On 2013/09/13 09:26:26, ulan wrote:
I think the change is correct. Do you know how it affects the benchmarks?
If
there is improvement, we can land it.
https://codereview.chromium.org/23480027/diff/10001/src/arm/macro-assembler-arm.cc
File src/arm/macro-assembler-arm.cc (right):
https://codereview.chromium.org/23480027/diff/10001/src/arm/macro-assembler-arm.cc#newcode3244
src/arm/macro-assembler-arm.cc:3244: b(lt, &word_loop);
Any reason why this is not "b(le, &word_loop)"? I think it should work and
would
be consistent with the unaligned_accesses case.
It speeds up sun spider benchmark by 0.3% with this optimization.
I have updated the branch condition to be consistent.
Thanks for review.
https://codereview.chromium.org/23480027/
--
--
v8-dev mailing list
[email protected]
http://groups.google.com/group/v8-dev
---
You received this message because you are subscribed to the Google Groups "v8-dev" group.
To unsubscribe from this group and stop receiving emails from it, send an email
to [email protected].
For more options, visit https://groups.google.com/groups/opt_out.
