diff options
author | Sergey Sharybin <sergey.vfx@gmail.com> | 2016-10-25 15:18:32 +0300 |
---|---|---|
committer | Sergey Sharybin <sergey.vfx@gmail.com> | 2016-10-25 15:18:32 +0300 |
commit | 81c9e0d2958a1274f8cb76386a3bafc08a181eed (patch) | |
tree | f0811fc51828b8ebd6ad9a1a8f172eac686140a4 /intern/cycles | |
parent | af411d918e68b487155309f5c1e29bb50924b69a (diff) |
Cycles: Avoid branching in SSE version of intersection pre-calculation
Similar to the previous commit, avoid negative effect of bad branch prediction.
Gives measurable performance up to ~2% in tests here.
Once again, thanks to Maxym Dmytrychenko!
Diffstat (limited to 'intern/cycles')
-rw-r--r-- | intern/cycles/kernel/geom/geom_triangle_intersect.h | 16 |
1 files changed, 14 insertions, 2 deletions
diff --git a/intern/cycles/kernel/geom/geom_triangle_intersect.h b/intern/cycles/kernel/geom/geom_triangle_intersect.h index 8d17e1240a5..5d76fc3dc58 100644 --- a/intern/cycles/kernel/geom/geom_triangle_intersect.h +++ b/intern/cycles/kernel/geom/geom_triangle_intersect.h @@ -59,21 +59,33 @@ void triangle_intersect_precalc(float3 dir, IsectPrecalc *isect_precalc) { /* Calculate dimension where the ray direction is maximal. */ +#ifndef __KERNEL_SSE__ int kz = util_max_axis(make_float3(fabsf(dir.x), fabsf(dir.y), fabsf(dir.z))); int kx = kz + 1; if(kx == 3) kx = 0; int ky = kx + 1; if(ky == 3) ky = 0; +#else + int kx, ky, kz; + /* Avoiding mispredicted branch on direction. */ + kz = util_max_axis(fabs(dir)); + static const char inc_xaxis[] = {1, 2, 0, 55}; + static const char inc_yaxis[] = {2, 0, 1, 55}; + kx = inc_xaxis[kz]; + ky = inc_yaxis[kz]; +#endif + + float dir_kz = IDX(dir, kz); /* Swap kx and ky dimensions to preserve winding direction of triangles. */ - if(IDX(dir, kz) < 0.0f) { + if(dir_kz < 0.0f) { int tmp = kx; kx = ky; ky = tmp; } /* Calculate the shear constants. */ - float inv_dir_z = 1.0f / IDX(dir, kz); + float inv_dir_z = 1.0f / dir_kz; isect_precalc->Sx = IDX(dir, kx) * inv_dir_z; isect_precalc->Sy = IDX(dir, ky) * inv_dir_z; isect_precalc->Sz = inv_dir_z; |