On Fri, Oct 24, 2014 at 5:47 AM, Timothy Arceri <t_arc...@yahoo.com.au> wrote: > Makes use of SSE to speed up compute of min and max elements > > Callgrind cpu usage results from pts benchmarks: > > Openarena 0.8.8: 3.67% -> 1.03% > UrbanTerror: 2.36% -> 0.81% > > Signed-off-by: Timothy Arceri <t_arc...@yahoo.com.au> > --- > src/mesa/Android.libmesa_dricore.mk | 3 +- > src/mesa/Makefile.am | 3 +- > src/mesa/Makefile.sources | 1 + > src/mesa/main/sse_minmax.c | 81 > +++++++++++++++++++++++++++++++++++++ > src/mesa/main/sse_minmax.h | 30 ++++++++++++++ > src/mesa/vbo/vbo_exec_array.c | 13 ++++-- > 6 files changed, 126 insertions(+), 5 deletions(-) > create mode 100644 src/mesa/main/sse_minmax.c > create mode 100644 src/mesa/main/sse_minmax.h > > This version includes all the suggestions from Brian and Matt, thanks for > the review guys. > > I haven't been able to do Matt's suggestion and compare this to what OpenMP > would generate as I only have one machine that supports SSE4.1 with Fedora 20 > and > I dont want to have to upgrade to Fedora 21 alpha (gcc 4.9) just to test this > (although I did consider it). If people are happy with this code I will > revisit > OpenMP for Mesa 10.5 and will look at using OpenMP for the short and byte > support too. > > diff --git a/src/mesa/Android.libmesa_dricore.mk > b/src/mesa/Android.libmesa_dricore.mk > index 1e6d948..52d626f 100644 > --- a/src/mesa/Android.libmesa_dricore.mk > +++ b/src/mesa/Android.libmesa_dricore.mk > @@ -51,7 +51,8 @@ endif # MESA_ENABLE_ASM > > ifeq ($(ARCH_X86_HAVE_SSE4_1),true) > LOCAL_SRC_FILES += \ > - $(SRCDIR)main/streaming-load-memcpy.c > + $(SRCDIR)main/streaming-load-memcpy.c \ > + $(SRCDIR)main/sse_minmax.c > LOCAL_CFLAGS := -msse4.1 > endif > > diff --git a/src/mesa/Makefile.am b/src/mesa/Makefile.am > index e71bccb..932db4f 100644 > --- a/src/mesa/Makefile.am > +++ b/src/mesa/Makefile.am > @@ -151,7 +151,8 @@ libmesagallium_la_LIBADD = \ > $(ARCH_LIBS) > > libmesa_sse41_la_SOURCES = \ > - main/streaming-load-memcpy.c > + main/streaming-load-memcpy.c \ > + main/sse_minmax.c > libmesa_sse41_la_CFLAGS = $(AM_CFLAGS) -msse4.1 > > pkgconfigdir = $(libdir)/pkgconfig > diff --git a/src/mesa/Makefile.sources b/src/mesa/Makefile.sources > index 4755018..dd10574 100644 > --- a/src/mesa/Makefile.sources > +++ b/src/mesa/Makefile.sources > @@ -93,6 +93,7 @@ MAIN_FILES = \ > $(SRCDIR)main/shaderobj.c \ > $(SRCDIR)main/shader_query.cpp \ > $(SRCDIR)main/shared.c \ > + $(SRCDIR)main/sse_minmax.c \
We can't add this here. You've already added it to libmesa_sse41.la above. _______________________________________________ mesa-dev mailing list mesa-dev@lists.freedesktop.org http://lists.freedesktop.org/mailman/listinfo/mesa-dev
