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

19459 Commits

Author SHA1 Message Date
Nate Begeman
84d0a2806a Use the new subtarget support to automatically choose the correct ABI
and asm printer for PowerPC if one is not specified.

llvm-svn: 22659
2005-08-04 20:49:48 +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
1800405b3d This should not run lli, that is for llvm-test.
llvm-svn: 22656
2005-08-04 19:56:35 +00:00
Chris Lattner
bc93ac834b None of these tests should require a working lli, they are codegen tests,
not execution tests.

llvm-svn: 22655
2005-08-04 19:55:39 +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
Chris Lattner
229765dee9 This testcase now passes
llvm-svn: 22651
2005-08-04 19:08:07 +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
Andrew Lenharth
bf363b1165 No, IDEFs shouldn't be JITed
llvm-svn: 22648
2005-08-04 15:32:36 +00:00
Misha Brukman
8b8272b648 * Unbreak release build
* Add comments to #endif pragmas for readability

llvm-svn: 22647
2005-08-04 14:22:41 +00:00
Misha Brukman
e094f6c611 * Unbreak optimized build (noticed by Eric van Riet Paap)
* Comment #endif clauses for readability

llvm-svn: 22646
2005-08-04 14:16:48 +00:00
Nate Begeman
09997f1012 Add Subtarget support to PowerPC. Next up, using it.
llvm-svn: 22644
2005-08-04 07:12:09 +00:00
Chris Lattner
ea82ef5db1 refactor some code
llvm-svn: 22643
2005-08-04 01:19:13 +00:00
Chris Lattner
4058094dce this is not implemented by lsr yet
llvm-svn: 22642
2005-08-04 01:18:48 +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
Nate Begeman
6cd034da8e Scalar SSE: load +0.0 -> xorps/xorpd
Scalar SSE: a < b ? c : 0.0 -> cmpss, andps
Scalar SSE: float -> i16 needs to be promoted

llvm-svn: 22637
2005-08-03 23:26:28 +00:00
Chris Lattner
215515c80b this now passes
llvm-svn: 22636
2005-08-03 22:51:40 +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
Andrew Lenharth
2865f0fe01 Alpha ABI specifies stack is always 16 byte alligned, and gcc does it, so I will too
llvm-svn: 22634
2005-08-03 22:33:21 +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
e69b731c71 Fix this to test the BE we care about
llvm-svn: 22631
2005-08-03 21:01:46 +00:00
Chris Lattner
b2f675c588 Fix an obvious bug in the Log2 stuff that broke SingleSource/UnitTests/2005-05-12-Int64ToFP
last night.

llvm-svn: 22630
2005-08-03 20:53:19 +00:00
Chris Lattner
d124203207 Fix PR611, codegen'ing SREM of FP operands to fmod or fmodf instead of
the sequence used for integer ops

llvm-svn: 22629
2005-08-03 20:31:37 +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
Chris Lattner
31641138cf new testcase for PR612
llvm-svn: 22627
2005-08-03 18:51:15 +00:00
Chris Lattner
edac412122 When inserting code, make sure not to insert it before PHI nodes. This
fixes PR612 and Transforms/LowerInvoke/2005-08-03-InvokeWithPHI.ll

llvm-svn: 22626
2005-08-03 18:34:29 +00:00
Chris Lattner
a9161fc936 new testcase for PR612
llvm-svn: 22625
2005-08-03 18:33:48 +00:00
Nate Begeman
3c0178c886 Add a couple rlwinm tests for bitfield clears
llvm-svn: 22624
2005-08-03 18:27:17 +00:00
Nate Begeman
5a5045430c Update rlwimi tests to catch all the cases we care about
llvm-svn: 22623
2005-08-03 18:11:23 +00:00
Chris Lattner
ed6b5692c7 Testcase that used to crash simplifycfg
llvm-svn: 22622
2005-08-03 18:01:07 +00:00
Chris Lattner
3672ceb70b Fix Transforms/SimplifyCFG/2005-08-03-PHIFactorCrash.ll, a problem that
occurred while bugpointing another testcase

llvm-svn: 22621
2005-08-03 17:59:45 +00:00
Chris Lattner
62b0ecdfb8 add support for Graphviz when viewing CFGs
llvm-svn: 22620
2005-08-03 17:55:05 +00:00
Misha Brukman
41a00bbfa6 Fix grammar: apostrophe-s ('s) is possessive, not plural; also iff vs. if.
llvm-svn: 22619
2005-08-03 17:29:52 +00:00
Chris Lattner
42474809e3 Wrap comments to 80 cols, fix code sequence for CountLeadingZeros_64 on
non-ppc GCC 4.0 machines.  Patch by Jim Laskey!

llvm-svn: 22618
2005-08-03 16:53:58 +00:00
Chris Lattner
adfe9f12ef minor capitalization thing, patch by Jim Laskey
llvm-svn: 22617
2005-08-03 16:52:22 +00:00
Chris Lattner
260411fd9f Fix another bug in the clz patch that caused miscompilations when !gcc4
llvm-svn: 22616
2005-08-03 01:04:40 +00:00
Chris Lattner
6e1d5a8b28 Finally, add the required constraint checks to fix Transforms/SimplifyCFG/2005-08-01-PHIUpdateFail.ll
the right way

llvm-svn: 22615
2005-08-03 00:59:12 +00:00
Chris Lattner
a0cf824bef un-xfail this
llvm-svn: 22614
2005-08-03 00:58:44 +00:00
Chris Lattner
cbf4b650ba Simplify some code, add the correct pred checks
llvm-svn: 22613
2005-08-03 00:38:27 +00:00
Chris Lattner
c59014baef Refactor code out of PropagatePredecessorsForPHIs, turning it into a pure function with no side-effects
llvm-svn: 22612
2005-08-03 00:29:26 +00:00
Chris Lattner
0f4e0d19cc use splice instead of remove/insert to avoid some symtab operations
llvm-svn: 22611
2005-08-03 00:23:42 +00:00
Chris Lattner
adbd086f50 move two functions up in the file, use SafeToMergeTerminators to eliminate
some duplicated code

llvm-svn: 22610
2005-08-03 00:19:45 +00:00
Chris Lattner
b9efb90e1a Rip some code out of the main SimplifyCFG function into a subfunction and
call it from the only place it is live.  No functionality changes.

llvm-svn: 22609
2005-08-03 00:11:16 +00:00
Chris Lattner
0bd6f5c29f This fails for now
llvm-svn: 22608
2005-08-03 00:10:28 +00:00
Chris Lattner
df31d75597 Disable this patch:
http://lists.cs.uiuc.edu/pipermail/llvm-commits/Week-of-Mon-20050801/027345.html

This breaks real programs and only fixes an obscure regression testcase.  A
real fix is in development.

llvm-svn: 22606
2005-08-02 23:31:38 +00:00