AlexIndustrial/mesa
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

glsl: rewrite sqrt(x) intrinsic to handle x=0

Browse Source 
Since sqrt() is basically implemented in terms of RSQ/RCP we'll do a
divide by zero if x=0 and wind up with unpredictable results.
Now use CMP instruction to test for x<=0 and return zero in that case.
This commit is contained in:
Brian Paul
2009-09-29 18:57:13 -06:00
parent 3c794e45b0
commit 65765c9f2c
1 changed files with 33 additions and 25 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/mesa/shader/slang/library/slang_common_builtin.gc
+33 -25
View File
@@ -602,42 +602,50 @@ vec4 exp2(const vec4 a)
float sqrt(const float x)
{
const float nx = -x;
float r;
__asm float_rsq r, x;
__asm float_rcp __retVal, r;
__asm float_rcp r, r;
__asm vec4_cmp __retVal, nx, r, 0.0;
}
vec2 sqrt(const vec2 v)
vec2 sqrt(const vec2 x)
{
float r;
__asm float_rsq r, v.x;
__asm float_rcp __retVal.x, r;
__asm float_rsq r, v.y;
__asm float_rcp __retVal.y, r;
const vec2 nx = -x, zero = vec2(0.0);
vec2 r;
__asm float_rsq r.x, x.x;
__asm float_rsq r.y, x.y;
__asm float_rcp r.x, r.x;
__asm float_rcp r.y, r.y;
__asm vec4_cmp __retVal, nx, r, zero;
}
vec3 sqrt(const vec3 v)
vec3 sqrt(const vec3 x)
{
float r;
__asm float_rsq r, v.x;
__asm float_rcp __retVal.x, r;
__asm float_rsq r, v.y;
__asm float_rcp __retVal.y, r;
__asm float_rsq r, v.z;
__asm float_rcp __retVal.z, r;
const vec3 nx = -x, zero = vec3(0.0);
vec3 r;
__asm float_rsq r.x, x.x;
__asm float_rsq r.y, x.y;
__asm float_rsq r.z, x.z;
__asm float_rcp r.x, r.x;
__asm float_rcp r.y, r.y;
__asm float_rcp r.z, r.z;
__asm vec4_cmp __retVal, nx, r, zero;
}
vec4 sqrt(const vec4 v)
vec4 sqrt(const vec4 x)
{
float r;
__asm float_rsq r, v.x;
__asm float_rcp __retVal.x, r;
__asm float_rsq r, v.y;
__asm float_rcp __retVal.y, r;
__asm float_rsq r, v.z;
__asm float_rcp __retVal.z, r;
__asm float_rsq r, v.w;
__asm float_rcp __retVal.w, r;
const vec4 nx = -x, zero = vec4(0.0);
vec4 r;
__asm float_rsq r.x, x.x;
__asm float_rsq r.y, x.y;
__asm float_rsq r.z, x.z;
__asm float_rsq r.w, x.w;
__asm float_rcp r.x, r.x;
__asm float_rcp r.y, r.y;
__asm float_rcp r.z, r.z;
__asm float_rcp r.w, r.w;
__asm vec4_cmp __retVal, nx, r, zero;
}