1. Automatic Detection of Extended Data-Race-Free Regions
Present self + team
Previous decades: Time is money  Performance
Current decade: Power is money  Energy
This work improves energy efficiency without damaging performance.
Sweden
Alexandra Jimborean
Jonatan Waern, Per Ekemark,
Stefanos Kaxiras,
Alberto Ros (Murcia, Spain)

2. Software-hardware co-designs Compiler-assisted cache coherence
Motivation and goal
Multi- and many-core processors and heterogeneous architectures pose challenges on scalable cache coherence
Simplify or even abandon hardware cache coherence
Goal
Software-hardware co-designs
Compiler-assisted cache coherence

3. Traditional cache coherence
Cache coherence ensures correct propagation of changes of data held in multiple private caches.
Problem: Not all updates to variables have to be
propagated. Unnecessary propagation of updates
uses resources in vain.
Background
Private data does not require coherence!
Solution: Design a dual-mode cache coherence
protocol and enable coherence on-demand.

4. Private-shared data Motivation Runtime classification
Static classification
Motivation
Compiler identifies most accesses
to target temporarily private data!
Identify the largest period during
which data remains private:
extended data race-free regions

5. Agenda Outline xDRF regions of private accesses
Examples
Compile-time xDRF analysis
xDRF regions for optimizing coherence protocols
Results: performance, energy on many-cores
Outline

6. Data race free code as input
Data-race free code, no data
races given synchronization
LOCK
Regions
UNLOCK

7. Synchronization points
Data-race free code, no data
races given synchronization
Synchronizations divide code
in two categories
LOCK
Regions
UNLOCK

8. Parallel DRF regions do not share data.
DRF and nDRF regions
Data-race free code, no data
races given synchronization
Synchronizations divide code
in two categories
DRF regions
outside synchronized code
nDRF regions, i.e.
synchronized code
LOCK
Regions
UNLOCK
Disclaimer:
DRF/nDRF
our notations
Parallel DRF regions do not share data.

9. Happens-before sync are xDRF boundaries.
Data-flow across a synchronization point  sync enforces a happens-before.
Regions
Happens-before sync are xDRF boundaries.

10. xDRF regions extend across enclave nDRFs.
Lock-set sync
No data-flow across a synchronization point 
sync ensures atomicity
nDRF is
enclave
Regions
xDRF regions extend across enclave nDRFs.

11. Lock-set sync Regions No data-flow across a synchronization point 
sync ensures atomicity
nDRF is
enclave
Regions
Extend the synchronization-free semantics
across enclave synchronization points.

12. Sync is an xDRF boundary  Different xDRF regions.
Data-flow across sync
xDRF
Conflict
Conflict
xDRF extends
across sync.
Sync is an xDRF boundary  Different xDRF regions.

13. Data-flow across sync
Signal-wait
with locks,
breaks xDRF.
xDRF

14. No data-flow across sync
Signal-wait
with locks,
no data-flow across sync, enclave in xDRF.
xDRF

15. Data-flow across transitive sync
xDRF
Transitive synchronization.
Conflict

16. xDRF static analysis xDRF analysis
Distinguish between nDRF regions which represent xDRF boundaries and nDRF regions enclave in xDRF regions.
xDRF analysis

17. Check the sync variable of each nDRF.
Identify nDRF regions
Identify synchronization points (nDRFs)
1. nDRF Regions
Check the sync variable of each nDRF.

18. Matching nDRFs sync on the same synchronization variable.
Matching nDRF regions
Identify nDRFs that sync one with another.
1. nDRF Regions
Matching nDRFs sync on the
same synchronization variable.

19. DRF paths 2. DRF regions nDRF DRF-before = {1,2} DRF-after = {3}
Not yet processed or previously identified as xDRF boundaries.
nDRF
DRF-before = {1,2}
DRF-after = {3}
DRF before
Currently analyzed nDRF
2. DRF regions
DRF after
nDRF
DRF region before = Union of DRF paths before
DRF region after = Union of DRF paths after

20. Currently analyzed nDRF
DRF regions
DRF before
DRF-before = {1,2,3}
DRF-after = {4,5}
nDRF
nDRF
Currently analyzed nDRF
2. DRF regions
DRF after
nDRF
nDRF

21. DRF regions 2. DRF regions DRF-before = {1,2,3} DRF-after = {1,3} nDRF
Currently analyzed nDRF
DRF after
nDRF
More details in the paper.

22. Merging DRF regions 2. DRF regions nDRF DRF-before = {1,2}
DRF-after = {3}
DRF before
1. No conflict between DRF-before and DRF-after
2. DRF regions
DRF after
2. No conflict between DRFs and current nDRF
nDRF

23. Merging DRF regions 3. xDRF regions nDRF DRF-before = {1,2}
DRF-after = {3}
DRF before
1. No conflict between DRF-before and DRF-after
xDRF region
Enclave
3. xDRF regions
DRF after
2. No conflict between DRFs and current nDRF
nDRF
Current nDRF is enclave.
Merge DRF-before and DRF-after in one xDRF.

24. xDRF regions 3. xDRF Regions xDRF-before = {1,2} xDRF-after = {3}
Not yet processed or previously identified as non-enclave.
xDRF-before = {1,2}
xDRF-after = {3}
xDRF before
Enclave
3. xDRF Regions
Currently analyzed nDRF
xDRF after
If no conflict,
merge xDRF-before and xDRF-after in one xDRF.

25. Transitive xDRF regions
xDRF-before = {1,2,3,4}
xDRF-after = {5}
Matching enclave nDRFs
3. xDRF regions
More details in the paper.

26. xDRF in practice Evaluation Number of static nDRF
70% non-enclave (inherent to the applications)
20% enclave (automatically detected)
10% potentially enclave (oracle)
Number of executed xDRF regions
Enclave nDRFs are on the hot path
Compiler approaches oracle
Evaluation

27. How are xDRF regions useful
Compiler-assisted cache coherence protocol
Deactivate coherence for xDRF accesses
(temporarily private data)
xDRF - cogerence

28. Traditional cache coherence
3xN
coherence actions
xDRF - coherence
Traditional c.c.

29. Optimized cache coherence
3xN
coherence actions
N+1
coherence actions
xDRF - coherence
Traditional c.c.
Optimized c.c.

30. xDRF cache coherence xDRF - coherence 3xN coherence actions N+1
Traditional c.c.
Optimized c.c.
xDRF c.c.

31. Performance – coherence prot.
-4% DRF only
7% Compiler
8% Oracle
Evaluation
Normalized to a traditional protocol
Compiler competitive with oracle

32. Energy savings – coherence protocol
-10% DRF only
12% Compiler
16% Oracle
Evaluation
Compiler competitive with oracle

33. Conclusions Conclusions Compiler techniques to detect xDRF regions
xDRF regions enable cache coherence optimizations
Performance 7%, energy savings 12%
Conclusions

34. Automatic Detection of Extended Data-Race-Free Regions
Present self + team
Previous decades: Time is money  Performance
Current decade: Power is money  Energy
This work improves energy efficiency without damaging performance.
Sweden
Thank you!
Alexandra Jimborean
Jonatan Waern, Per Ekemark ,
Stefanos Kaxiras,
Alberto Ros (Murcia, Spain)
Travelling to this conference
was financed by the
Swedish Wenner-Gren foundation

35. Enable compiler optimizations over
Future work
Enable compiler optimizations over
xDRF regions
Typical compiler optimizations for multi-threaded code operate within synchronization free regions
xDRF extends the scope of the optimizations making them more effective
Future work

36. Future work Future work
Instead of splitting xDRF regions upon a conflict, place nDRF markings around the conflicting accesses
xDRF limits: barriers, signal-waits, joins
Any shared (conflicting) accesses are handled as nDRF
 Larger xDRF regions
Future work