1
0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-10-30 07:22:55 +01:00
Commit Graph

1124 Commits

Author SHA1 Message Date
Chris Lattner
a295128ce5 Fix a bug where we would 'promote' an allocation from one type to another
where the second has less alignment required.  If we had explicit alignment
support in the IR, we could handle this case, but we can't until we do.

llvm-svn: 23960
2005-10-24 06:26:18 +00:00
Chris Lattner
3806b84861 Before promoting a malloc type, remove dead uses. This makes instcombine
more effective at promoting these allocations, catching them earlier in the
compile process.

llvm-svn: 23959
2005-10-24 06:22:12 +00:00
Chris Lattner
5ad6f085ab Pull some code out into a function, no functionality change
llvm-svn: 23958
2005-10-24 06:03:58 +00:00
Chris Lattner
e6f7a38925 DONT_BUILD_RELINKED is gone and implied by BUILD_ARCHIVE now
llvm-svn: 23940
2005-10-24 02:26:13 +00:00
Chris Lattner
a4b13acd52 Only build .a file versions of these libraries, instead of .a and .o versions.
This should speed up build times.

llvm-svn: 23933
2005-10-24 01:59:48 +00:00
Chris Lattner
46cc930a67 Make sure that anything using the ADCE pass pulls in the UnifyFunctionExitNodes
code

llvm-svn: 23931
2005-10-24 01:40:23 +00:00
Jeff Cohen
a38c737e85 When a function takes a variable number of pointer arguments, with a zero
pointer marking the end of the list, the zero *must* be cast to the pointer
type.  An un-cast zero is a 32-bit int, and at least on x86_64, gcc will
not extend the zero to 64 bits, thus allowing the upper 32 bits to be
random junk.

The new END_WITH_NULL macro may be used to annotate a such a function
so that GCC (version 4 or newer) will detect the use of un-casted zero
at compile time.

llvm-svn: 23888
2005-10-23 04:37:20 +00:00
Chris Lattner
63aa74e804 My previous patch was too conservative. Reject FP and void types, but do
allow pointer types.

llvm-svn: 23859
2005-10-21 05:45:41 +00:00
Chris Lattner
3451ac7691 Do NOT touch FP ops with LSR. This fixes a testcase Nate sent me from an
inner loop like this:

LBB_RateConvertMono8AltiVec_2:  ; no_exit
        lis r2, ha16(.CPI_RateConvertMono8AltiVec_0)
        lfs f3, lo16(.CPI_RateConvertMono8AltiVec_0)(r2)
        fmr f3, f3
        fadd f0, f2, f0
        fadd f3, f0, f3
        fcmpu cr0, f3, f1
        bge cr0, LBB_RateConvertMono8AltiVec_2  ; no_exit

to an inner loop like this:

LBB_RateConvertMono8AltiVec_1:  ; no_exit
        fsub f2, f2, f1
        fcmpu cr0, f2, f1
        fmr f0, f2
        bge cr0, LBB_RateConvertMono8AltiVec_1  ; no_exit

Doh! good catch!

llvm-svn: 23838
2005-10-20 04:47:10 +00:00
Chris Lattner
515ce6687d Make this work for FP constantexprs
llvm-svn: 23773
2005-10-17 20:18:38 +00:00
Chris Lattner
09b3b3d658 Oops, X+0.0 isn't foldable, but X+-0.0 is.
llvm-svn: 23772
2005-10-17 17:56:38 +00:00
Chris Lattner
00f8306943 relax this a bit, as we only support the default rounding mode
llvm-svn: 23771
2005-10-17 17:49:32 +00:00
Chris Lattner
23ecce5c82 Fix (hopefully the last) issue where LSR is nondeterminstic. When pulling
out CSE's of base expressions it could build a result whose order was
nondet.

llvm-svn: 23698
2005-10-11 18:41:04 +00:00
Chris Lattner
7effc54496 Fix another problem where LSR was being nondeterminstic. Also remove elements
from the end of a vector instead of the beginning

llvm-svn: 23697
2005-10-11 18:30:57 +00:00
Chris Lattner
1ec477da8f Fix another lsr-is-nondeterministic case
llvm-svn: 23695
2005-10-11 18:17:57 +00:00
Chris Lattner
1809933a31 Make MaskedValueIsZero a bit more aggressive
llvm-svn: 23677
2005-10-09 22:08:50 +00:00
Chris Lattner
d4ff47daf6 Fix funky xcode indentation
llvm-svn: 23674
2005-10-09 06:36:35 +00:00
Chris Lattner
f6c2411c40 Hrm, you didn't see this.
llvm-svn: 23673
2005-10-09 06:24:02 +00:00
Chris Lattner
6fa98d5979 Fix a source of non-determinism in the backend: the order of processing
IV strides dependend on the pointer order of the strides in memory.
Non-determinism is bad.

llvm-svn: 23672
2005-10-09 06:20:55 +00:00
Jeff Cohen
3c6db93125 Remove useless variable.
llvm-svn: 23656
2005-10-07 05:28:29 +00:00
Chris Lattner
be6f88a2e8 Make IVUseShouldUsePostIncValue more aggressive when the use is a PHI. In
particular, it should realize that phi's use their values in the pred block
not the phi block itself.  This change turns our em3d loop from this:

_test:
        cmpwi cr0, r4, 0
        bgt cr0, LBB_test_2     ; entry.no_exit_crit_edge
LBB_test_1:     ; entry.loopexit_crit_edge
        li r2, 0
        b LBB_test_6    ; loopexit
LBB_test_2:     ; entry.no_exit_crit_edge
        li r6, 0
LBB_test_3:     ; no_exit
        or r2, r6, r6
        lwz r6, 0(r3)
        cmpw cr0, r6, r5
        beq cr0, LBB_test_6     ; loopexit
LBB_test_4:     ; endif
        addi r3, r3, 4
        addi r6, r2, 1
        cmpw cr0, r6, r4
        blt cr0, LBB_test_3     ; no_exit
LBB_test_5:     ; endif.loopexit.loopexit_crit_edge
        addi r3, r2, 1
        blr
LBB_test_6:     ; loopexit
        or r3, r2, r2
        blr

into:

_test:
        cmpwi cr0, r4, 0
        bgt cr0, LBB_test_2     ; entry.no_exit_crit_edge
LBB_test_1:     ; entry.loopexit_crit_edge
        li r2, 0
        b LBB_test_5    ; loopexit
LBB_test_2:     ; entry.no_exit_crit_edge
        li r6, 0
LBB_test_3:     ; no_exit
        lwz r2, 0(r3)
        cmpw cr0, r2, r5
        or r2, r6, r6
        beq cr0, LBB_test_5     ; loopexit
LBB_test_4:     ; endif
        addi r3, r3, 4
        addi r6, r6, 1
        cmpw cr0, r6, r4
        or r2, r6, r6
        blt cr0, LBB_test_3     ; no_exit
LBB_test_5:     ; loopexit
        or r3, r2, r2
        blr


Unfortunately, this is actually worse code, because the register coallescer
is getting confused somehow.  If it were doing its job right, it could turn the
code into this:

_test:
        cmpwi cr0, r4, 0
        bgt cr0, LBB_test_2     ; entry.no_exit_crit_edge
LBB_test_1:     ; entry.loopexit_crit_edge
        li r6, 0
        b LBB_test_5    ; loopexit
LBB_test_2:     ; entry.no_exit_crit_edge
        li r6, 0
LBB_test_3:     ; no_exit
        lwz r2, 0(r3)
        cmpw cr0, r2, r5
        beq cr0, LBB_test_5     ; loopexit
LBB_test_4:     ; endif
        addi r3, r3, 4
        addi r6, r6, 1
        cmpw cr0, r6, r4
        blt cr0, LBB_test_3     ; no_exit
LBB_test_5:     ; loopexit
        or r3, r6, r6
        blr

... which I'll work on next. :)

llvm-svn: 23604
2005-10-03 02:50:05 +00:00
Chris Lattner
6a5ace34da Refactor some code into a function
llvm-svn: 23603
2005-10-03 01:04:44 +00:00
Chris Lattner
5a865c8598 This break is bogus and I have no idea why it was there. Basically it prevents
memoizing code when IV's are used by phinodes outside of loops.  In a simple
example, we were getting this code before (note that r6 and r7 are isomorphic
IV's):

        li r6, 0
        or r7, r6, r6
LBB_test_3:     ; no_exit
        lwz r2, 0(r3)
        cmpw cr0, r2, r5
        or r2, r7, r7
        beq cr0, LBB_test_5     ; loopexit
LBB_test_4:     ; endif
        addi r2, r7, 1
        addi r7, r7, 1
        addi r3, r3, 4
        addi r6, r6, 1
        cmpw cr0, r6, r4
        blt cr0, LBB_test_3     ; no_exit

Now we get:

        li r6, 0
LBB_test_3:     ; no_exit
        or r2, r6, r6
        lwz r6, 0(r3)
        cmpw cr0, r6, r5
        beq cr0, LBB_test_6     ; loopexit
LBB_test_4:     ; endif
        addi r3, r3, 4
        addi r6, r2, 1
        cmpw cr0, r6, r4
        blt cr0, LBB_test_3     ; no_exit

this was noticed in em3d.

llvm-svn: 23602
2005-10-03 00:37:33 +00:00
Chris Lattner
af938ddbe5 when checking if we should move a split edge block outside of a loop,
check the presplit pred, not the post-split pred.  This was causing us
to make the wrong decision in some cases, leaving the critical edge block
in the loop.

llvm-svn: 23601
2005-10-03 00:31:52 +00:00
Jeff Cohen
412582bcec Fix VC++ warnings.
llvm-svn: 23579
2005-10-01 03:57:14 +00:00
Chris Lattner
633db4c298 Insert stores after phi nodes in the normal dest. This fixes
LowerInvoke/2005-08-03-InvokeWithPHI.ll

llvm-svn: 23525
2005-09-29 17:44:20 +00:00
Chris Lattner
cd79ed877a add a note about a way to improve this code further, that I won't be getting
to right now.

llvm-svn: 23485
2005-09-27 22:44:59 +00:00
Chris Lattner
8ff6df40ba Avoid spilling stack slots... to stack slots.
llvm-svn: 23478
2005-09-27 21:33:12 +00:00
Chris Lattner
b2fa69f4b2 Completely rewrite 'correct' eh support. This changes how setjmp insertion
is performed so it is only at most once per function that contains an invoke
instead of once per invoke in the function.  This patch has the following perks:

1. It fixes PR631, which complains about slowness.
2. If fixes PR240, which complains about non-volatile vars being live across
   setjmp/longjmps.
3. It improves (but does not fix) the jmpbuf alignment issue on itanium by not
   forcing the jmpbufs to always be 8-bytes off the alignment of the structure.
4. It speeds up 253.perlbmk from 338s to 13.70s (a 25x improvement!), making us
   now about 4% faster than GCC.

Further improvements are also possible.

llvm-svn: 23477
2005-09-27 21:18:17 +00:00
Chris Lattner
29f2ba1384 Make the pass name simpler
llvm-svn: 23476
2005-09-27 21:10:32 +00:00
Chris Lattner
7c43a40871 Eliminate GetGEPGlobalInitializer in favor of the more powerful
ConstantFoldLoadThroughGEPConstantExpr function in the utils lib.

llvm-svn: 23446
2005-09-26 05:28:52 +00:00
Chris Lattner
6df0a740e8 Factor the GetGEPGlobalInitializer out of this pass and into Transforms/Utils
as ConstantFoldLoadThroughGEPConstantExpr.

llvm-svn: 23445
2005-09-26 05:28:06 +00:00
Chris Lattner
e6bfd80169 Move MaskedValueIsZero up.
Match a bunch of idioms for sign extensions, implementing InstCombine/signext.ll

llvm-svn: 23428
2005-09-24 23:43:33 +00:00
Chris Lattner
e40e2d4ec3 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 :)

llvm-svn: 23386
2005-09-18 07:22:02 +00:00
Chris Lattner
024a1c1a46 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

llvm-svn: 23385
2005-09-18 06:30:59 +00:00
Chris Lattner
3cd5e466ee 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

llvm-svn: 23384
2005-09-18 06:02:59 +00:00
Chris Lattner
b70b011734 fix typeo
llvm-svn: 23383
2005-09-18 05:25:20 +00:00
Chris Lattner
7fda14c978 Remove unintentionally committed code
llvm-svn: 23382
2005-09-18 05:12:51 +00:00
Chris Lattner
ae35713f00 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

llvm-svn: 23381
2005-09-18 05:12:10 +00:00
Chris Lattner
fa22870351 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

llvm-svn: 23379
2005-09-18 04:24:45 +00:00
Chris Lattner
c96a222019 remove debug output
llvm-svn: 23377
2005-09-18 03:50:25 +00:00
Chris Lattner
1466ade38b 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

llvm-svn: 23376
2005-09-18 03:42:07 +00:00
Chris Lattner
c7fe78d9a1 Fix the regression last night compiling povray
llvm-svn: 23348
2005-09-14 17:32:56 +00:00
Chris Lattner
f020513d57 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.

llvm-svn: 23328
2005-09-13 18:36:04 +00:00
Chris Lattner
26aef8992f 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.

llvm-svn: 23327
2005-09-13 02:09:55 +00:00
Chris Lattner
4284014415 Add a helper function, allowing us to simplify some code a bit, changing
indentation, no functionality change

llvm-svn: 23325
2005-09-13 00:40:14 +00:00
Chris Lattner
d35d5d2492 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.

llvm-svn: 23324
2005-09-12 23:23:25 +00:00
Chris Lattner
6eee5b16b1 Another load-peephole optimization: do gcse when two loads are next to
each other.  This implements InstCombine/load.ll:test9

llvm-svn: 23322
2005-09-12 22:21:03 +00:00
Chris Lattner
2657841260 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).

llvm-svn: 23320
2005-09-12 22:00:15 +00:00
Chris Lattner
a949a2836d 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

llvm-svn: 23318
2005-09-12 17:11:27 +00:00
Chris Lattner
780ffd9c1f _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

llvm-svn: 23313
2005-09-12 06:04:47 +00:00
Chris Lattner
ddec75fdf6 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.

llvm-svn: 23306
2005-09-10 01:18:45 +00:00
Chris Lattner
371f542759 Fix a problem that Dan Berlin noticed, where reassociation would not succeed
in building maximal expressions before simplifying them.  In particular, i
cases like this:

X-(A+B+X)

the code would consider A+B+X to be a maximal expression (not understanding
that the single use '-' would be turned into a + later), simplify it (a noop)
then later get simplified again.

Each of these simplify steps is where the cost of reassociation comes from,
so this patch should speed up the already fast pass a bit.

Thanks to Dan for noticing this!

llvm-svn: 23214
2005-09-02 07:07:58 +00:00
Chris Lattner
4cade5915d Avoid creating garbage instructions, just move the old add instruction
to where we need it when converting -(A+B+C) -> -A + -B + -C.

llvm-svn: 23213
2005-09-02 06:38:04 +00:00
Chris Lattner
dfba6f5029 add some assertions and fix problems where reassociate could access the
Ops vector out of range

llvm-svn: 23211
2005-09-02 05:23:22 +00:00
Chris Lattner
efc5937add Fix Regression/Transforms/Reassociate/2005-08-24-Crash.ll
llvm-svn: 23019
2005-08-24 17:55:32 +00:00
Chris Lattner
a852093954 Fix Transforms/LoopStrengthReduce/2005-08-17-OutOfLoopVariant.ll, a crash
on 177.mesa

llvm-svn: 22843
2005-08-17 21:22:41 +00:00
Chris Lattner
969232d2ec Use a new helper to split critical edges, making the code simpler.
Do not claim to not change the CFG.  We do change the cfg to split critical
edges.  This isn't causing us a problem now, but could likely do so in the
future.

llvm-svn: 22824
2005-08-17 06:35:16 +00:00
Chris Lattner
bc70c99aef Fix a bad case in gzip where we put lots of things in registers across the
loop, because a IV-dependent value was used outside of the loop and didn't
have immediate-folding capability

llvm-svn: 22798
2005-08-16 00:38:11 +00:00
Chris Lattner
57a2a74e99 Ooops, don't forget to clear this. The real inner loop is now:
.LBB_foo_3:     ; no_exit.1
        lfd f2, 0(r9)
        lfd f3, 8(r9)
        fmul f4, f1, f2
        fmadd f4, f0, f3, f4
        stfd f4, 8(r9)
        fmul f3, f1, f3
        fmsub f2, f0, f2, f3
        stfd f2, 0(r9)
        addi r9, r9, 16
        addi r8, r8, 1
        cmpw cr0, r8, r4
        ble .LBB_foo_3  ; no_exit.1

llvm-svn: 22782
2005-08-13 07:42:01 +00:00
Chris Lattner
f59e855dbc Recursively scan scev expressions for common subexpressions. This allows us
to handle nested loops much better, for example, by being able to tell that
these two expressions:

{( 8 + ( 16 * ( 1 +  %Tmp11 +  %Tmp12)) +  %c_),+,( 16 *  %Tmp 12)}<loopentry.1>

{(( 16 * ( 1 +  %Tmp11 +  %Tmp12)) +  %c_),+,( 16 *  %Tmp12)}<loopentry.1>

Have the following common part that can be shared:
{(( 16 * ( 1 +  %Tmp11 +  %Tmp12)) +  %c_),+,( 16 *  %Tmp12)}<loopentry.1>

This allows us to codegen an important inner loop in 168.wupwise as:

.LBB_foo_4:     ; no_exit.1
        lfd f2, 16(r9)
        fmul f3, f0, f2
        fmul f2, f1, f2
        fadd f4, f3, f2
        stfd f4, 8(r9)
        fsub f2, f3, f2
        stfd f2, 16(r9)
        addi r8, r8, 1
        addi r9, r9, 16
        cmpw cr0, r8, r4
        ble .LBB_foo_4  ; no_exit.1

instead of:

.LBB_foo_3:     ; no_exit.1
        lfdx f2, r6, r9
        add r10, r6, r9
        lfd f3, 8(r10)
        fmul f4, f1, f2
        fmadd f4, f0, f3, f4
        stfd f4, 8(r10)
        fmul f3, f1, f3
        fmsub f2, f0, f2, f3
        stfdx f2, r6, r9
        addi r9, r9, 16
        addi r8, r8, 1
        cmpw cr0, r8, r4
        ble .LBB_foo_3  ; no_exit.1

llvm-svn: 22781
2005-08-13 07:27:18 +00:00
Chris Lattner
87bcd2794b remove dead code. The exit block list is computed on demand, thus does not
need to be updated.  This code is a relic from when it did.

llvm-svn: 22775
2005-08-13 01:30:36 +00:00
Chris Lattner
811ef4cce0 When splitting critical edges, make sure not to leave the new block in the
middle of the loop.  This turns a critical loop in gzip into this:

.LBB_test_1:    ; loopentry
        or r27, r28, r28
        add r28, r3, r27
        lhz r28, 3(r28)
        add r26, r4, r27
        lhz r26, 3(r26)
        cmpw cr0, r28, r26
        bne .LBB_test_8 ; loopentry.loopexit_crit_edge
.LBB_test_2:    ; shortcirc_next.0
        add r28, r3, r27
        lhz r28, 5(r28)
        add r26, r4, r27
        lhz r26, 5(r26)
        cmpw cr0, r28, r26
        bne .LBB_test_7 ; shortcirc_next.0.loopexit_crit_edge
.LBB_test_3:    ; shortcirc_next.1
        add r28, r3, r27
        lhz r28, 7(r28)
        add r26, r4, r27
        lhz r26, 7(r26)
        cmpw cr0, r28, r26
        bne .LBB_test_6 ; shortcirc_next.1.loopexit_crit_edge
.LBB_test_4:    ; shortcirc_next.2
        add r28, r3, r27
        lhz r26, 9(r28)
        add r28, r4, r27
        lhz r25, 9(r28)
        addi r28, r27, 8
        cmpw cr7, r26, r25
        mfcr r26, 1
        rlwinm r26, r26, 31, 31, 31
        add r25, r8, r27
        cmpw cr7, r25, r7
        mfcr r25, 1
        rlwinm r25, r25, 29, 31, 31
        and. r26, r26, r25
        bne .LBB_test_1 ; loopentry

instead of this:

.LBB_test_1:    ; loopentry
        or r27, r28, r28
        add r28, r3, r27
        lhz r28, 3(r28)
        add r26, r4, r27
        lhz r26, 3(r26)
        cmpw cr0, r28, r26
        beq .LBB_test_3 ; shortcirc_next.0
.LBB_test_2:    ; loopentry.loopexit_crit_edge
        add r2, r30, r27
        add r8, r29, r27
        b .LBB_test_9   ; loopexit
.LBB_test_3:    ; shortcirc_next.0
        add r28, r3, r27
        lhz r28, 5(r28)
        add r26, r4, r27
        lhz r26, 5(r26)
        cmpw cr0, r28, r26
        beq .LBB_test_5 ; shortcirc_next.1
.LBB_test_4:    ; shortcirc_next.0.loopexit_crit_edge
        add r2, r11, r27
        add r8, r12, r27
        b .LBB_test_9   ; loopexit
.LBB_test_5:    ; shortcirc_next.1
        add r28, r3, r27
        lhz r28, 7(r28)
        add r26, r4, r27
        lhz r26, 7(r26)
        cmpw cr0, r28, r26
        beq .LBB_test_7 ; shortcirc_next.2
.LBB_test_6:    ; shortcirc_next.1.loopexit_crit_edge
        add r2, r9, r27
        add r8, r10, r27
        b .LBB_test_9   ; loopexit
.LBB_test_7:    ; shortcirc_next.2
        add r28, r3, r27
        lhz r26, 9(r28)
        add r28, r4, r27
        lhz r25, 9(r28)
        addi r28, r27, 8
        cmpw cr7, r26, r25
        mfcr r26, 1
        rlwinm r26, r26, 31, 31, 31
        add r25, r8, r27
        cmpw cr7, r25, r7
        mfcr r25, 1
        rlwinm r25, r25, 29, 31, 31
        and. r26, r26, r25
        bne .LBB_test_1 ; loopentry

Next up, improve the code for the loop.

llvm-svn: 22769
2005-08-12 22:22:17 +00:00
Chris Lattner
a5c0038c25 Fix a FIXME: if we are inserting code for a PHI argument, split the critical
edge so that the code is not always executed for both operands.  This
prevents LSR from inserting code into loops whose exit blocks contain
PHI uses of IV expressions (which are outside of loops).  On gzip, for
example, we turn this ugly code:

.LBB_test_1:    ; loopentry
        add r27, r3, r28
        lhz r27, 3(r27)
        add r26, r4, r28
        lhz r26, 3(r26)
        add r25, r30, r28    ;; Only live if exiting the loop
        add r24, r29, r28    ;; Only live if exiting the loop
        cmpw cr0, r27, r26
        bne .LBB_test_5 ; loopexit

into this:

.LBB_test_1:    ; loopentry
        or r27, r28, r28
        add r28, r3, r27
        lhz r28, 3(r28)
        add r26, r4, r27
        lhz r26, 3(r26)
        cmpw cr0, r28, r26
        beq .LBB_test_3 ; shortcirc_next.0
.LBB_test_2:    ; loopentry.loopexit_crit_edge
        add r2, r30, r27
        add r8, r29, r27
        b .LBB_test_9   ; loopexit
.LBB_test_2:    ; shortcirc_next.0
        ...
        blt .LBB_test_1


into this:

.LBB_test_1:    ; loopentry
        or r27, r28, r28
        add r28, r3, r27
        lhz r28, 3(r28)
        add r26, r4, r27
        lhz r26, 3(r26)
        cmpw cr0, r28, r26
        beq .LBB_test_3 ; shortcirc_next.0
.LBB_test_2:    ; loopentry.loopexit_crit_edge
        add r2, r30, r27
        add r8, r29, r27
        b .LBB_t_3:    ; shortcirc_next.0
.LBB_test_3:    ; shortcirc_next.0
        ...
        blt .LBB_test_1


Next step: get the block out of the loop so that the loop is all
fall-throughs again.

llvm-svn: 22766
2005-08-12 22:06:11 +00:00
Chris Lattner
67cef1a1d8 remove some trickiness that broke yacr2 and some other programs last night
llvm-svn: 22751
2005-08-10 17:15:20 +00:00
Chris Lattner
179fc33e59 Make loop-simplify produce better loops by turning PHI nodes like X = phi [X, Y]
into just Y.  This often occurs when it seperates loops that have collapsed loop
headers.  This implements LoopSimplify/phi-node-simplify.ll

llvm-svn: 22746
2005-08-10 02:07:32 +00:00
Chris Lattner
4ac016991c Allow indvar simplify to canonicalize ANY affine IV, not just affine IVs with
constant stride.  This implements Transforms/IndVarsSimplify/variable-stride-ivs.ll

llvm-svn: 22744
2005-08-10 01:12:06 +00:00
Chris Lattner
8c7e769325 Teach LSR to strength reduce IVs that have a loop-invariant but non-constant stride.
For code like this:

void foo(float *a, float *b, int n, int stride_a, int stride_b) {
  int i;
  for (i=0; i<n; i++)
      a[i*stride_a] = b[i*stride_b];
}

we now emit:

.LBB_foo2_2:    ; no_exit
        lfs f0, 0(r4)
        stfs f0, 0(r3)
        addi r7, r7, 1
        add r4, r2, r4
        add r3, r6, r3
        cmpw cr0, r7, r5
        blt .LBB_foo2_2 ; no_exit

instead of:

.LBB_foo_2:     ; no_exit
        mullw r8, r2, r7     ;; multiply!
        slwi r8, r8, 2
        lfsx f0, r4, r8
        mullw r8, r2, r6     ;; multiply!
        slwi r8, r8, 2
        stfsx f0, r3, r8
        addi r2, r2, 1
        cmpw cr0, r2, r5
        blt .LBB_foo_2  ; no_exit

loops with variable strides occur pretty often.  For example, in SPECFP2K
there are 317 variable strides in 177.mesa, 3 in 179.art, 14 in 188.ammp,
56 in 168.wupwise, 36 in 172.mgrid.

Now we can allow indvars to turn functions written like this:

void foo2(float *a, float *b, int n, int stride_a, int stride_b) {
  int i, ai = 0, bi = 0;
  for (i=0; i<n; i++)
    {
      a[ai] = b[bi];
      ai += stride_a;
      bi += stride_b;
    }
}

into code like the above for better analysis.  With this patch, they generate
identical code.

llvm-svn: 22740
2005-08-10 00:45:21 +00:00
Chris Lattner
3d251b90f3 Fix Regression/Transforms/LoopStrengthReduce/phi_node_update_multiple_preds.ll
by being more careful about updating PHI nodes

llvm-svn: 22739
2005-08-10 00:35:32 +00:00
Chris Lattner
24f927cfe9 Fix some 80 column violations.
Once we compute the evolution for a GEP, tell SE about it.  This allows users
of the GEP to know it, if the users are not direct.  This allows us to compile
this testcase:

void fbSolidFillmmx(int w, unsigned char *d) {
    while (w >= 64) {
        *(unsigned long long *) (d +  0) = 0;
        *(unsigned long long *) (d +  8) = 0;
        *(unsigned long long *) (d + 16) = 0;
        *(unsigned long long *) (d + 24) = 0;
        *(unsigned long long *) (d + 32) = 0;
        *(unsigned long long *) (d + 40) = 0;
        *(unsigned long long *) (d + 48) = 0;
        *(unsigned long long *) (d + 56) = 0;
        w -= 64;
        d += 64;
    }
}

into:

.LBB_fbSolidFillmmx_2:  ; no_exit
        li r2, 0
        stw r2, 0(r4)
        stw r2, 4(r4)
        stw r2, 8(r4)
        stw r2, 12(r4)
        stw r2, 16(r4)
        stw r2, 20(r4)
        stw r2, 24(r4)
        stw r2, 28(r4)
        stw r2, 32(r4)
        stw r2, 36(r4)
        stw r2, 40(r4)
        stw r2, 44(r4)
        stw r2, 48(r4)
        stw r2, 52(r4)
        stw r2, 56(r4)
        stw r2, 60(r4)
        addi r4, r4, 64
        addi r3, r3, -64
        cmpwi cr0, r3, 63
        bgt .LBB_fbSolidFillmmx_2       ; no_exit

instead of:

.LBB_fbSolidFillmmx_2:  ; no_exit
        li r11, 0
        stw r11, 0(r4)
        stw r11, 4(r4)
        stwx r11, r10, r4
        add r12, r10, r4
        stw r11, 4(r12)
        stwx r11, r9, r4
        add r12, r9, r4
        stw r11, 4(r12)
        stwx r11, r8, r4
        add r12, r8, r4
        stw r11, 4(r12)
        stwx r11, r7, r4
        add r12, r7, r4
        stw r11, 4(r12)
        stwx r11, r6, r4
        add r12, r6, r4
        stw r11, 4(r12)
        stwx r11, r5, r4
        add r12, r5, r4
        stw r11, 4(r12)
        stwx r11, r2, r4
        add r12, r2, r4
        stw r11, 4(r12)
        addi r4, r4, 64
        addi r3, r3, -64
        cmpwi cr0, r3, 63
        bgt .LBB_fbSolidFillmmx_2       ; no_exit

llvm-svn: 22737
2005-08-09 23:39:36 +00:00
Chris Lattner
2872f369f0 SCEVAddExpr::get() of an empty list is invalid.
llvm-svn: 22724
2005-08-09 01:13:47 +00:00
Chris Lattner
11dd32a826 Implement: LoopStrengthReduce/share_ivs.ll
Two changes:
  * Only insert one PHI node for each stride.  Other values are live in
    values.  This cannot introduce higher register pressure than the
    previous approach, and can take advantage of reg+reg addressing modes.
  * Factor common base values out of uses before moving values from the
    base to the immediate fields.  This improves codegen by starting the
    stride-specific PHI node out at a common place for each IV use.

As an example, we used to generate this for a loop in swim:

.LBB_main_no_exit_2E_6_2E_i_no_exit_2E_7_2E_i_2:        ; no_exit.7.i
        lfd f0, 0(r8)
        stfd f0, 0(r3)
        lfd f0, 0(r6)
        stfd f0, 0(r7)
        lfd f0, 0(r2)
        stfd f0, 0(r5)
        addi r9, r9, 1
        addi r2, r2, 8
        addi r5, r5, 8
        addi r6, r6, 8
        addi r7, r7, 8
        addi r8, r8, 8
        addi r3, r3, 8
        cmpw cr0, r9, r4
        bgt .LBB_main_no_exit_2E_6_2E_i_no_exit_2E_7_2E_i_1

now we emit:

.LBB_main_no_exit_2E_6_2E_i_no_exit_2E_7_2E_i_2:        ; no_exit.7.i
        lfdx f0, r8, r2
        stfdx f0, r9, r2
        lfdx f0, r5, r2
        stfdx f0, r7, r2
        lfdx f0, r3, r2
        stfdx f0, r6, r2
        addi r10, r10, 1
        addi r2, r2, 8
        cmpw cr0, r10, r4
        bgt .LBB_main_no_exit_2E_6_2E_i_no_exit_2E_7_2E_i_1

As another more dramatic example, we used to emit this:

.LBB_main_L_90_no_exit_2E_0_2E_i16_no_exit_2E_1_2E_i19_2:       ; no_exit.1.i19
        lfd f0, 8(r21)
        lfd f4, 8(r3)
        lfd f5, 8(r27)
        lfd f6, 8(r22)
        lfd f7, 8(r5)
        lfd f8, 8(r6)
        lfd f9, 8(r30)
        lfd f10, 8(r11)
        lfd f11, 8(r12)
        fsub f10, f10, f11
        fadd f5, f4, f5
        fmul f5, f5, f1
        fadd f6, f6, f7
        fadd f6, f6, f8
        fadd f6, f6, f9
        fmadd f0, f5, f6, f0
        fnmsub f0, f10, f2, f0
        stfd f0, 8(r4)
        lfd f0, 8(r25)
        lfd f5, 8(r26)
        lfd f6, 8(r23)
        lfd f9, 8(r28)
        lfd f10, 8(r10)
        lfd f12, 8(r9)
        lfd f13, 8(r29)
        fsub f11, f13, f11
        fadd f4, f4, f5
        fmul f4, f4, f1
        fadd f5, f6, f9
        fadd f5, f5, f10
        fadd f5, f5, f12
        fnmsub f0, f4, f5, f0
        fnmsub f0, f11, f3, f0
        stfd f0, 8(r24)
        lfd f0, 8(r8)
        fsub f4, f7, f8
        fsub f5, f12, f10
        fnmsub f0, f5, f2, f0
        fnmsub f0, f4, f3, f0
        stfd f0, 8(r2)
        addi r20, r20, 1
        addi r2, r2, 8
        addi r8, r8, 8
        addi r10, r10, 8
        addi r12, r12, 8
        addi r6, r6, 8
        addi r29, r29, 8
        addi r28, r28, 8
        addi r26, r26, 8
        addi r25, r25, 8
        addi r24, r24, 8
        addi r5, r5, 8
        addi r23, r23, 8
        addi r22, r22, 8
        addi r3, r3, 8
        addi r9, r9, 8
        addi r11, r11, 8
        addi r30, r30, 8
        addi r27, r27, 8
        addi r21, r21, 8
        addi r4, r4, 8
        cmpw cr0, r20, r7
        bgt .LBB_main_L_90_no_exit_2E_0_2E_i16_no_exit_2E_1_2E_i19_1

we now emit:

.LBB_main_L_90_no_exit_2E_0_2E_i16_no_exit_2E_1_2E_i19_2:       ; no_exit.1.i19
        lfdx f0, r21, r20
        lfdx f4, r3, r20
        lfdx f5, r27, r20
        lfdx f6, r22, r20
        lfdx f7, r5, r20
        lfdx f8, r6, r20
        lfdx f9, r30, r20
        lfdx f10, r11, r20
        lfdx f11, r12, r20
        fsub f10, f10, f11
        fadd f5, f4, f5
        fmul f5, f5, f1
        fadd f6, f6, f7
        fadd f6, f6, f8
        fadd f6, f6, f9
        fmadd f0, f5, f6, f0
        fnmsub f0, f10, f2, f0
        stfdx f0, r4, r20
        lfdx f0, r25, r20
        lfdx f5, r26, r20
        lfdx f6, r23, r20
        lfdx f9, r28, r20
        lfdx f10, r10, r20
        lfdx f12, r9, r20
        lfdx f13, r29, r20
        fsub f11, f13, f11
        fadd f4, f4, f5
        fmul f4, f4, f1
        fadd f5, f6, f9
        fadd f5, f5, f10
        fadd f5, f5, f12
        fnmsub f0, f4, f5, f0
        fnmsub f0, f11, f3, f0
        stfdx f0, r24, r20
        lfdx f0, r8, r20
        fsub f4, f7, f8
        fsub f5, f12, f10
        fnmsub f0, f5, f2, f0
        fnmsub f0, f4, f3, f0
        stfdx f0, r2, r20
        addi r19, r19, 1
        addi r20, r20, 8
        cmpw cr0, r19, r7
        bgt .LBB_main_L_90_no_exit_2E_0_2E_i16_no_exit_2E_1_2E_i19_1

llvm-svn: 22722
2005-08-09 00:18:09 +00:00
Chris Lattner
ea50bf5aca Suck the base value out of the UsersToProcess vector into the BasedUser
class to simplify the code.  Fuse two loops.

llvm-svn: 22721
2005-08-08 22:56:21 +00:00
Chris Lattner
b9d13099a7 Split MoveLoopVariantsToImediateField out from MoveImmediateValues. The
first is a correctness thing, and the later is an optzn thing.  This also
is needed to support a future change.

llvm-svn: 22720
2005-08-08 22:32:34 +00:00
Chris Lattner
c6571e5c64 Use the new 'moveBefore' method to simplify some code. Really, which is
easier to understand?  :)

llvm-svn: 22706
2005-08-08 19:11:57 +00:00
Chris Lattner
f6e6e25039 Not all constants are legal immediates in load/store instructions.
llvm-svn: 22704
2005-08-08 06:25:50 +00:00
Chris Lattner
ab45a77fed Implement LoopStrengthReduce/share_code_in_preheader.ll by having one
rewriter for all code inserted into the preheader, which is never flushed.

llvm-svn: 22702
2005-08-08 05:47:49 +00:00
Chris Lattner
dd97325bc0 Implement a simple optimization for the termination condition of the loop.
The termination condition actually wants to use the post-incremented value
of the loop, not a new indvar with an unusual base.

On PPC, for example, this allows us to compile
LoopStrengthReduce/exit_compare_live_range.ll to:

_foo:
        li r2, 0
.LBB_foo_1:     ; no_exit
        li r5, 0
        stw r5, 0(r3)
        addi r2, r2, 1
        cmpw cr0, r2, r4
        bne .LBB_foo_1  ; no_exit
        blr

instead of:

_foo:
        li r2, 1                ;; IV starts at 1, not 0
.LBB_foo_1:     ; no_exit
        li r5, 0
        stw r5, 0(r3)
        addi r5, r2, 1
        cmpw cr0, r2, r4
        or r2, r5, r5           ;; Reg-reg copy, extra live range
        bne .LBB_foo_1  ; no_exit
        blr

This implements LoopStrengthReduce/exit_compare_live_range.ll

llvm-svn: 22699
2005-08-08 05:28:22 +00:00
Chris Lattner
bbab417e32 Add some simple folds that occur in bitfield cases. Fix a minor bug in
isHighOnes, where it would consider 0 to have high ones.

llvm-svn: 22693
2005-08-07 07:03:10 +00:00
Chris Lattner
427319ff4b Fix typoCVS: ----------------------------------------------------------------------
llvm-svn: 22692
2005-08-07 07:00:52 +00:00
Chris Lattner
5b499da0a7 * Use the new PHINode::hasConstantValue method to simplify some code
* Teach this code to move allocas out of the loop when tail call eliminating
  a call marked 'tail'.  This implements TailCallElim/move_alloca_for_tail_call.ll
* Do not perform this transformation if a call is marked 'tail' and if there
  are allocas that we cannot move out of the loop in #2.  Doing so would increase
  the stack usage of the function.  This implements fixes
  PR615 and TailCallElim/dont-tce-tail-marked-call.ll.

llvm-svn: 22690
2005-08-07 04:27:41 +00:00
Chris Lattner
547cf56441 Make sure to clean CastedPointers after casts are potentially deleted.
This fixes LSR crashes on 301.apsi, 191.fma3d, and 189.lucas

llvm-svn: 22673
2005-08-05 01:30:11 +00:00
Chris Lattner
6fa790692f now that hasConstantValue defaults to only returning values that dominate
the PHI node, this ugly code can vanish.

llvm-svn: 22672
2005-08-05 01:04:30 +00:00
Chris Lattner
915053ba79 This code can handle non-dominating instructions
llvm-svn: 22667
2005-08-05 00:57:45 +00:00
Nate Begeman
ef41400067 Fix a fixme in CondPropagate.cpp by moving a PhiNode optimization into
BasicBlock's removePredecessor routine.  This requires shuffling around
the definition and implementation of hasContantValue from Utils.h,cpp into
Instructions.h,cpp

llvm-svn: 22664
2005-08-04 23:24:19 +00:00
Chris Lattner
855cfc4e90 Modify how immediates are removed from base expressions to deal with the fact
that the symbolic evaluator is not always able to use subtraction to remove
expressions.  This makes the code faster, and fixes the last crash on 178.galgel.
Finally, add a statistic to see how many phi nodes are inserted.

On 178.galgel, we get the follow stats:

2562 loop-reduce  - Number of PHIs inserted
3927 loop-reduce  - Number of GEPs strength reduced

llvm-svn: 22662
2005-08-04 22:34:05 +00:00
Chris Lattner
07466ea612 * Refactor some code into a new BasedUser::RewriteInstructionToUseNewBase
method.
* Fix a crash on 178.galgel, where we would insert expressions before PHI
  nodes instead of into the PHI node predecessor blocks.

llvm-svn: 22657
2005-08-04 20:03:32 +00:00
Chris Lattner
c4beaec288 Fix a case that caused this to crash on 178.galgel
llvm-svn: 22653
2005-08-04 19:26:19 +00:00
Chris Lattner
5a0587224a Teach LSR about loop-variant expressions, such as loops like this:
for (i = 0; i < N; ++i)
    A[i][foo()] = 0;

here we still want to strength reduce the A[i] part, even though foo() is
l-v.

This also simplifies some of the 'CanReduce' logic.

This implements Transforms/LoopStrengthReduce/ops_after_indvar.ll

llvm-svn: 22652
2005-08-04 19:08:16 +00:00
Nate Begeman
0ab0a0f72d Remove some more dead code.
llvm-svn: 22650
2005-08-04 18:13:56 +00:00
Chris Lattner
f63b85d9c2 Refactor this code substantially with the following improvements:
1. We only analyze instructions once, guaranteed
  2. AnalyzeGetElementPtrUsers has been ripped apart and replaced with
     something much simpler.

The next step is to handle expressions that are not all indvar+loop-invariant
values (e.g. handling indvar+loopvariant).

llvm-svn: 22649
2005-08-04 17:40:30 +00:00
Chris Lattner
ea82ef5db1 refactor some code
llvm-svn: 22643
2005-08-04 01:19:13 +00:00
Chris Lattner
09241be4c7 invert to if's to make the logic simpler
llvm-svn: 22641
2005-08-04 00:40:47 +00:00
Chris Lattner
df7961ec73 When processing outer loops and we find uses of an IV in inner loops, make
sure to handle the use, just don't recurse into it.

This permits us to generate this code for a simple nested loop case:

.LBB_foo_0:     ; entry
        stwu r1, -48(r1)
        stw r29, 44(r1)
        stw r30, 40(r1)
        mflr r11
        stw r11, 56(r1)
        lis r2, ha16(L_A$non_lazy_ptr)
        lwz r30, lo16(L_A$non_lazy_ptr)(r2)
        li r29, 1
.LBB_foo_1:     ; no_exit.0
        bl L_bar$stub
        li r2, 1
        or r3, r30, r30
.LBB_foo_2:     ; no_exit.1
        lfd f0, 8(r3)
        stfd f0, 0(r3)
        addi r4, r2, 1
        addi r3, r3, 8
        cmpwi cr0, r2, 100
        or r2, r4, r4
        bne .LBB_foo_2  ; no_exit.1
.LBB_foo_3:     ; loopexit.1
        addi r30, r30, 800
        addi r2, r29, 1
        cmpwi cr0, r29, 100
        or r29, r2, r2
        bne .LBB_foo_1  ; no_exit.0
.LBB_foo_4:     ; return
        lwz r11, 56(r1)
        mtlr r11
        lwz r30, 40(r1)
        lwz r29, 44(r1)
        lwz r1, 0(r1)
        blr

instead of this:

_foo:
.LBB_foo_0:     ; entry
        stwu r1, -48(r1)
        stw r28, 44(r1)                   ;; uses an extra register.
        stw r29, 40(r1)
        stw r30, 36(r1)
        mflr r11
        stw r11, 56(r1)
        li r30, 1
        li r29, 0
        or r28, r29, r29
.LBB_foo_1:     ; no_exit.0
        bl L_bar$stub
        mulli r2, r28, 800           ;; unstrength-reduced multiply
        lis r3, ha16(L_A$non_lazy_ptr)   ;; loop invariant address computation
        lwz r3, lo16(L_A$non_lazy_ptr)(r3)
        add r2, r2, r3
        mulli r4, r29, 800           ;; unstrength-reduced multiply
        addi r3, r3, 8
        add r3, r4, r3
        li r4, 1
.LBB_foo_2:     ; no_exit.1
        lfd f0, 0(r3)
        stfd f0, 0(r2)
        addi r5, r4, 1
        addi r2, r2, 8                 ;; multiple stride 8 IV's
        addi r3, r3, 8
        cmpwi cr0, r4, 100
        or r4, r5, r5
        bne .LBB_foo_2  ; no_exit.1
.LBB_foo_3:     ; loopexit.1
        addi r28, r28, 1               ;;; Many IV's with stride 1
        addi r29, r29, 1
        addi r2, r30, 1
        cmpwi cr0, r30, 100
        or r30, r2, r2
        bne .LBB_foo_1  ; no_exit.0
.LBB_foo_4:     ; return
        lwz r11, 56(r1)
        mtlr r11
        lwz r30, 36(r1)
        lwz r29, 40(r1)
        lwz r28, 44(r1)
        lwz r1, 0(r1)
        blr

llvm-svn: 22640
2005-08-04 00:14:11 +00:00
Chris Lattner
8b1b7c9e7d Teach loop-reduce to see into nested loops, to pull out immediate values
pushed down by SCEV.

In a nested loop case, this allows us to emit this:

        lis r3, ha16(L_A$non_lazy_ptr)
        lwz r3, lo16(L_A$non_lazy_ptr)(r3)
        add r2, r2, r3
        li r3, 1
.LBB_foo_2:     ; no_exit.1
        lfd f0, 8(r2)        ;; Uses offset of 8 instead of 0
        stfd f0, 0(r2)
        addi r4, r3, 1
        addi r2, r2, 8
        cmpwi cr0, r3, 100
        or r3, r4, r4
        bne .LBB_foo_2  ; no_exit.1

instead of this:

        lis r3, ha16(L_A$non_lazy_ptr)
        lwz r3, lo16(L_A$non_lazy_ptr)(r3)
        add r2, r2, r3
        addi r3, r3, 8
        li r4, 1
.LBB_foo_2:     ; no_exit.1
        lfd f0, 0(r3)
        stfd f0, 0(r2)
        addi r5, r4, 1
        addi r2, r2, 8
        addi r3, r3, 8
        cmpwi cr0, r4, 100
        or r4, r5, r5
        bne .LBB_foo_2  ; no_exit.1

llvm-svn: 22639
2005-08-03 23:44:42 +00:00
Chris Lattner
512f74d445 improve debug output
llvm-svn: 22638
2005-08-03 23:30:08 +00:00
Chris Lattner
1dcd811d36 Move from Stage 0 to Stage 1.
Only emit one PHI node for IV uses with identical bases and strides (after
moving foldable immediates to the load/store instruction).

This implements LoopStrengthReduce/dont_insert_redundant_ops.ll, allowing
us to generate this PPC code for test1:

        or r30, r3, r3
.LBB_test1_1:   ; Loop
        li r2, 0
        stw r2, 0(r30)
        stw r2, 4(r30)
        bl L_pred$stub
        addi r30, r30, 8
        cmplwi cr0, r3, 0
        bne .LBB_test1_1        ; Loop

instead of this code:

        or r30, r3, r3
        or r29, r3, r3
.LBB_test1_1:   ; Loop
        li r2, 0
        stw r2, 0(r29)
        stw r2, 4(r30)
        bl L_pred$stub
        addi r30, r30, 8        ;; Two iv's with step of 8
        addi r29, r29, 8
        cmplwi cr0, r3, 0
        bne .LBB_test1_1        ; Loop

llvm-svn: 22635
2005-08-03 22:51:21 +00:00
Chris Lattner
96367799a2 Rename IVUse to IVUsersOfOneStride, use a struct instead of a pair to
unify some parallel vectors and get field names more descriptive than
"first" and "second".  This isn't lisp afterall :)

llvm-svn: 22633
2005-08-03 22:21:05 +00:00
Chris Lattner
230700ef26 Fix a nasty dangling pointer issue. The ScalarEvolution pass would keep a
map from instruction* to SCEVHandles.  When we delete instructions, we have
to tell it about it.  We would run into nasty cases where new instructions
were reallocated at old instruction addresses and get the old map values.
Bad bad bad :(

llvm-svn: 22632
2005-08-03 21:36:09 +00:00
Chris Lattner
eee2daf85d The correct fix for PR612, which also fixes
Transforms/LowerInvoke/2005-08-03-InvokeWithPHIUse.ll

llvm-svn: 22628
2005-08-03 18:51:44 +00:00