chenlin/Mujoco_WASM
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Align all arrays in mjData's buffer to 64 byte boundaries.

Browse Source 
The introduction of additional mjData arrays for the implicit integrator caused in a shift in data alignment in memory. In certain combinations of machines and models, this change resulted in ~5% performance regression that appears to be attributable to L2 cache misses.

This change aligns all arrays in mjData to the boundary of a typical L2 cache line size. Benchmarking shows that this resolves the performance regression on a Broadwell machine.

PiperOrigin-RevId: 451652783
Change-Id: I4ed2c2d03453a83a0b4a9b8e224e2fd7c0dadea9
This commit is contained in:
Saran Tunyasuvunakool
2022-05-28 13:02:49 -07:00
committed by Copybara-Service
parent 981fa22302
commit 5cc73c30bf
6 changed files with 28 additions and 30 deletions
Download Patch File Download Diff File Expand all files Collapse all files
include/mujoco/mujoco.h
+1 -1
View File
@@ -732,7 +732,7 @@ MJAPI void mju_warning_s(const char* msg, const char* text);
// Clear user error and memory handlers.
MJAPI void mju_clearHandlers(void);
// Allocate memory; byte-align on 8; pad size to multiple of 8.
// Allocate memory; byte-align on 64; pad size to multiple of 64.
MJAPI void* mju_malloc(size_t size);
// Free memory, using free() by default.