maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
77,968 Commits 23 Branches 0 Tags 2.2 GiB
Commit Graph

57134 Commits

Author SHA1 Message Date
Daniel Dunbar 692d06fb77 MC: Fix bug where trailing tied operands were forgotten; the X86 assembler 
matcher is now free of implicit operands!
 - Still need to clean up the code now that we don't to worry about implicit
   operands, and to make it a hard error if an instruction fails to specify all
   of its operands for some reason.

llvm-svn: 95956
 2010-02-12 01:46:54 +00:00
Johnny Chen 905a2d7727 Added coprocessor Instructions CDP, CDP2, MCR, MCR2, MRC, MRC2, MCRR, MCRR2, 
MRRC, MRRc2.  For disassembly only.

llvm-svn: 95955
 2010-02-12 01:44:23 +00:00
Bob Wilson 0827e040e0 Add a new pass on machine instructions to optimize away PHI cycles that 
reduce down to a single value.  InstCombine already does this transformation
but DAG legalization may introduce new opportunities.  This has turned out to
be important for ARM where 64-bit values are split up during type legalization:
InstCombine is not able to remove the PHI cycles on the 64-bit values but
the separate 32-bit values can be optimized.  I measured the compile time 
impact of this (running llc on 176.gcc) and it was not significant.

llvm-svn: 95951
 2010-02-12 01:30:21 +00:00
Daniel Dunbar d7e9212e2d X86: Fix definition for RCL/RCR.*m? operations -- they were getting represented 
with "tied memory operands", which is wrong.

llvm-svn: 95950
 2010-02-12 01:22:03 +00:00
Chris Lattner 336f9abb45 add another bit of space for new kinds of instruction prefixes. 
llvm-svn: 95949
 2010-02-12 01:15:16 +00:00
Nate Begeman c780af6471 Add a missing pattern for movhps so that we get: 
movq	(%ecx,%edx,2), %xmm2
movhps	(%ecx,%eax,2), %xmm2

rather than:

movq     (%eax, %edx, 2), %xmm2		
movq     (%eax, %ebx, 2), %xmm3		
movlhps  %xmm3, %xmm2			

Testcase forthcoming.

llvm-svn: 95948
 2010-02-12 01:10:45 +00:00
Chris Lattner 1572e760bc fix the encodings of monitor and mwait, which were completely 
busted in both encoders.  I'm not bothering to fix it in the
old one at this point.

llvm-svn: 95947
 2010-02-12 01:06:22 +00:00
Chris Lattner 62f50dad8d improve support for minix, PR6280, patch by 
Kees van Reeuwijk!

llvm-svn: 95946
 2010-02-12 00:37:46 +00:00
Charles Davis be5557e86b Add a new function attribute, 'alignstack'. It will indicate (when the backends 
implement support for it) that the stack should be forcibly realigned in the
prologue (and the process reversed in the epilogue).

llvm-svn: 95945
 2010-02-12 00:31:15 +00:00
Jakob Stoklund Olesen 93c92225af Reapply coalescer fix for better cross-class coalescing. 
This time with fixed test cases.

llvm-svn: 95938
 2010-02-11 23:55:29 +00:00
Chris Lattner b1913c4df9 enhance llvm-mc -show-inst to print the enum of an instruction, like so: 
testb	%al, %al                ## <MCInst #2412 TEST8rr
                                        ##   <MCOperand Reg:2>
                                        ##   <MCOperand Reg:2>>
	jne	LBB1_7                  ## <MCInst #938 JNE_1
                                        ##   <MCOperand Expr:(LBB1_7)>>

llvm-svn: 95935
 2010-02-11 22:57:32 +00:00
Chris Lattner 524138176d add a new MCInstPrinter::getOpcodeName interface, when it is 
implemented, llvm-mc --show-inst now uses it to print the
instruction opcode as well as the number.

llvm-svn: 95929
 2010-02-11 22:39:10 +00:00
Anton Korobeynikov 9e8baa5c17 Document binutils requirements for coff targets (cygwin / mingw32). 
llvm-svn: 95928
 2010-02-11 21:51:51 +00:00
Chris Lattner b8af65ed0b improve encoding information for branches. We now know they have 
8 or 32-bit immediates, which allows the new encoder to handle
them.

llvm-svn: 95927
 2010-02-11 21:45:31 +00:00
Daniel Dunbar 1d34759721 MC: Move assembler-backend's fixup list into the fragment. 
llvm-svn: 95926
 2010-02-11 21:29:46 +00:00
Daniel Dunbar ee82e763e6 MC: Move MCSectionData::Fixup out to MCAsmFixup. 
llvm-svn: 95925
 2010-02-11 21:29:29 +00:00
Chris Lattner ddeceae839 make getFixupKindInfo return a const reference, allowing 
the tables to be const.  Teach MCCodeEmitter to handle
the target-indep kinds so that we don't crash on them.

llvm-svn: 95924
 2010-02-11 21:27:18 +00:00
Jakob Stoklund Olesen 0d642824d6 Revert functional change. This broke a bunch of tests. 
llvm-svn: 95921
 2010-02-11 21:19:44 +00:00
Chris Lattner 2a34015abc switch to target-indep fixups for 1/2/4/8 byte data. 
llvm-svn: 95920
 2010-02-11 21:17:54 +00:00
Devang Patel c07f1f4f7b revert 95903. 
llvm-svn: 95918
 2010-02-11 20:58:56 +00:00
Jakob Stoklund Olesen 28139f0043 It is always good to do a cross-class join when the large register has a tiny interval. 
Also avoid division by zero.

llvm-svn: 95917
 2010-02-11 20:58:45 +00:00
Johnny Chen af88c0a84d Added LDRT/LDRBT/STRT/STRBT for disassembly only. 
llvm-svn: 95916
 2010-02-11 20:31:08 +00:00
Chris Lattner 1f298326b0 unbreak the build. 
llvm-svn: 95915
 2010-02-11 19:52:11 +00:00
Dan Gohman f34f55b873 llvm-db was removed. 
llvm-svn: 95904
 2010-02-11 19:35:26 +00:00
Devang Patel 11ddc679ca Destroy MDNodes while destructing llvm context. 
llvm-svn: 95903
 2010-02-11 19:35:10 +00:00
Chris Lattner e140686d9f refactor x86 conditional branches to use a multipattern 
that generates the 1-byte and 4-byte immediate versions
from one definition.

llvm-svn: 95902
 2010-02-11 19:31:22 +00:00
Chris Lattner 2b0a7a2592 refactor the conditional jump instructions in the .td file to 
use a multipattern that generates both the 1-byte and 4-byte 
versions from the same defm

llvm-svn: 95901
 2010-02-11 19:25:55 +00:00
Jeffrey Yasskin 8a30324e51 Make Kaleidoscope not link against the interpreter, since that didn't 
work anyway (Interpreter::getPointerToFunction doesn't return a
callable pointer), and improve the error message when an
ExecutionEngine can't be created.

llvm-svn: 95896
 2010-02-11 19:15:20 +00:00
Johnny Chen 3964059a16 Forgot to also check in this file for vcvt (floating-point <-> fixed-point, VFP). 
Sorry!

llvm-svn: 95892
 2010-02-11 18:47:03 +00:00
Dale Johannesen 177ced3953 Allow for more than one DBG_VALUE targeting the 
same dead instruction.

llvm-svn: 95890
 2010-02-11 18:23:23 +00:00
Dale Johannesen 12565de705 Don't allow DBG_VALUE to affect codegen. 
llvm-svn: 95889
 2010-02-11 18:22:31 +00:00
Johnny Chen 2588efd071 Added VCVT (between floating-point and fixed-point, VFP) for disassembly. 
A8.6.297

llvm-svn: 95885
 2010-02-11 18:17:16 +00:00
Johnny Chen f40b8e03fb Added BKPT/tBKPT (breakpoint) to the instruction table for disassembly purpose. 
llvm-svn: 95884
 2010-02-11 18:12:29 +00:00
Jakob Stoklund Olesen 45396438c3 Use array_pod_sort instead of std::sort for improved code size. 
Use SmallVector instead of std::vector for better speed when indirectbr has
few successors.

llvm-svn: 95879
 2010-02-11 18:06:56 +00:00
Eric Christopher cccdc13662 Make sure that ConstantExpr offsets also aren't off of extern 
symbols.

Thanks to Duncan Sands for the testcase!

llvm-svn: 95877
 2010-02-11 17:44:04 +00:00
Johnny Chen 9c13dfb5dd Add pseudo instruction TRAP for disassembly, which is encoded according to A5-21 
as the "Permanently UNDEFINED" instruction.

llvm-svn: 95873
 2010-02-11 17:14:31 +00:00
Bill Wendling 243e1f21db Use .empty() instead of .size(). 
llvm-svn: 95871
 2010-02-11 10:37:57 +00:00
Chris Lattner fbf1f02fee dont' call getX86RegNum on X86::RIP, it doesn't like that. This 
fixes the remaining x86-64 jit failures afaik.

llvm-svn: 95867
 2010-02-11 08:45:56 +00:00
Chris Lattner 5a4ec879bf fix a really nasty bug I introduced in r95693: r12 (and r12d, 
r12b, etc) also encodes to a R/M value of 4, which is just
as illegal as ESP/RSP for the non-sib version an address.

This fixes x86-64 jit miscompilations of a bunch of programs.

llvm-svn: 95866
 2010-02-11 08:41:21 +00:00
Jeffrey Yasskin 00ea4a36d6 Fix (harmless) memory leak found by memcheck. 
llvm-svn: 95862
 2010-02-11 07:16:13 +00:00
Chris Lattner 6bb2463f85 Add and commonize encoder support for all immediates. 
Stub out some dummy fixups to make things work.

We can now emit fixups like this:
	subl	$20, %esp               ## encoding: [0x83,0xec,A]
                                        ##   fixup A - offset: 2, value: 20, kind: fixup_1byte_imm

Emitting $20 as a single-byte fixup to be later resolved
by the assembler is ridiculous of course (vs just emitting
the byte) but this is a failure of the matcher, which 
should be producing an imm of 20, not an MCExpr of 20.

llvm-svn: 95860
 2010-02-11 07:06:31 +00:00
Chris Lattner 167842f90b generalize EmitDisplacementField to work with any size 
and rename it to EmitImmediate.

llvm-svn: 95859
 2010-02-11 06:54:23 +00:00
Chris Lattner 3555993312 eliminate the dead IsPCRel argument. 
llvm-svn: 95858
 2010-02-11 06:51:36 +00:00
Chris Lattner 5a40e6c95c eliminate the dead "PCAdj" logic. 
llvm-svn: 95857
 2010-02-11 06:49:52 +00:00
Jeffrey Yasskin c660b23075 Fix some of the memcheck errors found in the JIT unittests. 
llvm-svn: 95856
 2010-02-11 06:41:30 +00:00
Chris Lattner 4e8137d678 Rename ValueRequiresCast to ShouldOptimizeCast, to better reflect 
what it does.  Enhance it to return false to optimizing vector
sign extensions from vector comparisions, which is the idiom used
to get a splatted vector for a vector comparison.

Doing this breaks vector-casts.ll, add some compensating 
transformations to handle the important case they cover without
depending on this canonicalization.

This fixes rdar://7434900 a serious pessimization of vector compares.

llvm-svn: 95855
 2010-02-11 06:26:33 +00:00
Chris Lattner 1d4eb8fac4 convert to filecheck. 
llvm-svn: 95854
 2010-02-11 06:24:37 +00:00
Chris Lattner c053cbbc4d Make DSE only scan blocks that are reachable from the entry 
block.  Other blocks may have pointer cycles that will crash
basicaa and other alias analyses.  In any case, there is no
point wasting cycles optimizing dead blocks.  This fixes 
rdar://7635088

llvm-svn: 95852
 2010-02-11 05:11:54 +00:00
Chris Lattner f492ece81e a testcase that doesn't crash GVN but could someday. 
llvm-svn: 95851
 2010-02-11 05:08:05 +00:00
Chris Lattner d924f63692 Make jump threading honor x|undef -> true and x&undef -> false, 
instead of considering x|undef -> x, which may not be true.

llvm-svn: 95850
 2010-02-11 04:40:44 +00:00