caio/clang-p2996
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
20,422 Commits 1 Branch 0 Tags
8e022b3d8940f451fcb4df233e737ab378d40708
Commit Graph

385 Commits

Author SHA1 Message Date
Chris Lattner
03b9eb506c Make MaskedValueIsZero a bit more aggressive 
llvm-svn: 23677
 2005-10-09 22:08:50 +00:00
Chris Lattner
62010c450f Fix funky xcode indentation 
llvm-svn: 23674
 2005-10-09 06:36:35 +00:00
Jeff Cohen
572910c9a2 Remove useless variable. 
llvm-svn: 23656
 2005-10-07 05:28:29 +00:00
Chris Lattner
0b011ec8e2 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
0b3557f54a 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
b4b2530a1a 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
797dee7705 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
01f56c68e9 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
4ebc8ab4e0 fix typeo 
llvm-svn: 23383
 2005-09-18 05:25:20 +00:00
Chris Lattner
e5b23a6d67 Remove unintentionally committed code 
llvm-svn: 23382
 2005-09-18 05:12:51 +00:00
Chris Lattner
27cb9dbd35 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
af517574ce 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
027eaf01cf remove debug output 
llvm-svn: 23377
 2005-09-18 03:50:25 +00:00
Chris Lattner
1521298993 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
a393e4d4b3 Fix the regression last night compiling povray 
llvm-svn: 23348
 2005-09-14 17:32:56 +00:00
Chris Lattner
2a8932960d 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
567b81f0d2 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
219175c84d 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
e0bfdf1485 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
b990f7d8ed 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
9f269e40c9 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
2c14cf7b74 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
9f9c260b8c 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
Nate Begeman
b392321cae 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
22d00a8e90 Update to use the new MathExtras.h support for log2 computation. 
Patch contributed by Jim Laskey!

llvm-svn: 22592
 2005-08-02 19:16:58 +00:00
Jeff Cohen
5f4ef3c5a8 Eliminate all remaining tabs and trailing spaces. 
llvm-svn: 22523
 2005-07-27 06:12:32 +00:00
Chris Lattner
18aa4d8196 Do not let MaskedValueIsZero consider undef to be zero, for reasons 
explained in the comment.

This fixes UnitTests/2003-09-18-BitFieldTest on darwin

llvm-svn: 22483
 2005-07-20 18:49:28 +00:00
Chris Lattner
247aef884c When transforming &A[i] < &A[j] -> i < j, make sure to perform the comparison 
as a signed compare.  This patch may fix PR597, but is correct in any case.

llvm-svn: 22465
 2005-07-18 23:07:33 +00:00
Chris Lattner
4ed40f7c6f Fix a problem that instcombine would hit when dealing with unreachable code. 
Because the instcombine has to scan the entire function when it starts up
to begin with, we might as well do it in DFO so we can nuke unreachable code.

This fixes: Transforms/InstCombine/2005-07-07-DeadPHILoop.ll

llvm-svn: 22348
 2005-07-07 20:40:38 +00:00
Reid Spencer
4fdd96c4e0 Clean up some uninitialized variables and missing return statements that 
GCC 4.0.0 compiler (sometimes incorrectly) warns about under release build.

llvm-svn: 22249
 2005-06-18 17:37:34 +00:00
Chris Lattner
2ceb6ee576 This is not true: (X != 13 | X < 15) -> X < 15 
It is actually always true.  This fixes PR586 and
Transforms/InstCombine/2005-06-16-SetCCOrSetCCMiscompile.ll

llvm-svn: 22236
 2005-06-17 03:59:17 +00:00
Chris Lattner
73bcba5f61 Don't crash when dealing with INTMIN. This fixes PR585 and 
Transforms/InstCombine/2005-06-16-RangeCrash.ll

llvm-svn: 22234
 2005-06-17 02:05:55 +00:00
Chris Lattner
c53cb9d3ff avoid constructing out of range shift amounts. 
llvm-svn: 22230
 2005-06-17 01:29:28 +00:00
Chris Lattner
89dc4f16f5 Fix PR583 and testcase Transforms/InstCombine/2005-06-15-DivSelectCrash.ll 
llvm-svn: 22227
 2005-06-16 04:55:52 +00:00
Chris Lattner
252a845e30 Fix PR571, removing code that does just the WRONG thing :) 
llvm-svn: 22225
 2005-06-16 03:00:08 +00:00
Chris Lattner
104002bee3 Fix a bug in my previous patch. Do not get the shift amount type (which 
is always ubyte, get the type being shifted).  This unbreaks espresso

llvm-svn: 22224
 2005-06-16 01:52:07 +00:00
Chris Lattner
19b57f55aa Fix PR577 and testcase InstCombine/2005-06-15-ShiftSetCCCrash.ll. 
Do not perform undefined out of range shifts.

llvm-svn: 22217
 2005-06-15 20:53:31 +00:00
Reid Spencer
a299d6f701 Put the hack back in that removes features, causes regressions to fail, but 
allows test programs to succeed. Actual fix for this is forthcoming.

llvm-svn: 22213
 2005-06-15 18:25:30 +00:00
Reid Spencer
6d231e55fa Unbreak several InstCombine regression checks introduced by a hack to 
fix the bzip2 test. A better hack is needed.

llvm-svn: 22209
 2005-06-13 06:41:26 +00:00
Andrew Lenharth
ffe65458e7 hack to fix bzip2 (bug 571) 
llvm-svn: 22192
 2005-06-04 12:43:56 +00:00
Chris Lattner
05c703ea85 preserve calling conventions when hacking on code 
llvm-svn: 22024
 2005-05-14 12:25:32 +00:00
Chris Lattner
61d9d81770 calling a function with the wrong CC is undefined, turn it into an unreachable 
instruction.  This is useful for catching optimizers that don't preserve
calling conventions

llvm-svn: 21928
 2005-05-13 07:09:09 +00:00
Chris Lattner
b62f5082c5 implement and.ll:test33 
llvm-svn: 21809
 2005-05-09 04:58:36 +00:00
Chris Lattner
b18dbbfff5 Strength reduce SAR into SHR if there is no way sign bits could be shifted 
in.  This tends to get cases like this:

  X = cast ubyte to int
  Y = shr int X, ...

Tested by: shift.ll:test24

llvm-svn: 21775
 2005-05-08 17:34:56 +00:00
Chris Lattner
4294cec0f1 Fix a miscompilation of crafty by clobbering the "A" variable. 
llvm-svn: 21770
 2005-05-07 23:49:08 +00:00
Chris Lattner
6aacb0f9da Preserve tail marker 
llvm-svn: 21737
 2005-05-06 06:48:21 +00:00
Chris Lattner
ef298a3b8a Teach instcombine propagate zeroness through shl instructions, implementing 
and.ll:test31

llvm-svn: 21717
 2005-05-06 04:53:20 +00:00
Chris Lattner
873804168e Implement shift.ll:test23. If we are shifting right then immediately truncating 
the result, turn signed shift rights into unsigned shift rights if possible.

This leads to later simplification and happens *often* in 176.gcc.  For example,
this testcase:

struct xxx { unsigned int code : 8; };
enum codes { A, B, C, D, E, F };
int foo(struct xxx *P) {
  if ((enum codes)P->code == A)
     bar();
}

used to be compiled to:

int %foo(%struct.xxx* %P) {
        %tmp.1 = getelementptr %struct.xxx* %P, int 0, uint 0           ; <uint*> [#uses=1]
        %tmp.2 = load uint* %tmp.1              ; <uint> [#uses=1]
        %tmp.3 = cast uint %tmp.2 to int                ; <int> [#uses=1]
        %tmp.4 = shl int %tmp.3, ubyte 24               ; <int> [#uses=1]
        %tmp.5 = shr int %tmp.4, ubyte 24               ; <int> [#uses=1]
        %tmp.6 = cast int %tmp.5 to sbyte               ; <sbyte> [#uses=1]
        %tmp.8 = seteq sbyte %tmp.6, 0          ; <bool> [#uses=1]
        br bool %tmp.8, label %then, label %UnifiedReturnBlock

Now it is compiled to:

        %tmp.1 = getelementptr %struct.xxx* %P, int 0, uint 0           ; <uint*> [#uses=1]
        %tmp.2 = load uint* %tmp.1              ; <uint> [#uses=1]
        %tmp.2 = cast uint %tmp.2 to sbyte              ; <sbyte> [#uses=1]
        %tmp.8 = seteq sbyte %tmp.2, 0          ; <bool> [#uses=1]
        br bool %tmp.8, label %then, label %UnifiedReturnBlock

which is the difference between this:

foo:
        subl $4, %esp
        movl 8(%esp), %eax
        movl (%eax), %eax
        shll $24, %eax
        sarl $24, %eax
        testb %al, %al
        jne .LBBfoo_2

and this:

foo:
        subl $4, %esp
        movl 8(%esp), %eax
        movl (%eax), %eax
        testb %al, %al
        jne .LBBfoo_2

This occurs 3243 times total in the External tests, 215x in povray,
6x in each f2c'd program, 1451x in 176.gcc, 7x in crafty, 20x in perl,
25x in gap, 3x in m88ksim, 25x in ijpeg.

Maybe this will cause a little jump on gcc tommorow :)

llvm-svn: 21715
 2005-05-06 04:18:52 +00:00
Chris Lattner
7208616ec0 Implement xor.ll:test22 
llvm-svn: 21713
 2005-05-06 02:07:39 +00:00
Chris Lattner
4c2d3781aa implement and.ll:test30 and set.ll:test21 
llvm-svn: 21712
 2005-05-06 01:53:19 +00:00