Closed
Bug 2087942
Opened 15 days ago
Closed 14 days ago
[loong64] Micro-optimize ma_mul_d and ma_mul
Categories
(Core :: JavaScript Engine: JIT, task)
Tracking
()
RESOLVED
FIXED
161 Branch
| Tracking | Status | |
|---|---|---|
| firefox161 | --- | fixed |
People
(Reporter: csmantle, Assigned: csmantle)
References
(Blocks 1 open bug)
Details
Attachments
(1 external file)
Based on benchmark results, LoongArch has slow MULs (4 cycles of latency on Loongson 3B6000, LA664). The current isel of ma_mul_d and ma_mul performs strength reduction for common patterns, but unfortunately they are not symmetric, nor exercised by codegen tests. We could try to improve it.
| Assignee | ||
Comment 1•15 days ago
|
||
This unifies both MASM methods with the following optimizations, with
latency in cycles and calcuated per 0:
RHS Latency
-1 1
0 1
1 1
2 1
2^n + 1, n<5 1
2^n + 1, n>=5 2
2^n 1
2^n - 1 2
2^n + 2^m, n>m 3
(otherwise) >=4
Pushed by webmaster@csmantle.top:
https://github.com/mozilla-firefox/firefox/commit/705a6d654db1
https://hg.mozilla.org/integration/autoland/rev/167a1e790edf
[loong64] Micro-optimize ma_mul_d and ma_mul. r=spidermonkey-reviewers,jandem
Comment 3•14 days ago
|
||
| bugherder | ||
Status: ASSIGNED → RESOLVED
Closed: 14 days ago
status-firefox161:
--- → fixed
Resolution: --- → FIXED
Target Milestone: --- → 161 Branch
Updated•7 days ago
|
QA Whiteboard: [qa-triage-done-c162/b161]
You need to log in
before you can comment on or make changes to this bug.
Description
•