pixman: Changes to 'upstream-experimental'
.gitignore | 13
COPYING | 1
RELEASING | 30
TODO | 5
autogen.sh | 2
configure.ac | 187 +-
libcomp.pc | 11
pixman/Makefile.am | 29
pixman/pixman-access.c | 206 +-
pixman/pixman-arm-common.h | 273 +++
pixman/pixman-arm-neon-asm.S | 1713 ++++++++++++++++++++++
pixman/pixman-arm-neon-asm.h | 906 +++++++++++
pixman/pixman-arm-neon.c | 2892 +++-----------------------------------
pixman/pixman-arm-simd-asm.S | 330 ++++
pixman/pixman-arm-simd.c | 225 +-
pixman/pixman-bits-image.c | 413 ++++-
pixman/pixman-compiler.h | 60
pixman/pixman-conical-gradient.c | 2
pixman/pixman-cpu.c | 14
pixman/pixman-edge-imp.h | 20
pixman/pixman-edge.c | 5
pixman/pixman-fast-path.c | 1004 ++++++++++---
pixman/pixman-general.c | 52
pixman/pixman-image.c | 306 +++-
pixman/pixman-implementation.c | 55
pixman/pixman-mmx.c | 290 +--
pixman/pixman-private.h | 277 ++-
pixman/pixman-region.c | 334 +++-
pixman/pixman-solid-fill.c | 35
pixman/pixman-sse2.c | 710 +++++----
pixman/pixman-trap.c | 14
pixman/pixman-utils.c | 620 --------
pixman/pixman-vmx.c | 7
pixman/pixman-x64-mmx-emulation.h | 8
pixman/pixman.c | 1012 +++++++++++--
pixman/pixman.h | 81 -
pixman/solaris-hwcap.mapfile | 36
test/Makefile.am | 52
test/a1-trap-test.c | 50
test/alpha-test.c | 12
test/alphamap.c | 49
test/blitters-test.c | 315 +---
test/clip-in.c | 2
test/clip-test.c | 4
test/composite-test.c | 7
test/composite.c | 901 +++++++++++
test/convolution-test.c | 2
test/fetch-test.c | 104 -
test/gradient-test.c | 10
test/gtk-utils.c | 113 +
test/gtk-utils.h | 13
test/region-test.c | 49
test/scaling-test.c | 207 --
test/screen-test.c | 2
test/trap-test.c | 2
test/utils.c | 289 ++-
test/utils.h | 47
test/window-test.c | 6
58 files changed, 8942 insertions(+), 5472 deletions(-)
New commits:
commit e9dc568d6f585a153c47e970168a9c71d3e45fde
Author: Søren Sandmann Pedersen <ssp@redhat.com>
Date: Thu Apr 1 05:23:31 2010 -0400
Pre-release version bump to 0.18.0
diff --git a/configure.ac b/configure.ac
index 95ba1c9..d13b6e6 100644
--- a/configure.ac
+++ b/configure.ac
@@ -53,8 +53,8 @@ AC_PREREQ([2.57])
#
m4_define([pixman_major], 0)
-m4_define([pixman_minor], 17)
-m4_define([pixman_micro], 15)
+m4_define([pixman_minor], 18)
+m4_define([pixman_micro], 0)
m4_define([pixman_version],[pixman_major.pixman_minor.pixman_micro])
commit efd41c62875d97c5127233cb6a4c353b4d495531
Author: Matthias Hopf <mhopf@suse.de>
Date: Wed Mar 24 18:54:29 2010 +0100
Revert "Improve PIXREGION_NIL to return true on degenerated regions."
This reverts commit ebba1493136a5a0dd7667073165b2115de203eda.
Scheduled for re-discussion after stable 0.18 has been released.
diff --git a/pixman/pixman-region.c b/pixman/pixman-region.c
index 179241d..a6a4005 100644
--- a/pixman/pixman-region.c
+++ b/pixman/pixman-region.c
@@ -69,11 +69,7 @@
#include <stdio.h>
#include "pixman-private.h"
-#define PIXREGION_NIL(reg) (((reg)->data && !(reg)->data->numRects) || \
- (! (reg)->data && \
- (reg)->extents.x1 == (reg)->extents.x2 && \
- (reg)->extents.y1 == (reg)->extents.y2))
-
+#define PIXREGION_NIL(reg) ((reg)->data && !(reg)->data->numRects)
/* not a region */
#define PIXREGION_NAR(reg) ((reg)->data == pixman_broken_data)
#define PIXREGION_NUMRECTS(reg) ((reg)->data ? (reg)->data->numRects : 1)
commit ebba1493136a5a0dd7667073165b2115de203eda
Author: Matthias Hopf <mhopf@suse.de>
Date: Wed Mar 24 12:00:21 2010 +0100
Improve PIXREGION_NIL to return true on degenerated regions.
Fixes Novell bug 568811.
diff --git a/pixman/pixman-region.c b/pixman/pixman-region.c
index a6a4005..179241d 100644
--- a/pixman/pixman-region.c
+++ b/pixman/pixman-region.c
@@ -69,7 +69,11 @@
#include <stdio.h>
#include "pixman-private.h"
-#define PIXREGION_NIL(reg) ((reg)->data && !(reg)->data->numRects)
+#define PIXREGION_NIL(reg) (((reg)->data && !(reg)->data->numRects) || \
+ (! (reg)->data && \
+ (reg)->extents.x1 == (reg)->extents.x2 && \
+ (reg)->extents.y1 == (reg)->extents.y2))
+
/* not a region */
#define PIXREGION_NAR(reg) ((reg)->data == pixman_broken_data)
#define PIXREGION_NUMRECTS(reg) ((reg)->data ? (reg)->data->numRects : 1)
commit c0f8d417b512b7d526fb6127954a50d14214f420
Author: Søren Sandmann Pedersen <ssp@redhat.com>
Date: Tue Mar 23 17:25:54 2010 -0400
Post-release version bump to 0.17.15
diff --git a/configure.ac b/configure.ac
index 3edca54..95ba1c9 100644
--- a/configure.ac
+++ b/configure.ac
@@ -54,7 +54,7 @@ AC_PREREQ([2.57])
m4_define([pixman_major], 0)
m4_define([pixman_minor], 17)
-m4_define([pixman_micro], 14)
+m4_define([pixman_micro], 15)
m4_define([pixman_version],[pixman_major.pixman_minor.pixman_micro])
commit b35f0b0158cd7aac388ba4c72c6c8aada77d2e22
Author: Søren Sandmann Pedersen <ssp@redhat.com>
Date: Tue Mar 23 16:52:02 2010 -0400
Pre-release version bump to 0.17.14
diff --git a/configure.ac b/configure.ac
index ed7d16a..3edca54 100644
--- a/configure.ac
+++ b/configure.ac
@@ -54,7 +54,7 @@ AC_PREREQ([2.57])
m4_define([pixman_major], 0)
m4_define([pixman_minor], 17)
-m4_define([pixman_micro], 13)
+m4_define([pixman_micro], 14)
m4_define([pixman_version],[pixman_major.pixman_minor.pixman_micro])
commit 3ef203331f124bf137c6e0c8d5516b1209c92dd9
Author: Siarhei Siamashka <siarhei.siamashka@nokia.com>
Date: Mon Mar 22 21:56:17 2010 +0200
ARM: SIMD optimizations moved to a separate .S file
This should be the last step in providing full armv4t compatibility
with CPU features runtime autodetection in pixman.
diff --git a/configure.ac b/configure.ac
index 4668715..ed7d16a 100644
--- a/configure.ac
+++ b/configure.ac
@@ -361,30 +361,24 @@ AC_SUBST(VMX_CFLAGS)
AM_CONDITIONAL(USE_VMX, test $have_vmx_intrinsics = yes)
-dnl ===========================================================================
-dnl Check for ARM SIMD instructions
-ARM_SIMD_CFLAGS=""
-
+dnl ==========================================================================
+dnl Check if assembler is gas compatible and supports ARM SIMD instructions
have_arm_simd=no
AC_MSG_CHECKING(whether to use ARM SIMD assembler)
-# check with default CFLAGS in case the toolchain turns on a sufficiently recent -mcpu=
-AC_COMPILE_IFELSE([
-int main () {
- asm("uqadd8 r1, r1, r2");
- return 0;
-}], have_arm_simd=yes,
- # check again with an explicit -mcpu= in case the toolchain defaults to an
- # older one; note that uqadd8 isn't available in Thumb mode on arm1136j-s
- # so we force ARM mode
- ARM_SIMD_CFLAGS="-mcpu=arm1136j-s -marm"
- xserver_save_CFLAGS=$CFLAGS
- CFLAGS="$ARM_SIMD_CFLAGS $CFLAGS"
- AC_COMPILE_IFELSE([
- int main () {
- asm("uqadd8 r1, r1, r2");
- return 0;
- }], have_arm_simd=yes)
- CFLAGS=$xserver_save_CFLAGS)
+xserver_save_CFLAGS=$CFLAGS
+CFLAGS="-x assembler-with-cpp $CFLAGS"
+AC_COMPILE_IFELSE([[
+.text
+.arch armv6
+.object_arch armv4
+.arm
+.altmacro
+#ifndef __ARM_EABI__
+#error EABI is required (to be sure that calling conventions are compatible)
+#endif
+pld [r0]
+uqadd8 r0, r0, r0]], have_arm_simd=yes)
+CFLAGS=$xserver_save_CFLAGS
AC_ARG_ENABLE(arm-simd,
[AC_HELP_STRING([--disable-arm-simd],
@@ -396,20 +390,16 @@ if test $enable_arm_simd = no ; then
fi
if test $have_arm_simd = yes ; then
- AC_DEFINE(USE_ARM_SIMD, 1, [use ARM SIMD compiler intrinsics])
-else
- ARM_SIMD_CFLAGS=
+ AC_DEFINE(USE_ARM_SIMD, 1, [use ARM SIMD assembly optimizations])
fi
+AM_CONDITIONAL(USE_ARM_SIMD, test $have_arm_simd = yes)
+
AC_MSG_RESULT($have_arm_simd)
if test $enable_arm_simd = yes && test $have_arm_simd = no ; then
AC_MSG_ERROR([ARM SIMD intrinsics not detected])
fi
-AC_SUBST(ARM_SIMD_CFLAGS)
-
-AM_CONDITIONAL(USE_ARM_SIMD, test $have_arm_simd = yes)
-
dnl ==========================================================================
dnl Check if assembler is gas compatible and supports NEON instructions
have_arm_neon=no
diff --git a/pixman/Makefile.am b/pixman/Makefile.am
index 5a0e7a9..66ad7f0 100644
--- a/pixman/Makefile.am
+++ b/pixman/Makefile.am
@@ -97,12 +97,14 @@ endif
if USE_ARM_SIMD
noinst_LTLIBRARIES += libpixman-arm-simd.la
libpixman_arm_simd_la_SOURCES = \
- pixman-arm-simd.c
-libpixman_arm_simd_la_CFLAGS = $(DEP_CFLAGS) $(ARM_SIMD_CFLAGS)
+ pixman-arm-simd.c \
+ pixman-arm-common.h \
+ pixman-arm-simd-asm.S
+libpixman_arm_simd_la_CFLAGS = $(DEP_CFLAGS)
libpixman_arm_simd_la_LIBADD = $(DEP_LIBS)
libpixman_1_la_LIBADD += libpixman-arm-simd.la
-ASM_CFLAGS_arm_simd=$(ARM_SIMD_CFLAGS)
+ASM_CFLAGS_arm_simd=
endif
# arm neon code
@@ -110,6 +112,7 @@ if USE_ARM_NEON
noinst_LTLIBRARIES += libpixman-arm-neon.la
libpixman_arm_neon_la_SOURCES = \
pixman-arm-neon.c \
+ pixman-arm-common.h \
pixman-arm-neon-asm.S \
pixman-arm-neon-asm.h
libpixman_arm_neon_la_CFLAGS = $(DEP_CFLAGS)
diff --git a/pixman/pixman-arm-simd-asm.S b/pixman/pixman-arm-simd-asm.S
new file mode 100644
index 0000000..1a1a0d6
--- /dev/null
+++ b/pixman/pixman-arm-simd-asm.S
@@ -0,0 +1,330 @@
+/*
+ * Copyright © 2008 Mozilla Corporation
+ *
+ * Permission to use, copy, modify, distribute, and sell this software and its
+ * documentation for any purpose is hereby granted without fee, provided that
+ * the above copyright notice appear in all copies and that both that
+ * copyright notice and this permission notice appear in supporting
+ * documentation, and that the name of Mozilla Corporation not be used in
+ * advertising or publicity pertaining to distribution of the software without
+ * specific, written prior permission. Mozilla Corporation makes no
+ * representations about the suitability of this software for any purpose. It
+ * is provided "as is" without express or implied warranty.
+ *
+ * THE COPYRIGHT HOLDERS DISCLAIM ALL WARRANTIES WITH REGARD TO THIS
+ * SOFTWARE, INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND
+ * FITNESS, IN NO EVENT SHALL THE COPYRIGHT HOLDERS BE LIABLE FOR ANY
+ * SPECIAL, INDIRECT OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN
+ * AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING
+ * OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS
+ * SOFTWARE.
+ *
+ * Author: Jeff Muizelaar (jeff@infidigm.net)
+ *
+ */
+
+/* Prevent the stack from becoming executable */
+#if defined(__linux__) && defined(__ELF__)
+.section .note.GNU-stack,"",%progbits
+#endif
+
+ .text
+ .arch armv6
+ .object_arch armv4
+ .arm
+ .altmacro
+
+/* Supplementary macro for setting function attributes */
+.macro pixman_asm_function fname
+ .func fname
+ .global fname
+#ifdef __ELF__
+ .hidden fname
+ .type fname, %function
+#endif
+fname:
+.endm
+
+/*
+ * The code below was generated by gcc 4.3.4 from the commented out
+ * functions in 'pixman-arm-simd.c' file with the following optimization
+ * options: "-O3 -mcpu=arm1136jf-s -fomit-frame-pointer"
+ *
+ * TODO: replace gcc generated code with hand tuned versions because
+ * the code quality is not very good, introduce symbolic register
+ * aliases for better readability and maintainability.
+ */
+
+pixman_asm_function pixman_composite_add_8000_8000_asm_armv6
+ push {r4, r5, r6, r7, r8, r9, r10, r11}
+ mov r10, r1
+ sub sp, sp, #4
+ subs r10, r10, #1
+ mov r11, r0
+ mov r8, r2
+ str r3, [sp]
+ ldr r7, [sp, #36]
+ bcc 0f
+6: cmp r11, #0
+ beq 1f
+ orr r3, r8, r7
+ tst r3, #3
+ beq 2f
+ mov r1, r8
+ mov r0, r7
+ mov r12, r11
+ b 3f
+5: tst r3, #3
+ beq 4f
+3: ldrb r2, [r0], #1
+ subs r12, r12, #1
+ ldrb r3, [r1]
+ uqadd8 r3, r2, r3
+ strb r3, [r1], #1
+ orr r3, r1, r0
+ bne 5b
+1: ldr r3, [sp]
+ add r8, r8, r3
+ ldr r3, [sp, #40]
+ add r7, r7, r3
+10: subs r10, r10, #1
+ bcs 6b
+0: add sp, sp, #4
+ pop {r4, r5, r6, r7, r8, r9, r10, r11}
+ bx lr
+2: mov r12, r11
+ mov r1, r8
+ mov r0, r7
+4: cmp r12, #3
+ subgt r6, r12, #4
+ movgt r9, r12
+ lsrgt r5, r6, #2
+ addgt r3, r5, #1
+ movgt r12, #0
+ lslgt r4, r3, #2
+ ble 7f
+8: ldr r3, [r0, r12]
+ ldr r2, [r1, r12]
+ uqadd8 r3, r3, r2
+ str r3, [r1, r12]
+ add r12, r12, #4
+ cmp r12, r4
+ bne 8b
+ sub r3, r9, #4
+ bic r3, r3, #3
+ add r3, r3, #4
+ subs r12, r6, r5, lsl #2
+ add r1, r1, r3
+ add r0, r0, r3
+ beq 1b
+7: mov r4, #0
+9: ldrb r3, [r1, r4]
+ ldrb r2, [r0, r4]
+ uqadd8 r3, r2, r3
+ strb r3, [r1, r4]
+ add r4, r4, #1
+ cmp r4, r12
+ bne 9b
+ ldr r3, [sp]
+ add r8, r8, r3
+ ldr r3, [sp, #40]
+ add r7, r7, r3
+ b 10b
+.endfunc
+
+pixman_asm_function pixman_composite_over_8888_8888_asm_armv6
+ push {r4, r5, r6, r7, r8, r9, r10, r11}
+ sub sp, sp, #20
+ cmp r1, #0
+ mov r12, r2
+ str r1, [sp, #12]
+ str r0, [sp, #16]
+ ldr r2, [sp, #52]
+ beq 0f
+ lsl r3, r3, #2
+ str r3, [sp]
+ ldr r3, [sp, #56]
+ mov r10, #0
+ lsl r3, r3, #2
+ str r3, [sp, #8]
+ mov r11, r3
+ b 1f
+6: ldr r11, [sp, #8]
+1: ldr r9, [sp]
+ mov r0, r12
+ add r12, r12, r9
+ mov r1, r2
+ str r12, [sp, #4]
+ add r2, r2, r11
+ ldr r12, [sp, #16]
+ ldr r3, =0x00800080
+ ldr r9, =0xff00ff00
+ mov r11, #255
+ cmp r12, #0
+ beq 4f
+5: ldr r5, [r1], #4
+ ldr r4, [r0]
+ sub r8, r11, r5, lsr #24
+ uxtb16 r6, r4
+ uxtb16 r7, r4, ror #8
+ mla r6, r6, r8, r3
+ mla r7, r7, r8, r3
+ uxtab16 r6, r6, r6, ror #8
+ uxtab16 r7, r7, r7, ror #8
+ and r7, r7, r9
+ uxtab16 r6, r7, r6, ror #8
+ uqadd8 r5, r6, r5
+ str r5, [r0], #4
+ subs r12, r12, #1
+ bne 5b
+4: ldr r3, [sp, #12]
+ add r10, r10, #1
+ cmp r10, r3
+ ldr r12, [sp, #4]
+ bne 6b
+0: add sp, sp, #20
+ pop {r4, r5, r6, r7, r8, r9, r10, r11}
+ bx lr
+.endfunc
+
+pixman_asm_function pixman_composite_over_8888_n_8888_asm_armv6
+ push {r4, r5, r6, r7, r8, r9, r10, r11}
+ sub sp, sp, #28
+ cmp r1, #0
+ str r1, [sp, #12]
+ ldrb r1, [sp, #71]
+ mov r12, r2
+ str r0, [sp, #16]
+ ldr r2, [sp, #60]
+ str r1, [sp, #24]
+ beq 0f
+ lsl r3, r3, #2
+ str r3, [sp, #20]
+ ldr r3, [sp, #64]
+ mov r10, #0
+ lsl r3, r3, #2
+ str r3, [sp, #8]
+ mov r11, r3
+ b 1f
+5: ldr r11, [sp, #8]
+1: ldr r4, [sp, #20]
+ mov r0, r12
+ mov r1, r2
+ add r12, r12, r4
+ add r2, r2, r11
+ str r12, [sp]
+ str r2, [sp, #4]
+ ldr r12, [sp, #16]
+ ldr r2, =0x00800080
+ ldr r3, [sp, #24]
+ mov r11, #255
+ cmp r12, #0
+ beq 3f
+4: ldr r5, [r1], #4
+ ldr r4, [r0]
+ uxtb16 r6, r5
+ uxtb16 r7, r5, ror #8
+ mla r6, r6, r3, r2
+ mla r7, r7, r3, r2
+ uxtab16 r6, r6, r6, ror #8
+ uxtab16 r7, r7, r7, ror #8
+ uxtb16 r6, r6, ror #8
+ uxtb16 r7, r7, ror #8
+ orr r5, r6, r7, lsl #8
+ uxtb16 r6, r4
+ uxtb16 r7, r4, ror #8
+ sub r8, r11, r5, lsr #24
+ mla r6, r6, r8, r2
+ mla r7, r7, r8, r2
+ uxtab16 r6, r6, r6, ror #8
+ uxtab16 r7, r7, r7, ror #8
+ uxtb16 r6, r6, ror #8
+ uxtb16 r7, r7, ror #8
+ orr r6, r6, r7, lsl #8
+ uqadd8 r5, r6, r5
+ str r5, [r0], #4
+ subs r12, r12, #1
+ bne 4b
+3: ldr r1, [sp, #12]
+ add r10, r10, #1
+ cmp r10, r1
+ ldr r12, [sp]
+ ldr r2, [sp, #4]
+ bne 5b
+0: add sp, sp, #28
+ pop {r4, r5, r6, r7, r8, r9, r10, r11}
+ bx lr
+.endfunc
+
+pixman_asm_function pixman_composite_over_n_8_8888_asm_armv6
+ push {r4, r5, r6, r7, r8, r9, r10, r11}
+ sub sp, sp, #28
+ cmp r1, #0
+ ldr r9, [sp, #60]
+ str r1, [sp, #12]
+ bic r1, r9, #-16777216
+ str r1, [sp, #20]
+ mov r12, r2
+ lsr r1, r9, #8
+ ldr r2, [sp, #20]
+ bic r1, r1, #-16777216
+ bic r2, r2, #65280
+ bic r1, r1, #65280
+ str r2, [sp, #20]
+ str r0, [sp, #16]
+ str r1, [sp, #4]
+ ldr r2, [sp, #68]
+ beq 0f
+ lsl r3, r3, #2
+ str r3, [sp, #24]
+ mov r0, #0
+ b 1f
+5: ldr r3, [sp, #24]
+1: ldr r4, [sp, #72]
+ mov r10, r12
+ mov r1, r2
+ add r12, r12, r3
+ add r2, r2, r4
+ str r12, [sp, #8]
+ str r2, [sp]
+ ldr r12, [sp, #16]
+ ldr r11, =0x00800080
+ ldr r2, [sp, #4]
+ ldr r3, [sp, #20]
+ cmp r12, #0
+ beq 3f
+4: ldrb r5, [r1], #1
+ ldr r4, [r10]
+ mla r6, r3, r5, r11
+ mla r7, r2, r5, r11
+ uxtab16 r6, r6, r6, ror #8
+ uxtab16 r7, r7, r7, ror #8
+ uxtb16 r6, r6, ror #8
+ uxtb16 r7, r7, ror #8
+ orr r5, r6, r7, lsl #8
+ uxtb16 r6, r4
+ uxtb16 r7, r4, ror #8
+ mvn r8, r5
+ lsr r8, r8, #24
+ mla r6, r6, r8, r11
+ mla r7, r7, r8, r11
+ uxtab16 r6, r6, r6, ror #8
+ uxtab16 r7, r7, r7, ror #8
+ uxtb16 r6, r6, ror #8
+ uxtb16 r7, r7, ror #8
+ orr r6, r6, r7, lsl #8
+ uqadd8 r5, r6, r5
+ str r5, [r10], #4
+ subs r12, r12, #1
+ bne 4b
+3: ldr r4, [sp, #12]
+ add r0, r0, #1
+ cmp r0, r4
+ ldr r12, [sp, #8]
+ ldr r2, [sp]
+ bne 5b
+0: add sp, sp, #28
+ pop {r4, r5, r6, r7, r8, r9, r10, r11}
+ bx lr
+.endfunc
diff --git a/pixman/pixman-arm-simd.c b/pixman/pixman-arm-simd.c
index f110753..389c9e0 100644
--- a/pixman/pixman-arm-simd.c
+++ b/pixman/pixman-arm-simd.c
@@ -30,6 +30,8 @@
#include "pixman-private.h"
#include "pixman-arm-common.h"
+#if 0 /* This code was moved to 'pixman-arm-simd-asm.S' */
+
void
pixman_composite_add_8000_8000_asm_armv6 (int32_t width,
int32_t height,
@@ -371,6 +373,8 @@ pixman_composite_over_n_8_8888_asm_armv6 (int32_t width,
}
}
+#endif
+
PIXMAN_ARM_BIND_FAST_PATH_SRC_DST (armv6, add_8000_8000,
uint8_t, 1, uint8_t, 1)
PIXMAN_ARM_BIND_FAST_PATH_SRC_DST (armv6, over_8888_8888,
commit 0a0591c2f7abde8880f4aebd510c27517a414450
Author: Siarhei Siamashka <siarhei.siamashka@nokia.com>
Date: Mon Mar 22 19:51:00 2010 +0200
ARM: SIMD optimizations updated to use common assembly calling conventions
diff --git a/pixman/pixman-arm-simd.c b/pixman/pixman-arm-simd.c
index 09a2888..f110753 100644
--- a/pixman/pixman-arm-simd.c
+++ b/pixman/pixman-arm-simd.c
@@ -28,31 +28,20 @@
#endif
#include "pixman-private.h"
-
-static void
-arm_composite_add_8000_8000 (pixman_implementation_t * impl,
- pixman_op_t op,
- pixman_image_t * src_image,
- pixman_image_t * mask_image,
- pixman_image_t * dst_image,
- int32_t src_x,
- int32_t src_y,
- int32_t mask_x,
- int32_t mask_y,
- int32_t dest_x,
- int32_t dest_y,
- int32_t width,
- int32_t height)
+#include "pixman-arm-common.h"
+
+void
+pixman_composite_add_8000_8000_asm_armv6 (int32_t width,
+ int32_t height,
+ uint8_t *dst_line,
+ int32_t dst_stride,
+ uint8_t *src_line,
+ int32_t src_stride)
{
- uint8_t *dst_line, *dst;
- uint8_t *src_line, *src;
- int dst_stride, src_stride;
+ uint8_t *dst, *src;
int32_t w;
uint8_t s, d;
- PIXMAN_IMAGE_GET_LINE (src_image, src_x, src_y, uint8_t, src_stride, src_line, 1);
- PIXMAN_IMAGE_GET_LINE (dst_image, dest_x, dest_y, uint8_t, dst_stride, dst_line, 1);
-
while (height--)
{
dst = dst_line;
@@ -101,32 +90,21 @@ arm_composite_add_8000_8000 (pixman_implementation_t * impl,
}
-static void
-arm_composite_over_8888_8888 (pixman_implementation_t * impl,
- pixman_op_t op,
- pixman_image_t * src_image,
- pixman_image_t * mask_image,
- pixman_image_t * dst_image,
- int32_t src_x,
- int32_t src_y,
- int32_t mask_x,
- int32_t mask_y,
- int32_t dest_x,
- int32_t dest_y,
- int32_t width,
- int32_t height)
+void
+pixman_composite_over_8888_8888_asm_armv6 (int32_t width,
+ int32_t height,
+ uint32_t *dst_line,
+ int32_t dst_stride,
+ uint32_t *src_line,
+ int32_t src_stride)
{
- uint32_t *dst_line, *dst;
- uint32_t *src_line, *src;
- int dst_stride, src_stride;
+ uint32_t *dst;
+ uint32_t *src;
int32_t w;
uint32_t component_half = 0x800080;
uint32_t upper_component_mask = 0xff00ff00;
uint32_t alpha_mask = 0xff;
- PIXMAN_IMAGE_GET_LINE (dst_image, dest_x, dest_y, uint32_t, dst_stride, dst_line, 1);
- PIXMAN_IMAGE_GET_LINE (src_image, src_x, src_y, uint32_t, src_stride, src_line, 1);
-
while (height--)
{
dst = dst_line;
@@ -194,33 +172,21 @@ arm_composite_over_8888_8888 (pixman_implementation_t * impl,
}
}
-static void
-arm_composite_over_8888_n_8888 (pixman_implementation_t * impl,
- pixman_op_t op,
- pixman_image_t * src_image,
- pixman_image_t * mask_image,
- pixman_image_t * dst_image,
- int32_t src_x,
- int32_t src_y,
- int32_t mask_x,
- int32_t mask_y,
- int32_t dest_x,
- int32_t dest_y,
- int32_t width,
- int32_t height)
+void
+pixman_composite_over_8888_n_8888_asm_armv6 (int32_t width,
+ int32_t height,
+ uint32_t *dst_line,
+ int32_t dst_stride,
+ uint32_t *src_line,
+ int32_t src_stride,
+ uint32_t mask)
{
- uint32_t *dst_line, *dst;
- uint32_t *src_line, *src;
- uint32_t mask;
- int dst_stride, src_stride;
+ uint32_t *dst;
+ uint32_t *src;
int32_t w;
uint32_t component_half = 0x800080;
uint32_t alpha_mask = 0xff;
- PIXMAN_IMAGE_GET_LINE (dst_image, dest_x, dest_y, uint32_t, dst_stride, dst_line, 1);
- PIXMAN_IMAGE_GET_LINE (src_image, src_x, src_y, uint32_t, src_stride, src_line, 1);
-
- mask = _pixman_image_get_solid (mask_image, PIXMAN_a8r8g8b8);
mask = (mask) >> 24;
while (height--)
@@ -303,33 +269,22 @@ arm_composite_over_8888_n_8888 (pixman_implementation_t * impl,
}
}
-static void
-arm_composite_over_n_8_8888 (pixman_implementation_t * impl,
- pixman_op_t op,
- pixman_image_t * src_image,
- pixman_image_t * mask_image,
- pixman_image_t * dst_image,
- int32_t src_x,
- int32_t src_y,
- int32_t mask_x,
- int32_t mask_y,
- int32_t dest_x,
- int32_t dest_y,
- int32_t width,
- int32_t height)
+void
+pixman_composite_over_n_8_8888_asm_armv6 (int32_t width,
+ int32_t height,
+ uint32_t *dst_line,
+ int32_t dst_stride,
+ uint32_t src,
+ int32_t unused,
+ uint8_t *mask_line,
+ int32_t mask_stride)
{
- uint32_t src, srca;
- uint32_t *dst_line, *dst;
- uint8_t *mask_line, *mask;
- int dst_stride, mask_stride;
+ uint32_t srca;
+ uint32_t *dst;
+ uint8_t *mask;
int32_t w;
- src = _pixman_image_get_solid (src_image, dst_image->bits.format);
-
- /* bail out if fully transparent */
srca = src >> 24;
- if (src == 0)
- return;
uint32_t component_mask = 0xff00ff;
uint32_t component_half = 0x800080;
@@ -337,9 +292,6 @@ arm_composite_over_n_8_8888 (pixman_implementation_t * impl,
uint32_t src_hi = (src >> 8) & component_mask;
uint32_t src_lo = src & component_mask;
- PIXMAN_IMAGE_GET_LINE (dst_image, dest_x, dest_y, uint32_t, dst_stride, dst_line, 1);
- PIXMAN_IMAGE_GET_LINE (mask_image, mask_x, mask_y, uint8_t, mask_stride, mask_line, 1);
-
while (height--)
{
dst = dst_line;
@@ -419,21 +371,34 @@ arm_composite_over_n_8_8888 (pixman_implementation_t * impl,
}
}
+PIXMAN_ARM_BIND_FAST_PATH_SRC_DST (armv6, add_8000_8000,
+ uint8_t, 1, uint8_t, 1)
+PIXMAN_ARM_BIND_FAST_PATH_SRC_DST (armv6, over_8888_8888,
+ uint32_t, 1, uint32_t, 1)
+
+PIXMAN_ARM_BIND_FAST_PATH_SRC_N_DST (armv6, over_8888_n_8888,
+ uint32_t, 1, uint32_t, 1)
+
+PIXMAN_ARM_BIND_FAST_PATH_N_MASK_DST (armv6, over_n_8_8888,
+ uint8_t, 1, uint32_t, 1)
+
static const pixman_fast_path_t arm_simd_fast_paths[] =
{
- PIXMAN_STD_FAST_PATH (OVER, a8r8g8b8, null, a8r8g8b8, arm_composite_over_8888_8888),
- PIXMAN_STD_FAST_PATH (OVER, a8r8g8b8, null, x8r8g8b8, arm_composite_over_8888_8888),
- PIXMAN_STD_FAST_PATH (OVER, a8b8g8r8, null, a8b8g8r8, arm_composite_over_8888_8888),
- PIXMAN_STD_FAST_PATH (OVER, a8b8g8r8, null, x8b8g8r8, arm_composite_over_8888_8888),
- PIXMAN_STD_FAST_PATH (OVER, a8r8g8b8, solid, a8r8g8b8, arm_composite_over_8888_n_8888),
- PIXMAN_STD_FAST_PATH (OVER, a8r8g8b8, solid, x8r8g8b8, arm_composite_over_8888_n_8888),
-
- PIXMAN_STD_FAST_PATH (ADD, a8, null, a8, arm_composite_add_8000_8000),
-
- PIXMAN_STD_FAST_PATH (OVER, solid, a8, a8r8g8b8, arm_composite_over_n_8_8888),
- PIXMAN_STD_FAST_PATH (OVER, solid, a8, x8r8g8b8, arm_composite_over_n_8_8888),
- PIXMAN_STD_FAST_PATH (OVER, solid, a8, a8b8g8r8, arm_composite_over_n_8_8888),
- PIXMAN_STD_FAST_PATH (OVER, solid, a8, x8b8g8r8, arm_composite_over_n_8_8888),
+ PIXMAN_STD_FAST_PATH (OVER, a8r8g8b8, null, a8r8g8b8, armv6_composite_over_8888_8888),
+ PIXMAN_STD_FAST_PATH (OVER, a8r8g8b8, null, x8r8g8b8, armv6_composite_over_8888_8888),
+ PIXMAN_STD_FAST_PATH (OVER, a8b8g8r8, null, a8b8g8r8, armv6_composite_over_8888_8888),
+ PIXMAN_STD_FAST_PATH (OVER, a8b8g8r8, null, x8b8g8r8, armv6_composite_over_8888_8888),
+ PIXMAN_STD_FAST_PATH (OVER, a8r8g8b8, solid, a8r8g8b8, armv6_composite_over_8888_n_8888),
+ PIXMAN_STD_FAST_PATH (OVER, a8r8g8b8, solid, x8r8g8b8, armv6_composite_over_8888_n_8888),
+ PIXMAN_STD_FAST_PATH (OVER, a8b8g8r8, solid, a8b8g8r8, armv6_composite_over_8888_n_8888),
+ PIXMAN_STD_FAST_PATH (OVER, a8b8g8r8, solid, x8b8g8r8, armv6_composite_over_8888_n_8888),
+
+ PIXMAN_STD_FAST_PATH (ADD, a8, null, a8, armv6_composite_add_8000_8000),
+
+ PIXMAN_STD_FAST_PATH (OVER, solid, a8, a8r8g8b8, armv6_composite_over_n_8_8888),
+ PIXMAN_STD_FAST_PATH (OVER, solid, a8, x8r8g8b8, armv6_composite_over_n_8_8888),
+ PIXMAN_STD_FAST_PATH (OVER, solid, a8, a8b8g8r8, armv6_composite_over_n_8_8888),
+ PIXMAN_STD_FAST_PATH (OVER, solid, a8, x8b8g8r8, armv6_composite_over_n_8_8888),
{ PIXMAN_OP_NONE },
};
commit c1e8d4533aea3aa10c49465cf5e9a44d946f70bb
Author: Siarhei Siamashka <siarhei.siamashka@nokia.com>
Date: Mon Mar 22 18:51:54 2010 +0200
ARM: Helper ARM NEON assembly binding macros moved into a separate header
This is needed for future reuse of the same macros for the other
ARM assembly optimizations (armv4t, armv6)
diff --git a/pixman/pixman-arm-common.h b/pixman/pixman-arm-common.h
new file mode 100644
index 0000000..8d432b1
--- /dev/null
+++ b/pixman/pixman-arm-common.h
@@ -0,0 +1,273 @@
+/*
+ * Copyright © 2010 Nokia Corporation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice (including the next
+ * paragraph) shall be included in all copies or substantial portions of the
+ * Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+ * DEALINGS IN THE SOFTWARE.
+ *
+ * Author: Siarhei Siamashka (siarhei.siamashka@nokia.com)
+ */
+
+#ifndef PIXMAN_ARM_COMMON_H
+#define PIXMAN_ARM_COMMON_H
+
+/* Define some macros which can expand into proxy functions between
+ * ARM assembly optimized functions and the rest of pixman fast path API.
+ *
+ * All the low level ARM assembly functions have to use ARM EABI
+ * calling convention and take up to 8 arguments:
+ * width, height, dst, dst_stride, src, src_stride, mask, mask_stride
+ *
+ * The arguments are ordered with the most important coming first (the
+ * first 4 arguments are passed to function in registers, the rest are
+ * on stack). The last arguments are optional, for example if the
+ * function is not using mask, then 'mask' and 'mask_stride' can be
+ * omitted when doing a function call.
+ *
+ * Arguments 'src' and 'mask' contain either a pointer to the top left
+ * pixel of the composited rectangle or a pixel color value depending
+ * on the function type. In the case of just a color value (solid source
+ * or mask), the corresponding stride argument is unused.
+ */
+
+#define PIXMAN_ARM_BIND_FAST_PATH_SRC_DST(cputype, name, \
+ src_type, src_cnt, \
+ dst_type, dst_cnt) \
+void \
+pixman_composite_##name##_asm_##cputype (int32_t w, \
+ int32_t h, \
+ dst_type *dst, \
+ int32_t dst_stride, \
+ src_type *src, \
+ int32_t src_stride); \
+ \
+static void \
+cputype##_composite_##name (pixman_implementation_t *imp, \
+ pixman_op_t op, \
+ pixman_image_t * src_image, \
+ pixman_image_t * mask_image, \
+ pixman_image_t * dst_image, \
+ int32_t src_x, \
+ int32_t src_y, \
+ int32_t mask_x, \
+ int32_t mask_y, \
+ int32_t dest_x, \
+ int32_t dest_y, \
+ int32_t width, \
+ int32_t height) \
+{ \
+ dst_type *dst_line; \
+ src_type *src_line; \
+ int32_t dst_stride, src_stride; \
+ \
+ PIXMAN_IMAGE_GET_LINE (src_image, src_x, src_y, src_type, \
+ src_stride, src_line, src_cnt); \
+ PIXMAN_IMAGE_GET_LINE (dst_image, dest_x, dest_y, dst_type, \
+ dst_stride, dst_line, dst_cnt); \
+ \
+ pixman_composite_##name##_asm_##cputype (width, height, \
+ dst_line, dst_stride, \
+ src_line, src_stride); \
+}
+
+#define PIXMAN_ARM_BIND_FAST_PATH_N_DST(cputype, name, \
+ dst_type, dst_cnt) \
+void \
+pixman_composite_##name##_asm_##cputype (int32_t w, \
+ int32_t h, \
+ dst_type *dst, \
Reply to: