Magic-Mirror/gecko-dev
1
0
Fork 0
mirror of https://github.com/mozilla/gecko-dev.git synced 2024-11-01 06:35:42 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity
90af140600
gecko-dev/gfx/qcms/Makefile.in

71 lines
1.5 KiB
Makefile
Raw Normal View History

Bug 481926 - Rewrite color management component sr=vlad, r=ted, r=joedrew (\o/) Replaces lcms with qcms
2009-04-07 16:02:11 +00:00
DEPTH = ../..
topsrcdir = @top_srcdir@
srcdir = @srcdir@
VPATH = @srcdir@
include $(DEPTH)/config/autoconf.mk
MODULE = qcms
LIBRARY_NAME = mozqcms
LIBXUL_LIBRARY = 1
GRE_MODULE = 1
DIST_INSTALL = 1
EXPORTS = qcms.h qcmstypes.h
CSRCS = iccread.c transform.c
Bug 512865. qcms: Improve SSE2 performance, add SSE support. r=jrmuizel This patch greatly improves the performance of QCMS transformations on x86 & x86_64 systems. Some notes: 0. On 32-bit x86 systems it does runtime selection between non-SIMD, SSE, and SSE2 code paths. 1. On x86_64 systems the SSE2 code path is always taken. The non-SIMD and SSE code paths are left intact, but contemporary versions of the GCC and MSVC compilers will see that they cannot be reached and optimize them away. 2. The execution of the SSE2 code path is reduced by 67%, relative to the original Intel/Microsoft formatted ASM code. The relative performance is seen on a Pentium4 (Northwood) 2.4GHz CPU with DDR1 RAM. 3. The SSE code path provides a 80% reduction in execution time, relative to the non-SIMD code path. The relative performance is seen on a Pentium3 (Coppermine) 1.26GHz CPU with SDRAM. 4. The code has been split out into separate files so that it can be built with different cflags (-msse, and -msse2) when using gcc. 5. Try to land again, this time with __attribute__((__force_align_arg_pointer__)) to avoid crashes on linux.
2009-10-01 18:19:41 +00:00
ifeq (86,$(findstring 86,$(OS_TEST)))
Bug 569475 - Fix qcms linking failure on mingw-w64. r=jmuizelaar --HG-- extra : rebase_source : 07a082564d002faeaedc4fb57911ec9d64b605fd
2010-06-07 08:16:22 +00:00
CSRCS += transform-sse2.c
ifdef _MSC_VER
ifneq ($(OS_ARCH)_$(OS_TEST),WINNT_x86_64)
CSRCS += transform-sse1.c
endif
Bug 536725 - Disable SSE1 code on Windows x64 r=jmuizelaar
2010-02-01 08:43:21 +00:00
else
Bug 569475 - Fix qcms linking failure on mingw-w64. r=jmuizelaar --HG-- extra : rebase_source : 07a082564d002faeaedc4fb57911ec9d64b605fd
2010-06-07 08:16:22 +00:00
CSRCS += transform-sse1.c
Bug 512865. qcms: Improve SSE2 performance, add SSE support. r=jrmuizel This patch greatly improves the performance of QCMS transformations on x86 & x86_64 systems. Some notes: 0. On 32-bit x86 systems it does runtime selection between non-SIMD, SSE, and SSE2 code paths. 1. On x86_64 systems the SSE2 code path is always taken. The non-SIMD and SSE code paths are left intact, but contemporary versions of the GCC and MSVC compilers will see that they cannot be reached and optimize them away. 2. The execution of the SSE2 code path is reduced by 67%, relative to the original Intel/Microsoft formatted ASM code. The relative performance is seen on a Pentium4 (Northwood) 2.4GHz CPU with DDR1 RAM. 3. The SSE code path provides a 80% reduction in execution time, relative to the non-SIMD code path. The relative performance is seen on a Pentium3 (Coppermine) 1.26GHz CPU with SDRAM. 4. The code has been split out into separate files so that it can be built with different cflags (-msse, and -msse2) when using gcc. 5. Try to land again, this time with __attribute__((__force_align_arg_pointer__)) to avoid crashes on linux.
2009-10-01 18:19:41 +00:00
ifdef GNU_CC
SSE1_FLAGS=-msse
SSE2_FLAGS=-msse2
Bug 522440 QCMS: Make sse/sse2 code built with Sun Studio 12 on Solaris r=jmuizelaar, ted.mielczarek
2009-11-20 06:15:39 +00:00
else
ifeq ($(SOLARIS_SUNPRO_CC),1)
Bug 537070 qcms failed to build with -m64 on Solaris x86_64 r=jrmuizel
2010-01-06 07:02:04 +00:00
ifneq (64,$(findstring 64,$(OS_TEST)))
Bug 522440 QCMS: Make sse/sse2 code built with Sun Studio 12 on Solaris r=jmuizelaar, ted.mielczarek
2009-11-20 06:15:39 +00:00
SSE1_FLAGS=-xarch=sse
SSE2_FLAGS=-xarch=sse2
Bug 537070 qcms failed to build with -m64 on Solaris x86_64 r=jrmuizel
2010-01-06 07:02:04 +00:00
else
# Sun Studio doesn't work correctly for x86 intristics
# with -m64 and without optimization.
SSE1_FLAGS= -xO4
SSE2_FLAGS= -xO4
endif
Bug 512865. qcms: Improve SSE2 performance, add SSE support. r=jrmuizel This patch greatly improves the performance of QCMS transformations on x86 & x86_64 systems. Some notes: 0. On 32-bit x86 systems it does runtime selection between non-SIMD, SSE, and SSE2 code paths. 1. On x86_64 systems the SSE2 code path is always taken. The non-SIMD and SSE code paths are left intact, but contemporary versions of the GCC and MSVC compilers will see that they cannot be reached and optimize them away. 2. The execution of the SSE2 code path is reduced by 67%, relative to the original Intel/Microsoft formatted ASM code. The relative performance is seen on a Pentium4 (Northwood) 2.4GHz CPU with DDR1 RAM. 3. The SSE code path provides a 80% reduction in execution time, relative to the non-SIMD code path. The relative performance is seen on a Pentium3 (Coppermine) 1.26GHz CPU with SDRAM. 4. The code has been split out into separate files so that it can be built with different cflags (-msse, and -msse2) when using gcc. 5. Try to land again, this time with __attribute__((__force_align_arg_pointer__)) to avoid crashes on linux.
2009-10-01 18:19:41 +00:00
else
SSE1_FLAGS=
SSE2_FLAGS=
endif
endif
Bug 522440 QCMS: Make sse/sse2 code built with Sun Studio 12 on Solaris r=jmuizelaar, ted.mielczarek
2009-11-20 06:15:39 +00:00
endif
Bug 536725 - Disable SSE1 code on Windows x64 r=jmuizelaar
2010-02-01 08:43:21 +00:00
endif
Bug 512865. qcms: Improve SSE2 performance, add SSE support. r=jrmuizel This patch greatly improves the performance of QCMS transformations on x86 & x86_64 systems. Some notes: 0. On 32-bit x86 systems it does runtime selection between non-SIMD, SSE, and SSE2 code paths. 1. On x86_64 systems the SSE2 code path is always taken. The non-SIMD and SSE code paths are left intact, but contemporary versions of the GCC and MSVC compilers will see that they cannot be reached and optimize them away. 2. The execution of the SSE2 code path is reduced by 67%, relative to the original Intel/Microsoft formatted ASM code. The relative performance is seen on a Pentium4 (Northwood) 2.4GHz CPU with DDR1 RAM. 3. The SSE code path provides a 80% reduction in execution time, relative to the non-SIMD code path. The relative performance is seen on a Pentium3 (Coppermine) 1.26GHz CPU with SDRAM. 4. The code has been split out into separate files so that it can be built with different cflags (-msse, and -msse2) when using gcc. 5. Try to land again, this time with __attribute__((__force_align_arg_pointer__)) to avoid crashes on linux.
2009-10-01 18:19:41 +00:00
Bug 481926 - Rewrite color management component sr=vlad, r=ted, r=joedrew (\o/) Replaces lcms with qcms
2009-04-07 16:02:11 +00:00
FORCE_STATIC_LIB = 1
# This library is used by other shared libs
FORCE_USE_PIC = 1
include $(topsrcdir)/config/rules.mk
CFLAGS += -DMOZ_QCMS
Bug 512865. qcms: Improve SSE2 performance, add SSE support. r=jrmuizel This patch greatly improves the performance of QCMS transformations on x86 & x86_64 systems. Some notes: 0. On 32-bit x86 systems it does runtime selection between non-SIMD, SSE, and SSE2 code paths. 1. On x86_64 systems the SSE2 code path is always taken. The non-SIMD and SSE code paths are left intact, but contemporary versions of the GCC and MSVC compilers will see that they cannot be reached and optimize them away. 2. The execution of the SSE2 code path is reduced by 67%, relative to the original Intel/Microsoft formatted ASM code. The relative performance is seen on a Pentium4 (Northwood) 2.4GHz CPU with DDR1 RAM. 3. The SSE code path provides a 80% reduction in execution time, relative to the non-SIMD code path. The relative performance is seen on a Pentium3 (Coppermine) 1.26GHz CPU with SDRAM. 4. The code has been split out into separate files so that it can be built with different cflags (-msse, and -msse2) when using gcc. 5. Try to land again, this time with __attribute__((__force_align_arg_pointer__)) to avoid crashes on linux.
2009-10-01 18:19:41 +00:00
Bug 503279: disable spammy 'missing initializer' warning in imported code within gfx. r=jrmuizel
2010-07-13 18:50:18 +00:00
# Disable spammy "missing initializer" GCC warning
ifdef GNU_CC
CFLAGS += -Wno-missing-field-initializers
endif # GNU_CC
Bug 512865. qcms: Improve SSE2 performance, add SSE support. r=jrmuizel This patch greatly improves the performance of QCMS transformations on x86 & x86_64 systems. Some notes: 0. On 32-bit x86 systems it does runtime selection between non-SIMD, SSE, and SSE2 code paths. 1. On x86_64 systems the SSE2 code path is always taken. The non-SIMD and SSE code paths are left intact, but contemporary versions of the GCC and MSVC compilers will see that they cannot be reached and optimize them away. 2. The execution of the SSE2 code path is reduced by 67%, relative to the original Intel/Microsoft formatted ASM code. The relative performance is seen on a Pentium4 (Northwood) 2.4GHz CPU with DDR1 RAM. 3. The SSE code path provides a 80% reduction in execution time, relative to the non-SIMD code path. The relative performance is seen on a Pentium3 (Coppermine) 1.26GHz CPU with SDRAM. 4. The code has been split out into separate files so that it can be built with different cflags (-msse, and -msse2) when using gcc. 5. Try to land again, this time with __attribute__((__force_align_arg_pointer__)) to avoid crashes on linux.
2009-10-01 18:19:41 +00:00
# special rules for transform-sse*.c to get the right cflags. (taken from pixman/src/Makefile.in)
Bug 467051 - Introduce GLOBAL_DEPS to build system (gfx/cairo) r=vlad, feedback+=ted --HG-- extra : rebase_source : 3dee9c67387cb9b72dd81da6d52ad996afa2bfae
2010-05-31 02:49:32 +00:00
transform-sse1.$(OBJ_SUFFIX): transform-sse1.c $(GLOBAL_DEPS)
Bug 512865. qcms: Improve SSE2 performance, add SSE support. r=jrmuizel This patch greatly improves the performance of QCMS transformations on x86 & x86_64 systems. Some notes: 0. On 32-bit x86 systems it does runtime selection between non-SIMD, SSE, and SSE2 code paths. 1. On x86_64 systems the SSE2 code path is always taken. The non-SIMD and SSE code paths are left intact, but contemporary versions of the GCC and MSVC compilers will see that they cannot be reached and optimize them away. 2. The execution of the SSE2 code path is reduced by 67%, relative to the original Intel/Microsoft formatted ASM code. The relative performance is seen on a Pentium4 (Northwood) 2.4GHz CPU with DDR1 RAM. 3. The SSE code path provides a 80% reduction in execution time, relative to the non-SIMD code path. The relative performance is seen on a Pentium3 (Coppermine) 1.26GHz CPU with SDRAM. 4. The code has been split out into separate files so that it can be built with different cflags (-msse, and -msse2) when using gcc. 5. Try to land again, this time with __attribute__((__force_align_arg_pointer__)) to avoid crashes on linux.
2009-10-01 18:19:41 +00:00
$(REPORT_BUILD)
@$(MAKE_DEPS_AUTO_CC)
$(ELOG) $(CC) $(OUTOPTION)$@ -c $(COMPILE_CFLAGS) $(SSE1_FLAGS) $(_VPATH_SRCS)
Bug 467051 - Introduce GLOBAL_DEPS to build system (gfx/cairo) r=vlad, feedback+=ted --HG-- extra : rebase_source : 3dee9c67387cb9b72dd81da6d52ad996afa2bfae
2010-05-31 02:49:32 +00:00
transform-sse2.$(OBJ_SUFFIX): transform-sse2.c $(GLOBAL_DEPS)
Bug 512865. qcms: Improve SSE2 performance, add SSE support. r=jrmuizel This patch greatly improves the performance of QCMS transformations on x86 & x86_64 systems. Some notes: 0. On 32-bit x86 systems it does runtime selection between non-SIMD, SSE, and SSE2 code paths. 1. On x86_64 systems the SSE2 code path is always taken. The non-SIMD and SSE code paths are left intact, but contemporary versions of the GCC and MSVC compilers will see that they cannot be reached and optimize them away. 2. The execution of the SSE2 code path is reduced by 67%, relative to the original Intel/Microsoft formatted ASM code. The relative performance is seen on a Pentium4 (Northwood) 2.4GHz CPU with DDR1 RAM. 3. The SSE code path provides a 80% reduction in execution time, relative to the non-SIMD code path. The relative performance is seen on a Pentium3 (Coppermine) 1.26GHz CPU with SDRAM. 4. The code has been split out into separate files so that it can be built with different cflags (-msse, and -msse2) when using gcc. 5. Try to land again, this time with __attribute__((__force_align_arg_pointer__)) to avoid crashes on linux.
2009-10-01 18:19:41 +00:00
$(REPORT_BUILD)
@$(MAKE_DEPS_AUTO_CC)
$(ELOG) $(CC) $(OUTOPTION)$@ -c $(COMPILE_CFLAGS) $(SSE2_FLAGS) $(_VPATH_SRCS)
Reference in New Issue Copy Permalink