1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-10-29 23:12:55 +01:00
Commit Graph

1621 Commits

Author SHA1 Message Date
Nate Begeman
0be60963bd Fix some of the stuff in the PPC README file, and clean up legalization
of the SELECT_CC, BR_CC, and BRTWOWAY_CC nodes.

llvm-svn: 25875
2006-02-01 07:19:44 +00:00
Chris Lattner
d2fb7bf108 add a note, I'll take care of this after nate commits his big patch
llvm-svn: 25873
2006-02-01 06:40:32 +00:00
Evan Cheng
ef93bdc0cf - Use xor to clear integer registers (set R, 0).
- Added a new format for instructions where the source register is implied
  and it is same as the destination register. Used for pseudo instructions
  that clear the destination register.

llvm-svn: 25872
2006-02-01 06:13:50 +00:00
Evan Cheng
6523b2de76 Remove another entry.
llvm-svn: 25871
2006-02-01 06:08:48 +00:00
Chris Lattner
0e7d439232 Another regression from the pattern isel
llvm-svn: 25867
2006-02-01 01:44:25 +00:00
Evan Cheng
27738f635e Return's chain should be matching either the chain produced by the
value or the chain going into the load.

llvm-svn: 25863
2006-02-01 01:19:32 +00:00
Evan Cheng
329e86ddfa When folding a load into a return of SSE value, check the chain to
ensure the memory location has not been clobbered.

llvm-svn: 25861
2006-02-01 00:20:21 +00:00
Evan Cheng
19b80eebb2 Remove an item. It's done.
llvm-svn: 25860
2006-02-01 00:15:53 +00:00
Evan Cheng
7eb36f4721 Be smarter about whether to store the SSE return value in memory. If
it is already available in memory, do a fld directly from there.

llvm-svn: 25859
2006-01-31 23:19:54 +00:00
Chris Lattner
bb410d0b63 turning these into 'adds' would require extra copies
llvm-svn: 25858
2006-01-31 22:59:46 +00:00
Evan Cheng
45ebd632f2 - Allow XMM load (for scalar use) to be folded into ANDP* and XORP*.
- Use XORP* to implement fneg.

llvm-svn: 25857
2006-01-31 22:28:30 +00:00
Evan Cheng
6d9aae44f9 Remove entries on fabs and fneg. These are done.
llvm-svn: 25856
2006-01-31 22:26:21 +00:00
Chris Lattner
5587b270e4 * Fix 80-column violations
* Rename hasSSE -> hasSSE1 to avoid my continual confusion with 'has any SSE'.
* Add inline asm constraint specification.

llvm-svn: 25854
2006-01-31 19:43:35 +00:00
Evan Cheng
49467b6b5b Added custom lowering of fabs
llvm-svn: 25831
2006-01-31 03:14:29 +00:00
Chris Lattner
9b89cad951 Another high-prio selection performance bug
llvm-svn: 25828
2006-01-31 02:10:06 +00:00
Chris Lattner
899754747c more mumbling
llvm-svn: 25826
2006-01-31 00:45:37 +00:00
Chris Lattner
76a85bd047 add some notes
llvm-svn: 25825
2006-01-31 00:20:38 +00:00
Evan Cheng
38aacb5f09 Don't generate complex sequence for SETOLE, SETOLT, SETULT, and SETUGT. Flip
the order of the compare operands and generate SETOGT, SETOGE, SETUGE, and
SETULE instead.

llvm-svn: 25824
2006-01-30 23:41:35 +00:00
Evan Cheng
8ea651a9a4 i64 -> f32, f32 -> i64 and some clean up.
llvm-svn: 25818
2006-01-30 22:13:22 +00:00
Evan Cheng
d2d96373dc Always use FP stack instructions to perform i64 to f64 as well as f64 to i64
conversions. SSE does not have instructions to handle these tasks.

llvm-svn: 25817
2006-01-30 08:02:57 +00:00
Chris Lattner
a44182300b Move MaskedValueIsZero from the DAGCombiner to the TargetLowering interface,making isMaskedValueZeroForTargetNode simpler, and useable from other partsof the compiler.
llvm-svn: 25803
2006-01-30 04:09:27 +00:00
Chris Lattner
754bc1f46c adjust prototype
llvm-svn: 25798
2006-01-30 03:49:07 +00:00
Chris Lattner
9bb580ac23 add another note
llvm-svn: 25789
2006-01-29 09:46:06 +00:00
Chris Lattner
7ec490d6d6 add some performance notes from looking at sgefa
llvm-svn: 25788
2006-01-29 09:42:20 +00:00
Chris Lattner
7a775bff1e add a high-priority SSE issue from sgefa
llvm-svn: 25787
2006-01-29 09:14:47 +00:00
Chris Lattner
7048df99cd add a missed optimization
llvm-svn: 25786
2006-01-29 09:08:15 +00:00
Reid Spencer
2669d4cb81 Add a note about lowering llvm.memset, llvm.memcpy, and llvm.memmove to a
few stores under certain conditions.

llvm-svn: 25777
2006-01-29 06:48:25 +00:00
Chris Lattner
73262d78b8 remove now-dead code, the legalizer takes care of this for us
llvm-svn: 25776
2006-01-29 06:45:31 +00:00
Chris Lattner
b66484069a The FP stack doesn't support UNDEF, ask the legalizer to legalize it
instead of lying and saying we have it.

llvm-svn: 25775
2006-01-29 06:44:22 +00:00
Chris Lattner
5f0a3df176 Targets all now request ConstantFP to be legalized into TargetConstantFP.
'fpimm' in .td files is now TargetConstantFP.

llvm-svn: 25771
2006-01-29 06:26:08 +00:00
Jeff Cohen
28a7bd94c9 Fix typo.
llvm-svn: 25760
2006-01-29 03:45:35 +00:00
Jeff Cohen
3ef56b005a Flesh out AMD family/models.
llvm-svn: 25755
2006-01-28 20:30:18 +00:00
Jeff Cohen
08656fa2a6 Correctly determine CPU vendor.
llvm-svn: 25754
2006-01-28 19:48:34 +00:00
Jeff Cohen
057816014c Use union instead of reinterpret_cast.
llvm-svn: 25751
2006-01-28 18:47:32 +00:00
Jeff Cohen
6d330738c1 Fix recognition of Intel CPUs.
llvm-svn: 25750
2006-01-28 18:38:20 +00:00
Chris Lattner
e5bf55bf7b Is64Bit reflects the capability of the chip, not an aspect of the target os
llvm-svn: 25749
2006-01-28 18:23:48 +00:00
Chris Lattner
0256ca3257 Fix a bunch of JIT failures with the new isel
llvm-svn: 25748
2006-01-28 18:19:37 +00:00
Jeff Cohen
4d971bdfa7 Improve X86 subtarget support for Windows and AMD.
llvm-svn: 25747
2006-01-28 18:09:06 +00:00
Chris Lattner
744d9a40f0 silence a warning
llvm-svn: 25745
2006-01-28 10:34:47 +00:00
Chris Lattner
686a1203f0 make this work on non-native hosts
llvm-svn: 25734
2006-01-28 06:05:41 +00:00
Evan Cheng
442713efd7 A bit of wisdom from Chris on the last entry.
llvm-svn: 25715
2006-01-27 22:54:32 +00:00
Evan Cheng
03aaa82992 AT&T assembly convention: registers are in lower case.
llvm-svn: 25714
2006-01-27 22:53:29 +00:00
Chris Lattner
35d325e8aa initialize all instance vars
llvm-svn: 25711
2006-01-27 22:37:09 +00:00
Evan Cheng
51c1d32061 Added notes about a x86 isel deficiency.
llvm-svn: 25706
2006-01-27 22:11:01 +00:00
Evan Cheng
5c1d0d40dc Added a temporary option -enable-x86-sse to enable sse support. It is used by
llc-beta.

llvm-svn: 25701
2006-01-27 21:49:34 +00:00
Evan Cheng
746086dc97 Bye bye Pattern ISel, hello DAG ISel.
llvm-svn: 25700
2006-01-27 21:26:54 +00:00
Nate Begeman
d2c6fbef4a Remove TLI.LowerReturnTo, and just let targets custom lower ISD::RET for
the same functionality.  This addresses another piece of bug 680.  Next,
on to fixing Alpha VAARG, which I broke last time.

llvm-svn: 25696
2006-01-27 21:09:22 +00:00
Evan Cheng
577ea086c4 A better workaround
llvm-svn: 25692
2006-01-27 19:30:30 +00:00
Chris Lattner
932260bb64 force sse/3dnow off until they work. This fixes all the x86 failures last night
llvm-svn: 25690
2006-01-27 18:30:50 +00:00
Chris Lattner
e1f4b9e384 Unbreak the JIT with SSE
llvm-svn: 25688
2006-01-27 18:27:18 +00:00
Evan Cheng
5891f49c47 x86 CPU detection and proper subtarget support
llvm-svn: 25679
2006-01-27 08:10:46 +00:00
Chris Lattner
20d4194a0d PHI and INLINEASM are now built-in instructions provided by Target.td
llvm-svn: 25674
2006-01-27 01:46:15 +00:00
Jeff Cohen
f329a41a66 Improve compatibility with VC2005, patch by Morten Ofstad!
llvm-svn: 25661
2006-01-26 20:41:32 +00:00
Chris Lattner
bfd5404cbf Improve compatibility with VC2005, patch by Morten Ofstad!
llvm-svn: 25653
2006-01-26 19:55:20 +00:00
Evan Cheng
670dc80530 Added preliminary x86 subtarget support.
llvm-svn: 25645
2006-01-26 09:53:06 +00:00
Evan Cheng
7a77e3f80c Work around some x86 Darwin assembler bugs
llvm-svn: 25638
2006-01-26 02:27:43 +00:00
Evan Cheng
bf29b90240 When trying to fold X86::SETCC into a Select, make a copy if it has more than
one use. This allows more CMOV instructions.

llvm-svn: 25634
2006-01-26 02:13:10 +00:00
Evan Cheng
224e14daa1 Remove the uses of STATUS flag register. Rely on node property SDNPInFlag,
SDNPOutFlag, and SDNPOptInFlag instead.

llvm-svn: 25629
2006-01-26 00:29:36 +00:00
Nate Begeman
c29fac7fce First part of bug 680:
Remove TLI.LowerVA* and replace it with SDNodes that are lowered the same
way as everything else.

llvm-svn: 25606
2006-01-25 18:21:52 +00:00
Evan Cheng
46f85ddd84 X86 prefer scheduling for reduced register pressure.
llvm-svn: 25602
2006-01-25 09:15:17 +00:00
Evan Cheng
b463e81b83 Fix a selectcc lowering bug. Make a copy of X86ISD::CMP when folding it.
llvm-svn: 25596
2006-01-25 09:05:09 +00:00
Chris Lattner
8ddb0c3df8 Loosen up these checks to allow direct uses of ESP
llvm-svn: 25595
2006-01-25 08:00:36 +00:00
Chris Lattner
f2a2d62f48 use ESP directly, not a copy of ESP into some other register for fastcc calls
llvm-svn: 25584
2006-01-24 06:14:44 +00:00
Chris Lattner
c078165ea6 Emit the copies out of call return registers *after* the ISD::CALLSEQ_END
node, fixing fastcc and the case where a function has a frame pointer due
to dynamic allocas.

llvm-svn: 25580
2006-01-24 05:17:12 +00:00
Chris Lattner
2873307819 Allow jit-beta to work
llvm-svn: 25578
2006-01-24 04:50:48 +00:00
Chris Lattner
aafc339b4e Add explicit #includes of <iostream>
llvm-svn: 25515
2006-01-22 23:41:00 +00:00
Evan Cheng
2e4479d4a8 Rename fcmovae to fcmovnb and fcmova to fcmovnbe (following Intel manual).
Some assemblers can't recognize the aliases.

llvm-svn: 25494
2006-01-21 02:55:41 +00:00
Chris Lattner
eacfe56de8 LowerReturn now doesn't have to handle f32 returns.
llvm-svn: 25484
2006-01-20 18:41:25 +00:00
Evan Cheng
ffbc93d829 Stop doing that accidental commit.
llvm-svn: 25474
2006-01-20 01:14:05 +00:00
Evan Cheng
2b24240110 A few more SH{L|R}D peepholes.
llvm-svn: 25473
2006-01-20 01:13:30 +00:00
Evan Cheng
d2c0ccedd3 Didn't mean to commit the last one.
llvm-svn: 25469
2006-01-19 23:27:08 +00:00
Evan Cheng
e0f6454c5e Added i16 SH{L|R}D patterns.
llvm-svn: 25468
2006-01-19 23:26:24 +00:00
Evan Cheng
680a8e070b Avoid generating a redundant setcc.
llvm-svn: 25457
2006-01-19 08:52:46 +00:00
Evan Cheng
cfe9d47379 adc and sbb need an incoming flag to ensure it reads the carry flag
from add / sub.

llvm-svn: 25444
2006-01-19 06:53:20 +00:00
Evan Cheng
be2cf5f948 Two peepholes:
(or (x >> c) | (y << (32 - c))) ==> (shrd x, y, c)
(or (x << c) | (y >> (32 - c))) ==> (shld x, y, c)

llvm-svn: 25438
2006-01-19 01:56:29 +00:00
Evan Cheng
ddb170b73e Didn't mean to check that in.
llvm-svn: 25436
2006-01-19 01:52:56 +00:00
Evan Cheng
aebece2f7b A obvious typo
llvm-svn: 25435
2006-01-19 01:46:14 +00:00
Evan Cheng
92c122b26f SRA shift amount must be in i8
llvm-svn: 25416
2006-01-18 09:26:46 +00:00
Evan Cheng
4d841aaa98 If a call return type is i1, insert a truncate from X86::AL to i1.
llvm-svn: 25415
2006-01-18 08:08:38 +00:00
Evan Cheng
208f5076a0 Fix lowering of calls which return f32 values.
llvm-svn: 25413
2006-01-17 21:58:21 +00:00
Evan Cheng
1e112de44a Zero extending load from i1 to i8.
llvm-svn: 25391
2006-01-17 07:02:46 +00:00
Evan Cheng
759a96e1a3 SSE does not support i64 SINT_TO_FP (FP stack doesn't either, but we custom
expand it), so ask legalizer to expand i32 UINT_TO_FP.

llvm-svn: 25386
2006-01-17 02:32:49 +00:00
Evan Cheng
53520a8cee Added a FIXME comment about why FST is currently flagged to fpGETRESULT.
llvm-svn: 25381
2006-01-17 00:37:42 +00:00
Evan Cheng
3ce28c990a Bug fixes: fpGETRESULT should produces a flag result and X86ISD::FST should
read a flag.

llvm-svn: 25378
2006-01-17 00:19:47 +00:00
Evan Cheng
e678b39014 More typo's
llvm-svn: 25375
2006-01-16 23:26:53 +00:00
Evan Cheng
f7c719fe10 Some typo's
llvm-svn: 25374
2006-01-16 22:48:46 +00:00
Evan Cheng
de33ca2831 Fix FP_TO_INT**_IN_MEM lowering.
llvm-svn: 25368
2006-01-16 21:21:29 +00:00
Chris Lattner
62ab456f6b transfer some notes from my email to somewhere useful.
llvm-svn: 25361
2006-01-16 17:53:00 +00:00
Evan Cheng
fe83dd85c8 Added patterns for 8-bit multiply
llvm-svn: 25338
2006-01-15 10:05:20 +00:00
Chris Lattner
20f25dc8c2 Use the default lowering of ISD::DYNAMIC_STACKALLOC, delete now dead code.
llvm-svn: 25333
2006-01-15 09:00:21 +00:00
Chris Lattner
95882698e5 silence a warning
llvm-svn: 25322
2006-01-14 20:11:13 +00:00
Nate Begeman
85b2dc0c4e bswap implementation
llvm-svn: 25312
2006-01-14 03:14:10 +00:00
Evan Cheng
d92410b194 A typo.
llvm-svn: 25307
2006-01-14 01:18:49 +00:00
Evan Cheng
4d9bab5789 Add truncstore i1 patterns.
llvm-svn: 25296
2006-01-13 21:45:19 +00:00
Chris Lattner
b839f31954 Fix a bug in my last X86 checkin, pointed out by cozmic
llvm-svn: 25293
2006-01-13 20:19:44 +00:00
Evan Cheng
a26ed7b9b2 LHS = X86ISD::CMOVcc LHS, RHS means LHS = RHS if cc. So the operands must be
flipped around.

llvm-svn: 25290
2006-01-13 19:51:46 +00:00
Chris Lattner
344642961e Enable X86 support for savestack/restorestack
llvm-svn: 25278
2006-01-13 18:00:54 +00:00
Chris Lattner
80fed2d66e expand unsupported stacksave/stackrestore nodes
llvm-svn: 25272
2006-01-13 02:42:53 +00:00
Evan Cheng
e43fbe0d93 Minor update.
llvm-svn: 25263
2006-01-13 01:20:42 +00:00
Evan Cheng
bed984a1c8 More typo's. I need new eye glasses...
llvm-svn: 25261
2006-01-13 01:17:24 +00:00
Evan Cheng
ae2915ac91 Oops. Typo.
llvm-svn: 25260
2006-01-13 01:06:49 +00:00
Evan Cheng
3f2ae15472 Fix a SETCC / BRCOND folding bug.
llvm-svn: 25259
2006-01-13 01:03:02 +00:00
Evan Cheng
794a7cf6fe Fix sint_to_fp (fild*) support.
llvm-svn: 25257
2006-01-12 22:54:21 +00:00
Evan Cheng
169206c67f Specify transformation from GlobalAddress to TargetGlobalAddress and
ExternalSymbol to TargetExternalSymbol.

llvm-svn: 25253
2006-01-12 19:36:31 +00:00
Evan Cheng
978f5581c4 X86ISD::SETCC (e.g. SETEr) produces a flag (so multiple SETCC can be
linked together).

llvm-svn: 25247
2006-01-12 08:27:59 +00:00
Evan Cheng
dd45d29b56 * Materialize GlobalAddress and ExternalSym with MOV32ri rather than
LEA32r.
* Do not lower GlobalAddress to TargetGlobalAddress. Let isel does it.

llvm-svn: 25246
2006-01-12 07:56:47 +00:00
Evan Cheng
5841005bdf Added ROTL and ROTR.
llvm-svn: 25232
2006-01-11 23:20:05 +00:00
Evan Cheng
66540aa32c Support for MEMCPY and MEMSET.
llvm-svn: 25226
2006-01-11 22:15:48 +00:00
Evan Cheng
3c3391632d Select DYNAMIC_STACKALLOC
llvm-svn: 25225
2006-01-11 22:15:18 +00:00
Nate Begeman
cff96008ac Add bswap, rotl, and rotr nodes
Add dag combiner code to recognize rotl, rotr
Add ppc code to match rotl

Targets should add rotl/rotr patterns if they have them

llvm-svn: 25222
2006-01-11 21:21:00 +00:00
Evan Cheng
e42281bcba * Add special entry code main() (to set x87 to 64-bit precision).
* Allow a register node as SelectAddr() base.
* ExternalSymbol -> TargetExternalSymbol as direct function callee.
* Use X86::ESP register rather than CopyFromReg(X86::ESP) as stack ptr for
  call parmater passing.

llvm-svn: 25207
2006-01-11 06:09:51 +00:00
Chris Lattner
1d0926075f implement FP_REG_KILL insertion for the dag-dag instruction selector
llvm-svn: 25192
2006-01-11 01:15:34 +00:00
Chris Lattner
b4e9082f18 Fit into 80 cols
llvm-svn: 25191
2006-01-11 00:46:55 +00:00
Evan Cheng
9adc8e5a3d SSE cmov support.
llvm-svn: 25190
2006-01-11 00:33:36 +00:00
Evan Cheng
0cb5e32cda * fp to sint patterns.
* fiadd, fisub, etc.

llvm-svn: 25189
2006-01-10 22:22:02 +00:00
Evan Cheng
8504673bb2 FP_TO_INT*_IN_MEM and x87 FP Select support.
llvm-svn: 25188
2006-01-10 20:26:56 +00:00
Evan Cheng
154cef5ccb * Added undef patterns.
* Some reorg.

llvm-svn: 25163
2006-01-09 23:10:28 +00:00
Evan Cheng
c0b3a2166b More typos
llvm-svn: 25162
2006-01-09 22:29:54 +00:00
Evan Cheng
5baec4d0e2 typo
llvm-svn: 25160
2006-01-09 20:49:21 +00:00
Evan Cheng
d3babfe458 Support for ADD_PARTS, SUB_PARTS, SHL_PARTS, SHR_PARTS, and SRA_PARTS.
llvm-svn: 25158
2006-01-09 18:33:28 +00:00
Evan Cheng
6a9c735e21 * Added integer div / rem.
* Fixed a load folding bug.

llvm-svn: 25136
2006-01-06 23:19:29 +00:00
Evan Cheng
060b19c708 ISEL code for MULHU, MULHS, and UNDEF.
llvm-svn: 25132
2006-01-06 20:36:21 +00:00
Chris Lattner
88239024ca silence a bogus gcc warning
llvm-svn: 25129
2006-01-06 17:56:38 +00:00
Evan Cheng
66355df170 Addd (shl x, 1) ==> (shl x, x) peepholes.
llvm-svn: 25123
2006-01-06 02:31:59 +00:00
Evan Cheng
efe621adce fold (shl x, 1) -> (add x, x)
llvm-svn: 25120
2006-01-06 01:06:31 +00:00
Evan Cheng
1e0d7b98f3 * Fast call support.
* FP cmp, setcc, etc.

llvm-svn: 25117
2006-01-06 00:43:03 +00:00
Evan Cheng
6c86cf3a5f Added ConstantFP patterns.
llvm-svn: 25108
2006-01-05 02:08:37 +00:00
Jim Laskey
41b3ee3c4f Had expand logic backward.
llvm-svn: 25105
2006-01-05 01:47:43 +00:00
Jim Laskey
5eddaee9f3 Added initial support for DEBUG_LABEL allowing debug specific labels to be
inserted in the code.

llvm-svn: 25104
2006-01-05 01:25:28 +00:00
Evan Cheng
2329411038 DAG based isel call support.
llvm-svn: 25103
2006-01-05 00:27:02 +00:00
Chris Lattner
cee6093ca8 Fix a problem duraid pointed out to me compiling kc++ with -enable-x86-fastcc
llvm-svn: 25024
2005-12-27 03:02:18 +00:00
Evan Cheng
231b11ba87 Added field noResults to Instruction.
Currently tblgen cannot tell which operands in the operand list are results so
it assumes the first one is a result. This is bad. Ideally we would fix this
by separating results from inputs, e.g. (res R32:$dst),
(ops R32:$src1, R32:$src2). But that's a more distruptive change. Adding
'let noResults = 1' is the workaround to tell tblgen that the instruction does
not produces a result. It works for now since tblgen does not support
instructions which produce multiple results.

llvm-svn: 25017
2005-12-26 09:11:45 +00:00
Evan Cheng
cd69c81c5e Let the helper functions know about X86::FR32RegClass and X86::FR64RegClass.
llvm-svn: 25004
2005-12-24 09:48:35 +00:00
Evan Cheng
d87688fe72 * Removed the use of FLAG. Now use hasFlagIn and hasFlagOut instead.
* Added a pseudo instruction (for each target) that represent "return void".
  This is a workaround for lack of optional flag operand (return void is not
  lowered so it does not have a flag operand.)

llvm-svn: 24997
2005-12-23 22:14:32 +00:00
Evan Cheng
995503fc91 More X86 floating point patterns.
llvm-svn: 24990
2005-12-23 07:31:11 +00:00
Chris Lattner
8e80a247ff make sure bit_convert's are expanded
llvm-svn: 24979
2005-12-23 05:15:23 +00:00
Evan Cheng
e458553c73 Bye bye HACKTROCITY.
llvm-svn: 24935
2005-12-22 02:26:21 +00:00
Evan Cheng
fb6413e05a * Fix a GlobalAddress lowering bug.
* Teach DAG combiner about X86ISD::SETCC by adding a TargetLowering hook.

llvm-svn: 24921
2005-12-21 23:05:39 +00:00
Evan Cheng
add305de26 Oops. Accidentally deleted RET pattern. It's still needed for return void;
llvm-svn: 24920
2005-12-21 22:22:16 +00:00
Jim Laskey
d82881490c Disengage DEBUG_LOC from non-PPC targets.
llvm-svn: 24919
2005-12-21 20:51:37 +00:00
Evan Cheng
6f15189a77 * Added support for X86 RET with an additional operand to specify number of
bytes to pop off stack.
* Added support for X86 SETCC.

llvm-svn: 24917
2005-12-21 20:21:51 +00:00
Chris Lattner
347c6eedae This was meant to go in
llvm-svn: 24900
2005-12-21 07:50:26 +00:00
Chris Lattner
884def40f4 Rewrite FP stackifier support in the X86InstrInfo.td file, splitting patterns
that were overloaded to work before and after the stackifier runs.  With the
new clean world, it is possible to write patterns for these instructions: woo!

This also adds a few simple patterns here and there, though there are a lot
still missing.  These should be easy to add though. :)

See the comments under "Floating Point Stack Support" for more details on
the new world order.

This patch as absolutely no effect on the generated code, woo!

llvm-svn: 24899
2005-12-21 07:47:04 +00:00
Chris Lattner
ee15b5393f Wrap some long lines: no functionality change
llvm-svn: 24898
2005-12-21 05:34:58 +00:00
Evan Cheng
cab6710034 Remove ISD::RET select code. Now tblgen'd.
llvm-svn: 24889
2005-12-21 02:41:57 +00:00
Evan Cheng
0226113ed5 * Added lowering hook for external weak global address. It inserts a load
for Darwin.
* Added lowering hook for ISD::RET. It inserts CopyToRegs for the return
  value (or store / fld / copy to ST(0) for floating point value). This
  eliminate the need to write C++ code to handle RET with variable number
  of operands.

llvm-svn: 24888
2005-12-21 02:39:21 +00:00
Evan Cheng
ace8f1fafa SSE2 floating point load / store patterns. SSE2 fp to int conversion patterns.
llvm-svn: 24886
2005-12-20 22:59:51 +00:00
Evan Cheng
1c3ea75ffc Added X86 readport patterns.
llvm-svn: 24879
2005-12-20 07:38:38 +00:00
Evan Cheng
44e4e6a57f Added a hook to print out names of target specific DAG nodes.
llvm-svn: 24877
2005-12-20 06:22:03 +00:00
Evan Cheng
bb34a50cb0 X86 conditional branch support.
llvm-svn: 24870
2005-12-19 23:12:38 +00:00
Evan Cheng
c87099506c It's essential we clear CodeGenMap after isel every basic block!
llvm-svn: 24867
2005-12-19 22:36:02 +00:00
Chris Lattner
399dfec939 eliminate some redundancy
llvm-svn: 24781
2005-12-17 19:47:05 +00:00
Evan Cheng
56649f9616 Darwin API issue: indirect load of external and weak symbols.
llvm-svn: 24775
2005-12-17 09:13:43 +00:00
Evan Cheng
a3ff796fda Remove a few lines of dead code.
llvm-svn: 24768
2005-12-17 07:18:44 +00:00
Evan Cheng
de142995a1 Added an idea about any_extend for performance tuning.
llvm-svn: 24763
2005-12-17 06:54:43 +00:00
Evan Cheng
c308dfb801 Added truncate.
llvm-svn: 24760
2005-12-17 02:02:50 +00:00
Evan Cheng
6a94c77c55 Added anyext, modelled as zext on X86.
llvm-svn: 24759
2005-12-17 01:47:57 +00:00
Evan Cheng
19550821d1 Added some isel ideas.
llvm-svn: 24757
2005-12-17 01:25:19 +00:00
Evan Cheng
5d90b26707 Added support for cmp, test, and conditional move instructions.
llvm-svn: 24756
2005-12-17 01:24:02 +00:00
Evan Cheng
566600c17d Only lower SELECT when using DAG based isel.
llvm-svn: 24755
2005-12-17 01:22:13 +00:00
Evan Cheng
d51da93a03 X86 lowers SELECT to a cmp / test followed by a conditional move.
llvm-svn: 24754
2005-12-17 01:21:05 +00:00
Chris Lattner
71443a0e36 Don't globalize internal functions
llvm-svn: 24727
2005-12-16 00:07:30 +00:00
Evan Cheng
43152cb8b6 * Promote all 1 bit entities to 8 bit.
* Handling extload (1 bit -> 8 bit) and remove C++ code that handle 1 bit
zextload.

llvm-svn: 24726
2005-12-15 19:49:23 +00:00
Evan Cheng
f72e7055c0 Added frameindex, constpool, globaladdr, and externalsym as root nodes of
leaaddr.

llvm-svn: 24724
2005-12-15 08:31:04 +00:00
Evan Cheng
cc6efa8b6f Handling zero extension of 1 bit value.
llvm-svn: 24722
2005-12-15 01:02:48 +00:00
Evan Cheng
576b826f71 Use MOV8rm to load 1 bit value.
llvm-svn: 24721
2005-12-15 00:59:17 +00:00
Evan Cheng
40e397521c Fixed a typo: line 2323: MOVSX16rm8 -> MOVZX16rm8. This was the cause fo 12/14/2005 hbd failure.
llvm-svn: 24717
2005-12-14 22:28:18 +00:00
Evan Cheng
3b094e89fb Added sext and zext patterns.
llvm-svn: 24705
2005-12-14 02:22:27 +00:00
Evan Cheng
ad1e2fd14a Add load + store folding srl and sra patterns.
llvm-svn: 24696
2005-12-13 07:24:22 +00:00
Chris Lattner
95555853ad Use the shared asmprinter code for printing special llvm globals
llvm-svn: 24695
2005-12-13 06:32:50 +00:00
Chris Lattner
0975e89328 Add ELF and darwin support for static ctors and dtors
llvm-svn: 24693
2005-12-13 04:53:51 +00:00
Evan Cheng
63f60d3edb Beautify a few patterns.
llvm-svn: 24690
2005-12-13 02:40:18 +00:00
Evan Cheng
95d46be9e6 Some shl patterns which do load + store folding.
llvm-svn: 24689
2005-12-13 02:34:51 +00:00
Evan Cheng
6beadf1c29 A few helper fragments for loads. e.g. (i8 (load addr:$src)) -> (loadi8 addr:$src). Only to improve readibility.
llvm-svn: 24688
2005-12-13 01:57:51 +00:00
Evan Cheng
d233c28d29 Add and, or, and xor patterns which fold load + stores.
llvm-svn: 24687
2005-12-13 01:41:36 +00:00
Evan Cheng
62999d6c5d Add inc + dec patterns which fold load + stores.
llvm-svn: 24686
2005-12-13 01:02:47 +00:00
Evan Cheng
7f9fb7b095 Add neg and not patterns which fold load + stores.
llvm-svn: 24685
2005-12-13 00:54:44 +00:00
Evan Cheng
240071c011 Missed a couple redundant explicit type casts.
llvm-svn: 24684
2005-12-13 00:25:07 +00:00
Evan Cheng
e80ec06aaf Fix some bad choice of names: i16SExt8 ->i16immSExt8, etc.
llvm-svn: 24683
2005-12-13 00:14:11 +00:00
Evan Cheng
ea7f208813 * Split immSExt8 to i16SExt8 and i32SExt8 for i16 and i32 immediate operands.
This enables the removal of some explicit type casts.
* Rename immZExt8 to i16ZExt8 as well.

llvm-svn: 24682
2005-12-13 00:01:09 +00:00
Evan Cheng
0ee9dc460a Add some integer mul patterns.
llvm-svn: 24681
2005-12-12 23:47:46 +00:00
Evan Cheng
6c9f9ea7ec Add some sub patterns.
llvm-svn: 24675
2005-12-12 21:54:05 +00:00
Evan Cheng
76923d3512 When SelectLEAAddr() fails, it shouldn't cause the side effect of having the
base or index operands being selected.

llvm-svn: 24674
2005-12-12 21:49:40 +00:00
Evan Cheng
cf34770b28 For ISD::RET, if # of operands >= 2, try selection the real data dep. operand
first before the chain.
e.g.
int X;

int foo(int x)
{
  x += X + 37;
  return x;
}

If chain operand is selected first, we would generate:
	movl X, %eax
	movl 4(%esp), %ecx
	leal 37(%ecx,%eax), %eax

rather than
	movl $37, %eax
	addl 4(%esp), %eax
	addl X, %eax

which does not require %ecx. (Due to ADD32rm not matching.)

llvm-svn: 24673
2005-12-12 20:32:18 +00:00
Chris Lattner
08c38b28db remove some never-completed and now-obsolete code.
llvm-svn: 24671
2005-12-12 20:12:20 +00:00
Evan Cheng
145318aefb Add a few more add / store patterns. e.g. ADD32mi8.
llvm-svn: 24670
2005-12-12 19:45:23 +00:00
Evan Cheng
56f62789d7 * Added X86 store patterns.
* Added X86 dec patterns.

llvm-svn: 24654
2005-12-10 00:48:20 +00:00
Evan Cheng
6610545b7e Added patterns for ADD8rm, etc. These fold load operands. e.g. addb 4(%esp), %al
llvm-svn: 24648
2005-12-09 22:48:48 +00:00
Evan Cheng
6eb25df63a Added explicit type field to ComplexPattern.
llvm-svn: 24637
2005-12-08 02:15:07 +00:00
Evan Cheng
1712ee5ab9 * Added intelligence to X86 LEA addressing mode matching routine so it returns
false if the match is not profitable. e.g. leal 1(%eax), %eax.
* Added patterns for X86 integer loads and LEA32.

llvm-svn: 24635
2005-12-08 02:01:35 +00:00
Chris Lattner
5df0bce13a X86 doesn't support sextinreg for 8-bit things either.
llvm-svn: 24631
2005-12-07 17:59:14 +00:00
Evan Cheng
60cc8da341 Remove unnecessary let hasCtrlDep=1 now it can be inferred.
llvm-svn: 24611
2005-12-05 23:09:43 +00:00
Chris Lattner
3583f5337b Several things:
1. Remove redundant type casts now that PR673 is implemented.
2. Implement the OUT*ir instructions correctly.  The port number really
   *is* a 16-bit value, but the patterns should only match if the number
   is 0-255.  Update the patterns so they now match.
3. Fix patterns for shifts to reflect that the shift amount is always an
   i8, not an i16 as they were believed to be before.  This previous fib
   stopped working when we started knowing that CL has type i8.
4. Change use of i16i8imm in SH*ri patterns to all be imm.

llvm-svn: 24599
2005-12-05 02:40:25 +00:00
Evan Cheng
1ce02890ce Added isel patterns for RET, JMP, and WRITEPORT.
llvm-svn: 24588
2005-12-04 08:19:43 +00:00
Chris Lattner
4d34819930 Fix PR672 another way which should be more robust
llvm-svn: 24585
2005-12-04 06:03:50 +00:00
Chris Lattner
1b8459d092 Fix test/Regression/ExecutionEngine/2005-12-02-TailCallBug.ll and PR672.
This also fixes 177.mesa, the only program that fails with --enable-x86-fastcc
turned on.  Given a clean nightly tester run, we should be able to turn it
on by default!

llvm-svn: 24578
2005-12-03 07:15:55 +00:00
Chris Lattner
a2a404ff3a add a note
llvm-svn: 24572
2005-12-02 00:11:20 +00:00
Nate Begeman
811a41a87c Support multiple ValueTypes per RegisterClass, needed for upcoming vector
work.  This change has no effect on generated code.

llvm-svn: 24563
2005-12-01 04:51:06 +00:00
Evan Cheng
f1352fa7d6 Proper support for shifts with register shift value.
llvm-svn: 24559
2005-12-01 00:43:55 +00:00
Chris Lattner
b88f251144 SelectNodeTo now returns its result, we must pay attention to it.
llvm-svn: 24550
2005-11-30 22:59:19 +00:00
Nate Begeman
47bb0eba00 Fix a typo in my latest change
llvm-svn: 24542
2005-11-30 18:57:39 +00:00
Nate Begeman
84be54b731 No longer track value types for asm printer operands, and remove them as
an argument to every operand printing function.  Requires some slight
tweaks to x86, the only user.

llvm-svn: 24541
2005-11-30 18:54:35 +00:00
Chris Lattner
fdc786b18f Fix a bug in a recent patch that broke shifts
llvm-svn: 24526
2005-11-30 05:11:18 +00:00
Evan Cheng
bc51bc83b6 Added support to STORE and shifts to DAG to DAG isel.
llvm-svn: 24525
2005-11-30 02:51:20 +00:00
Evan Cheng
16b8b9d532 Fixed a minor bug: - -offset != offset iff offset == MININT
llvm-svn: 24522
2005-11-30 01:59:00 +00:00
Evan Cheng
f412b7ba0c Add more X86 ISel patterns.
llvm-svn: 24520
2005-11-29 19:38:52 +00:00
Chris Lattner
47feb1ecbb No targets support line number info yet.
llvm-svn: 24513
2005-11-29 06:16:21 +00:00
Chris Lattner
0edc0fd222 Add a missed optimization
llvm-svn: 24495
2005-11-28 04:52:39 +00:00
Chris Lattner
3efe6171f1 Use HasDotTypeDotSizeDirective instead of forELF
llvm-svn: 24481
2005-11-21 23:06:54 +00:00
Chris Lattner
fb4a026c32 Remove a level of indentation by using a continue.
llvm-svn: 24479
2005-11-21 22:48:18 +00:00
Chris Lattner
d17b6f1f1f Simplify the subtarget info, allow the asmwriter to do some target sensing
based on TargetType.

llvm-svn: 24478
2005-11-21 22:43:58 +00:00
Chris Lattner
77bd127e14 Use subtarget information computed by X86Subtarget instead of rolling our own.
llvm-svn: 24477
2005-11-21 22:39:40 +00:00
Chris Lattner
4e1e8b180b Make the X86 subtarget compute the basic target type: ELF, Cygwin, Darwin,
or native Win32

llvm-svn: 24476
2005-11-21 22:31:58 +00:00
Chris Lattner
0a2fc68b8a Add a forELF flag, allowing the removal of forCygwin and simplification of
conditionals.

llvm-svn: 24475
2005-11-21 22:19:48 +00:00
Chris Lattner
fe8b9b90d4 simplify and genericize this code
llvm-svn: 24473
2005-11-21 19:50:31 +00:00
Chris Lattner
9a74c980e8 prune #include
llvm-svn: 24468
2005-11-21 08:33:17 +00:00
Chris Lattner
03d9332c4f Switch to using the shared constant pool printer, along with using shorter
CPI ids

llvm-svn: 24467
2005-11-21 08:32:23 +00:00
Chris Lattner
3e2c6c1d15 Adjust to capitalized AsmPrinter method names
llvm-svn: 24456
2005-11-21 07:51:23 +00:00
Chris Lattner
0716cec311 Use PrivateGlobalPrefix for basic block labels. This allows the x86 darwin
port to properly use L for the bb prefix instead of .

llvm-svn: 24454
2005-11-21 07:43:59 +00:00
Chris Lattner
83215f8935 convert the rest of this over to use SwitchSection
llvm-svn: 24448
2005-11-21 07:16:34 +00:00
Chris Lattner
a19d2349b1 Start using the AsmPrinter shared SwitchSection code. This allows the X86
backend to implement global variables in sections.

llvm-svn: 24447
2005-11-21 07:11:11 +00:00
Chris Lattner
e5d0064a9d Rename SwitchSection -> switchSection to avoid conflicting with a future
change.

llvm-svn: 24443
2005-11-21 06:55:27 +00:00
Chris Lattner
00a2d1554b Naturally align doubles in the constant pool, set PrivateGlobalPrefix on
darwin, use it when printing the constant pool indices so the labels are
appropriately private, emit cp entries to .const instead of .data on darwin
and only emit a single .section for the constant pool, not one for each
entry.

llvm-svn: 24440
2005-11-21 06:46:22 +00:00
Chris Lattner
d122fc01dd Lower READCYCLECOUNTER correctly, preserving the chain result
llvm-svn: 24438
2005-11-20 22:57:19 +00:00
Chris Lattner
5d9ecff961 encode rdtsc correctly
llvm-svn: 24435
2005-11-20 22:13:18 +00:00
Chris Lattner
f4f66fafd9 use chain operands to ensure the copies don't wander from the rdtsc instruction.
llvm-svn: 24434
2005-11-20 22:01:40 +00:00
Andrew Lenharth
a369904fc5 The second patch of X86 support for read cycle counter.
llvm-svn: 24430
2005-11-20 21:41:10 +00:00
Chris Lattner
af79013023 Teach the x86 backend about the register constraints of its addressing mode.
Patch by Evan Cheng

llvm-svn: 24423
2005-11-19 07:01:30 +00:00
Chris Lattner
6e0171ba8b Add load and other support to the dag-dag isel. Patch contributed by Evan
Cheng!

llvm-svn: 24419
2005-11-19 02:11:08 +00:00
Chris Lattner
72fa26a85b add more patterns, patch by Evan Cheng.
llvm-svn: 24406
2005-11-18 01:04:42 +00:00
Chris Lattner
f829636c6b Add patterns for some 16-bit immediate instructions, patch contributed by
Evan Cheng.

llvm-svn: 24384
2005-11-17 02:01:55 +00:00
Chris Lattner
fec54e57a0 Add patterns for several simple instructions that take i32 immediates.
Patch contributed by Evan Cheng!

llvm-svn: 24382
2005-11-16 22:59:19 +00:00
Chris Lattner
9caa214f72 initial step at adding a dag-to-dag isel for X86 backend. Patch contributed
by Evan Cheng!

llvm-svn: 24371
2005-11-16 01:54:32 +00:00
Chris Lattner
792ac11aee Separate X86ISelLowering stuff out from the X86ISelPattern.cpp file. Patch
contributed by Evan Cheng.

llvm-svn: 24358
2005-11-15 00:40:23 +00:00
Chris Lattner
3fdc97d460 Add a new option to indicate we want the code generator to emit code quickly,not spending tons of time microoptimizing it. This is useful for an -O0style of build.
llvm-svn: 24233
2005-11-08 02:11:51 +00:00
Chris Lattner
bdcb2a99b6 add a note that Nate mentioned last week
llvm-svn: 23898
2005-10-23 21:44:59 +00:00
Chris Lattner
11c044d7cf Put some of my random notes somewhere public
llvm-svn: 23897
2005-10-23 19:52:42 +00:00
Nate Begeman
6c42f509bc Invert the TargetLowering flag that controls divide by consant expansion.
Add a new flag to TargetLowering indicating if the target has really cheap
  signed division by powers of two, make ppc use it.  This will probably go
  away in the future.
Implement some more ISD::SDIV folds in the dag combiner
Remove now dead code in the x86 backend.

llvm-svn: 23853
2005-10-21 00:02:42 +00:00
Nate Begeman
0eeb198d81 Remove some dead code now that the dag combiner exists.
llvm-svn: 23754
2005-10-15 22:08:02 +00:00
Nate Begeman
3b6c2df603 Properly split f32 and f64 into separate register classes for scalar sse fp
fixing a bunch of nasty hackery

llvm-svn: 23735
2005-10-14 22:06:00 +00:00
Chris Lattner
462fe8b2cc silence some warnings
llvm-svn: 23594
2005-10-02 16:29:36 +00:00
Chris Lattner
f70bf81bb6 simplify this code using the new regclass info passed in
llvm-svn: 23557
2005-09-30 17:12:38 +00:00
Chris Lattner
a1266f8ed5 Pass extra regclasses into spilling code
llvm-svn: 23537
2005-09-30 01:29:42 +00:00
Chris Lattner
d3b3d07c41 Add FP versions of the binary operators, keeping the int and fp worlds seperate.
Though I have done extensive testing, it is possible that this will break
things in configs I can't test.  Please let me know if this causes a problem
and I'll fix it ASAP.

llvm-svn: 23505
2005-09-28 22:29:17 +00:00
Chris Lattner
4a8f6d97ff Implement the isLoadFromStackSlot interface
llvm-svn: 23387
2005-09-19 05:23:44 +00:00
Chris Lattner
54139f0b83 give all operands names
llvm-svn: 23356
2005-09-14 21:10:24 +00:00
Chris Lattner
fa644b391f fix a major regression from my patch this afternoon
llvm-svn: 23347
2005-09-14 06:06:45 +00:00
Chris Lattner
00bfb7812d This code is no longer needed, it is moved to the target-indep code
llvm-svn: 23332
2005-09-13 19:31:44 +00:00
Chris Lattner
70e3e44ec4 Handle any_extend like zext
llvm-svn: 23202
2005-09-02 00:16:09 +00:00
Jim Laskey
f32ef9a37f 1. Use SubtargetFeatures in llc/lli.
2. Propagate feature "string" to all targets.

3. Implement use of SubtargetFeatures in PowerPCTargetSubtarget.

llvm-svn: 23192
2005-09-01 21:38:21 +00:00
Reid Spencer
a4acd20ae2 Adjust to member variable name change.
llvm-svn: 23119
2005-08-27 19:09:48 +00:00
Chris Lattner
439ef36320 Fix a bug in my previous checkin
llvm-svn: 23082
2005-08-26 17:18:44 +00:00
Chris Lattner
a31708e6b3 Change ConstantPoolSDNode to actually hold the Constant itself instead of
putting it into the constant pool.  This allows the isel machinery to
create constants that it will end up deciding are not needed, without them
ending up in the resultant function constant pool.

llvm-svn: 23081
2005-08-26 17:15:30 +00:00
Chris Lattner
fc59d17656 Fix a warning
llvm-svn: 23031
2005-08-25 00:05:15 +00:00
Chris Lattner
0444d66753 Adjust to new livevars interface
llvm-svn: 22991
2005-08-23 23:41:14 +00:00
Chris Lattner
51bad854a7 Simplify this code by using LiveVariables::KillsRegister
llvm-svn: 22988
2005-08-23 22:49:55 +00:00
Chris Lattner
2ac3fd08d2 Split RegisterClass 'Methods' into MethodProtos and MethodBodies
llvm-svn: 22929
2005-08-19 19:13:20 +00:00
Chris Lattner
f86654ffde Put register classes into namespaces
llvm-svn: 22925
2005-08-19 18:51:57 +00:00
Chris Lattner
e894de1791 The simple isel being gone makes this dead!
llvm-svn: 22914
2005-08-19 18:32:03 +00:00
Chris Lattner
d7bd59d77e add a few missing cases
llvm-svn: 22891
2005-08-19 00:41:29 +00:00
Chris Lattner
f62a66a21c Give ADJCALLSTACKDOWN/UP the correct operands.
Give a whole bunch of other stuff variable operands, particularly FP.  The
FP stackifier is playing fast and loose with operands here, so we have to
mark them all as variable.  This will have to be fixed before we can dag->dag
the X86 backend.  The solution is for the pre-stackifier and post-stackifier
instructions to all be disjoint.

llvm-svn: 22890
2005-08-19 00:38:22 +00:00
Chris Lattner
abad70eaf8 The variable SAR's only take one operand too
llvm-svn: 22888
2005-08-19 00:31:37 +00:00
Chris Lattner
8ce7dd449a Stop adding bogus operands to variable shifts on X86. These instructions
only take one operand.  The other comes implicitly in through CL.

llvm-svn: 22887
2005-08-19 00:16:17 +00:00
Nate Begeman
a978ae8b7d Remove the X86 and PowerPC Simple instruction selectors; their time has
passed.

llvm-svn: 22886
2005-08-18 23:53:15 +00:00
Chris Lattner
583658a766 update the backends to work with the new CopyFromReg/CopyToReg/ImplicitDef nodes
llvm-svn: 22807
2005-08-16 21:56:37 +00:00
Nate Begeman
f6b6378f23 Implement BR_CC and BRTWOWAY_CC. This allows the removal of a rather nasty
fixme from the PowerPC backend.  Emit slightly better code for legalizing
select_cc.

llvm-svn: 22805
2005-08-16 19:49:35 +00:00
Nate Begeman
6e0168fe5f Fix last night's X86 regressions by putting code for SSE in the if(SSE)
block.  nur.

llvm-svn: 22788
2005-08-14 18:37:02 +00:00
Nate Begeman
89f12b7721 Fix FP_TO_UINT with Scalar SSE2 now that the legalizer can handle it. We
now generate the relatively good code sequences:
unsigned short foo(float a) { return a; }
_foo:
        movss 4(%esp), %xmm0
        cvttss2si %xmm0, %eax
        movzwl %ax, %eax
        ret

and
unsigned bar(float a) { return a; }
_bar:
        movss .CPI_bar_0, %xmm0
        movss 4(%esp), %xmm1
        movapd %xmm1, %xmm2
        subss %xmm0, %xmm2
        cvttss2si %xmm2, %eax
        xorl $-2147483648, %eax
        cvttss2si %xmm1, %ecx
        ucomiss %xmm0, %xmm1
        cmovb %ecx, %eax
        ret

llvm-svn: 22786
2005-08-14 04:36:51 +00:00
Chris Lattner
1277703a48 Update the targets to the new SETCC/CondCodeSDNode interfaces.
llvm-svn: 22729
2005-08-09 20:21:10 +00:00
Chris Lattner
07af090121 adjust to change in getSubtarget() api
llvm-svn: 22687
2005-08-05 21:54:27 +00:00
Nate Begeman
09997f1012 Add Subtarget support to PowerPC. Next up, using it.
llvm-svn: 22644
2005-08-04 07:12:09 +00:00
Nate Begeman
6cd034da8e Scalar SSE: load +0.0 -> xorps/xorpd
Scalar SSE: a < b ? c : 0.0 -> cmpss, andps
Scalar SSE: float -> i16 needs to be promoted

llvm-svn: 22637
2005-08-03 23:26:28 +00:00
Chris Lattner
cc8ae687e1 Update to use the new MathExtras.h support for log2 computation.
Patch contributed by Jim Laskey!

llvm-svn: 22594
2005-08-02 19:26:06 +00:00
Jeff Cohen
019104459d Keep tabs and trailing spaces out.
llvm-svn: 22565
2005-07-30 18:33:25 +00:00
Chris Lattner
11be5c11d5 fix a typeo
llvm-svn: 22561
2005-07-30 00:43:00 +00:00
Chris Lattner
a681fc64d6 Change the fp to integer code to not perform 2-byte stores followed by
1 byte loads and other operations.  This is bad for store-forwarding on
common CPUs.  We now do this:

fnstcw WORD PTR [%ESP]
mov %AX, WORD PTR [%ESP]

instead of:

fnstcw WORD PTR [%ESP]
mov %AL, BYTE PTR [%ESP + 1]

llvm-svn: 22559
2005-07-30 00:17:52 +00:00
Chris Lattner
cf208334d9 Use a custom expander for all FP to int conversions, as the X86 only has
FP-to-int-in-memory: this exposes the load from the stored slot to the
selection dag, allowing it to be folded into other operaions.

llvm-svn: 22556
2005-07-30 00:05:54 +00:00
Andrew Lenharth
3a7dc9f0bd turn off GOT on archs that didn't use it (not that it appeard to harm them much with it on)
llvm-svn: 22553
2005-07-29 23:32:02 +00:00
Chris Lattner
2aa847898d Implement a FIXME: move a bunch of cruft for handling FP_TO_*INT operations
that the X86 does not support to the legalizer.  This allows it to be better
optimized, etc, and will help with SSE support.

llvm-svn: 22551
2005-07-29 01:00:29 +00:00
Chris Lattner
9db78c43c5 Don't forget to diddle with the control word when performing an FISTP64.
llvm-svn: 22550
2005-07-29 00:54:34 +00:00
Chris Lattner
a30d4be57d Use a custom expander to compile this:
long %test4(double %X) {
        %tmp.1 = cast double %X to long         ; <long> [#uses=1]
        ret long %tmp.1
}

to this:

_test4:
        sub %ESP, 12
        fld QWORD PTR [%ESP + 16]
        fistp QWORD PTR [%ESP]
        mov %EDX, DWORD PTR [%ESP + 4]
        mov %EAX, DWORD PTR [%ESP]
        add %ESP, 12
        ret

instead of this:

_test4:
        sub %ESP, 28
        fld QWORD PTR [%ESP + 32]
        fstp QWORD PTR [%ESP]
        call ___fixdfdi
        add %ESP, 28
        ret

llvm-svn: 22549
2005-07-29 00:40:01 +00:00
Jeff Cohen
bd51ec7461 Eliminate all remaining tabs and trailing spaces.
llvm-svn: 22523
2005-07-27 06:12:32 +00:00
Jeff Cohen
81980781a1 Eliminate tabs and trailing spaces.
llvm-svn: 22520
2005-07-27 05:53:44 +00:00
Andrew Lenharth
0e1c0e7c79 update interface
llvm-svn: 22498
2005-07-22 20:49:37 +00:00
Reid Spencer
40c5ebe4eb For: memory operations -> stores
This is the first incremental patch to implement this feature. It adds no
functionality to LLVM but setup up the information needed from targets in
order to implement the optimization correctly. Each target needs to specify
the maximum number of store operations for conversion of the llvm.memset,
llvm.memcpy, and llvm.memmove intrinsics into a sequence of store operations.
The limit needs to be chosen at the threshold of performance for such an
optimization (generally smallish). The target also needs to specify whether
the target can support unaligned stores for multi-byte store operations.
This helps ensure the optimization doesn't generate code that will trap on
an alignment errors.
More patches to follow.

llvm-svn: 22468
2005-07-19 04:52:44 +00:00
Nate Begeman
160c12d896 Teach the legalizer how to promote SINT_TO_FP to a wider SINT_TO_FP that
the target natively supports.  This eliminates some special-case code from
the x86 backend and generates better code as well.

For an i8 to f64 conversion, before & after:

_x87 before:
        subl $2, %esp
        movb 6(%esp), %al
        movsbw %al, %ax
        movw %ax, (%esp)
        filds (%esp)
        addl $2, %esp
        ret

_x87 after:
        subl $2, %esp
        movsbw 6(%esp), %ax
        movw %ax, (%esp)
        filds (%esp)
        addl $2, %esp
        ret

_sse before:
        subl $12, %esp
        movb 16(%esp), %al
        movsbl %al, %eax
        cvtsi2sd %eax, %xmm0
        addl $12, %esp
        ret

_sse after:
        subl $12, %esp
        movsbl 16(%esp), %eax
        cvtsi2sd %eax, %xmm0
        addl $12, %esp
        ret

llvm-svn: 22452
2005-07-16 02:02:34 +00:00
Nate Begeman
7a1bc7318d Teach the register allocator that movaps is also a move instruction
llvm-svn: 22451
2005-07-16 02:00:20 +00:00
Nate Begeman
c93c1c5148 A couple more darwinisms
llvm-svn: 22450
2005-07-16 01:59:47 +00:00
Chris Lattner
79573b1a93 Remove all knowledge of UINT_TO_FP from the X86 backend, relying on the
legalizer to eliminate them.  With this comes the expected code quality
improvements, such as, for this:

double foo(unsigned short X) { return X; }

we now generate this:

_foo:
        subl $4, %esp
        movzwl 8(%esp), %eax
        movl %eax, (%esp)
        fildl (%esp)
        addl $4, %esp
        ret

instead of this:

_foo:
        subl $4, %esp
        movw 8(%esp), %ax
        movzwl %ax, %eax   ;; Load not folded into this.
        movl %eax, (%esp)
        fildl (%esp)
        addl $4, %esp
        ret

-Chris

llvm-svn: 22449
2005-07-16 00:28:20 +00:00
Nate Begeman
957e0e7c9e Get closer to fully working scalar FP in SSE regs. This gets singlesource
working, and Olden/power.

llvm-svn: 22441
2005-07-15 00:38:55 +00:00
Nate Begeman
8c2dadc92e Add support for printing the sse scalar comparison instruction mnemonics.
llvm-svn: 22440
2005-07-14 22:52:25 +00:00
Nate Begeman
7330d9cd80 Check in the last of the darwin-specific code necessary to get shootout
working before modifying the asm printer to use the subtarget info.

llvm-svn: 22408
2005-07-12 18:34:58 +00:00
Nate Begeman
4d96f2769c Clean up the TargetSubtarget class a bit, removing an unnecessary argument
to the constructor.

llvm-svn: 22392
2005-07-12 02:41:19 +00:00
Chris Lattner
b383dec36f Minor changes to improve comments and fix the build on _WIN32 systems.
llvm-svn: 22391
2005-07-12 02:36:10 +00:00
Chris Lattner
855fe2ea0c Add a note
llvm-svn: 22390
2005-07-12 02:35:36 +00:00
Nate Begeman
626fb671c8 Implement Subtarget support
Implement the X86 Subtarget.

This consolidates the checks for target triple, and setting options based
on target triple into one place.  This allows us to convert the asm printer
and isel over from being littered with "forDarwin", "forCygwin", etc. into
just having the appropriate flags for each subtarget feature controlling
the code for that feature.

This patch also implements indirect external and weak references in the
X86 pattern isel, for darwin.  Next up is to convert over the asm printers
to use this new interface.

llvm-svn: 22389
2005-07-12 01:41:54 +00:00
Nate Begeman
faf9b5b763 Commit some pending darwin changes before subtarget support.
llvm-svn: 22388
2005-07-12 01:37:28 +00:00
Chris Lattner
cace336deb Output .size directives to tell the assembler the size of each function.
llvm-svn: 22381
2005-07-11 06:29:14 +00:00
Chris Lattner
af83621722 Fix crazy indentation
llvm-svn: 22380
2005-07-11 06:25:47 +00:00
Chris Lattner
a556fc183f Refactor things a bit to allow the ELF code emitter to run the X86 machine code emitter
after itself.

llvm-svn: 22376
2005-07-11 05:17:48 +00:00