caio/clang-p2996
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
31,724 Commits 1 Branch 0 Tags
da17029218cf0c19cf0341dda1ba557471e33871
Commit Graph

3543 Commits

Author SHA1 Message Date
Chris Lattner
be02d430a9 Lower to the correct functions. This fixes FreeBench/fourinarow 
llvm-svn: 19436
 2005-01-10 21:02:37 +00:00
Chris Lattner
41b764144d Implement a couple of more simplifications. This lets us codegen: 
int test2(int * P, int* Q, int A, int B) {
        return P+A == P;
}

into:

test2:
        movl 4(%esp), %eax
        movl 12(%esp), %eax
        shll $2, %eax
        cmpl $0, %eax
        sete %al
        movzbl %al, %eax
        ret

instead of:

test2:
        movl 4(%esp), %eax
        movl 12(%esp), %ecx
        leal (%eax,%ecx,4), %ecx
        cmpl %eax, %ecx
        sete %al
        movzbl %al, %eax
        ret

ICC is producing worse code:

test2:
        movl      4(%esp), %eax                                 #8.5
        movl      12(%esp), %edx                                #8.5
        lea       (%edx,%edx), %ecx                             #9.9
        addl      %ecx, %ecx                                    #9.9
        addl      %eax, %ecx                                    #9.9
        cmpl      %eax, %ecx                                    #9.16
        movl      $0, %eax                                      #9.16
        sete      %al                                           #9.16
        ret                                                     #9.16

as is GCC (looks like our old code):

test2:
        movl    4(%esp), %edx
        movl    12(%esp), %eax
        leal    (%edx,%eax,4), %ecx
        cmpl    %edx, %ecx
        sete    %al
        movzbl  %al, %eax
        ret

llvm-svn: 19430
 2005-01-10 02:03:02 +00:00
Chris Lattner
00c231baa7 Fix incorrect constant folds, fixing Stepanov after the SHR patch. 
llvm-svn: 19429
 2005-01-10 01:16:03 +00:00
Chris Lattner
0966a75e76 Constant fold shifts, turning this loop: 
.LBB_Z5test0PdS__3:     # no_exit.1
        fldl data(,%eax,8)
        fldl 24(%esp)
        faddp %st(1)
        fstl 24(%esp)
        incl %eax
        movl $16000, %ecx
        sarl $3, %ecx
        cmpl %eax, %ecx
        fstpl 16(%esp)
        #FP_REG_KILL
        jg .LBB_Z5test0PdS__3   # no_exit.1

into:

.LBB_Z5test0PdS__3:     # no_exit.1
        fldl data(,%eax,8)
        fldl 24(%esp)
        faddp %st(1)
        fstl 24(%esp)
        incl %eax
        cmpl $2000, %eax
        fstpl 16(%esp)
        #FP_REG_KILL
        jl .LBB_Z5test0PdS__3   # no_exit.1

llvm-svn: 19427
 2005-01-10 00:07:15 +00:00
Chris Lattner
fde3a212e2 Add some folds for == and != comparisons. This allows us to 
codegen this loop in stepanov:

no_exit.i:              ; preds = %entry, %no_exit.i, %then.i, %_Z5checkd.exit
        %i.0.0 = phi int [ 0, %entry ], [ %i.0.0, %no_exit.i ], [ %inc.0, %_Z5checkd.exit ], [ %inc.012, %then.i ]              ; <int> [#uses=3]
        %indvar = phi uint [ %indvar.next, %no_exit.i ], [ 0, %entry ], [ 0, %then.i ], [ 0, %_Z5checkd.exit ]          ; <uint> [#uses=3]
        %result_addr.i.0 = phi double [ %tmp.4.i.i, %no_exit.i ], [ 0.000000e+00, %entry ], [ 0.000000e+00, %then.i ], [ 0.000000e+00, %_Z5checkd.exit ]          ; <double> [#uses=1]
        %first_addr.0.i.2.rec = cast uint %indvar to int                ; <int> [#uses=1]
        %first_addr.0.i.2 = getelementptr [2000 x double]* %data, int 0, uint %indvar           ; <double*> [#uses=1]
        %inc.i.rec = add int %first_addr.0.i.2.rec, 1           ; <int> [#uses=1]
        %inc.i = getelementptr [2000 x double]* %data, int 0, int %inc.i.rec            ; <double*> [#uses=1]
        %tmp.3.i.i = load double* %first_addr.0.i.2             ; <double> [#uses=1]
        %tmp.4.i.i = add double %result_addr.i.0, %tmp.3.i.i            ; <double> [#uses=2]
        %tmp.2.i = seteq double* %inc.i, getelementptr ([2000 x double]* %data, int 0, int 2000)                ; <bool> [#uses=1]
        %indvar.next = add uint %indvar, 1              ; <uint> [#uses=1]
        br bool %tmp.2.i, label %_Z10accumulateIPddET0_T_S2_S1_.exit, label %no_exit.i

To this:

.LBB_Z4testIPddEvT_S1_T0__1:    # no_exit.i
        fldl data(,%eax,8)
        fldl 16(%esp)
        faddp %st(1)
        fstpl 16(%esp)
        incl %eax
        movl %eax, %ecx
        shll $3, %ecx
        cmpl $16000, %ecx
        #FP_REG_KILL
        jne .LBB_Z4testIPddEvT_S1_T0__1 # no_exit.i

instead of this:

.LBB_Z4testIPddEvT_S1_T0__1:    # no_exit.i
        fldl data(,%eax,8)
        fldl 16(%esp)
        faddp %st(1)
        fstpl 16(%esp)
        incl %eax
        leal data(,%eax,8), %ecx
        leal data+16000, %edx
        cmpl %edx, %ecx
        #FP_REG_KILL
        jne .LBB_Z4testIPddEvT_S1_T0__1 # no_exit.i

llvm-svn: 19425
 2005-01-09 20:52:51 +00:00
Jeff Cohen
7d1670da3f Fix VC++ compilation error 
llvm-svn: 19423
 2005-01-09 20:41:56 +00:00
Chris Lattner
e6f7882c27 Print the DAG out more like a DAG in nested format. 
llvm-svn: 19422
 2005-01-09 20:38:33 +00:00
Chris Lattner
1270acc1ce Print out nodes sorted by their address to make it easier to find them in a list. 
llvm-svn: 19421
 2005-01-09 20:26:36 +00:00
Chris Lattner
3d5d5022d5 Add a simple transformation. This allows us to compile one of the inner 
loops in stepanov to this:

.LBB_Z5test0PdS__2:     # no_exit.1
        fldl data(,%eax,8)
        fldl 24(%esp)
        faddp %st(1)
        fstl 24(%esp)
        incl %eax
        cmpl $2000, %eax
        fstpl 16(%esp)
        #FP_REG_KILL
        jl .LBB_Z5test0PdS__2

instead of this:

.LBB_Z5test0PdS__2:     # no_exit.1
        fldl data(,%eax,8)
        fldl 24(%esp)
        faddp %st(1)
        fstl 24(%esp)
        incl %eax
        movl $data, %ecx
        movl %ecx, %edx
        addl $16000, %edx
        subl %ecx, %edx
        movl %edx, %ecx
        sarl $2, %ecx
        shrl $29, %ecx
        addl %ecx, %edx
        sarl $3, %edx
        cmpl %edx, %eax
        fstpl 16(%esp)
        #FP_REG_KILL
        jl .LBB_Z5test0PdS__2

The old instruction selector produced:

.LBB_Z5test0PdS__2:     # no_exit.1
        fldl 24(%esp)
        faddl data(,%eax,8)
        fstl 24(%esp)
        movl %eax, %ecx
        incl %ecx
        incl %eax
        leal data+16000, %edx
        movl $data, %edi
        subl %edi, %edx
        movl %edx, %edi
        sarl $2, %edi
        shrl $29, %edi
        addl %edi, %edx
        sarl $3, %edx
        cmpl %edx, %ecx
        fstpl 16(%esp)
        #FP_REG_KILL
        jl .LBB_Z5test0PdS__2   # no_exit.1

Which is even worse!

llvm-svn: 19419
 2005-01-09 20:09:57 +00:00
Chris Lattner
9242c504da Fix a bug legalizing call instructions (make sure to remember all result 
values), and eliminate some switch statements.

llvm-svn: 19417
 2005-01-09 19:43:23 +00:00
Chris Lattner
02f5ce2077 Fix a minor bug legalizing dynamic_stackalloc. This allows us to compile 
std::__pad<wchar_t, std::char_traits<wchar_t> >::_S_pad(std::ios_base&, wchar_t, wchar_t*, wchar_t const*, int, int, bool)

from libstdc++

llvm-svn: 19416
 2005-01-09 19:07:54 +00:00
Chris Lattner
ec26b48d61 Teach legalize to deal with DYNAMIC_STACKALLOC (aka a dynamic llvm alloca) 
llvm-svn: 19415
 2005-01-09 19:03:49 +00:00
Chris Lattner
a2c5d9168c Handle static alloca arguments to PHI nodes. 
llvm-svn: 19409
 2005-01-09 01:16:24 +00:00
Chris Lattner
58cfd7945d Use new interfaces to correctly lower varargs and return/frame address intrinsics. 
llvm-svn: 19407
 2005-01-09 00:00:49 +00:00
Chris Lattner
18d2b34637 Add support for llvm.setjmp and longjmp. Only 3 SingleSource/UnitTests fail now. 
llvm-svn: 19404
 2005-01-08 22:48:57 +00:00
Chris Lattner
c0f31c5e96 Tighten up assertions. 
llvm-svn: 19397
 2005-01-08 20:35:13 +00:00
Chris Lattner
0b955fd2d5 Silence VS warnings 
llvm-svn: 19388
 2005-01-08 19:59:10 +00:00
Chris Lattner
e64ff1c4b2 Silence warnings from VS 
llvm-svn: 19386
 2005-01-08 19:55:00 +00:00
Chris Lattner
78100c41ca Silence VS warnings 
llvm-svn: 19385
 2005-01-08 19:53:50 +00:00
Chris Lattner
d006195517 Silence VS warnings. 
llvm-svn: 19384
 2005-01-08 19:52:31 +00:00
Chris Lattner
7e6eeba6c5 Implement handling of most long operators through libcalls. 
Fix a bug legalizing "ret (Val,Val)"

llvm-svn: 19375
 2005-01-08 19:27:05 +00:00
Chris Lattner
1f45cd7418 Adjust to changes in LowerCAllTo interfaces 
llvm-svn: 19374
 2005-01-08 19:26:18 +00:00
Chris Lattner
2a6db3c351 Add support for FP->INT conversions and back. 
llvm-svn: 19369
 2005-01-08 08:08:56 +00:00
Chris Lattner
e69daaf71d Implement the 'store FPIMM, Ptr' -> 'store INTIMM, Ptr' optimization for 
all targets.

llvm-svn: 19366
 2005-01-08 06:25:56 +00:00
Chris Lattner
9a97e4d5b6 1ULL << 64 is undefined, don't do it. 
llvm-svn: 19365
 2005-01-08 06:24:30 +00:00
Chris Lattner
e0f1fe181a Fix a pointer invalidation problem. This fixes Generic/badarg6.ll 
llvm-svn: 19361
 2005-01-07 23:32:00 +00:00
Chris Lattner
5c66e45b92 Fold conditional branches on constants away. 
llvm-svn: 19360
 2005-01-07 22:49:57 +00:00
Chris Lattner
cda3efa6e5 Fix a thinko in the reassociation code, fixing Generic/badlive.ll 
llvm-svn: 19359
 2005-01-07 22:44:09 +00:00
Chris Lattner
a65a2f0c36 Add support for truncating integer casts from long. 
llvm-svn: 19358
 2005-01-07 22:37:48 +00:00
Chris Lattner
ea4ca94cae Fix a bug in load expansion legalization and ret legalization. This fixes 
CodeGen/Generic/select.ll:castconst.

llvm-svn: 19357
 2005-01-07 22:28:47 +00:00
Chris Lattner
68a12140c0 Legalize unconditional branches too 
llvm-svn: 19356
 2005-01-07 22:12:08 +00:00
Chris Lattner
19a83990e1 Implement support for long GEP indices on 32-bit archs and support for 
int GEP indices on 64-bit archs.

llvm-svn: 19354
 2005-01-07 21:56:57 +00:00
Chris Lattner
4d5ba99283 Simplify: truncate ({zero|sign}_extend (X)) 
llvm-svn: 19353
 2005-01-07 21:56:24 +00:00
Chris Lattner
32f20bfa93 implement legalization of a bunch more operators. 
llvm-svn: 19352
 2005-01-07 21:45:56 +00:00
Chris Lattner
fa854eb012 Fix another bug legalizing calls! 
llvm-svn: 19350
 2005-01-07 21:35:32 +00:00
Chris Lattner
8ea875fb05 Fix handling of dead PHI nodes. 
llvm-svn: 19349
 2005-01-07 21:34:19 +00:00
Chris Lattner
f025d6788c Fix a bug legalizing calls 
llvm-svn: 19348
 2005-01-07 21:34:13 +00:00
Chris Lattner
473825ccec After legalizing a DAG, delete dead nodes to save space. 
llvm-svn: 19346
 2005-01-07 21:09:37 +00:00
Chris Lattner
9c667933c1 Implement RemoveDeadNodes 
llvm-svn: 19345
 2005-01-07 21:09:16 +00:00
Chris Lattner
ec3fe7c4a8 Teach legalize how to handle condbranches 
llvm-svn: 19339
 2005-01-07 08:19:42 +00:00
Chris Lattner
7a60d91953 Initial implementation of the SelectionDAGISel class. This contains most 
of the code for lowering from LLVM code to a SelectionDAG.

llvm-svn: 19331
 2005-01-07 07:47:53 +00:00
Chris Lattner
f8ba6987a4 This file is obsolete 
llvm-svn: 19330
 2005-01-07 07:47:23 +00:00
Chris Lattner
dc75059005 Initial implementation of the DAG legalization. This still has a long way 
to go, but it does work for some non-trivial cases now.

llvm-svn: 19329
 2005-01-07 07:47:09 +00:00
Chris Lattner
061a1ea9e3 Complete rewrite of the SelectionDAG class. 
llvm-svn: 19327
 2005-01-07 07:46:32 +00:00
Chris Lattner
9590870a0d Make the 2-address instruction lowering pass smarter in two ways: 
1. If we are two-addressing a commutable instruction and the LHS is not the
   last use of the variable, see if the instruction is the last use of the
   RHS.  If so, commute the instruction, allowing us to avoid a
   register-register copy in many cases for common instructions like ADD, OR,
   AND, etc on X86.
2. If #1 doesn't hold, and if this is an instruction that also existing in
   3-address form, promote the instruction to a 3-address instruction to
   avoid the register-register copy.  We can do this for several common
   instructions in X86, including ADDrr, INC, DEC, etc.

This patch implements test/Regression/CodeGen/X86/commute-two-addr.ll,
overlap-add.ll, and overlap-shift.ll when I check in the X86 support for it.

llvm-svn: 19245
 2005-01-02 02:34:12 +00:00
Chris Lattner
e09dbe2732 Move virtual method call out of loop 
llvm-svn: 18955
 2004-12-15 07:04:32 +00:00
Nate Begeman
784a0dcbd0 Move virtual function call out of loop to speed up getFreePhysReg by about 
20%, shaving 0.1s off hbd compile time on my g5.  Yay.

llvm-svn: 18592
 2004-12-07 05:25:53 +00:00
Reid Spencer
9083936835 For PR387:\ 
Make only one print method to avoid overloaded virtual warnings when \
compiled with -Woverloaded-virtual

llvm-svn: 18589
 2004-12-07 04:03:45 +00:00
Chris Lattner
5684f4817f Prevent accessing past the end of the intervals vector, this fixes 
Prolang-C/bison in the JIT

llvm-svn: 18477
 2004-12-04 01:22:09 +00:00
Chris Lattner
ebb54c55e1 Fix SingleSource/UnitTests/2004-11-28-GlobalBoolLayout.c, and hopefully 
PR449

llvm-svn: 18306
 2004-11-28 17:56:47 +00:00