55 lines
1 KiB
Text
55 lines
1 KiB
Text
|
|
Last updated 15 Nov 04
|
|
~~~~~~~~~~~~~~~~~~~~~~
|
|
|
|
Critical (correctness)
|
|
~~~~~~~~~~~~~~~~~~~~~~
|
|
x86 isel: should free up all fp reg tags when calling a helper.
|
|
And save FP and SSE insns across the helper.
|
|
|
|
iropt: reconsider precise exceptions
|
|
|
|
x86 guest: look at FP accuracy
|
|
|
|
|
|
Optimisation opportunities
|
|
~~~~~~~~~~~~~~~~~~~~~~~~~~
|
|
Improved isel for memcheck artefacts on x86 (generate neg ; sbbl)
|
|
|
|
Assess tt_fast miss rates
|
|
|
|
improve stack-update pass
|
|
|
|
proper profiling machinery
|
|
|
|
do not CSE exprs :: Ity_Bit
|
|
|
|
x86 iselIntExpr_RMI: actually generate the M case if possible
|
|
|
|
|
|
JIT speedups
|
|
~~~~~~~~~~~~
|
|
Ensure incremental flatness throughout
|
|
|
|
Profile again with cachegrind/calltree
|
|
|
|
change IRTemp to 16 bits?
|
|
|
|
|
|
Integration
|
|
~~~~~~~~~~~
|
|
Get rid of sloppy-malloc
|
|
|
|
Get rid of partial-loads-ok
|
|
|
|
Optimisation after first instrumentation rather than 2nd ?
|
|
|
|
disallow dirty helpers from writing SP/IP
|
|
|
|
write API doc, clarify IR semantics
|
|
|
|
make IR utils module
|
|
|
|
generic stack pointer identification at startup?
|
|
|
|
New memstack_k: old or new sp?
|