[crankshaft] Address the deoptimization loops of Math.floor, Math.round and Math.ceil.

[crankshaft] Address the deoptimization loops of Math.floor, Math.round and Math.ceil.

Fix and re-enable the flexible representation for Math.floor (which is used to
implement Math.ceil) and Math.round, which allows Math.floor and Math.round to
return double results instead of int32, and therefore allows values outside
the int32 range, especially -0 is now a valid result, which doesn't deopt.

Also port this feature to x64 and ia32 when the CPU supports the SSE4.1
extension.

This addresses all the known deoptimization loops related to Math.round
in the Kraken benchmark suite, and seems to also address most of the
deoptimization loops related to Math.floor in the Oort Online benchmark.

Drive-by-fix: Import the regression tests for the broken HMathFloorOfDiv
optimization that caused the initial revert of the feature (for arm64 only
back then).

BUG=chromium:476477, v8:2890, v8:4059
R=jarin@chromium.org
LOG=n

Committed: https://crrev.com/978ad03b9275fb338f6dd484c1ef732d1a97ccfe
Cr-Commit-Position: refs/heads/master@{#35094}

[Benedikt Meurer, 2016-03-29 09:31:03]

Hey Jaro,

Here's the baby we talked about; it's actually quite simple (since the ARM folks
did a lot of pre-work already).
Please take a look.

Thanks,
Benedikt

[Jarin, 2016-03-29 10:21:49]

lgtm

[Benedikt Meurer, 2016-03-29 10:22:13]

The CQ bit was checked by bmeurer@chromium.org

[commit-bot: I haz the power, 2016-03-29 10:22:24]

CQ is trying da patch. Follow status at
 https://chromium-cq-status.appspot.com/patch-status/1841513003/20001
View timeline at
 https://chromium-cq-status.appspot.com/patch-timeline/1841513003/20001

[commit-bot: I haz the power, 2016-03-29 10:24:36]

Committed patchset #2 (id:20001)

[commit-bot: I haz the power, 2016-03-29 10:25:08]

Description was changed from

==========
[crankshaft] Address the deoptimization loops of Math.floor, Math.round and
Math.ceil.

Fix and re-enable the flexible representation for Math.floor (which is used to
implement Math.ceil) and Math.round, which allows Math.floor and Math.round to
return double results instead of int32, and therefore allows values outside
the int32 range, especially -0 is now a valid result, which doesn't deopt.

Also port this feature to x64 and ia32 when the CPU supports the SSE4.1
extension.

This addresses all the known deoptimization loops related to Math.round
in the Kraken benchmark suite, and seems to also address most of the
deoptimization loops related to Math.floor in the Oort Online benchmark.

Drive-by-fix: Import the regression tests for the broken HMathFloorOfDiv
optimization that caused the initial revert of the feature (for arm64 only
back then).

BUG=chromium:476477,v8:2890,v8:4059
R=jarin@chromium.org
LOG=n
==========

to

==========
[crankshaft] Address the deoptimization loops of Math.floor, Math.round and
Math.ceil.

Fix and re-enable the flexible representation for Math.floor (which is used to
implement Math.ceil) and Math.round, which allows Math.floor and Math.round to
return double results instead of int32, and therefore allows values outside
the int32 range, especially -0 is now a valid result, which doesn't deopt.

Also port this feature to x64 and ia32 when the CPU supports the SSE4.1
extension.

This addresses all the known deoptimization loops related to Math.round
in the Kraken benchmark suite, and seems to also address most of the
deoptimization loops related to Math.floor in the Oort Online benchmark.

Drive-by-fix: Import the regression tests for the broken HMathFloorOfDiv
optimization that caused the initial revert of the feature (for arm64 only
back then).

BUG=chromium:476477,v8:2890,v8:4059
R=jarin@chromium.org
LOG=n

Committed: https://crrev.com/978ad03b9275fb338f6dd484c1ef732d1a97ccfe
Cr-Commit-Position: refs/heads/master@{#35094}
==========

[commit-bot: I haz the power, 2016-03-29 10:25:09]

Patchset 2 (id:??) landed as
https://crrev.com/978ad03b9275fb338f6dd484c1ef732d1a97ccfe
Cr-Commit-Position: refs/heads/master@{#35094}