Age | Commit message (Collapse) | Author |
|
mult microops.
|
|
|
|
|
|
LLFLAG
|
|
|
|
|
|
The instruction was encoded as a load instead of the intended store.
|
|
|
|
If the control flow of M5's executable and statetrace's target process get out
of sync even a little, there will be a LOT of output, very little of which
will be useful. There's also almost no hope for recovery. In those cases, we
might as well give up and not generate a huge, mostly worthless trace file.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
When registers have incorrect values but aren't actively changing, it's likely
they're not being modified at all. The fact that they're still wrong isn't
very important.
|
|
--HG--
rename : src/arch/sparc/SparcNativeTrace.py => src/arch/arm/ArmNativeTrace.py
rename : src/arch/sparc/nativetrace.cc => src/arch/arm/nativetrace.cc
rename : src/arch/sparc/nativetrace.hh => src/arch/arm/nativetrace.hh
|
|
|
|
|
|
|
|
|
|
|
|
Also a few more style fixes.
|
|
Some breakage was from my BitUnion change, some was much older.
|
|
White space, commented out code, some other minor fixes.
|
|
|
|
Also fix style issues in regions around these changes.
|
|
--HG--
rename : src/cpu/nativetrace.cc => src/arch/sparc/nativetrace.cc
rename : src/cpu/nativetrace.hh => src/arch/sparc/nativetrace.hh
rename : src/cpu/NativeTrace.py => src/arch/x86/X86NativeTrace.py
|
|
|
|
|
|
|
|
|
|
|
|
|
|
operands.
|
|
|
|
|
|
|
|
A separate operand type is not necessary to use two bitfields to generate the
index.
|
|
Using a look up table changed the run time of the SPARC_FS solaris boot
regression from:
real 14m45.951s
user 13m57.528s
sys 0m3.452s
to:
real 12m19.777s
user 12m2.685s
sys 0m2.420s
|
|
|
|
|