util: try to use SSE instructions with MSVC and 32-bit gcc

The lrint() and lrintf() functions are pretty slow and make some
texture transfers very inefficient.  This patch makes a better effort
at using those intrisics for 32-bit gcc and MSVC.

Note, this patch doesn't address the use of SSE4.1 with MSVC.

v2: get rid of the ROUND_WITH_SSE symbol, per Matt.

Reviewed-by: José Fonseca <jfonseca@vmware.com>
Reviewed-by: Matt Turner <mattst88@gmail.com>

diff --git a/src/util/rounding.h b/src/util/rounding.h
index afb38fbdb56b31188b50529a8f8006e12188329c..dfc691eaf1369f21c0375059a5da0ba8e299afc2 100644 (file)
--- a/src/util/rounding.h
+++ b/src/util/rounding.h
@@ -29,7 +29,8 @@
 #include <limits.h>
 #include <stdint.h>
 
-#ifdef __x86_64__
+#if defined(__SSE__) || defined(_MSC_VER)
+/* MSVC always has SSE nowadays */
 #include <xmmintrin.h>
 #include <emmintrin.h>
 #endif
@@ -95,7 +96,7 @@ _mesa_roundeven(double x)
 static inline long
 _mesa_lroundevenf(float x)
 {
-#ifdef __x86_64__
+#if defined(__SSE__) || defined(_MSC_VER)
 #if LONG_MAX == INT64_MAX
    return _mm_cvtss_si64(_mm_load_ss(&x));
 #elif LONG_MAX == INT32_MAX
@@ -115,7 +116,7 @@ _mesa_lroundevenf(float x)
 static inline long
 _mesa_lroundeven(double x)
 {
-#ifdef __x86_64__
+#if defined(__SSE__) || defined(_MSC_VER)
 #if LONG_MAX == INT64_MAX
    return _mm_cvtsd_si64(_mm_load_sd(&x));
 #elif LONG_MAX == INT32_MAX