diff options
| author | Brian Paul <brianp@vmware.com> | 2016-08-17 10:41:30 -0600 |
|---|---|---|
| committer | Brian Paul <brianp@vmware.com> | 2016-08-17 12:53:20 -0600 |
| commit | 5de29aeef00f6adf4b9ef278415d8f753283ef03 (patch) | |
| tree | 779b850f6ff438a00573ffd9c62ee6f8ec546d3f /src/util | |
| parent | 18e6e0796a6b0d714e58ca95d70cff2bbb2027e1 (diff) | |
| download | external_mesa3d-5de29aeef00f6adf4b9ef278415d8f753283ef03.zip external_mesa3d-5de29aeef00f6adf4b9ef278415d8f753283ef03.tar.gz external_mesa3d-5de29aeef00f6adf4b9ef278415d8f753283ef03.tar.bz2 | |
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>
Diffstat (limited to 'src/util')
| -rw-r--r-- | src/util/rounding.h | 7 |
1 files changed, 4 insertions, 3 deletions
diff --git a/src/util/rounding.h b/src/util/rounding.h index afb38fb..dfc691e 100644 --- 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 |