1 / 23

RTR: 1 Byte/Kilo- I nstruction Race Recording

Explore Regulated Transitive Reduction (RTR) for efficient race recording, reducing log size, and avoiding deadlock in program execution. Discuss how RTR works with dependencies, compresses logs, and optimizes for minimal data replication. This talk delves into hardware acceleration, byte/kilo-instruction concepts, and the importance of RTR in countering nondeterminism. Learn how to enhance race recording systems with RTR's strict dependencies and efficient log compression. Future opportunities include support for snooping and simultaneous multithreading.

emeyers
Download Presentation

RTR: 1 Byte/Kilo- I nstruction Race Recording

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. RTR: 1 Byte/Kilo-InstructionRace Recording Rastislav Bodik Mark D. Hill Min Xu

  2. Why Do You Need a Recorder? • % gdb a.out • gdb> run • Program received SIGSEGV. • In get() at hash.c:45 • 45 a = bucket->d; • % gcc sim.c • % a.out • Segmentation fault • % • % gcc para-sim.c • % a.out • Segmentation fault • % • % gdb a.out • gdb> run • Program exited normally. • gdb> • % gcc para-sim.c • % a.out • Segmentation fault • Race recorded in “log” • % • % gdb a.out log • gdb> run • Program received SIGSEGV. • In get() at para-hash.c:67 • 67 a = bucket->d;

  3. Applicability: Programs – data race Systems – non-SC Ideally … Long recording: small log Low runtime overhead Low cost • % gcc para-sim.c • % a.out • Segmentation fault • Race recorded in “log” • % • % gdb a.out log • gdb> run • Program received SIGSEGV. • In get() at para-hash.c:67 • 67 a = bucket->d;

  4. Better and Better Recorders

  5. Hardware Acceleration [ISCA’03] Less Hardware [ASPLOS’06] SC & TSO [ASPLOS’06] A New Recorder 1 Byte/Kilo- Instruction [ASPLOS’06] • This talk covers only RTR • Regulated Transitive Reduction algorithm Result: One more step toward practical

  6. Outline Race Recording RTR Algorithm Compress log during recording  replay more “regularly” Results with Commercial Workloads Conclusion

  7. Technically, what’s race recording?

  8. Log - X = X*5 - - Recording X= 6 Race Recording Thread I Thread J Thread I Thread J X = 1 X++ print(X) - - - X = X*5 - - X = X*5 - - X = 1 X++ print(X) Original Replay X=6 X=10

  9. Terminologies and Assumptions Dependence (black) Conflicts (red) Thread I Thread J Thread I Thread J ld A add ld A add st B st B st C st C st C Log st C ld B ld B ld D ld D st A st A sub sub st C st C ld B ld B st D st D Recording Replay • Goal: Reproduce same conflicts with minimum log data

  10. Regulated Transitive Reduction (RTR)

  11. Dependence Log 1 1 Log J: 23 14 35 46 16 bytes 2 2 3 3 Log I: 23 4 4 5 5 Log Size: 5*16=80 bytes (10 integers) 6 6 Log All Conflicts Thread I Thread J ld A add st B st C st C ld B ld D st A sub st C ld B st D Replay • But too many conflicts

  12. TR Reduced Log Log J: 23 35 46 Log I: 23 Log Size: 64 bytes (8 integers) Netzer’s Transitive Reduction (TR) Thread I Thread J TR reduced 1 ld A add 1 st B st C 2 2 st C ld B 3 3 ld D st A 4 4 sub st C 5 5 ld B st D 6 6 Replay • How to further reduce log size?

  13. From I to J Vectors • “Regulate” Replay From J to I Vectors The Intuition of the RTR Algorithm After Reduction

  14. New Reduced Log Log J: 23 45 Log I: 23 stricter sub st C 5 5 Reduced Log Size: 48 bytes (6 integers) ld B st D 6 6 Stricter Dependences to Aid Vectorization Thread I Thread J 1 ld A add 1 st B st C 2 2 st C ld B 3 3 ld D st A 4 4 Replay • Fewer dependencies to log

  15. Vectorized Log Log J: x=3,5, ∆=1 Log I: x=3, ∆=1 Vector Deps. Log Size: 40 bytes (5 integers) Compress Vectorized Dependencies Thread I Thread J 1 ld A add 1 st B st C 2 2 st C ld B 3 3 ld D st A 4 4 sub st C 5 5 ld B st D 6 6 Replay • TRRTR: fewer deps + fewer byte/dep

  16. Replay Cycle i:4j:1 j:2 i:3 i:4 Deadlock Avoidance of RTR Thread I Thread J 1 ld A add 1 st B st C 2 2 st C ld B 3 3 ld D st A 4 4 sub st C 5 5 ld B st D 6 6 Recording • Limit the strict dependencies (see paper)

  17. Results with Commercial Workloads

  18. C3 C0 L2 C2 C1 Full-system Simulation Method • Commercial server hardware • GEMS: http://www.cs.wisc.edu/gems • Full-system (OS + application) executions • 4-core CMP (Sequential Consistent) • 1-way in-order issue, 2 GHz, • 64KB I/D L1, 4MB L2, 64byte lines, MOSI directory • Commercial server software • Apache – static web serving • SpecJBB – middleware • OLTP – TPC-C like • Zeus – static web serving

  19. KB/core/s byte/core/KI 200 2.0 150 1.5 100 1.0 50 0.5 0 0.0 Apache JBB OLTP Zeus AVG Apache JBB OLTP Zeus AVG Log Size: 1 byte/KI • Less buffer, longer recording, smaller logs

  20. 100 80 60 40 20 0 Apache JBB OLTP Zeus AVG RTR vs. Netzer’s TR • 28% smaller log • TR was “optimal” Log Size TR RTR

  21. Why Does RTR WorkWell? • RTR • Instructions execute at similar speed • Dependencies are often “vectorizable”

  22. Hardware Acceleration [ISCA’03] 1 Byte/Kilo- Instruction [ASPLOS’06] A New Recorder • “Less hardware” & “TSO” not covered • Equally important • More details in the paper Less Hardware [ASPLOS’06] SC & TSO [ASPLOS’06] Result: One more step toward practical

  23. Conclusion • Race recording Counter nondeterminism • RTR1 byte/kilo-instruction • Based on Netzer’s transitive reduction • Create stricter dependencies • Vectorize dependencies to compress log • Avoid overly-strict hence no deadlock • Future work • Support snooping, SMT, replayer

More Related