a19838e107
MC: Simplify MayNeedRelaxation to not provide the fixups, so we can query it
...
before encoding.
llvm-svn: 104707
2010-05-26 17:45:29 +00:00
b34440a6a8
MC: Eliminate MCAsmFixup, replace with MCFixup.
...
llvm-svn: 104699
2010-05-26 15:18:56 +00:00
353a91ff76
MC: Use accessors for access to MCAsmFixup.
...
llvm-svn: 104697
2010-05-26 15:18:31 +00:00
870e5759e7
MC: Eliminate MCFragment vtable, which was unnecessary.
...
llvm-svn: 104689
2010-05-26 06:50:57 +00:00
4bce748aa2
MC: Switch to completely lazy layout.
...
- The eliminates the last major algorithmic problem with MC.
llvm-svn: 103754
2010-05-14 00:51:14 +00:00
9abade1017
MC: Extend MCAsmLayout to explicitly track which fragments have been layed out, and enforce several invariants to LayoutFragment to ensure we only do layout in a sensible order.
...
llvm-svn: 103753
2010-05-14 00:37:21 +00:00
3eedc26e18
MC: Implicitly assign section addresses when the previous fragment is layed out.
...
llvm-svn: 103752
2010-05-14 00:37:17 +00:00
8f9d2266e6
MC: Switch MCFragment to storing the layout order index, not its index in the file.
...
llvm-svn: 103751
2010-05-14 00:37:14 +00:00
a99a23b061
MC: Change LayoutSection() to only do the section initializiation.
...
Also, elimminate MCAsmLayout::set*, which are no longer needed.
llvm-svn: 103750
2010-05-14 00:37:11 +00:00
b9f6ac094a
MC: Move Layout{Fragment,Section} into MCAsmLayout, and add LayoutFile().
...
llvm-svn: 103738
2010-05-13 20:40:12 +00:00
454ea716a3
MC: Factor out MCAssembler::ComputeFragmentSize.
...
llvm-svn: 103724
2010-05-13 18:35:06 +00:00
484c6fc825
MC: Add section layout order indices to MCSectionData.
...
llvm-svn: 103715
2010-05-13 15:17:26 +00:00
aa8bd69886
MC: Move ordinal calculation, to make sure fragments synthesized for layout get assigned ordinals properly.
...
llvm-svn: 103711
2010-05-13 08:43:37 +00:00
e73353c720
MC: Create dummy fragments to avoid ever having empty sections, which simplifies layout.
...
llvm-svn: 103710
2010-05-13 08:43:34 +00:00
e8845ef4db
MC: Add MCAsmLayout::FragmentReplaced() helper function.
...
llvm-svn: 103709
2010-05-13 08:43:31 +00:00
5a93253fc8
Fix -Asserts warning.
...
llvm-svn: 103697
2010-05-13 03:50:50 +00:00
d83889bd87
MC: Eliminate MCSectionData::{,Address,File}Size, which can now be computed by
...
utility functions.
llvm-svn: 103695
2010-05-13 03:19:50 +00:00
c7c53ea715
MC: Switch to using explicit MCAlignFragments with OnlyAlignAddress bit instead
...
of manually doing padding/editing layout in LayoutSection().
- This probably seems like six-of-one and half-dozen of another, but there
is a method to my madness.
llvm-svn: 103693
2010-05-13 02:34:14 +00:00
a6780da661
MC: Add MCAlignFragment::OnlyAlignAddress bit. This is a bit of magic that says the align fragment shouldn't contribute to the logical section size, it is will be used for cleaning up the code to handle section alignment.
...
llvm-svn: 103690
2010-05-13 01:10:26 +00:00
4dac59dcb7
MC: Add MCSectionData::AddressSize, which is the size of the address space consumed by the section. This can differ from both the section logical size, and the section size on disk (although the current code handles this without making an explicit distinction).
...
llvm-svn: 103689
2010-05-13 01:10:22 +00:00
b76df22a2e
MC: Move MCAlignFragment::EmitNops value out of the constructor.
...
llvm-svn: 103665
2010-05-12 22:56:23 +00:00
4405ffc688
MC: Eliminate MCZeroFillFragment, it is no longer needed.
...
llvm-svn: 103664
2010-05-12 22:51:38 +00:00
7cd309f7dc
MC: Explicitly check that only virtual fragments appear in virtual sections.
...
llvm-svn: 103663
2010-05-12 22:51:35 +00:00
597eb48168
MC: Switch MCFillFragment to storing total fill size instead of a count. This allows using ValueSize==0 to represent a virtual fill.
...
llvm-svn: 103662
2010-05-12 22:51:32 +00:00
51402b79e4
MC: Drop support for alignment in ZeroFill fragment, we can just use
...
MCAlignFragments for this.
llvm-svn: 103661
2010-05-12 22:51:27 +00:00
7d73564b82
Simplify.
...
llvm-svn: 103651
2010-05-12 21:47:55 +00:00
a7cc32a7b6
MC: Factor out MCAssembler::LayoutFragment
...
llvm-svn: 103649
2010-05-12 21:35:25 +00:00
2abec791f1
MC: Tweak section layout to not relying on accumulating address value.
...
llvm-svn: 103648
2010-05-12 21:35:22 +00:00
a11479eb49
MC: Simplify LayoutSection to just take the index of the section to layout.
...
llvm-svn: 103627
2010-05-12 17:56:47 +00:00
e02c1f6834
MC: Track section layout order explicitly, and use to simplify.
...
llvm-svn: 103616
2010-05-12 15:42:59 +00:00
ba2f4c3884
MC/Mach-O/x86_64: Add a new hook for checking whether a particular section can
...
be diced into atoms, and adjust getAtom() to take this into account.
- This fixes relocations to symbols in fixed size literal sections, for
example.
llvm-svn: 103532
2010-05-12 00:38:17 +00:00
3937e28da0
MC/Mach-O x86_64: Switch to using fragment atom symbol.
...
- This eliminates getAtomForAddress() (which was a linear search) and
simplifies getAtom().
- This also fixes some correctness problems where local labels at the same
address as non-local labels could be assigned to the wrong atom.
llvm-svn: 103480
2010-05-11 17:22:50 +00:00
aadb2cac49
MC/Mach-O: Explicitly track atoms, as represented by their defining symbol, for each fragment (not yet used).
...
llvm-svn: 103438
2010-05-10 22:45:09 +00:00
ce0c1e11ce
llvm-mc: Fix case were we would skip a line in the .s file after an instruction
...
match failure.
Also, fixes a few memory leak FIXMEs.
llvm-svn: 102986
2010-05-04 00:33:07 +00:00
2104b8d36e
rename llvm::llvm_report_error -> llvm::report_fatal_error
...
llvm-svn: 100709
2010-04-07 22:58:41 +00:00
d821f4ac60
llvm-mc: Add a -mc-relax-all option, which relaxes every fixup. We always need
...
exactly two passes in that case, and don't ever need to recompute any layout,
so this is a nice baseline for relaxation performance.
llvm-svn: 99563
2010-03-25 22:49:09 +00:00
6432bd744e
MC: Stop restarting layout on every relaxation.
...
- Still O(N^2), just a faster form, and now its the MCAsmLayout's fault.
On the .s I am tuning against (combine.s from 403.gcc):
--
ddunbar@lordcrumb:MC$ diff stats-before.txt stats-after.txt
5,10c5,10
< 1728 assembler - Number of assembler layout and relaxation steps
< 7707 assembler - Number of emitted assembler fragments
< 120588 assembler - Number of emitted object file bytes
< 2233448 assembler - Number of evaluated fixups
< 1727 assembler - Number of relaxed instructions
< 6723845 mcexpr - Number of MCExpr evaluations
---
> 3 assembler - Number of assembler layout and relaxation steps
> 7707 assembler - Number of emitted assembler fragments
> 120588 assembler - Number of emitted object file bytes
> 14796 assembler - Number of evaluated fixups
> 1727 assembler - Number of relaxed instructions
> 67889 mcexpr - Number of MCExpr evaluations
--
Feel free to LOL at the -before numbers, if you like.
I am a little surprised we make more than 2 relaxation passes. It's pretty
trivial for us to do relaxation out-of-order if that would give a speedup.
llvm-svn: 99543
2010-03-25 19:35:56 +00:00
0ba6a671d4
MC: Simplify main section layout process by moving alignment into LayoutSection.
...
llvm-svn: 99529
2010-03-25 18:16:42 +00:00
25d114b2b2
MC: Sink Section address assignment into LayoutSection.
...
llvm-svn: 99528
2010-03-25 18:16:38 +00:00
4108802628
MC: Explicity track section and fragment ordinals.
...
llvm-svn: 99500
2010-03-25 07:10:11 +00:00
5b07334c0d
MC: Route access to SectionData offset and file size through MCAsmLayout.
...
llvm-svn: 99474
2010-03-25 02:00:07 +00:00
2522dd1c49
MC: Route access to Fragment offset and effective size through MCAsmLayout.
...
llvm-svn: 99473
2010-03-25 02:00:02 +00:00
5d98824615
MC: Eliminate MC{Fragment,{Section,Symbol}Data}::getAddress.
...
llvm-svn: 99467
2010-03-25 01:03:24 +00:00
7c969558d9
MC: Direct all {fragment,section,symbol} address access through the MCAsmLayout object.
...
llvm-svn: 99380
2010-03-24 03:43:40 +00:00
5376c2a431
MC: Sprinkle in some more interesting statistics.
...
llvm-svn: 99350
2010-03-23 23:47:14 +00:00
de04b3f62c
MC: Switch to using MCInst fragments to do relaxation.
...
Also, both MCMachOStreamer and MCAssembler are now target independent!
llvm-svn: 99256
2010-03-23 05:09:03 +00:00
86face8333
MC: Add TargetAsmBackend::MayNeedRelaxation, for checking whether a particular instruction + fixups might need relaxation.
...
llvm-svn: 99249
2010-03-23 03:13:05 +00:00
a9ae3ae698
MC: Add TargetAsmBackend::WriteNopData and use to eliminate some target dependencies in MCMachOStreamer and MCAssembler.
...
llvm-svn: 99248
2010-03-23 02:36:58 +00:00
16cbe95dd6
MC: Tweak MCInstFragment to include the encoded data and fixups, so that we don't need to recompute them during relaxation. I will revisit this once all the other pieces of fast relaxation are in place.
...
llvm-svn: 99244
2010-03-23 01:39:05 +00:00
b31c49a70d
MC: Add MCInstFragment, not used yet.
...
llvm-svn: 99229
2010-03-22 23:16:48 +00:00
Daniel Dunbar