[vm] Implement more efficient CAS in simarm/simarm64 modes, v.2

[vm] Implement more efficient CAS in simarm/simarm64 modes, v.2

This CL includes db26c8934799de6205b1c9c9dc498d8fc58a0d07 (patch set #1)
with fix (patch set #2):
* Include simulator.h explicitly where it is required as it is no
  longer included implicitly through other header files.

Original review: https://codereview.chromium.org/2995803002/

When running on the simulator for arm/arm64, compare-and-swap operations
used in VM were synchronized with simulator using mutex.
It heavily impacts performance when doing parallel marking due to high
contention (see #30317).
This synchronization was implemented in order to make simulated
LDREX/STREX instructions aware of CAS performed in VM.

This CL drops this synchronization between VM and simulator:
CAS operations in VM become regular, and simulator remembers value loaded
with load-exclusive and performs CAS when doing store-exclusive to catch
any concurrent modifications.

Speeds up gen_snapshot of flutter benchmark complex_layout from 9.2s
to 8.0s on my MacBook.

R=asiva@google.com

Committed: https://github.com/dart-lang/sdk/commit/5aead50245aa8e761506409094060fa5267befbc

[alexmarkov, 2017-08-12 01:00:36]

Description was changed from

==========
[vm] Implement more efficient CAS in simarm/simarm64 modes, v.2

This CL includes 8ee4436355cf8434b99893fa014980adb17f572e (patch set #1)
with fixes.

When running on the simulator for arm/arm64, compare-and-swap operations
used in VM were synchronized with simulator using mutex.
It heavily impacts performance when doing parallel marking due to high
contention (see #30317).
This synchronization was implemented in order to make simulated
LDREX/STREX instructions aware of CAS performed in VM.

This CL drops this synchronization between VM and simulator:
CAS operations in VM become regular, and simulator remembers value loaded
with load-exclusive and performs CAS when doing store-exclusive to catch
any concurrent modifications.

Speeds up gen_snapshot of flutter benchmark complex_layout from 9.2s
to 8.0s on my MacBook.
==========

to

==========
[vm] Implement more efficient CAS in simarm/simarm64 modes, v.2

This CL includes db26c8934799de6205b1c9c9dc498d8fc58a0d07 (patch set #1)
with fixes.

When running on the simulator for arm/arm64, compare-and-swap operations
used in VM were synchronized with simulator using mutex.
It heavily impacts performance when doing parallel marking due to high
contention (see #30317).
This synchronization was implemented in order to make simulated
LDREX/STREX instructions aware of CAS performed in VM.

This CL drops this synchronization between VM and simulator:
CAS operations in VM become regular, and simulator remembers value loaded
with load-exclusive and performs CAS when doing store-exclusive to catch
any concurrent modifications.

Speeds up gen_snapshot of flutter benchmark complex_layout from 9.2s
to 8.0s on my MacBook.
==========

[alexmarkov, 2017-08-14 15:45:09]

Description was changed from

==========
[vm] Implement more efficient CAS in simarm/simarm64 modes, v.2

This CL includes db26c8934799de6205b1c9c9dc498d8fc58a0d07 (patch set #1)
with fixes.

When running on the simulator for arm/arm64, compare-and-swap operations
used in VM were synchronized with simulator using mutex.
It heavily impacts performance when doing parallel marking due to high
contention (see #30317).
This synchronization was implemented in order to make simulated
LDREX/STREX instructions aware of CAS performed in VM.

This CL drops this synchronization between VM and simulator:
CAS operations in VM become regular, and simulator remembers value loaded
with load-exclusive and performs CAS when doing store-exclusive to catch
any concurrent modifications.

Speeds up gen_snapshot of flutter benchmark complex_layout from 9.2s
to 8.0s on my MacBook.
==========

to

==========
[vm] Implement more efficient CAS in simarm/simarm64 modes, v.2

This CL includes db26c8934799de6205b1c9c9dc498d8fc58a0d07 (patch set #1)
with fix (patch set #2):
* Include simulator.h explicitly where it is required as it is no
  longer included implicitly through other header files.

Original review: https://codereview.chromium.org/2995803002/

When running on the simulator for arm/arm64, compare-and-swap operations
used in VM were synchronized with simulator using mutex.
It heavily impacts performance when doing parallel marking due to high
contention (see #30317).
This synchronization was implemented in order to make simulated
LDREX/STREX instructions aware of CAS performed in VM.

This CL drops this synchronization between VM and simulator:
CAS operations in VM become regular, and simulator remembers value loaded
with load-exclusive and performs CAS when doing store-exclusive to catch
any concurrent modifications.

Speeds up gen_snapshot of flutter benchmark complex_layout from 9.2s
to 8.0s on my MacBook.
==========

[alexmarkov, 2017-08-14 15:45:46]

alexmarkov@google.com changed reviewers:
+ asiva@google.com, rmacnak@google.com, zra@google.com

[siva, 2017-08-14 17:59:43]

lgtm

[alexmarkov, 2017-08-14 18:10:34]

Description was changed from

==========
[vm] Implement more efficient CAS in simarm/simarm64 modes, v.2

This CL includes db26c8934799de6205b1c9c9dc498d8fc58a0d07 (patch set #1)
with fix (patch set #2):
* Include simulator.h explicitly where it is required as it is no
  longer included implicitly through other header files.

Original review: https://codereview.chromium.org/2995803002/

When running on the simulator for arm/arm64, compare-and-swap operations
used in VM were synchronized with simulator using mutex.
It heavily impacts performance when doing parallel marking due to high
contention (see #30317).
This synchronization was implemented in order to make simulated
LDREX/STREX instructions aware of CAS performed in VM.

This CL drops this synchronization between VM and simulator:
CAS operations in VM become regular, and simulator remembers value loaded
with load-exclusive and performs CAS when doing store-exclusive to catch
any concurrent modifications.

Speeds up gen_snapshot of flutter benchmark complex_layout from 9.2s
to 8.0s on my MacBook.
==========

to

==========
[vm] Implement more efficient CAS in simarm/simarm64 modes, v.2

This CL includes db26c8934799de6205b1c9c9dc498d8fc58a0d07 (patch set #1)
with fix (patch set #2):
* Include simulator.h explicitly where it is required as it is no
  longer included implicitly through other header files.

Original review: https://codereview.chromium.org/2995803002/

When running on the simulator for arm/arm64, compare-and-swap operations
used in VM were synchronized with simulator using mutex.
It heavily impacts performance when doing parallel marking due to high
contention (see #30317).
This synchronization was implemented in order to make simulated
LDREX/STREX instructions aware of CAS performed in VM.

This CL drops this synchronization between VM and simulator:
CAS operations in VM become regular, and simulator remembers value loaded
with load-exclusive and performs CAS when doing store-exclusive to catch
any concurrent modifications.

Speeds up gen_snapshot of flutter benchmark complex_layout from 9.2s
to 8.0s on my MacBook.

R=asiva@google.com

Committed:
https://github.com/dart-lang/sdk/commit/5aead50245aa8e761506409094060fa5267befbc
==========

[alexmarkov, 2017-08-14 18:10:35]

Committed patchset #2 (id:20001) manually as
5aead50245aa8e761506409094060fa5267befbc (presubmit successful).