jra101
Joined 17 years ago
Karma
420
Submissions
97
Member since
Aug 5
Joined 17 years ago
[1] https://registry.khronos.org/OpenGL/extensions/NV/NV_fill_re...
Instead of computing 8 independent values, compute one with 8x more iterations:
for (int i = 0; i < count * 8; i++) {
v0 += acc * v0;
}
That plus inlining the iteration count so the compiler can unroll the loop might help get closer to SOL.Switch is averaging 20M units/year and PS4 is averaging 13M units/year.