Closed GoogleCodeExporter closed 9 years ago
Initial results show almost 40% increase in performance of the innerloop for
the
branchless SIMD implementation.
For some of the benchmarks, this results in an overall performance improvement
of
about 5 to 10%.
Original comment by erwin.coumans
on 29 Nov 2008 at 11:03
SSE/SIMD innerloop has been added and released in Bullet 2.73 SP1:
http://code.google.com/p/bullet/source/detail?r=1542
Original comment by erwin.coumans
on 3 Dec 2008 at 10:50
Original comment by erwin.coumans
on 5 Dec 2008 at 11:08
Original issue reported on code.google.com by
erwin.coumans
on 29 Nov 2008 at 11:01