maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
19,151 Commits 23 Branches 0 Tags 2.2 GiB
Commit Graph

19151 Commits

Author SHA1 Message Date
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
Andrew Lenharth a4a12983cc more complete Lowering for vacopy and vaarg 
llvm-svn: 22274
 2005-06-22 23:04:28 +00:00
Andrew Lenharth 253145299b If we support structs as va_list, we must pass pointers to them to va_copy 
See last commit for LangRef, this implements it on all targets.

llvm-svn: 22273
 2005-06-22 21:04:42 +00:00
Andrew Lenharth 5305ea5c86 SelectionDAG is very unhappy when the argument to an intrinsic is a struct 
llvm-svn: 22272
 2005-06-22 20:38:11 +00:00
Andrew Lenharth cf9008afea Make it easier to find alpha stuff in doxygen, and fixup labeling 
of memory instructions in the assembly, to allow later linking
of traces with LLVM Value*s.

llvm-svn: 22271
 2005-06-22 17:19:45 +00:00
John Criswell 9cb5a82cdc Fixed indentation. 
llvm-svn: 22270
 2005-06-20 19:59:22 +00:00
Andrew Lenharth d6bee05fc4 because some functions just use va_start and pass things to vfprintf 
llvm-svn: 22269
 2005-06-20 15:41:37 +00:00
Andrew Lenharth 5488847304 the correct fix was to fix AliasAnalysis.getModRefInfo 
llvm-svn: 22268
 2005-06-20 15:25:22 +00:00
Andrew Lenharth f42d7b54c0 make AliasAnalysis know that VAArg writes memory. This is extremely conservative and should be fixed 
llvm-svn: 22267
 2005-06-20 15:24:23 +00:00
Andrew Lenharth 805d84a077 prevent GCSE from forwarding stores to loads around vaarg. This is uggly, and I am trying to fix the AliasInfo, as it should catch the problem instead. 
llvm-svn: 22266
 2005-06-20 15:02:05 +00:00
Andrew Lenharth cf52eb2b99 prevent va_arg from being hoisted from a loop 
llvm-svn: 22265
 2005-06-20 13:36:33 +00:00
Andrew Lenharth 2929266127 fix DCE + va_arg problem 
llvm-svn: 22264
 2005-06-19 14:46:20 +00:00
Andrew Lenharth d4b103107e prevent DCE of vaarg intrinsics. This should take care of most regressions 
llvm-svn: 22263
 2005-06-19 14:41:20 +00:00
Andrew Lenharth 717f1610f0 va_end fix 
llvm-svn: 22262
 2005-06-19 14:04:55 +00:00