Commit Graph

11126 Commits

Author SHA1 Message Date
Chris Lattner
ea874f3306 Teach the dag isel generator how to construct arbitrary immediates. The
generated isel now tries li then lis, then lis+ori.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23418 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-24 00:41:58 +00:00
Chris Lattner
b60e0815df remove some debugging code
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23411 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-23 18:49:09 +00:00
Chris Lattner
263d1e469d Fold two consequtive branches that share a common destination between them.
This implements SimplifyCFG/branch-fold.ll, and is useful on ?:/min/max heavy
code


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23410 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-23 18:47:20 +00:00
Chris Lattner
055dc102e9 simplify some logic further
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23408 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-23 07:23:18 +00:00
Chris Lattner
f58c1a578e pull a bunch of logic out of SimplifyCFG into a helper fn
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23407 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-23 06:39:30 +00:00
Chris Lattner
7c439929bc speed up Archive::isBytecodeArchive in the case when the archive doesn't have
an llvm-ranlib symtab.  This speeds up gccld -native on an almost empty .o file
from 1.63s to 0.18s.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23406 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-23 06:22:58 +00:00
Chris Lattner
5ae7911b24 Turn (X^C1) == C2 into X == C1^C2 iff X&~C1 = 0 (and move a function)
This happens all the time on PPC for bool values, e.g. eliminating a xori
in inverted-bool-compares.ll.

This should be added to the dag combiner as well.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23403 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-23 00:55:52 +00:00
Chris Lattner
3c3fe462f7 Expose the LiveInterval interfaces as public headers.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23400 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-21 04:19:09 +00:00
Chris Lattner
e9487f0dc8 Start threading across blocks with code in them, so long as the code does
not define a value that is used outside of it's block.  This catches many
more simplifications, e.g. 854 in 176.gcc, 137 in vpr, etc.

This implements branch-phi-thread.ll:test3.ll


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23397 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-20 01:48:40 +00:00
Chris Lattner
2e42e36698 Implement merging of blocks with the same condition if the block has multiple
predecessors.  This implements branch-phi-thread.ll::test1


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23395 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-20 00:43:16 +00:00
Chris Lattner
9c88d98162 Reject a case we don't handle yet
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23393 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-19 23:57:04 +00:00
Chris Lattner
7e1ff8d2d9 remove debugging code :-/
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23392 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-19 23:50:15 +00:00
Chris Lattner
eaba3a194c Implement SimplifyCFG/branch-phi-thread.ll, the most trivial case of threading
control across branches with determined outcomes.  More generality to follow.
This triggers a couple thousand times in specint.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23391 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-19 23:49:37 +00:00
Nate Begeman
44728a7bb6 Stub out the rest of the DAG Combiner. Just need to fill in the
select_cc bits and then wrap it in a convenience function for  use with
regular select.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23389 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-19 22:34:01 +00:00
Chris Lattner
cea8688ee4 Teach the local spiller to turn stack slot loads into register-register copies
when possible, avoiding the load (and avoiding the copy if the value is already
in the right register).

This patch came about when I noticed code like the following being generated:

  store R17 -> [SS1]
  ...blah...
  R4 = load [SS1]

This was causing an LSU reject on the G5.  This problem was due to the register
allocator folding spill code into a reg-reg copy (producing the load), which
prevented the spiller from being able to rewrite the load into a copy, despite
the fact that the value was already available in a register.  In the case
above, we now rip out the R4 load and replace it with a R4 = R17 copy.

This speeds up several programs on X86 (which spills a lot :) ), e.g.
smg2k from 22.39->20.60s, povray from 12.93->12.66s, 168.wupwise from
68.54->53.83s (!), 197.parser from 7.33->6.62s (!), etc.  This may have a larger
impact in some cases on the G5 (by avoiding LSU rejects), though it probably
won't trigger as often (less spilling in general).

Targets that implement folding of loads/stores into copies should implement
the isLoadFromStackSlot hook to get this.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23388 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-19 06:56:21 +00:00
Chris Lattner
a92aab74dd Implement the isLoadFromStackSlot interface
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23387 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-19 05:23:44 +00:00
Chris Lattner
7203e158da Refactor this code a bit and make it more general. This now compiles:
struct S { unsigned int i : 6, j : 11, k : 15; } b;
void plus2 (unsigned int x) { b.j += x; }

To:

_plus2:
        lis r2, ha16(L_b$non_lazy_ptr)
        lwz r2, lo16(L_b$non_lazy_ptr)(r2)
        lwz r4, 0(r2)
        slwi r3, r3, 6
        add r3, r4, r3
        rlwimi r3, r4, 0, 26, 14
        stw r3, 0(r2)
        blr


instead of:

_plus2:
        lis r2, ha16(L_b$non_lazy_ptr)
        lwz r2, lo16(L_b$non_lazy_ptr)(r2)
        lwz r4, 0(r2)
        rlwinm r5, r4, 26, 21, 31
        add r3, r5, r3
        rlwimi r4, r3, 6, 15, 25
        stw r4, 0(r2)
        blr

by eliminating an 'and'.

I'm pretty sure this is as small as we can go :)


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23386 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-18 07:22:02 +00:00
Chris Lattner
150f12af7f Compile
struct S { unsigned int i : 6, j : 11, k : 15; } b;
void plus2 (unsigned int x) {
  b.j += x;
}

to:

plus2:
        mov %EAX, DWORD PTR [b]
        mov %ECX, %EAX
        and %ECX, 131008
        mov %EDX, DWORD PTR [%ESP + 4]
        shl %EDX, 6
        add %EDX, %ECX
        and %EDX, 131008
        and %EAX, -131009
        or %EDX, %EAX
        mov DWORD PTR [b], %EDX
        ret

instead of:

plus2:
        mov %EAX, DWORD PTR [b]
        mov %ECX, %EAX
        shr %ECX, 6
        and %ECX, 2047
        add %ECX, DWORD PTR [%ESP + 4]
        shl %ECX, 6
        and %ECX, 131008
        and %EAX, -131009
        or %ECX, %EAX
        mov DWORD PTR [b], %ECX
        ret


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23385 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-18 06:30:59 +00:00
Chris Lattner
0b7c0bf249 Generalize this transform, using MaskedValueIsZero, allowing us to compile:
struct S { unsigned int i : 6, j : 11, k : 15; } b;
void plus3 (unsigned int x) { b.k += x; }

To:

plus3:
        mov %EAX, DWORD PTR [%ESP + 4]
        shl %EAX, 17
        add DWORD PTR [b], %EAX
        ret

instead of:

plus3:
        mov %EAX, DWORD PTR [%ESP + 4]
        shl %EAX, 17
        mov %ECX, DWORD PTR [b]
        add %EAX, %ECX
        and %EAX, -131072
        and %ECX, 131071
        or %ECX, %EAX
        mov DWORD PTR [b], %ECX
        ret


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23384 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-18 06:02:59 +00:00
Chris Lattner
5aa7666ebe fix typeo
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23383 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-18 05:25:20 +00:00
Chris Lattner
0d947ea943 Remove unintentionally committed code
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23382 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-18 05:12:51 +00:00
Chris Lattner
11021cb988 implement shift.ll:test25. This compiles:
struct S { unsigned int i : 6, j : 11, k : 15; } b;
void plus3 (unsigned int x) {
  b.k += x;
}

to:

_plus3:
        lis r2, ha16(L_b$non_lazy_ptr)
        lwz r2, lo16(L_b$non_lazy_ptr)(r2)
        lwz r3, 0(r2)
        rlwinm r4, r3, 0, 0, 14
        add r4, r4, r3
        rlwimi r4, r3, 0, 15, 31
        stw r4, 0(r2)
        blr

instead of:

_plus3:
        lis r2, ha16(L_b$non_lazy_ptr)
        lwz r2, lo16(L_b$non_lazy_ptr)(r2)
        lwz r4, 0(r2)
        srwi r5, r4, 17
        add r3, r5, r3
        slwi r3, r3, 17
        rlwimi r3, r4, 0, 15, 31
        stw r3, 0(r2)
        blr


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23381 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-18 05:12:10 +00:00
Chris Lattner
c8e7756791 Implement add.ll:test29. Codegening:
struct S { unsigned int i : 6, j : 11, k : 15; } b;
void plus1 (unsigned int x) {
  b.i += x;
}

as:
_plus1:
        lis r2, ha16(L_b$non_lazy_ptr)
        lwz r2, lo16(L_b$non_lazy_ptr)(r2)
        lwz r4, 0(r2)
        add r3, r4, r3
        rlwimi r3, r4, 0, 0, 25
        stw r3, 0(r2)
        blr

instead of:

_plus1:
        lis r2, ha16(L_b$non_lazy_ptr)
        lwz r2, lo16(L_b$non_lazy_ptr)(r2)
        lwz r4, 0(r2)
        rlwinm r5, r4, 0, 26, 31
        add r3, r5, r3
        rlwimi r3, r4, 0, 0, 25
        stw r3, 0(r2)
        blr


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23379 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-18 04:24:45 +00:00
Chris Lattner
3255bd101d remove debug output
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23377 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-18 03:50:25 +00:00
Chris Lattner
e9bed7d107 Implement or.ll:test21. This teaches instcombine to be able to turn this:
struct {
   unsigned int bit0:1;
   unsigned int ubyte:31;
} sdata;

void foo() {
  sdata.ubyte++;
}

into this:

foo:
        add DWORD PTR [sdata], 2
        ret

instead of this:

foo:
        mov %EAX, DWORD PTR [sdata]
        mov %ECX, %EAX
        add %ECX, 2
        and %ECX, -2
        and %EAX, 1
        or %EAX, %ECX
        mov DWORD PTR [sdata], %EAX
        ret


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23376 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-18 03:42:07 +00:00
Chris Lattner
6a78c2157a Implement hook for ppc
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23374 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-17 01:03:26 +00:00
Nate Begeman
452d7bebaa More DAG combining. Still need the branch instructions, and select_cc
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23371 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-16 00:54:12 +00:00
Chris Lattner
4ac85b3e94 disable this for now
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23366 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-15 21:44:00 +00:00
Chris Lattner
2e3f5db9ff Give all operands names
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23357 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-14 21:11:13 +00:00
Chris Lattner
43ef1318c6 give all operands names
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23356 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-14 21:10:24 +00:00
Chris Lattner
4345a4a452 Fix some issues exposed by more testing. XORIS had the wrong operands
specified.  The various *imm operands defined by PPC are really all i32,
even though the actual immediate is restricted to a smaller value in it.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23352 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-14 20:53:05 +00:00
Chris Lattner
c36d065dce Fix some bugs noticed by new checking code
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23350 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-14 18:18:39 +00:00
Chris Lattner
6e2f843114 Fix the regression last night compiling povray
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23348 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-14 17:32:56 +00:00
Chris Lattner
3452d23c34 fix a major regression from my patch this afternoon
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23347 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-14 06:06:45 +00:00
Chris Lattner
303b555164 we don't need this proto any longer
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23342 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-13 22:05:21 +00:00
Chris Lattner
af16538511 move the #include for the generated code into the isel class body so we
can use/define class methods


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23339 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-13 22:03:06 +00:00
Chris Lattner
7b738342f0 Change the arg lowering code to use copyfromreg from vregs associated
with incoming arguments instead of the pregs themselves.  This fixes
the scheduler from causing problems by moving a copyfromreg for an argument
to after a select_cc node (now it can, and bad things won't happen).


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23334 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-13 19:33:40 +00:00
Chris Lattner
8c4469840e This has been moved to the target-indep code
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23333 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-13 19:32:18 +00:00
Chris Lattner
82da52299c This code is no longer needed, it is moved to the target-indep code
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23332 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-13 19:31:44 +00:00
Chris Lattner
fa57702388 If a function has liveins, and if the target requested that they be plopped
into particular vregs, emit copies into the entry MBB.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23331 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-13 19:30:54 +00:00
Chris Lattner
f2cded73c4 Majik numbers are bad
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23330 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-13 19:03:13 +00:00
Chris Lattner
31262ce53d Remove some dead vectors
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23329 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-13 18:47:49 +00:00
Chris Lattner
7835cdde40 Add a simple xform to simplify array accesses with casts in the way.
This is useful for 178.galgel where resolution of dope vectors (by the
optimizer) causes the scales to become apparent.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23328 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-13 18:36:04 +00:00
Chris Lattner
396b2baf3c Fix an issue where LSR would miss rewriting a use of an IV expression by a PHI node that is not the original PHI.
This fixes up a dot-product loop in galgel, speeding it up from 18.47s to
16.13s.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23327 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-13 02:09:55 +00:00
Chris Lattner
eed48275a1 Add a helper function, allowing us to simplify some code a bit, changing
indentation, no functionality change


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23325 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-13 00:40:14 +00:00
Chris Lattner
408902b3c4 Implement a simple xform to turn code like this:
if () { store A -> P; } else { store B -> P; }

into a PHI node with one store, in the most trival case.  This implements
load.ll:test10.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23324 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-12 23:23:25 +00:00
Chris Lattner
9c1f0fd8de Another load-peephole optimization: do gcse when two loads are next to
each other.  This implements InstCombine/load.ll:test9


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23322 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-12 22:21:03 +00:00
Chris Lattner
62f254df04 Implement a trivial form of store->load forwarding where the store and the
load are exactly consequtive.  This is picked up by other passes, but this
triggers thousands of times in fortran programs that use static locals
(and is thus a compile-time speedup).


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23320 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-12 22:00:15 +00:00
Chris Lattner
12b50410cd Fix a regression from last night, which caused this pass to create invalid
code for IV uses outside of loops that are not dominated by the latch block.
We should only convert these uses to use the post-inc value if they ARE
dominated by the latch block.

Also use a new LoopInfo method to simplify some code.

This fixes Transforms/LoopStrengthReduce/2005-09-12-UsesOutOutsideOfLoop.ll


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23318 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-12 17:11:27 +00:00
Chris Lattner
b6a69e70e0 Add a new getLoopLatch() method.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23315 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-12 17:03:55 +00:00
Chris Lattner
c6bae65b49 _test:
li r2, 0
LBB_test_1:     ; no_exit.2
        li r5, 0
        stw r5, 0(r3)
        addi r2, r2, 1
        addi r3, r3, 4
        cmpwi cr0, r2, 701
        blt cr0, LBB_test_1     ; no_exit.2
LBB_test_2:     ; loopexit.2.loopexit
        addi r2, r2, 1
        stw r2, 0(r4)
        blr
[zion ~/llvm]$ cat > ~/xx
Uses of IV's outside of the loop should use hte post-incremented version
of the IV, not the preincremented version.  This helps many loops (e.g. in sixtrack)
which used to generate code like this (this is the code from the
dont-hoist-simple-loop-constants.ll testcase):

_test:
        li r2, 0                 **** IV starts at 0
LBB_test_1:     ; no_exit.2
        or r5, r2, r2            **** Copy for loop exit
        li r2, 0
        stw r2, 0(r3)
        addi r3, r3, 4
        addi r2, r5, 1
        addi r6, r5, 2           **** IV+2
        cmpwi cr0, r6, 701
        blt cr0, LBB_test_1     ; no_exit.2
LBB_test_2:     ; loopexit.2.loopexit
        addi r2, r5, 2       ****  IV+2
        stw r2, 0(r4)
        blr

And now generated code like this:

_test:
        li r2, 1               *** IV starts at 1
LBB_test_1:     ; no_exit.2
        li r5, 0
        stw r5, 0(r3)
        addi r2, r2, 1
        addi r3, r3, 4
        cmpwi cr0, r2, 701     *** IV.postinc + 0
        blt cr0, LBB_test_1
LBB_test_2:     ; loopexit.2.loopexit
        stw r2, 0(r4)          *** IV.postinc + 0
        blr


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23313 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-12 06:04:47 +00:00
Chris Lattner
7259df3ab8 implement Transforms/LoopStrengthReduce/dont-hoist-simple-loop-constants.ll.
We used to emit this code for it:

_test:
        li r2, 1     ;; Value tying up a register for the whole loop
        li r5, 0
LBB_test_1:     ; no_exit.2
        or r6, r5, r5
        li r5, 0
        stw r5, 0(r3)
        addi r5, r6, 1
        addi r3, r3, 4
        add r7, r2, r5  ;; should be addi r7, r5, 1
        cmpwi cr0, r7, 701
        blt cr0, LBB_test_1     ; no_exit.2
LBB_test_2:     ; loopexit.2.loopexit
        addi r2, r6, 2
        stw r2, 0(r4)
        blr

now we emit this:

_test:
        li r2, 0
LBB_test_1:     ; no_exit.2
        or r5, r2, r2
        li r2, 0
        stw r2, 0(r3)
        addi r3, r3, 4
        addi r2, r5, 1
        addi r6, r5, 2   ;; whoa, fold those adds!
        cmpwi cr0, r6, 701
        blt cr0, LBB_test_1     ; no_exit.2
LBB_test_2:     ; loopexit.2.loopexit
        addi r2, r5, 2
        stw r2, 0(r4)
        blr

more improvement coming.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23306 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-10 01:18:45 +00:00
Chris Lattner
e6ec9f20c9 PowerPC cannot truncstore i1 natively
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23304 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-10 00:21:06 +00:00
Chris Lattner
13d58e71b7 Allow targets to say they don't support truncstore i1 (which includes a mask
when storing to an 8-bit memory location), as most don't.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23303 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-10 00:20:18 +00:00
Chris Lattner
a500fc681d Add a missing #include, patch courtesy of Baptiste Lepilleur.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23302 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-09 23:53:39 +00:00
Chris Lattner
3ec5d74fc5 Fix a problem duraid encountered on itanium where this folding:
select (x < y), 1, 0 -> (x < y) incorrectly: the setcc returns i1 but the
select returned i32.  Add the zero extend as needed.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23301 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-09 23:00:07 +00:00
Chris Lattner
08addbd477 Fix a crash viewing dags that have target nodes in them
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23300 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-09 22:35:03 +00:00
Chris Lattner
c9fe7508a5 I forgot that we always spill fp values as 64-bits. Implement spill folding
for FP as well.  This triggers a couple dozen times on 177.mesa (for example).


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23299 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-09 21:59:44 +00:00
Chris Lattner
f38df04c3a Fix a problem that Nate noticed, where spill code was not getting coallesced
with copies, leading to code like this:

       lwz r4, 380(r1)
       or r10, r4, r4    ;; Last use of r4

By teaching the PPC backend how to fold spills into copies, we now get this
code:

       lwz r10, 380(r1)

wow. :)

This reduces a testcase nate sent me from 1505 instructions to 1484.

Note that this could handle FP values but doesn't currently, for reasons
mentioned in the patch


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23298 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-09 21:46:49 +00:00
Chris Lattner
1463019e84 code cleanup
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23297 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-09 20:51:08 +00:00
Chris Lattner
50ea01ed5b Use continue in the use-processing loop to make it clear what the early exits
are, simplify logic, and cause things to not be nested as deeply.  This also
uses MRI->areAliases instead of an explicit loop.

No functionality change, just code cleanup.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23296 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-09 20:29:51 +00:00
Nate Begeman
39ee1ac7e5 Last round of 2-node folds from SD.cpp. Will move on to 3 node ops such
as setcc and select next.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23295 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-09 19:49:52 +00:00
Chris Lattner
ceb0a52231 remove debugging code *slaps head*
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23294 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-09 19:19:20 +00:00
Chris Lattner
b11443dc84 When spilling a live range that is used multiple times by one instruction,
only add a reload live range once for the instruction.  This is one step
towards fixing a regalloc pessimization that Nate notice, but is later undone
by the spiller (so no code is changed).


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23293 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-09 19:17:47 +00:00
Chris Lattner
043870dd85 Teach the code generator that rlwimi is commutable if the rotate amount
is zero.  This lets the register allocator elide some copies in some cases.

This implements CodeGen/PowerPC/rlwimi-commute.ll


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23292 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-09 18:17:41 +00:00
Chris Lattner
2eb2517fbe Introduce two new concepts:
1. Add support for defining Pattern's, which can match expressions when there
   is no instruction that directly implements something.  Instructions usually
   implicitly define patterns.
2. Add support for defining SDNodeXForm's, which are node transformations.
   This seperates the concept of a node xform out from the existing predicate
   support.

Using this new stuff, we add a few instruction patterns, one for testing, and
two for OR/XOR by an arbitrary immediate.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23286 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-09 00:39:56 +00:00
Chris Lattner
b85c64c4d8 whitespace/comment changes, no functionality diffs
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23283 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-08 23:17:26 +00:00
Nate Begeman
223df2269d Move yet more folds over to the dag combiner from sd.cpp
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23278 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-08 20:18:10 +00:00
Chris Lattner
47f01f1b44 Add a bunch of stuff needed for node type inference. Move 'BLR' down with
the rest of the instructions, add comment markers to seperate portions of
the file into logical parts


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23277 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-08 19:50:41 +00:00
Chris Lattner
bfde080ce0 add patterns for x?oris?
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23268 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-08 17:40:49 +00:00
Chris Lattner
3e63ead49b add patterns to the addi/addis/mulli etc instructions. Define predicates
for matching signed 16-bit and shifted 16-bit ppc immediates


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23267 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-08 17:33:10 +00:00
Chris Lattner
d1cdc7028c Add patterns for some new instructions, allowing the use of the ineg fragment.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23266 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-08 17:01:54 +00:00
Chris Lattner
8c65344a15 ignore generated files
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23263 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-07 23:47:44 +00:00
Chris Lattner
19c0907ba1 Remove some cases handled by the generated portion of the isel
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23262 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-07 23:45:15 +00:00
Nate Begeman
9980119270 Another round of dag combiner changes. This fixes some missing XOR folds
as well as fixing how we replace old values with new values.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23260 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-07 23:25:52 +00:00
Chris Lattner
dc6e2e0a5f Fix a bug that Tzu-Chien Chiu noticed: live interval analysis does NOT
preserve livevar


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23259 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-07 17:34:39 +00:00
Nate Begeman
f89d78d7c7 Implement a common missing fold, (add (add x, c1), c2) -> (add x, c1+c2).
This restores all of stanford to being identical with and without the dag
combiner with the add folding turned off in sd.cpp.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23258 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-07 16:09:19 +00:00
Chris Lattner
c98d823649 On non-apple systems, when using -march=ppc32, do not print:
'' is not a recognized processor for this target (ignoring processor)

Default to "generic" instead of "" for the default CPU.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23257 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-07 05:45:33 +00:00
Chris Lattner
3eb3369a25 Print:
'' is not a recognized processor for this target (ignoring processor)

instead of:

 is not a recognized processor for this target (ignoring processor)


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23256 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-07 05:44:14 +00:00
Chris Lattner
1e111c7bbb Fix a bug nate ran into with replacealluseswith. In the recursive cse case,
we were losing a node, causing an assertion to fail.  Now we eagerly delete
discovered CSE's, and provide an optional vector to keep track of these
discovered equivalences.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23255 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-07 05:37:01 +00:00
Nate Begeman
2300f55046 Add an option to the DAG Combiner to enable it for beta runs, and turn on
that option for PowerPC's beta.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23253 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-07 00:15:36 +00:00
Nate Begeman
c09eeec0eb Implement i64<->fp using the fctidz/fcfid instructions on PowerPC when we
are allowed to generate 64-bit-only PowerPC instructions for 32 bit hosts,
such as the PowerPC 970.

This speeds up 189.lucas from 81.99 to 32.64 seconds.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23250 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-06 22:03:27 +00:00
Andrew Lenharth
46a776e664 Fix up the AssertXext problem, as well as adding it at calls
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23246 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-06 17:00:23 +00:00
Nate Begeman
92cce90c66 Add note about future optimization noted in the ppc compiler writer's guide
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23245 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-06 15:30:48 +00:00
Nate Begeman
d401dff796 Add accessor for 64bit flag, so that we can tell when it is safe to
generate the fun in-register fp<->long instructions.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23244 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-06 15:30:12 +00:00
Nate Begeman
83e75ecd27 Next round of DAGCombiner changes. This version now passes all the tests
I have run so far when run before Legalize.  It still needs to pick up the
SetCC folds, and nodes that use SetCC.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23243 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-06 04:43:02 +00:00
Andrew Lenharth
f71df33671 revert part of the last change, should fix regressions
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23241 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-04 06:12:19 +00:00
Chris Lattner
e147ceb2fa explicitly specify an operands list for patterns with inputs (e.g. neg)
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23240 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-03 01:28:40 +00:00
Chris Lattner
6cd40d5888 include the dag isel fragment
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23239 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-03 01:17:22 +00:00
Chris Lattner
bb38b6f8c0 ask for a dag isel
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23238 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-03 01:15:41 +00:00
Chris Lattner
6a8a21ced4 Fix a checking failure in gs
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23235 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-03 01:04:40 +00:00
Chris Lattner
25dae727f3 Change the isel to not break out of the big giant switch. Instead, the
switch should never be exited, so its bottom is now unreachable.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23234 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-03 00:53:47 +00:00
Chris Lattner
7cd09cf942 rearrange logical ops to group them together more consistently.
Define the PatFrag class which can be used to define subpatterns to match
things with.  Define 'not', and use it to define the patterns for andc,
nand, etc.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23233 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-03 00:21:51 +00:00
Chris Lattner
6159fb20c2 Add AND/OR/XOR
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23232 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-02 22:35:53 +00:00
Nate Begeman
646d7e2727 Next round of DAG Combiner changes. Just need to support multiple return
values, and then we should be able to hook it up.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23231 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-02 21:18:40 +00:00
Chris Lattner
218a15d02c Add some initial patterns to simple binary instructions, though they
currently don't do anything.  This elides patterns for binary operators
that ping on the carry flag, since we don't model it yet.

This patch also removes PPC::SUB, because it is dead.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23230 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-02 21:18:00 +00:00
Chris Lattner
6fdcb250d5 Clean up some code from the last checkin
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23229 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-02 20:32:45 +00:00
Chris Lattner
99c25b86aa Fix a bug in legalize where it would emit two calls to libcalls that return
i64 values on targets that need that expanded to 32-bit registers.  This fixes
PowerPC/2005-09-02-LegalizeDuplicatesCalls.ll and speeds up 189.lucas from
taking 122.72s to 81.96s on my desktop.


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23228 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-02 20:26:58 +00:00
Chris Lattner
73e37c35be turn on dag isel by default
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23226 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-02 19:53:54 +00:00
Chris Lattner
70b9b1098a Make sure to auto-cse nullary ops
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@23224 91177308-0d34-0410-b5e6-96231b3b80d8
2005-09-02 19:36:17 +00:00