RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-10-21 20:12:56 +02:00
Code Issues Projects Releases Wiki Activity
26,709 Commits 4 Branches 5 Tags 704 MiB
275825195a
Commit Graph

26709 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Andrew Lenharth
2ccefe5b91 Add Note 
llvm-svn: 30530
 2006-09-20 14:40:01 +00:00
Jim Laskey
a46690e7de Trim the home directory from the dejagnu test 
llvm-svn: 30519
 2006-09-20 09:20:22 +00:00
Chris Lattner
6b434ee662 item done 
llvm-svn: 30518
 2006-09-20 06:41:56 +00:00
Chris Lattner
a0243b3ad3 Compile: 
int test3(int a, int b) { return (a < 0) ? a : 0; }

to:

_test3:
        srawi r2, r3, 31
        and r3, r2, r3
        blr

instead of:

_test3:
        cmpwi cr0, r3, 1
        li r2, 0
        blt cr0, LBB2_2 ;entry
LBB2_1: ;entry
        mr r3, r2
LBB2_2: ;entry
        blr


This implements: PowerPC/select_lt0.ll:seli32_a_a

llvm-svn: 30517
 2006-09-20 06:41:35 +00:00
Chris Lattner
2d711ecbc2 new testcase 
llvm-svn: 30516
 2006-09-20 06:40:37 +00:00
Chris Lattner
f9c4e07bf7 add a note 
llvm-svn: 30515
 2006-09-20 06:32:10 +00:00
Chris Lattner
e78d019082 Fold the full generality of (any_extend (truncate x)) 
llvm-svn: 30514
 2006-09-20 06:29:17 +00:00
Chris Lattner
6440707b6f Two things: 
1. teach SimplifySetCC that '(srl (ctlz x), 5) == 0' is really x != 0.
2. Teach visitSELECT_CC to use SimplifySetCC instead of calling it and
   ignoring the result.  This allows us to compile:

bool %test(ulong %x) {
  %tmp = setlt ulong %x, 4294967296
  ret bool %tmp
}

to:

_test:
        cntlzw r2, r3
        cmplwi cr0, r3, 1
        srwi r2, r2, 5
        li r3, 0
        beq cr0, LBB1_2 ;
LBB1_1: ;
        mr r3, r2
LBB1_2: ;
        blr

instead of:

_test:
        addi r2, r3, -1
        cntlzw r2, r2
        cntlzw r3, r3
        srwi r2, r2, 5
        cmplwi cr0, r2, 0
        srwi r2, r3, 5
        li r3, 0
        bne cr0, LBB1_2 ;
LBB1_1: ;
        mr r3, r2
LBB1_2: ;
        blr

This isn't wonderful, but it's an improvement.

llvm-svn: 30513
 2006-09-20 06:19:26 +00:00
Chris Lattner
102718b1b2 This is already done 
llvm-svn: 30512
 2006-09-20 04:59:33 +00:00
Chris Lattner
6ddcf6bba8 We went through all that trouble to compute whether it was safe to transform 
this comparison, but never checked it.  Whoops, no wonder we miscompiled
177.mesa!

llvm-svn: 30511
 2006-09-20 04:44:59 +00:00
Chris Lattner
4d97247875 Improve PPC64 equality comparisons like PPC32 comparisons. 
llvm-svn: 30510
 2006-09-20 04:33:27 +00:00
Chris Lattner
69390a3f80 Two improvements: 
1. Codegen this comparison:
     if (X == 0x8000)

as:

        cmplwi cr0, r3, 32768
        bne cr0, LBB1_2 ;cond_next

instead of:

        lis r2, 0
        ori r2, r2, 32768
        cmpw cr0, r3, r2
        bne cr0, LBB1_2 ;cond_next


2. Codegen this comparison:
      if (X == 0x12345678)

as:

        xoris r2, r3, 4660
        cmplwi cr0, r2, 22136
        bne cr0, LBB1_2 ;cond_next

instead of:

        lis r2, 4660
        ori r2, r2, 22136
        cmpw cr0, r3, r2
        bne cr0, LBB1_2 ;cond_next

llvm-svn: 30509
 2006-09-20 04:25:47 +00:00
Chris Lattner
ee42b9ae24 Add a note that we should match rlwnm better 
llvm-svn: 30508
 2006-09-20 03:59:25 +00:00
Chris Lattner
3057944738 Legalize is no longer limited to cleverness with just constant shift amounts. 
Allow it to be clever when possible and fall back to the gross code when needed.

This allows us to compile:

long long foo1(long long X, int C) {
  return X << (C|32);
}
long long foo2(long long X, int C) {
  return X << (C&~32);
}

to:
_foo1:
        rlwinm r2, r5, 0, 27, 31
        slw r3, r4, r2
        li r4, 0
        blr


        .globl  _foo2
        .align  4
_foo2:
        rlwinm r2, r5, 0, 27, 25
        subfic r5, r2, 32
        slw r3, r3, r2
        srw r5, r4, r5
        or r3, r3, r5
        slw r4, r4, r2
        blr

instead of:

_foo1:
        ori r2, r5, 32
        subfic r5, r2, 32
        addi r6, r2, -32
        srw r5, r4, r5
        slw r3, r3, r2
        slw r6, r4, r6
        or r3, r3, r5
        slw r4, r4, r2
        or r3, r3, r6
        blr


        .globl  _foo2
        .align  4
_foo2:
        rlwinm r2, r5, 0, 27, 25
        subfic r5, r2, 32
        addi r6, r2, -32
        srw r5, r4, r5
        slw r3, r3, r2
        slw r6, r4, r6
        or r3, r3, r5
        slw r4, r4, r2
        or r3, r3, r6
        blr

llvm-svn: 30507
 2006-09-20 03:47:40 +00:00
Chris Lattner
644c6814ae Expand 64-bit shifts more optimally if we know that the high bit of the 
shift amount is one or zero.  For example, for:

long long foo1(long long X, int C) {
  return X << (C|32);
}

long long foo2(long long X, int C) {
  return X << (C&~32);
}

we get:

_foo1:
        movb $31, %cl
        movl 4(%esp), %edx
        andb 12(%esp), %cl
        shll %cl, %edx
        xorl %eax, %eax
        ret
_foo2:
        movb $223, %cl
        movl 4(%esp), %eax
        movl 8(%esp), %edx
        andb 12(%esp), %cl
        shldl %cl, %eax, %edx
        shll %cl, %eax
        ret

instead of:

_foo1:
        subl $4, %esp
        movl %ebx, (%esp)
        movb $32, %bl
        movl 8(%esp), %eax
        movl 12(%esp), %edx
        movb %bl, %cl
        orb 16(%esp), %cl
        shldl %cl, %eax, %edx
        shll %cl, %eax
        xorl %ecx, %ecx
        testb %bl, %bl
        cmovne %eax, %edx
        cmovne %ecx, %eax
        movl (%esp), %ebx
        addl $4, %esp
        ret
_foo2:
        subl $4, %esp
        movl %ebx, (%esp)
        movb $223, %cl
        movl 8(%esp), %eax
        movl 12(%esp), %edx
        andb 16(%esp), %cl
        shldl %cl, %eax, %edx
        shll %cl, %eax
        xorl %ecx, %ecx
        xorb %bl, %bl
        testb %bl, %bl
        cmovne %eax, %edx
        cmovne %ecx, %eax
        movl (%esp), %ebx
        addl $4, %esp
        ret

llvm-svn: 30506
 2006-09-20 03:38:48 +00:00
Evan Cheng
a7347758f5 Back out Chris' last set of changes. This breaks 177.mesa and povray somehow. 
llvm-svn: 30505
 2006-09-20 01:39:40 +00:00
Evan Cheng
8652c13f13 80 col. 
llvm-svn: 30504
 2006-09-20 01:10:02 +00:00
Evan Cheng
c5be7540d2 Allow PatFrag to be a leaf node. 
llvm-svn: 30498
 2006-09-19 19:08:04 +00:00
Evan Cheng
f020ff9440 Add result of a Xform to isel queue. 
llvm-svn: 30497
 2006-09-19 18:40:15 +00:00
Andrew Lenharth
0240d56eb6 If we have an add, do it in the pointer realm, not the int realm. This is critical in the linux kernel for pointer analysis correctness 
llvm-svn: 30496
 2006-09-19 18:24:51 +00:00
Andrew Lenharth
17889b837e Inspired by the linux kernel, the more we keep adds in the pointer realm, the better pointer analysis works. 
llvm-svn: 30495
 2006-09-19 18:23:39 +00:00
Chris Lattner
66029d909b Fix UnitTests/2005-05-12-Int64ToFP.c with llc-beta. In particular, do not 
allow it to go into an infinite loop, filling up the disk!

llvm-svn: 30494
 2006-09-19 18:02:01 +00:00
Rafael Espindola
cd52f85028 fix header 
add comments
untabify

llvm-svn: 30486
 2006-09-19 16:41:40 +00:00
Rafael Espindola
6c7627e002 Implement a MachineFunctionPass to fix the mul instruction 
llvm-svn: 30485
 2006-09-19 15:49:25 +00:00
Chris Lattner
30d772fbb1 number test right 
llvm-svn: 30484
 2006-09-19 06:19:19 +00:00
Chris Lattner
2b076f26b7 item done 
llvm-svn: 30483
 2006-09-19 06:19:03 +00:00
Chris Lattner
2d2d80a4c2 implement select.ll:test19-22 
llvm-svn: 30482
 2006-09-19 06:18:21 +00:00
Chris Lattner
96ca5b26b0 make this harder 
llvm-svn: 30481
 2006-09-19 06:17:55 +00:00
Chris Lattner
7656fc26d8 new testcases 
llvm-svn: 30480
 2006-09-19 06:16:46 +00:00
Chris Lattner
92c8924309 Fold the PPCISD shifts when presented with 0 inputs. This occurs for code 
like:
long long test(long long X, int Y) {
  return 1ULL << Y;
}
long long test2(long long X, int Y) {
  return -1LL << Y;
}

which we used to compile to:

_test:
        li r2, 1
        subfic r3, r5, 32
        li r4, 0
        addi r6, r5, -32
        srw r3, r2, r3
        slw r4, r4, r5
        slw r6, r2, r6
        or r3, r4, r3
        slw r4, r2, r5
        or r3, r3, r6
        blr
_test2:
        li r2, -1
        subfic r3, r5, 32
        addi r6, r5, -32
        srw r3, r2, r3
        slw r4, r2, r5
        slw r2, r2, r6
        or r3, r4, r3
        or r3, r3, r2
        blr

Now we produce:

_test:
        li r2, 1
        addi r3, r5, -32
        subfic r4, r5, 32
        slw r3, r2, r3
        srw r4, r2, r4
        or r3, r4, r3
        slw r4, r2, r5
        blr
_test2:
        li r2, -1
        subfic r3, r5, 32
        addi r6, r5, -32
        srw r3, r2, r3
        slw r4, r2, r5
        slw r2, r2, r6
        or r3, r4, r3
        or r3, r3, r2
        blr

llvm-svn: 30479
 2006-09-19 05:22:59 +00:00
Chris Lattner
61d08597df Fold extract_element(cst) to cst 
llvm-svn: 30478
 2006-09-19 05:02:39 +00:00
Chris Lattner
556f869e88 Minor speedup for legalize by avoiding some malloc traffic 
llvm-svn: 30477
 2006-09-19 04:51:23 +00:00
Chris Lattner
87d05ea43b If multiple predicates are listed, they must all pass 
llvm-svn: 30476
 2006-09-19 00:41:36 +00:00
Nick Lewycky
d17ad3593b Enable dejagnu tests for predicate simplifier. 
llvm-svn: 30475
 2006-09-19 00:31:54 +00:00
Evan Cheng
65afc6af9f Fix a typo. 
llvm-svn: 30474
 2006-09-18 23:28:33 +00:00
Chris Lattner
7498e29ca4 There! 
llvm-svn: 30473
 2006-09-18 22:41:07 +00:00
Chris Lattner
b54881691d Fix Regression/TableGen/2006-09-18-LargeInt.td 
llvm-svn: 30472
 2006-09-18 22:28:27 +00:00
Chris Lattner
d3b2f9e7cc new testcase 
llvm-svn: 30471
 2006-09-18 22:28:07 +00:00
Evan Cheng
67b248dbc6 Allow i32 UDIV, SDIV, UREM, SREM to be expanded into libcalls. 
llvm-svn: 30470
 2006-09-18 21:49:04 +00:00
Nick Lewycky
96939f2d94 Walk down the dominator tree instead of the control flow graph. That means 
that we can't modify the CFG any more, at least not until it's possible
to update the dominator tree (PR217).

llvm-svn: 30469
 2006-09-18 21:09:35 +00:00
Nick Lewycky
ad4eb4f0de Fix findCaseDest to return null when BB is both the default dest and one 
of the numeric cases.

llvm-svn: 30468
 2006-09-18 20:44:37 +00:00
Andrew Lenharth
6d43749a47 A pass to remove the worst of the replay trap offenders, and as a bonus, align basic blocks when it is free to do so 
llvm-svn: 30467
 2006-09-18 19:44:29 +00:00
Nick Lewycky
87f79d5d69 Add a new helper method to SwitchInst. Useful when you've got a BB from 
somewhere (like the dominator graph) and would like to know which case it
came from.

llvm-svn: 30466
 2006-09-18 19:03:59 +00:00
Chris Lattner
1efde528d6 Fix an infinite loop building the CFE 
llvm-svn: 30465
 2006-09-18 18:27:05 +00:00
Chris Lattner
6392e78191 new testcase 
llvm-svn: 30464
 2006-09-18 18:07:51 +00:00
Andrew Lenharth
5d958d3405 Jump tables on Alpha 
llvm-svn: 30463
 2006-09-18 18:01:03 +00:00
Andrew Lenharth
9c54a925e8 oops 
llvm-svn: 30462
 2006-09-18 18:00:18 +00:00
Andrew Lenharth
00bbd5641b absolute addresses must match pointer size 
llvm-svn: 30461
 2006-09-18 17:59:35 +00:00
Jim Laskey
07ac577a34 Sort out mangled names for globals 
llvm-svn: 30460
 2006-09-18 14:47:26 +00:00
Chris Lattner
39218c2b0c Implement a trivial optzn: of vastart is never called in a function that takes 
... args, remove the '...'.

This is Transforms/DeadArgElim/dead_vaargs.ll

llvm-svn: 30459
 2006-09-18 07:02:31 +00:00