Commit Graph

19114 Commits

Author SHA1 Message Date
Chris Lattner d313b92b66 Varargs is apparently currently broken on PPC. This hacks it so that it
is at least overloading the right virtual methods.  The implementations
are currently wrong though.  This fixes Ptrdist/bc, but not other programs
(e.g. siod).

llvm-svn: 22326
2005-07-01 23:11:56 +00:00
Chris Lattner b97404687a Refactor X86AsmPrinter.cpp into multiple files. Patch contributed
by Aaron Gray, cleaned up by me.

llvm-svn: 22324
2005-07-01 22:44:09 +00:00
Andrew Lenharth 21da9b669e simplify call code, remove pseudo ops for div and rem, track more loads and stores
llvm-svn: 22323
2005-07-01 19:14:02 +00:00
Andrew Lenharth dd55b1566b simplify call code, remove pseudo ops for div and rem, track more loads and stores
llvm-svn: 22322
2005-07-01 19:12:13 +00:00
Chris Lattner e8ab64b5c3 remove some debugging code
llvm-svn: 22321
2005-07-01 06:40:58 +00:00
Andrew Lenharth 0a370f4de5 oops
llvm-svn: 22320
2005-06-30 19:32:57 +00:00
Andrew Lenharth b5597e38f6 FP EXTLOAD is not support on all archs, expand to LOAD and FP_EXTEND
llvm-svn: 22319
2005-06-30 19:22:37 +00:00
Chris Lattner 937c71f2b3 Fix PR590 and Transforms/Mem2Reg/2005-06-30-ReadBeforeWrite.ll.
The optimization for locally used allocas was not safe for allocas that
were read before they were written.  This change disables that optimization
in that case.

llvm-svn: 22318
2005-06-30 07:29:44 +00:00
Chris Lattner ba613f478a new testcase for PR590
llvm-svn: 22317
2005-06-30 07:28:54 +00:00
Nate Begeman 718387e491 Make the x86 asm printer darwin-aware. This mostly entails doing the same
thing as cygwin most of the time, and printing our alignments in log2
rather than number of bytes.

llvm-svn: 22316
2005-06-30 00:53:20 +00:00
Andrew Lenharth 2edc1881ac restore old srcValueNode behavior and try to to work around it
llvm-svn: 22315
2005-06-29 18:54:02 +00:00
Chris Lattner f550554c02 Don't crash on a query where the block is not in any loop. Thanks to
Sameer D. Sahasrabuddhe for pointing this out!

llvm-svn: 22314
2005-06-29 17:41:25 +00:00
John Criswell 51e2a48b35 Bug fixed.
llvm-svn: 22313
2005-06-29 16:22:34 +00:00
John Criswell 810b4f8d55 Doh! Forgot to LLVMify the style.
llvm-svn: 22312
2005-06-29 15:57:50 +00:00
Andrew Lenharth 8192568fbc tracking the instructions causing loads and stores provides more information than just the pointer being loaded or stored
llvm-svn: 22311
2005-06-29 15:57:19 +00:00
John Criswell 4642afdcc1 Basic fix for PR#591; don't convert an fprintf() to an fwrite() if there
is a mismatch in their character type pointers (i.e. fprintf() prints an
array of ubytes while fwrite() takes an array of sbytes).
We can probably do better than this (such as casting the ubyte to an
sbyte).

llvm-svn: 22310
2005-06-29 15:03:18 +00:00
Andrew Lenharth 4401049f05 thinko
llvm-svn: 22309
2005-06-29 13:35:05 +00:00
Andrew Lenharth d0a2f0f95a unify SelectExpr and SelectFP
llvm-svn: 22308
2005-06-29 12:49:51 +00:00
Andrew Lenharth d0f59dedf8 fix most regressions
llvm-svn: 22307
2005-06-29 12:23:34 +00:00
Andrew Lenharth 47a9c4715a support more relocations for stores also
llvm-svn: 22306
2005-06-29 00:39:17 +00:00
Andrew Lenharth 1ef3c0c798 Get rid of all symbolic loads. I now do gernate all relocations sequences
rather than relying on the assembler.  Only a few more pseudo instructions
left.  Also merge load code paths.

llvm-svn: 22305
2005-06-29 00:31:08 +00:00
Jeff Cohen 8d9d9d7af0 Add ElfWriter stuff to Visual Studio
llvm-svn: 22304
2005-06-28 02:43:03 +00:00
Andrew Lenharth 93bf000891 some call work
llvm-svn: 22303
2005-06-27 23:59:51 +00:00
Andrew Lenharth d74877a46d Adapt the code for handling uint -> fp conversion for the 32 bit case to
handling it in the 64 bit case.  The two code paths should probably be merged.

llvm-svn: 22302
2005-06-27 23:28:32 +00:00
Andrew Lenharth a50adcf57d So, it turns out I forgot that one valid way of restoring GP after a call
is to use RA, which assumes the called function uses RA for the register
holding the return address when it issues a ret.

llvm-svn: 22301
2005-06-27 23:24:11 +00:00
Nate Begeman db32921535 Initial set of .td file changes necessary to get scalar fp in xmm registers
working.  The instruction selector changes will hopefully be coming later
this week once they are debugged.  This is necessary to support the darwin
x86 FP model, and is recommended by intel as the replacement for x87.  As
a bonus, the register allocator knows how to deal with these registers
across basic blocks, unliky the FP stackifier.  This leads to significantly
better codegen in several cases.

llvm-svn: 22300
2005-06-27 21:20:31 +00:00
Andrew Lenharth 595646f934 get rid of another pseudo op
llvm-svn: 22299
2005-06-27 21:11:40 +00:00
Andrew Lenharth 1291a85883 generate address of constant pool entries
llvm-svn: 22298
2005-06-27 21:02:56 +00:00
Andrew Lenharth 02ffa5a7ed Misha happification patch
llvm-svn: 22297
2005-06-27 17:39:17 +00:00
Andrew Lenharth 7aba58ab89 Reduce use of pseudo ops
Namely, output the rellocation flags explicitly when loading constants.
Added benifit: save a load when loading from the constant pool.

llvm-svn: 22296
2005-06-27 17:15:36 +00:00
Andrew Lenharth fcb112eb7a missed a load
llvm-svn: 22295
2005-06-27 16:40:26 +00:00
Andrew Lenharth 96db51a3b6 make constant pool labels local
llvm-svn: 22294
2005-06-27 16:29:54 +00:00
Andrew Lenharth 53bb83bc43 who said we had to use the return address in the return address register. Might save a move in many cases
llvm-svn: 22293
2005-06-27 15:36:48 +00:00
Chris Lattner 10594206f4 Add support to the X86 backend for emitting ELF files. To use this, we
currently use: llc t.bc --filetype=obj

This will produce a t.o file which is dumpable with readelf.  Currently
the file produced is empty, but the scaffolding to do more is now in place.

llvm-svn: 22292
2005-06-27 06:30:12 +00:00
Chris Lattner 386b151ce6 iniital checkin of ELFWriter implementation
For now, the elf writer is only capable of emitting an empty elf file, with
a section table and a section table string table.  This will be enhanced
in the future :)

llvm-svn: 22291
2005-06-27 06:29:00 +00:00
Chris Lattner a1debbc634 iniital checkin of ELFWriter header.
For now, the elf writer is only capable of emitting an empty elf file, with
a section table and a section table string table.  This will be enhanced
in the future :)

llvm-svn: 22290
2005-06-27 06:28:45 +00:00
Andrew Lenharth dac0b3cb8a depend more on legalize putting constants on the RHS
llvm-svn: 22289
2005-06-26 23:01:11 +00:00
Andrew Lenharth 331380b2e2 With setOperationAction(ISD::UINT_TO_FP, MVT::i64, Expand), Legalize
should be able to handle this case.  The code is there, so let's see
if it works.

llvm-svn: 22288
2005-06-26 22:23:06 +00:00
Chris Lattner 06fcc4cb75 add a new -filetype argument to llc.
llvm-svn: 22287
2005-06-25 03:32:05 +00:00
Chris Lattner 4c661789c1 add some new file types
llvm-svn: 22286
2005-06-25 03:31:43 +00:00
Chris Lattner 09b0eb387a minor cleanups, use copy ctor instead of manually doing it.
llvm-svn: 22285
2005-06-25 03:00:34 +00:00
Chris Lattner 6a7b48e747 refactor this interface
llvm-svn: 22284
2005-06-25 02:50:35 +00:00
Chris Lattner f11f48ba61 Refactor the addPassesToEmitAssembly interface into a addPassesToEmitFile
interface.

llvm-svn: 22282
2005-06-25 02:48:37 +00:00
Chris Lattner f96366550c refactor these interfaces a bit
llvm-svn: 22281
2005-06-25 02:47:50 +00:00
Chris Lattner aad30b0dc9 improve comments
llvm-svn: 22280
2005-06-24 18:17:33 +00:00
Chris Lattner 805ecf0c79 Fix grammar
llvm-svn: 22279
2005-06-24 18:00:40 +00:00
Chris Lattner c0ad71edd4 add a note about variable length array
llvm-svn: 22278
2005-06-24 17:22:57 +00:00
Chris Lattner 9610c6f287 add a debug type
llvm-svn: 22277
2005-06-24 16:00:46 +00:00
Andrew Lenharth af1e825112 remove a pseudo instruction, make ret always right, and fix vararg chains
llvm-svn: 22276
2005-06-23 23:42:05 +00:00
Andrew Lenharth 01cebcc131 finally, Working varargs
llvm-svn: 22275
2005-06-23 16:48:51 +00:00