Jeff Cohen
e128d5f724
Improve X86 subtarget support for Windows and AMD.
...
llvm-svn: 25747
2006-01-28 18:09:06 +00:00
Chris Lattner
d02b05473c
Use the new "UpdateNodeOperands" method to simplify LegalizeDAG and make it
...
faster. This cuts about 120 lines of code out of the legalizer (mostly code
checking to see if operands have changed).
It also fixes an ugly performance issue, where the legalizer cloned the entire
graph after any change. Now the "UpdateNodeOperands" method gives it a chance
to reuse nodes if the operands of a node change but not its opcode or valuetypes.
This speeds up instruction selection time on kimwitu++ by about 8.2% with a
release build.
llvm-svn: 25746
2006-01-28 10:58:55 +00:00
Chris Lattner
ccd2a20c4b
silence a warning
...
llvm-svn: 25745
2006-01-28 10:34:47 +00:00
Chris Lattner
580b12ad34
add another method variant
...
llvm-svn: 25744
2006-01-28 10:09:25 +00:00
Chris Lattner
64f934f07f
add another variant
...
llvm-svn: 25743
2006-01-28 10:08:58 +00:00
Chris Lattner
f34156e8cb
add some methods for updating nodes
...
llvm-svn: 25742
2006-01-28 09:32:45 +00:00
Chris Lattner
009c53f688
Add some methods
...
llvm-svn: 25741
2006-01-28 09:32:01 +00:00
Chris Lattner
eb63751499
minor tweaks
...
llvm-svn: 25740
2006-01-28 08:31:04 +00:00
Chris Lattner
689bdcc9cf
move a bunch of code, no other change.
...
llvm-svn: 25739
2006-01-28 08:25:58 +00:00
Chris Lattner
fcfda5a174
remove a couple more now-extraneous legalizeop's
...
llvm-svn: 25738
2006-01-28 08:22:56 +00:00
Chris Lattner
364b89a784
fix a bug
...
llvm-svn: 25737
2006-01-28 07:42:08 +00:00
Chris Lattner
9dcce6da8e
Several major changes:
...
1. Pull out the expand cases for BSWAP and CT* into a separate function,
reducing the size of LegalizeOp.
2. Fix a bug where expand(bswap i64) was wrong when i64 is legal.
3. Changed LegalizeOp/PromoteOp so that the legalizer never needs to be
iterative. It now operates in a single pass over the nodes.
4. Simplify a LOT of code, with a net reduction of ~280 lines.
llvm-svn: 25736
2006-01-28 07:39:30 +00:00
Chris Lattner
30432e07f0
Fix a bug in my elimination of ISD::CALL this morning. PPC now has to
...
provide the expansion for i64 calls itself
llvm-svn: 25735
2006-01-28 07:33:03 +00:00
Chris Lattner
dc8bbb6527
make this work on non-native hosts
...
llvm-svn: 25734
2006-01-28 06:05:41 +00:00
Chris Lattner
0c7b4666a3
add a note about how we should implement this FIXME from the legalizer:
...
// FIXME: revisit this when we have some kind of mechanism by which targets
// can decided legality of vector constants, of which there may be very
// many.
llvm-svn: 25733
2006-01-28 05:40:47 +00:00
Chris Lattner
fd4a7f76a9
Eliminate the need for ExpandOp to set 'needsanotheriteration', as it already
...
relegalizes the stuff it returns.
Add the ability to custom expand ADD/SUB, so that targets don't need to deal
with ADD_PARTS/SUB_PARTS if they don't want.
Fix some obscure potential bugs and simplify code.
llvm-svn: 25732
2006-01-28 05:07:51 +00:00
Chris Lattner
10f677508f
Instead of making callers of ExpandLibCall legalize the result, make
...
ExpandLibCall do it itself.
llvm-svn: 25731
2006-01-28 04:28:26 +00:00
Chris Lattner
a593acfe66
Eliminate the need to do another iteration of the legalizer after inserting
...
a libcall.
llvm-svn: 25730
2006-01-28 04:23:12 +00:00
Chris Lattner
b256104073
remove this method I just added, now is not the time.
...
llvm-svn: 25729
2006-01-28 03:43:33 +00:00
Chris Lattner
98ed05c81d
remove method I just added
...
llvm-svn: 25728
2006-01-28 03:43:09 +00:00
Chris Lattner
43b867dd3b
add a new callback
...
llvm-svn: 25727
2006-01-28 03:37:03 +00:00
Nate Begeman
595ec734fc
Implement Promote for VAARG, and allow it to be custom promoted for people
...
who don't want the default behavior (Alpha).
llvm-svn: 25726
2006-01-28 03:14:31 +00:00
Nate Begeman
6c82262289
Add a couple more things to the readme.
...
llvm-svn: 25724
2006-01-28 01:22:10 +00:00
Nate Begeman
af397cec0b
Add a missing case to the dag combiner.
...
llvm-svn: 25723
2006-01-28 01:06:30 +00:00
Chris Lattner
fb16a62fba
Remove the ISD::CALL and ISD::TAILCALL nodes
...
llvm-svn: 25721
2006-01-28 00:18:58 +00:00
Chris Lattner
b95594b2f0
The 'target-independent' ISD::CALL isn't. Nuke it, making way for Nate's
...
future work.
llvm-svn: 25720
2006-01-28 00:18:27 +00:00
Chris Lattner
b292de6703
Remove some dead code
...
llvm-svn: 25719
2006-01-28 00:02:51 +00:00
Chris Lattner
2c00db82bd
Switch to AlphaISD::CALL instead of ISD::CALL
...
llvm-svn: 25718
2006-01-27 23:39:00 +00:00
Chris Lattner
f424a66524
Use PPCISD::CALL instead of ISD::CALL
...
llvm-svn: 25717
2006-01-27 23:34:02 +00:00
Chris Lattner
a9382ca59e
Use V8ISD::CALL instead of ISD::CALL
...
llvm-svn: 25716
2006-01-27 23:30:03 +00:00
Evan Cheng
18243826fd
A bit of wisdom from Chris on the last entry.
...
llvm-svn: 25715
2006-01-27 22:54:32 +00:00
Evan Cheng
63045d221b
AT&T assembly convention: registers are in lower case.
...
llvm-svn: 25714
2006-01-27 22:53:29 +00:00
Evan Cheng
6a92822173
Use Intel assembly syntax to look for ST
...
llvm-svn: 25713
2006-01-27 22:51:51 +00:00
Chris Lattner
a502b93fae
initialize member vars
...
llvm-svn: 25712
2006-01-27 22:38:36 +00:00
Chris Lattner
dbfc299915
initialize all instance vars
...
llvm-svn: 25711
2006-01-27 22:37:09 +00:00
Chris Lattner
4d967a4cbb
Make llvm.frame/returnaddr not crash on ppc
...
llvm-svn: 25710
2006-01-27 22:25:06 +00:00
Jeff Cohen
e251e92c23
Teach tablegen to generate code that is VC++ warning-free.
...
llvm-svn: 25709
2006-01-27 22:22:28 +00:00
Evan Cheng
e555a92c8d
(store (op (load ...)), ...)
...
If store's chain operand is load, then use load's chain operand instead. If
it isn't (likely a TokenFactor), then do not allow the folding.
llvm-svn: 25708
2006-01-27 22:13:45 +00:00
Chris Lattner
b3eb31f7f9
* Eliminate FAKE_SOURCES
...
* Make runtimes and projects build with the new front-end by not relying on
'llvm-gcc -c' to build a .bc file. Instead, use llvm-gcc -S -emit-llvm,
then an explicit invocation of gccas. Also, don't use llvm-gcc to link
.bc files together, use gccld directly.
llvm-svn: 25707
2006-01-27 22:13:12 +00:00
Evan Cheng
9857d075b5
Added notes about a x86 isel deficiency.
...
llvm-svn: 25706
2006-01-27 22:11:01 +00:00
Chris Lattner
4c251f89b4
Remove out of date comment
...
llvm-svn: 25705
2006-01-27 22:06:50 +00:00
Chris Lattner
a4575c7349
Remove the only use of FAKE_SOURCES
...
llvm-svn: 25704
2006-01-27 22:06:23 +00:00
Chris Lattner
35b707cfcc
Remove FAKE_SOURCES
...
llvm-svn: 25703
2006-01-27 22:06:01 +00:00
Evan Cheng
1073ae07b0
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
a814f0b31c
Bye bye Pattern ISel, hello DAG ISel.
...
llvm-svn: 25700
2006-01-27 21:26:54 +00:00
Evan Cheng
822f629538
X86 dag isel is now (soon) the default.
...
llvm-svn: 25699
2006-01-27 21:15:22 +00:00
Evan Cheng
7ca86912b7
These are fp stack test cases.
...
llvm-svn: 25698
2006-01-27 21:14:23 +00:00
Evan Cheng
a3b41703f0
XFAIL tailcall test cases until it's implemented.
...
llvm-svn: 25697
2006-01-27 21:13:27 +00:00
Nate Begeman
8c47c3a3b1
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
Jim Laskey
0cda006a69
Using bit size of integers instead of ambiguous "long" et all.
...
llvm-svn: 25694
2006-01-27 20:31:25 +00:00