13a642da0b
Now that the profitable bits of EnableFullLoadPRE have been enabled by default, rip out the remainder.
...
Anyone interested in more general PRE would be better served by implementing it separately, to get real
anticipation calculation, etc.
llvm-svn: 115337
2010-10-01 20:02:55 +00:00
d3fe5fa5d1
Fix code gen crash reported in PR 8235. We still lose debug info for the unused argument here. This is a known limitation recorded debuginfo-tests/trunk/dbg-declare2.ll function 'f6' test case.
...
llvm-svn: 115323
2010-10-01 19:00:44 +00:00
a39904e6b9
We must check for something.
...
llvm-svn: 115309
2010-10-01 10:20:10 +00:00
0e5e4b7b76
Disable tests until I can figure out why they're failing on just two machines but not others.
...
llvm-svn: 115308
2010-10-01 10:01:10 +00:00
b3a1022572
Try adding an mtriple.
...
llvm-svn: 115307
2010-10-01 09:40:50 +00:00
56f7cd255b
Zap some redundant 'ori $?, $?, 0' from SPU.
...
Also remove some code that died in the process.
One now non-existant ori is checked for.
llvm-svn: 115306
2010-10-01 09:20:01 +00:00
3b2b1e7942
FileCheck-ize this test.
...
llvm-svn: 115304
2010-10-01 08:55:48 +00:00
9b6853c6eb
FileCheck-ize this test.
...
llvm-svn: 115303
2010-10-01 08:50:12 +00:00
c663a67384
fix PR8267 - Instcombine shouldn't optimizer away volatile memcpy's.
...
llvm-svn: 115296
2010-10-01 05:51:02 +00:00
98e82678bd
upgrade this test.
...
llvm-svn: 115295
2010-10-01 05:47:16 +00:00
a205055857
fix rdar://8494845 + PR8244 - a miscompile exposed by my patch in r101350
...
llvm-svn: 115294
2010-10-01 05:36:09 +00:00
f419de0852
One more +sse2.
...
llvm-svn: 115293
2010-10-01 05:08:18 +00:00
4ca7bb52d0
move X86 subdir up a level
...
llvm-svn: 115292
2010-10-01 04:32:20 +00:00
bb6b961867
Mark all these as needing SSE2. Should fix PPC and
...
maybe even Linux.
llvm-svn: 115291
2010-10-01 04:17:55 +00:00
ab60ae3cf3
Disable these tests for now; it's not obvious why they fail on Linux.
...
llvm-svn: 115257
2010-10-01 00:59:21 +00:00
c6f17f7420
Make test not sensitive to register choice.
...
llvm-svn: 115250
2010-10-01 00:16:17 +00:00
dd224d2333
Massive rewrite of MMX:
...
The x86_mmx type is used for MMX intrinsics, parameters and
return values where these use MMX registers, and is also
supported in load, store, and bitcast.
Only the above operations generate MMX instructions, and optimizations
do not operate on or produce MMX intrinsics.
MMX-sized vectors <2 x i32> etc. are lowered to XMM or split into
smaller pieces. Optimizations may occur on these forms and the
result casted back to x86_mmx, provided the result feeds into a
previous existing x86_mmx operation.
The point of all this is prevent optimizations from introducing
MMX operations, which is unsafe due to the EMMS problem.
llvm-svn: 115243
2010-09-30 23:57:10 +00:00
bb995ae261
test/CodeGen/X86/sibcall.ll: Add explicit triplets and remove XFAIL: apple-darwin8.
...
llvm-svn: 115215
2010-09-30 22:02:06 +00:00
3170a25a84
We do want to allow LoadPRE to perform LICM-like transformations: we already consider PHI nodes to be negligible for
...
code size (making this transform code size neutral), and it allows us to hoist values out of loops, which is always
a good thing.
llvm-svn: 115205
2010-09-30 20:53:04 +00:00
eb12f49fb7
Try again to disable critical edge splitting in CodeGenPrepare.
...
The bug that broke i386 linux has been fixed in r115191.
llvm-svn: 115204
2010-09-30 20:51:52 +00:00
f987d5ea1c
Factor some logic into ShouldRelocOnSymbol. This simplifies the code and
...
fixes some cases where we were producing relocations with at symbol that
should use a section instead.
llvm-svn: 115194
2010-09-30 20:18:35 +00:00
665aa6efcc
When isel is emitting instructions for an x86 target without CMOV, the CFG is
...
edited during emission.
If the basic block ends in a switch that gets lowered to a jump table, any
phis at the default edge were getting updated wrong. The jump table data
structure keeps a pointer to the header blocks that wasn't getting updated
after the MBB is split.
This bug was exposed on 32-bit Linux when disabling critical edge splitting in
codegen prepare.
The fix is to uipdate stale MBB pointers whenever a block is split during
emission.
llvm-svn: 115191
2010-09-30 19:44:31 +00:00
1dee57fb7d
more cleanups.
...
llvm-svn: 115178
2010-09-30 17:29:05 +00:00
288a5f9652
merge and clean up tests.
...
llvm-svn: 115177
2010-09-30 17:24:05 +00:00
60217e765e
merge two tests.
...
llvm-svn: 115175
2010-09-30 17:18:22 +00:00
41a0cd14b7
rename test
...
llvm-svn: 115174
2010-09-30 17:16:49 +00:00
ea226b24ff
generalize test.
...
llvm-svn: 115172
2010-09-30 17:15:42 +00:00
28307d1a1e
rename test.
...
llvm-svn: 115171
2010-09-30 17:14:55 +00:00
45a52f3c34
merge two tests.
...
llvm-svn: 115170
2010-09-30 17:14:30 +00:00
73a7caee4b
preemptively add the rest of the non-n fpstack instructions.
...
llvm-svn: 115168
2010-09-30 17:11:29 +00:00
28b3b43fb4
merge two tests.
...
llvm-svn: 115165
2010-09-30 17:05:37 +00:00
1e9e49f421
fix this to not be completely broken.
...
llvm-svn: 115164
2010-09-30 17:04:59 +00:00
c8f0e29b5e
update, unxfail, fix bogus encodings.
...
llvm-svn: 115163
2010-09-30 17:03:20 +00:00
a9e913e139
update and unxfail
...
llvm-svn: 115162
2010-09-30 17:00:53 +00:00
ccf2c765f0
unxfail this by fixing syntactic differences.
...
llvm-svn: 115161
2010-09-30 16:59:28 +00:00
4373badcdf
implement support for finit, PR8258
...
llvm-svn: 115156
2010-09-30 16:42:53 +00:00
adc0dbe470
add support for fstcw, PR8259
...
llvm-svn: 115154
2010-09-30 16:39:29 +00:00
efbdbe5565
Move logic of determining ELF entsize from the .s printer to initialization
...
time. That way, the EntrySize field is initialized for other code paths,
namely, the .ll -> .o code path.
llvm-svn: 115141
2010-09-30 05:59:22 +00:00
9d98ac645e
Add another test that now passes.
...
llvm-svn: 115137
2010-09-30 04:22:07 +00:00
70d6e0e0ff
Correctly produce R_X86_64_32 or R_X86_64_32S.
...
With this patch in
movq $foo, foo(%rip)
foo:
.long foo
We produce a R_X86_64_32S for the first relocation and R_X86_64_32 for the
second one.
llvm-svn: 115134
2010-09-30 03:11:42 +00:00
645f6c2bef
Tiny patch for proof-of-concept cleanup of ARMAsmPrinter::EmitStartOfAsmFile()
...
Small test for sanity check of resulting ARM .s file.
Tested against -r115129.
llvm-svn: 115133
2010-09-30 02:45:56 +00:00
b96b2d8e4d
Have ELFAsmParser.cpp use the already parsed "Size" (entry size) when
...
constructing a section. Test for a few cases also included.
llvm-svn: 115132
2010-09-30 02:41:46 +00:00
2ebaee9c75
Make it possible for the MCObjectWriter to decide if a given fixup is fully
...
resolved or not. Different object files have different restrictions and
different native assemblers have different idiosyncrasies we want to emulate
for now.
Move the existing MachO logic to the new place and implement an ELF one that
gets fixups to globals right.
llvm-svn: 115131
2010-09-30 02:22:20 +00:00
2b76c66fd6
Add constant folding for strspn and strcspn to SimplifyLibCalls.
...
llvm-svn: 115116
2010-09-30 00:58:35 +00:00
38d22f69fc
Add strpbrk folding to SimplifyLibCalls.
...
llvm-svn: 115111
2010-09-29 23:52:12 +00:00
8e861d7eee
Simplify the loop in StrChrOptimizer. FileCheckize test.
...
llvm-svn: 115095
2010-09-29 22:29:12 +00:00
824645abc9
Teach SimplifyLibCalls how to optimize strrchr.
...
llvm-svn: 115091
2010-09-29 21:50:51 +00:00
95ae73c394
Generalize DISubprogram element to encode various flags instead of just one boolean for isArtificial.
...
This is a backword compatible change.
llvm-svn: 115084
2010-09-29 21:04:46 +00:00
99c985c37d
Fix PR8247: JumpThreading can cause a block to become unreachable while still having predecessor, if it is part of a self-loop.
...
Because of this, we cannot use the Simplify* APIs, as they can assert-fail on unreachable code. Since it's not easy to determine
if a given threading will cause a block to become unreachable, simply defer simplifying simplification to later InstCombine and/or
DCE passes.
llvm-svn: 115082
2010-09-29 20:34:41 +00:00
0aea752f6d
Remove PointerTracking tests.
...
llvm-svn: 115072
2010-09-29 19:20:35 +00:00
2b43c1cf42
implement rdar://8491845 - Gas supports commuted forms of non-commutable instructions.
...
llvm-svn: 115061
2010-09-29 18:39:16 +00:00
97bf273870
Increase ARM APCS preferred alignment for i64 and f64 from 32 bits to 64 bits.
...
LDM/STM instructions can run one cycle faster on some ARM processors if the
memory address is 64-bit aligned. Radar 8489376.
llvm-svn: 115047
2010-09-29 17:54:10 +00:00
53f0bf194a
Move "local commons" to the end of .bss to match the gnu as behavior.
...
llvm-svn: 115037
2010-09-29 14:52:01 +00:00
68e05d404a
Add a test that I forgot to add with a previous commit.
...
llvm-svn: 115036
2010-09-29 14:40:49 +00:00
c2eb72dc2a
do not compare actual branch labels; this may fix llvm-gcc-x86_64-darwin10-cross-mingw32 buildbot too
...
llvm-svn: 115034
2010-09-29 10:45:43 +00:00
d36e3e8850
improve heuristics to find the 'and' corresponding to 'tst' to also catch opportunities on thumb2
...
added some doxygen on the way
llvm-svn: 115033
2010-09-29 10:12:08 +00:00
8f7851d2b4
fix rdar://8490728 - llvm-mc rejects gpr64 form of 'movmskpd'
...
llvm-svn: 115029
2010-09-29 05:05:03 +00:00
52e6020883
add assembler support for the cvtsd2sil/cvtsd2siq mnemonics, rdar://8456382
...
llvm-svn: 115027
2010-09-29 04:55:40 +00:00
822dc48c3a
MC-COFF: Fix test. IMAGE_SYM_CLASS_LABEL should never have been emitted.
...
llvm-svn: 115024
2010-09-29 03:59:25 +00:00
5da7f9fcfd
make the x86 mccode emitter emit the 0x67 and 0x66 prefix bytes in the same
...
order as cctools for diffability.
llvm-svn: 115022
2010-09-29 03:43:43 +00:00
a4e1c74947
implement support for 32-bit address operands in 64-bit mode, which
...
are defined to emit the 0x67 prefix byte. rdar://8482675
llvm-svn: 115021
2010-09-29 03:33:25 +00:00
f60062fd55
add basic avx support to the disassembler, also teach it about ssmem/sdmem
...
operands.
With this done, we can remove the _Int suffixes from the round instructions
without the disassembler blowing up. This allows the assembler to support
them, implementing rdar://8456376 - llvm-mc rejects 'roundss'
llvm-svn: 115019
2010-09-29 02:57:56 +00:00
ff3a3930a0
add asmparser support for cvttpd2dq by removing some Int_ prefixes.
...
Clean up cvttps2dq by removing some redundant implementations of the
same instruction. rdar://8456382
llvm-svn: 115018
2010-09-29 02:36:32 +00:00
ef1c2fc305
implement rdar://8456382 - cvtsd2si support, by removing some Int_ prefixes.
...
llvm-svn: 115017
2010-09-29 02:24:57 +00:00
a63292a3ca
implement rdar://8456378 and PR7557 - support for the fstsw,
...
an instruction that requires a WHOLE NEW wonderful kind of alias.
llvm-svn: 115015
2010-09-29 01:50:45 +00:00
cc91601211
And remove r114997's test.
...
llvm-svn: 115003
2010-09-28 23:24:18 +00:00
b0b2c57149
Revert r114997. It was causing a failure on darwin10-selfhost.
...
llvm-svn: 115002
2010-09-28 23:11:55 +00:00
d848beb1e5
Fix a FIXME. _foo.eh symbols are currently always exported so that the linker
...
knows about them. This is not necessary on 10.6 and later.
llvm-svn: 114997
2010-09-28 22:36:56 +00:00
a3181e2d79
Add a subtarget hook for reporting the misprediction penalty. Use this to provide more precise
...
cost modeling for if-conversion. Now if only we had a way to estimate the misprediction probability.
Adjsut CodeGen/ARM/ifcvt10.ll. The pipeline on Cortex-A8 is long enough that it is still profitable
to predicate an ldm, but the shorter pipeline on Cortex-A9 makes it unprofitable.
llvm-svn: 114995
2010-09-28 21:57:50 +00:00
81bdc93bbb
User proper libcall names & condcodes while compiling for ARM EABI.
...
Patch by Evzen Muller!
llvm-svn: 114991
2010-09-28 21:39:26 +00:00
88af7d00fc
Part one of switching to using a more sane heuristic for determining if-conversion profitability.
...
Rather than having arbitrary cutoffs, actually try to cost model the conversion.
For now, the constants are tuned to more or less match our existing behavior, but these will be
changed to reflect realistic values as this work proceeds.
llvm-svn: 114973
2010-09-28 18:32:13 +00:00
0ab27ea44f
Add target triple info to these tests to make the results comparable when
...
hosted on different platforms.
llvm-svn: 114965
2010-09-28 17:10:36 +00:00
01d20a76fe
On elf, undefined symbols can start with .L.
...
llvm-svn: 114958
2010-09-28 16:19:11 +00:00
3dc97324c1
Add a command line option "-arm-strict-align" to disallow unaligned memory
...
accesses for ARM targets that would otherwise allow it. Radar 8465431.
llvm-svn: 114941
2010-09-28 04:09:35 +00:00
96bfb50c03
Write relocations in the end of the file. This matches what gas does and
...
makes files easier to diff.
llvm-svn: 114898
2010-09-27 22:04:54 +00:00
9ca41113f6
Make sure .text doesn't produce extra alignment.
...
llvm-svn: 114895
2010-09-27 21:40:27 +00:00
1083573796
Don't try to constant fold libm functions with non-finite arguments.
...
Usually we wouldn't do this anyway because llvm_fenv_testexcept would return an
exception, but we have seen some cases where neither errno nor fenv detect an
exception on arm-linux.
llvm-svn: 114893
2010-09-27 21:29:20 +00:00
d116d8a4e9
MC/AsmParser: Handle exponents in floating point literals.
...
llvm-svn: 114861
2010-09-27 20:12:52 +00:00
415a7a6fec
Revert "Disable codegen prepare critical edge splitting. Machine instruction passes now"
...
This reverts revision 114633. It was breaking llvm-gcc-i386-linux-selfhost.
It seems there is a downstream bug that is exposed by
-cgp-critical-edge-splitting=0. When that bug is fixed, this patch can go back
in.
Note that the changes to tailcallfp2.ll are not reverted. They were good are
required.
llvm-svn: 114859
2010-09-27 18:43:48 +00:00
4f3443e74d
Explicitly disable CGP critical edge splitting for this test so it won't break
...
by reenabling it temporarily.
llvm-svn: 114858
2010-09-27 18:43:43 +00:00
f2a279b902
Don't depend on basic block numbering.
...
llvm-svn: 114857
2010-09-27 18:43:40 +00:00
d628377a2d
MC-COFF: Drop empty sections, and label symbols. Convert relocations
...
targeted at symbols into relocations relative to the containing section.
Patch by Nathan Jeffords!
llvm-svn: 114823
2010-09-27 08:58:26 +00:00
b6a7f97c88
yet more aliases.
...
llvm-svn: 114822
2010-09-27 07:24:57 +00:00
882626cd5b
add a couple more aliases, rdar://8456378
...
llvm-svn: 114821
2010-09-27 07:21:41 +00:00
972c60d821
fix rdar://8470918 - llvm-mc can't assemble smovl
...
llvm-svn: 114819
2010-09-27 07:11:53 +00:00
ff0062af62
Fix rdar://8468087 - llvm-mc commutes fmul (and friend) operands.
...
My previous fix for rdar://8456371 should only apply to fmulp/faddp,
not to fmul/fadd. Instruction set orthogonality is overrated or
something.
llvm-svn: 114818
2010-09-27 07:08:21 +00:00
9f06f911d1
the latest assembler that runs on powerpc 10.4 machines doesn't
...
support aligned comm. Detect when compiling for 10.4 and don't
emit an alignment for comm. THis will hopefully fix PR8198.
llvm-svn: 114817
2010-09-27 06:44:54 +00:00
4f59cbfb66
implement support for 'clr' alias. This is part of rdar://8416805,
...
but balrog was wanting it on irc.
llvm-svn: 114809
2010-09-27 04:23:03 +00:00
d6142976de
Add test case for PTX ret instruction
...
llvm-svn: 114789
2010-09-25 07:49:54 +00:00
299479020a
Add ret instruction to PTX backend
...
llvm-svn: 114788
2010-09-25 07:46:17 +00:00
75d65b9a03
Move ELF to HasReliableSymbolDifference=true. Also take the opportunity to put
...
symbols defined in merge sections in independent atoms.
llvm-svn: 114786
2010-09-25 05:42:19 +00:00
b590a927cd
LoadPRE was not properly checking that the load it was PRE'ing post-dominated the block it was being hoisted to.
...
Splitting critical edges at the merge point only addressed part of the issue; it is also possible for non-post-domination
to occur when the path from the load to the merge has branches in it. Unfortunately, full anticipation analysis is
time-consuming, so for now approximate it. This is strictly more conservative than real anticipation, so we will miss
some cases that real PRE would allow, but we also no longer insert loads into paths where they didn't exist before. :-)
This is a very slight net positive on SPEC for me (0.5% on average). Most of the benchmarks are largely unaffected, but
when it pays off it pays off decently: 181.mcf improves by 4.5% on my machine.
llvm-svn: 114785
2010-09-25 05:26:18 +00:00
cf1f985838
Reapply 114678 and 114667. Reverting them did not fix the bot:
...
http://google1.osuosl.org:8011/builders/llvm-gcc-i386-linux-selfhost/builds/69
llvm-svn: 114761
2010-09-24 21:19:03 +00:00
9d06adcf88
Be more precise when trying to XFAIL this tester: http://google1.osuosl.org:8011/builders/llvm-arm-linux
...
llvm-svn: 114755
2010-09-24 20:34:49 +00:00
dbcc4b4d4d
Enable code placement optimization pass for ARM.
...
llvm-svn: 114746
2010-09-24 19:07:23 +00:00
3843bb9d2c
Revert 114678 and 114667 to see if
...
http://google1.osuosl.org:8011/builders/llvm-gcc-i386-linux-selfhost
gets happy.
llvm-svn: 114742
2010-09-24 18:48:08 +00:00
ce17f72c38
MC/AsmParser: Handle a missed case of floating literals in the lexer.
...
llvm-svn: 114733
2010-09-24 17:10:26 +00:00
10d274d874
CMake: Build unittests.
...
llvm-svn: 114725
2010-09-24 09:01:13 +00:00
1444f47deb
Fix whitespace.
...
llvm-svn: 114724
2010-09-24 09:00:56 +00:00
2af1653032
MC/AsmParser: Support .single and .double for embedding floating point literals.
...
- I believe more modern 'gas' supports a more enhanced set of arithmetic on
them, but for now the only thing we can do is emit them as data.
llvm-svn: 114719
2010-09-24 01:59:56 +00:00
Owen Anderson