chenlin/Mujoco_WASM
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity
584 Commits 2 Branches 1 Tag
222ee00a66b1fc05804792b1e2da378438d0d69b
Commit Graph

13 Commits

Author SHA1 Message Date
Yuval Tassa 7e7cb177a4 Cosmetic changes. 
PiperOrigin-RevId: 511008317
Change-Id: Id8d7cd4f4e22e0658857d16b47d51053f1477bb9
 2023-02-20 09:23:32 -08:00
Kyle Bayes c741dfce7d Implement a more performant mju_transposeSparse that doesn't require dense memory allocation. 
PiperOrigin-RevId: 505044194
Change-Id: Ibe0e39e3ad711b2b5bdad45180ca4f83b5c8fc82
 2023-01-27 00:20:01 -08:00
Alessio Quaglino 2d304d65e5 Use memcmp for mju_compare if no AVX. 15% faster on Humanoid. 
PiperOrigin-RevId: 493324356
Change-Id: I5f71dc1a8ae40c18864ea80f00a5f86ff952f72c
 2022-12-06 09:14:33 -08:00
Alessio Quaglino c17375fa32 Stop profiling mju_halton in testspeed and bechmarks. 
PiperOrigin-RevId: 490239351
Change-Id: Id73c101672e5b974f16b6b4da3aae757a657de15
 2022-11-22 07:41:02 -08:00
Alessio Quaglino 7b0fbc63f8 Speed improvement with no AVX. 40% on Linux Intel Xeon and 60% on ARM Mac. 
PiperOrigin-RevId: 488360660
Change-Id: I423269cd362fdcc2434393b691638ac6ed778ef2
 2022-11-14 07:31:32 -08:00
Alessio Quaglino ae29a22d55 Add flag benchmark. 
PiperOrigin-RevId: 487788256
Change-Id: Iefab760cafc0123368e5bcd4ec4a579b170f1aba
 2022-11-11 04:26:32 -08:00
Alessio Quaglino 9fc9823a8c Speed improvements in mj_solveLD (14% on Intel Skylake Xeon 36 cores). 
PiperOrigin-RevId: 486960670
Change-Id: I8fce96427158ec36069dea893500059e93bd40db
 2022-11-08 08:38:45 -08:00
Saran Tunyasuvunakool b1a79aa01b Replace internal-only imports and comments that aren't valid externally. 
PiperOrigin-RevId: 476492651
Change-Id: I310a21a73a65da3a5939f5cb8a1c8a67c8595863
 2022-09-23 16:58:58 -07:00
Kevin Zakka f8b9e3e00f Add CMake entry for engine_util_spatial_benchmark_test. 
PiperOrigin-RevId: 454424726
Change-Id: If79e9452c18220ddf0107157d78a2f08ce099a04
 2022-06-12 01:01:46 -07:00
Nimrod Gileadi 5ac797965c Use batch mode in step_benchmark_test. 
d8880e9a12 introduced measuring performance of a fixed batch of 50 steps, with a fixed starting state.
The Google Benchmark library has a more direct API for doing this, which ends up with nicer looking reported numbers.

PiperOrigin-RevId: 454133316
Change-Id: I368b985dc871084b9ed8c41a87016408719b53ad
 2022-06-10 04:22:18 -07:00
Yuval Tassa d8880e9a12 Modify step_benchmark_test.cc to benchmark a fixed, 50-step sequence. 
- Also remove multithreaded benchmark results.

PiperOrigin-RevId: 454102292
Change-Id: I5bd5fb1642adc547e695d2d3553bcaf0cf5c7bed
 2022-06-10 00:52:43 -07:00
Kevin Zakka 78c7e6e21f Add an example benchmark for methods in engine_util_spatial. 
PiperOrigin-RevId: 453609626
Change-Id: I4986196ea3573bc22669c146ab6a311566035b73
 2022-06-07 23:56:43 -07:00
Saran Tunyasuvunakool 1913a02b40 Initial open sourcing of MuJoCo. 
PiperOrigin-RevId: 450374687
Change-Id: Ie3225a46ce095fc28ae8e63c326a640261f562bb
 2022-05-23 01:08:49 -07:00