable traps for floating point exceptions */
 void enable_fp_exceptions(void);
 
+pixman_bool_t
+write_png (pixman_image_t *image, const char *filename);
+
 /* A pair of macros which can help to detect corruption of
  * floating point registers after a function call. This may
  * happen if _mm_empty() call is forgotten in MMX/SSE2 fast