ShuriZma
/
project64
mirror of https://github.com/project64/project64.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Use generic _mm_loadu_ps instead of GCC specific __builtin_ia32_loadups 

be0a027273
This commit is contained in:
zilmar 2015-10-12 07:08:12 +11:00
parent 32c64b3d54
commit 3d002e831f
1 changed files with 5 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
Source/Glide64/3dmath.cpp
View File

@ -241,14 +241,14 @@ void MulMatricesSSE(float m1[4][4],float m2[4][4],float r[4][4])
#if defined(__GNUC__) && !defined(NO_ASM) && !defined(NOSSE)
/* [row][col]*/
typedef float v4sf __attribute__ ((vector_size (16)));
v4sf row0 = __builtin_ia32_loadups(m2[0]);
v4sf row1 = __builtin_ia32_loadups(m2[1]);
v4sf row2 = __builtin_ia32_loadups(m2[2]);
v4sf row3 = __builtin_ia32_loadups(m2[3]);
v4sf row0 = _mm_loadu_ps(m2[0]);
v4sf row1 = _mm_loadu_ps(m2[1]);
v4sf row2 = _mm_loadu_ps(m2[2]);
v4sf row3 = _mm_loadu_ps(m2[3]);
for (int i = 0; i < 4; ++i)
{
v4sf leftrow = __builtin_ia32_loadups(m1[i]);
v4sf leftrow = _mm_loadu_ps(m1[i]);
// Fill tmp with four copies of leftrow[0]
v4sf tmp = leftrow;