x86-to-ARM LnQ Status

Block mode, test inputs

400.perlbench                               NR
401.bzip2          --   180              -- S
403.gcc            --   466              -- S
429.mcf            --    53.7            -- S
445.gobmk          --   874              -- S
456.hmmer                                   NR                              
458.sjeng          --   129              -- S
462.libquantum     --    15.7            -- S                            
464.h264ref        --     0.0248            RE                        
471.omnetpp        --    62.1               RE                        
473.astar          --   126              -- S                            
483.xalancbmk      --   218              -- S

------------------------------------------------------------------------------------

Summary:

• 400.perlbench, and 456.hmmer can not run due to floating point precision error
• 464.h264ref
• 471.omnetpp 

================================================================
Trace Mode, test inputs

400.perlbench                               NR

401.bzip2          --   140              -- S                               

403.gcc            --   335                 RE                              

429.mcf            --    53.5            -- S                               

445.gobmk          --   533                 RE

456.hmmer                                   NR                             

458.sjeng          --   106              -- S                           

462.libquantum     --    14.3            -- S                            

464.h264ref        --     0.0257            RE                             

471.omnetpp        --    50.3               RE

473.astar          --   104              -- S

483.xalancbmk      --   169              -- S

------------------------------------------------------------------------------------

Summary:

• Error inherit from block mode 
• 403.gcc
• 445.gobmk

===============================================================

guest applications are re-compiled with gcc 4.7 to make sure it really use SSE instructions

• Perlbench still stuck in arith.t due to precision problem
• bzip OK
• gcc: KILLILL, illegal instruction due to incorrect encoding of VST1LNd32
• fix alignment encoding for these instructions in getAddrMode6AddressOpValue() in ARMCodeEmitter.cpp
• Re-test all but perlbench and hmmer
• hang on leslie3d, try to find out why...
• trap in infinite loop; maybe due to precision error?
• skip it.
• Omnetpp: Fail to run; try to find out why...
• QEMU cannot run either.
• Bwaves: mis-compare; does QEMU get the same result?
• 
  
• Gamess: mis-compare; does QEMU get the same result?
• NOTE: unlike bwaves, there are minus signs where it should not appear
• Milc: mis-compare;
• Zeus: segfault.
• Reason: On ARM Linux, the shared library, like ld-2.13.so, libpthread-2.13.so, etc..., are loaded starting at 0x40000000, and and the image of x86 guest starts at 0x08048000.  Zeus asks for 0x45efa000 memory for its image, which cannot fit in the ``hole'' between 0x08048000 and 0x40000000.
• And I move qemu image to 0x90000000;
• So, the guest image is finally put in between 0x40000000 and 0x90000000.
• however, during execution, the guest asks more memory, and finally shit happen...
• Gromacs: mis-compare
• Leslie3d: mis-compare

--------------------------------------------------------------------------------------

Summary:

• QEMU FP precision problem
• Perlbench and hmmer trap in infinite loop due to FP precision problem
• Omnetpp fail to run; 
• Only cactum and namd success in floating point benchmarks...
• 9 CINT2006 benchmarks run successfully.
• Measure timing...

400.perlbench                               NR

401.bzip2          --      163           -- S

403.gcc            --      507           -- S

429.mcf            --       56.1         -- S

445.gobmk          --      955           -- S

456.hmmer                                   NR

458.sjeng          --      126           -- S

462.libquantum     --       16.3         -- S

464.h264ref        --      387              VE

471.omnetpp                                 NR

473.astar          --      114           -- S

483.xalancbmk      --      230           -- S

======================================================================

Trace :

401.bzip2: NOT OK

• Infinite loop

403.gcc: mis-compare
429.mcf: OK
445.gobmk: OK
458.sjeng: OK
462.libquantum: OK
473.astar: OK

464.h264ref: NOT OK

*** longjmp causes uninitialized stack frame ***: /home/tk/lnq/install/bin/qemu-i386 terminated
Aborted (core dumped)

483.xalancbmk: NOT OK

• Terminate without printing anything

400.perlbench                               NR

401.bzip2                                   NR

403.gcc            --      460              VE

429.mcf            --       56.5         -- S

445.gobmk          --      874           -- S

456.hmmer                                   NR

458.sjeng          --      112           -- S

462.libquantum     --       14.7         -- S

464.h264ref                                 NR

471.omnetpp                                 NR

473.astar          --       98.4         -- S

483.xalancbmk                               NR

===============================================================
Debug Trace Mode:
===============================================================
First, try to find out whose fault, and always use easiest-bug-first strategy to fight.
===============================================================
GCC: Mis-compare

•  When in trace mode, the blocks are compiled with IFastEnable and Opt::None options. So, check whether this error comes from fast instruction selection mode.
• Set optimization options to ``Default'' and disable IFastEnable.
• This error is gone.
• Confirm!
• Now debug becomes simple: run $l gcc two times: enabling and disabling FastISel, and compares logs to locate where went wrong.
• FAIL!
• Another approach:
• EnableFastISel does not affect correctness.
• llvm optimization does!
• When opt is set to None, gcc got segfault!
• When opt is set to Less, gcc runs successfully.
• Run block with None, and compare used MI.
• Run experiment!
• Nothing found!
• Still don't know why llvm::CodeGenOpt::None cause fault, try find reduced example.
• Run CINT2006 with llvm::CodeGenOpt::None
• Wait for result...
• Error: 1x401.bzip2 1x403.gcc 1x445.gobmk 1x464.h264ref 1x483.xalancbmk
• Success: 1x429.mcf 1x458.sjeng 1x462.libquantum 1x473.astar 1x999.specrand