llvm-svn: 31923

and handle it like constant stride vars.  This fixes some bad codegen in
variable stride cases.  For example, it compiles this:

void foo(int k, int i) {
  for (k=i+i; k <= 8192; k+=i)
    flags2[k] = 0;
}

to:

LBB1_1: #bb.preheader
        movl %eax, %ecx
        addl %ecx, %ecx
        movl L_flags2$non_lazy_ptr, %edx
LBB1_2: #bb
        movb $0, (%edx,%ecx)
        addl %eax, %ecx
        cmpl $8192, %ecx
        jle LBB1_2      #bb
LBB1_5: #return
        ret

or (if the array is local and we are in dynamic-nonpic or static mode):

LBB3_2: #bb
        movb $0, _flags2(%ecx)
        addl %eax, %ecx
        cmpl $8192, %ecx
        jle LBB3_2      #bb

and:

        lis r2, ha16(L_flags2$non_lazy_ptr)
        lwz r2, lo16(L_flags2$non_lazy_ptr)(r2)
        slwi r3, r4, 1
LBB1_2: ;bb
        li r5, 0
        add r6, r4, r3
        stbx r5, r2, r3
        cmpwi cr0, r6, 8192
        bgt cr0, LBB1_5 ;return

instead of:

        leal (%eax,%eax,2), %ecx
        movl %eax, %edx
        addl %edx, %edx
        addl L_flags2$non_lazy_ptr, %edx
        xorl %esi, %esi
LBB1_2: #bb
        movb $0, (%edx,%esi)
        movl %eax, %edi
        addl %esi, %edi
        addl %ecx, %esi
        cmpl $8192, %esi
        jg LBB1_5       #return

and:

        lis r2, ha16(L_flags2$non_lazy_ptr)
        lwz r2, lo16(L_flags2$non_lazy_ptr)(r2)
        mulli r3, r4, 3
        slwi r5, r4, 1
        li r6, 0
        add r2, r2, r5
LBB1_2: ;bb
        li r5, 0
        add r7, r3, r6
        stbx r5, r2, r6
        add r6, r4, r6
        cmpwi cr0, r7, 8192
        ble cr0, LBB1_2 ;bb

This speeds up Benchmarks/Shootout/sieve from 8.533s to 6.464s and
implements LoopStrengthReduce/var_stride_used_by_compare.ll

llvm-svn: 31809

Turn on -Wunused and -Wno-unused-parameter. Clean up most of the resulting
fall out by removing unused variables. Remaining warnings have to do with
unused functions (I didn't want to delete code without review) and unused
variables in generated code. Maintainers should clean up the remaining
issues when they see them. All changes pass DejaGnu tests and Olden.

llvm-svn: 31380

llvm-svn: 31257

llvm-svn: 31248

This patch implements the first increment for the Signless Types feature.
All changes pertain to removing the ConstantSInt and ConstantUInt classes
in favor of just using ConstantInt.

llvm-svn: 31063

llvm-svn: 29925

llvm-svn: 29911

Changes:
  1. Update an obsolete comment.
  2. Make the sorting by base an explicit (though still N^2) step, so
     that the code is more clear on what it is doing.
  3. Partition uses so that uses inside the loop are handled before uses
     outside the loop.

Note that none of these changes currently changes the code inserted by LSR,
but they are a stepping stone to getting there.

This code is the result of some crazy pair programming with Nate. :)

llvm-svn: 29493

llvm-svn: 29186

dropped.  This shrinks libllvmgcc.dylib another 67K

llvm-svn: 28975

post-increment value, should be first cast to the appropriated type (to the
type of the common expr). Otherwise, the rewrite of a use based on (common +
iv) may end up with an incorrect type.

llvm-svn: 28735

llvm-svn: 27625

llvm-svn: 27052

llvm-svn: 26953

- Added more debugging info.
- Allow reuse of IV of negative stride. e.g. -4 stride == 2 * iv of -2 stride.

llvm-svn: 26841

for more IV reuses.

llvm-svn: 26837

of a smaller stride even if they have a common loop invariant expression part.

llvm-svn: 26828

stride. For a set of uses of the IV of a stride which is a multiple
of another stride, do not insert a new IV expression. Rather, reuse the
previous IV and rewrite the uses as uses of IV expression multiplied by
the factor.

e.g.
x = 0 ...; x ++
y = 0 ...; y += 4
then use of y can be rewritten as use of 4*x for x86.

llvm-svn: 26803

transformation decisions.

llvm-svn: 26738

#LLVM LOC, and auto-cse's cast instructions.

llvm-svn: 25974

1. When rewriting code in outer loops, sometimes we would insert code into
   inner loops that is invariant in that loop.
2. Notice that 4*(2+x) is 8+4*x and use that to simplify expressions.

This is a performance neutral change.

llvm-svn: 25964

llvm-svn: 25514

Patch written by Daniel Berlin!

llvm-svn: 25202

know that small negative values fit into the immediate field of addressing
modes.

llvm-svn: 24608

allow pointer types.

llvm-svn: 23859

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

out CSE's of base expressions it could build a result whose order was
nondet.

llvm-svn: 23698

from the end of a vector instead of the beginning

llvm-svn: 23697

llvm-svn: 23695

llvm-svn: 23673

IV strides dependend on the pointer order of the strides in memory.
Non-determinism is bad.

llvm-svn: 23672

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

llvm-svn: 23603

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

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

llvm-svn: 23476

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

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

        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