Closed Bug 503445 Opened 15 years ago Closed 15 years ago

TM: atomic increment in Scope::hold() accounts for 24% of our obj allocation time

Categories

(Core :: JavaScript Engine, defect)

Product:
Core
Component:
JavaScript Engine
Platform:
x86
macOS
Type:
defect
Priority:
Not set
Severity:
normal

Tracking

()

Status:
RESOLVED DUPLICATE of bug 505004

People

(Reporter: gal, Unassigned)

Details

Tight loop allocating. We spend 8% in hold(). The rest of the allocator path is 34%. We have to come up with a clever way to bypass the atomic op. # Report 0 - Session 3 - Time Profile of js <Mozilla> SharkProfileViewer # Generated from the visible portion of the outline view - 40.7%, js_Interpret, js - 34.0%, js_NewGCObject, js - 15.4%, js_GC, js - 8.0%, JSScope::hold(), js - 1.7%, JS_FinalizeStub, js
This can be fixed by the fix to bug 503080, I claim. /be
Depends on: 503080
Rather, this is bug 505004. /be
Status: NEW → RESOLVED
Closed: 15 years ago
Resolution: --- → DUPLICATE
No longer depends on: 503080
You need to log in before you can comment on or make changes to this bug.