d9d5c05b50
$ compare-android.sh bench --match bitmap_ --repeat 30 master -> ssse3 N=30 p=0.001000 (corrected to 0.000033) sig? speedup bench n -1.16% bitmap_scale_filter_256_64 y -0.72% bitmap_8888_A_scale_bicubic y -0.21% bitmap_index8_A n -0.00% bitmap_565 n -0.00% bitmap_scale_filter_90_80 n 0.03% bitmap_8888_A_source_transparent y 0.06% bitmap_index8 y 0.30% bitmap_8888_A_source_stripes_two n 0.34% bitmap_scale_filter_80_90 y 0.42% bitmap_8888_A y 0.44% bitmap_8888_A_source_opaque n 0.53% bitmap_scale_filter_90_10 y 0.71% bitmap_8888_A_source_stripes_three y 0.91% bitmap_8888_A_scale_rotate_bicubic y 1.04% bitmap_8888_update n 1.19% bitmap_scale_filter_10_90 n 1.39% bitmap_scale_filter_90_90 y 1.77% bitmap_8888_update_volatile y 1.89% bitmap_8888 y 2.37% bitmap_scale_filter_30_90 y 9.57% bitmap_scale_filter_64_256 n 17.86% bitmap_scale_filter_90_30 y 25.40% bitmap_8888_A_scale_rotate_bilerp y 27.19% bitmap_8888_scale_rotate_bilerp y 27.23% bitmap_8888_update_scale_rotate_bilerp y 27.29% bitmap_8888_update_volatile_scale_rotate_bilerp y 55.08% bitmap_8888_A_scale_bilerp y 58.75% bitmap_8888_update_volatile_scale_bilerp y 58.90% bitmap_8888_scale_bilerp y 58.92% bitmap_8888_update_scale_bilerp Overall speedup: 10.52% BUG=skia:1111 R=djsollen@google.com Review URL: https://codereview.chromium.org/21203005 git-svn-id: http://skia.googlecode.com/svn/trunk@10474 2bbb7eff-a529-9590-31e7-b0007b416f81
188 lines
6.3 KiB
Python
188 lines
6.3 KiB
Python
{
|
|
'targets': [
|
|
# Due to an unfortunate intersection of lameness between gcc and gyp,
|
|
# we have to build the *_SSE2.cpp files in a separate target. The
|
|
# gcc lameness is that, in order to compile SSE2 intrinsics code, it
|
|
# must be passed the -msse2 flag. However, with this flag, it may
|
|
# emit SSE2 instructions even for scalar code, such as the CPUID
|
|
# test used to test for the presence of SSE2. So that, and all other
|
|
# code must be compiled *without* -msse2. The gyp lameness is that it
|
|
# does not allow file-specific CFLAGS, so we must create this extra
|
|
# target for those files to be compiled with -msse2.
|
|
#
|
|
# This is actually only a problem on 32-bit Linux (all Intel Macs have
|
|
# SSE2, Linux x86_64 has SSE2 by definition, and MSC will happily emit
|
|
# SSE2 from instrinsics, while generating plain ol' 386 for everything
|
|
# else). However, to keep the .gyp file simple and avoid platform-specific
|
|
# build breakage, we do this on all platforms.
|
|
|
|
# For about the same reason, we need to compile the ARM opts files
|
|
# separately as well.
|
|
{
|
|
'target_name': 'opts',
|
|
'product_name': 'skia_opts',
|
|
'type': 'static_library',
|
|
'standalone_static_library': 1,
|
|
'dependencies': [
|
|
'core.gyp:*',
|
|
],
|
|
'include_dirs': [
|
|
'../src/core',
|
|
'../src/opts',
|
|
],
|
|
'conditions': [
|
|
[ 'skia_arch_type == "x86" and skia_os != "ios"', {
|
|
'conditions': [
|
|
[ 'skia_os in ["linux", "freebsd", "openbsd", "solaris", "nacl", "chromeos", "android"]', {
|
|
'cflags': [
|
|
'-msse2',
|
|
],
|
|
}],
|
|
],
|
|
'include_dirs': [
|
|
'../include/utils',
|
|
],
|
|
'dependencies': [
|
|
'opts_ssse3',
|
|
],
|
|
'sources': [
|
|
'../src/opts/opts_check_SSE2.cpp',
|
|
'../src/opts/SkBitmapProcState_opts_SSE2.cpp',
|
|
'../src/opts/SkBitmapFilter_opts_SSE2.cpp',
|
|
'../src/opts/SkBlitRow_opts_SSE2.cpp',
|
|
'../src/opts/SkBlitRect_opts_SSE2.cpp',
|
|
'../src/opts/SkUtils_opts_SSE2.cpp',
|
|
],
|
|
}],
|
|
[ 'skia_arch_type == "arm" and arm_version >= 7', {
|
|
# The assembly uses the frame pointer register (r7 in Thumb/r11 in
|
|
# ARM), the compiler doesn't like that.
|
|
'cflags!': [
|
|
'-fno-omit-frame-pointer',
|
|
'-mapcs-frame',
|
|
'-mapcs',
|
|
],
|
|
'cflags': [
|
|
'-fomit-frame-pointer',
|
|
'-mno-apcs-frame',
|
|
],
|
|
'variables': {
|
|
'arm_neon_optional%': '<(arm_neon_optional>',
|
|
},
|
|
'sources': [
|
|
'../src/opts/opts_check_arm.cpp',
|
|
'../src/opts/memset.arm.S',
|
|
'../src/opts/SkBitmapProcState_opts_arm.cpp',
|
|
'../src/opts/SkBlitRow_opts_arm.cpp',
|
|
'../src/opts/SkBlitRow_opts_arm.h',
|
|
],
|
|
'conditions': [
|
|
[ 'arm_neon == 1 or arm_neon_optional == 1', {
|
|
'dependencies': [
|
|
'opts_neon',
|
|
]
|
|
}],
|
|
[ 'skia_os == "ios"', {
|
|
'sources!': [
|
|
# these fail to compile under xcode for ios
|
|
'../src/opts/memset.arm.S',
|
|
'../src/opts/SkBitmapProcState_opts_arm.cpp',
|
|
'../src/opts/SkBlitRow_opts_arm.cpp',
|
|
],
|
|
}],
|
|
],
|
|
}],
|
|
[ '(skia_arch_type == "arm" and arm_version < 7) or (skia_os == "ios")', {
|
|
'sources': [
|
|
'../src/opts/SkBitmapProcState_opts_none.cpp',
|
|
'../src/opts/SkBlitRow_opts_none.cpp',
|
|
'../src/opts/SkUtils_opts_none.cpp',
|
|
],
|
|
}],
|
|
],
|
|
},
|
|
# For the same lame reasons as what is done for skia_opts, we have to
|
|
# create another target specifically for SSSE3 code as we would not want
|
|
# to compile the SSE2 code with -mssse3 which would potentially allow
|
|
# gcc to generate SSSE3 code.
|
|
{
|
|
'target_name': 'opts_ssse3',
|
|
'product_name': 'skia_opts_ssse3',
|
|
'type': 'static_library',
|
|
'standalone_static_library': 1,
|
|
'dependencies': [
|
|
'core.gyp:*',
|
|
],
|
|
'include_dirs': [
|
|
'../src/core',
|
|
],
|
|
'conditions': [
|
|
[ 'skia_os in ["linux", "freebsd", "openbsd", "solaris", "nacl", "chromeos", "android"]', {
|
|
'cflags': [
|
|
'-mssse3',
|
|
],
|
|
}],
|
|
# TODO(epoger): the following will enable SSSE3 on Macs, but it will
|
|
# break once we set OTHER_CFLAGS anywhere else (the first setting will
|
|
# be replaced, not added to)
|
|
[ 'skia_os in ["mac"]', {
|
|
'xcode_settings': {
|
|
'OTHER_CFLAGS': ['-mssse3',],
|
|
},
|
|
}],
|
|
[ 'skia_arch_type == "x86"', {
|
|
'sources': [
|
|
'../src/opts/SkBitmapProcState_opts_SSSE3.cpp',
|
|
],
|
|
}],
|
|
],
|
|
},
|
|
# NEON code must be compiled with -mfpu=neon which also affects scalar
|
|
# code. To support dynamic NEON code paths, we need to build all
|
|
# NEON-specific sources in a separate static library. The situation
|
|
# is very similar to the SSSE3 one.
|
|
{
|
|
'target_name': 'opts_neon',
|
|
'product_name': 'skia_opts_neon',
|
|
'type': 'static_library',
|
|
'standalone_static_library': 1,
|
|
'dependencies': [
|
|
'core.gyp:*',
|
|
],
|
|
'include_dirs': [
|
|
'../src/core',
|
|
'../src/opts',
|
|
],
|
|
'cflags!': [
|
|
'-fno-omit-frame-pointer',
|
|
'-mfpu=vfp', # remove them all, just in case.
|
|
'-mfpu=vfpv3',
|
|
'-mfpu=vfpv3-d16',
|
|
],
|
|
'cflags': [
|
|
'-mfpu=neon',
|
|
'-fomit-frame-pointer',
|
|
],
|
|
'ldflags': [
|
|
'-march=armv7-a',
|
|
'-Wl,--fix-cortex-a8',
|
|
],
|
|
'sources': [
|
|
'../src/opts/memset16_neon.S',
|
|
'../src/opts/memset32_neon.S',
|
|
'../src/opts/SkBitmapProcState_arm_neon.cpp',
|
|
'../src/opts/SkBitmapProcState_matrixProcs_neon.cpp',
|
|
'../src/opts/SkBitmapProcState_matrix_clamp_neon.h',
|
|
'../src/opts/SkBitmapProcState_matrix_repeat_neon.h',
|
|
'../src/opts/SkBlitRow_opts_arm_neon.cpp',
|
|
],
|
|
},
|
|
],
|
|
}
|
|
|
|
# Local Variables:
|
|
# tab-width:2
|
|
# indent-tabs-mode:nil
|
|
# End:
|
|
# vim: set expandtab tabstop=2 shiftwidth=2:
|