Commit Graph

25208 Commits

Author SHA1 Message Date
Dale Johannesen
585457e37e (re)Put const weak strings in appropriate section on Darwin.
g++dg/abi/key2.C



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57309 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-08 21:49:47 +00:00
Nuno Lopes
7a85a62f50 dont specialize weak functions and the like
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57305 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-08 18:45:59 +00:00
Jim Grosbach
309c80adb5 Comment to be explicit that the enumeration values for CondCodes matter.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57295 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-08 16:24:35 +00:00
Duncan Sands
43d9c8cd56 Use template to distinguish between function variants.
GCC 4.4.0 gives an error on the "int" declaration for example
saying that it has already been declared (using the "short"
one). Using templates here allow the compiler to distinguish
between the function to choose.

Also, "llvm/Support/DataTypes.h" was not included, leading to
error messages about not knowing "uint32_t" for example.

Patch by Samuel Tardieu.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57292 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-08 07:44:52 +00:00
Duncan Sands
4520dd2b7b Add <cstdio> include where needed by gcc-4.4.
Patch by Samuel Tardieu.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57291 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-08 07:23:46 +00:00
Chris Lattner
9fc4da40ef regenerate
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57290 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-08 06:44:45 +00:00
Chris Lattner
cd16843499 Add missing semicolumns in parser rules, those missing semicolumns
are required to compile with the latest Bison.

Patch by Samuel Tardieu!


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57289 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-08 06:44:36 +00:00
Chris Lattner
de17ddc65f Add parentheses to avoid warnings in GCC 4.4.0,
patch by Samuel Tardieu!



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57288 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-08 06:42:28 +00:00
Owen Anderson
04764deac8 Fix the case where an instruction is not properly marked as using all registers that alias its inputs.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57286 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-08 04:30:51 +00:00
Dan Gohman
eb0d6abee3 Remove -disable-fast-isel. Use cl::boolOrDefault with -fast-isel
instead.

So now: -fast-isel or -fast-isel=true enable fast-isel, and
-fast-isel=false disables it. Fast-isel is also on by default
with -fast, and off by default otherwise.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57270 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-07 23:00:56 +00:00
Dan Gohman
8c3f8b6dea Add MBB successors and physreg Uses in the same order that
SDISel typically adds them in. This makes it a little easier
to compare FastISel output with SDISel output.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57266 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-07 22:10:33 +00:00
Dan Gohman
1e9e8c3bd5 Avoid emitting redundant materializations of integer constants
for things like null pointers, which at this level aren't
different from regular integer constants.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57265 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-07 22:03:27 +00:00
Dan Gohman
145b828014 Instead of emitting an implicit use for the super-register of
X86::CL that was used, emit an EXTRACT_SUBREG from the CL
super-register to CL. This more precisely describes how the
CL register is being used.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57264 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-07 21:50:36 +00:00
Jim Grosbach
76e9661b6c Unconditional branch instruction encoding fix. Needs to use ABI, not AXI, to get the proper opcode bits.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57262 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-07 21:08:09 +00:00
Jim Grosbach
cbc47b8934 need ARM.h for ARMCC definition
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57261 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-07 21:01:51 +00:00
Owen Anderson
95dad830bb Add an option to enable StrongPHIElimination, for ease of testing.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57259 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-07 20:22:28 +00:00
Jim Grosbach
3341262de2 Encode the conditional execution predicate when JITing.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57258 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-07 19:05:35 +00:00
Dale Johannesen
2cb48eaeb8 Model hardwired inputs & outputs of x86 8-bit divides correctly.
Fixes local RA miscompilation of gcc.c-torture/execute/20020904-1.c -O0.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57257 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-07 18:54:28 +00:00
Andrew Lenharth
2163ca11d5 Use Dan's supperior check
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57255 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-07 18:27:23 +00:00
Andrew Lenharth
82cf32e5ef Correctly set attributes when removing args during cloning. Fixes PR2765
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57254 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-07 18:08:38 +00:00
Jim Grosbach
9e729a2de5 Clarify naming and correct conditional so that CMP and CMN instructions get the Rn operand encoded properly
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57252 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-07 17:42:09 +00:00
Jim Grosbach
17a415a4f2 Fix Opcode values of CMP and CMN
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57251 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-07 17:40:46 +00:00
Andrew Lenharth
ff75d9edbb No need for |=
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57249 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-07 17:11:29 +00:00
Andrew Lenharth
1ad0c8201b Use ADDC if it is valid at any smaller size. Do it right this time
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57248 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-07 17:09:16 +00:00
Andrew Lenharth
5c9cc1392c Use ADDC if it is valid at any smaller size. fixes test/Codegen/Generic/i128-addsub.ll on x86
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57247 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-07 17:03:15 +00:00
Anders Carlsson
ae436cecca Certain patterns involving the "movss" instruction were marked as requiring SSE2, when in reality movss is an SSE1 instruction.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57246 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-07 16:14:11 +00:00
Andrew Lenharth
40d513960a Expand arith on machines without carry flags
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57243 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-07 14:15:42 +00:00
Andrew Lenharth
1b19ef0295 Note that ADDC and company don't actually expand yet (missing in legalize
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57226 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-07 02:10:26 +00:00
Dale Johannesen
e4a4245906 Mark negative-zero-to-int conversion as Inexact,
since -0.0 can't be represented as an int.
This prevents llvm from reducing -0.0 to a
load-and-convert of int 0.  Fixes
ieee.exp/mzero[2356].c in gcc testsuite.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57224 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-07 00:40:01 +00:00
Dan Gohman
b5cc34d098 Correctly handle calls with no return values. This fixes
2006-01-23-UnionInit on x86-64 when inlining is not enabled.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57223 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-07 00:12:37 +00:00
Devang Patel
d44b7c1b07 Fix typo, fix PR 2865.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57221 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-06 23:22:54 +00:00
Dale Johannesen
2df5eec2ff Be more precise about which conversions of NaNs
are Inexact.  (These are not Inexact as defined
by IEEE754, but that seems like a reasonable way
to abstract what happens:  information is lost.)



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57218 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-06 22:59:10 +00:00
Evan Cheng
882cdfde51 Fix PR2850 and PR2863. Only generate movddup for 128-bit SSE vector shuffles.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57210 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-06 21:13:08 +00:00
Dale Johannesen
65609f2efa Temporarily revert functionality change from my previous patch;
it is too aggressive.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57203 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-06 20:43:48 +00:00
Devang Patel
617fddf51c Remove interfaces implemented by dead pass from the list of available passes.
Patch By Matthijs Kooijman.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57202 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-06 20:36:36 +00:00
Dale Johannesen
d3d8ce3aba Mark shortening NaN conversions as Inexact. PR 2856.
Improve description of unsupported formats.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57185 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-06 18:22:29 +00:00
Devang Patel
e76225a4c1 It is possible that all functions in one module are not being
optimized for size. Set OptForSize for each function separately.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57182 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-06 18:03:39 +00:00
Dan Gohman
4daa9071ed Don't dereference the end() iterator. Thanks to
ENABLE_EXPENSIVE_CHECKS for finding this.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57181 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-06 18:00:07 +00:00
Devang Patel
e4d4b8c533 Remove unncessary isDeclaration() checks.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57179 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-06 17:30:07 +00:00
Matthijs Kooijman
5fac55fafb Allow scalarrepl to treat an all-zero GEP just as bitcast.
This includes not marking a GEP involving a vector as unsafe, but only when it
has all zero indices. This allows scalarrepl to work in a few more cases.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57177 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-06 16:23:31 +00:00
Chris Lattner
d20a00d011 reorder #include order, patch by Kenneth Boyd!
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57148 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-06 03:54:25 +00:00
Chris Lattner
78129446ca Add #include to get alloca, patch by Kenneth Boyd!
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57147 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-06 03:53:16 +00:00
Chris Lattner
834eb40f44 fix an incorrect and extremely confusing error message
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57123 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-05 18:24:03 +00:00
Chris Lattner
9a6cb15980 make the autoupgrade code for ret attributes dramatically simpler
and actually work.  We can now read the llvm 2.3 bc file from PR2849



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57122 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-05 18:22:09 +00:00
Nuno Lopes
8a88a37b16 regenerate
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57114 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-05 16:49:34 +00:00
Nuno Lopes
d0ad67788d clean ArgTypeListI production: free the PATypeHolder
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57113 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-05 16:49:03 +00:00
Anton Korobeynikov
ff4ca2e088 Emit type-correct constant null. Also fix a typo.
Patch by Robert G. Jakabosky!

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57110 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-05 15:07:06 +00:00
Anton Korobeynikov
6381a1334a Fix weird think-o and unbreak build on all gcc-3.4.x-based platforms (e.g. mingw)
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57106 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-05 08:53:29 +00:00
Chris Lattner
b1ac769873 this case is matched now.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57096 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-05 02:16:12 +00:00
Chris Lattner
8c34cd287a rewrite bswap matching to be more general, allowing arbitrary
shifting and masking inside a bswap expr.  This allows it to handle
the cases from PR2842, which involve the intermediate 'or' 
expressions being shifted, not just the input value.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@57095 91177308-0d34-0410-b5e6-96231b3b80d8
2008-10-05 02:13:19 +00:00