File specific optimization as used for src/mesa/main/streaming-load-memcpy.c
currently will cause problems with LTO in the future
(see: https://bugs.freedesktop.org/show_bug.cgi?id=83669). Replace it with
in-file target specification.
This only works for gcc for now. The intel compiler has
__attribute__((cpu_specific(cpuid))) with cpuid core_2_duo_sse4_1, but I'm
not sure if mesa compiles with it and how it behaves on different platforms.
Signed-off-by: Marc Dietrich <marvi...@gmx.de>
---
src/mesa/Makefile.am | 1 -
src/mesa/main/streaming-load-memcpy.c | 4 ++--
2 files changed, 2 insertions(+), 3 deletions(-)
diff --git a/src/mesa/Makefile.am b/src/mesa/Makefile.am
index e71bccb..bbdb36f 100644
--- a/src/mesa/Makefile.am
+++ b/src/mesa/Makefile.am
@@ -152,7 +152,6 @@ libmesagallium_la_LIBADD = \
libmesa_sse41_la_SOURCES = \
main/streaming-load-memcpy.c
-libmesa_sse41_la_CFLAGS = $(AM_CFLAGS) -msse4.1
pkgconfigdir = $(libdir)/pkgconfig
pkgconfig_DATA = gl.pc
diff --git a/src/mesa/main/streaming-load-memcpy.c
b/src/mesa/main/streaming-load-memcpy.c
index 8427149..94b0e0a 100644
--- a/src/mesa/main/streaming-load-memcpy.c
+++ b/src/mesa/main/streaming-load-memcpy.c
@@ -26,7 +26,7 @@
*
*/
-#ifdef __SSE4_1__
+#ifdef USE_SSE41
#include "main/macros.h"
#include "main/streaming-load-memcpy.h"
#include <smmintrin.h>
@@ -34,7 +34,7 @@
/* Copies memory from src to dst, using SSE 4.1's MOVNTDQA to get streaming
* read performance from uncached memory.
*/
-void
+void __attribute__ ((target("sse4.1")))
_mesa_streaming_load_memcpy(void *restrict dst, void *restrict src, size_t len)
{
char *restrict d = dst;
--
2.1.0
_______________________________________________
mesa-dev mailing list
mesa-dev@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/mesa-dev
