| Commit message (Collapse) | Author | Age | Files | Lines |
| ... | |
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
successors), and make island block movement more general.
This compiles CodeGen/X86/2006-04-27-ISelFoldingBug.ll to:
_loadAndRLEsource_no_exit_2E_1_label_2E_0:
subl $8, %esp
movl %esi, 4(%esp)
movl %ebx, (%esp)
movl 16(%esp), %eax
movl 12(%esp), %ecx
LBB1_3: #label.0
movl _last, %edx
movl %edx, %esi
incl %esi
movl %esi, _last
movl %ecx, %ebx
# TRUNCATE movb %bl, %bl
movl _block, %esi
movb %bl, 1(%esi,%edx)
cmpl %eax, _last
jge LBB1_2 #codeRepl5.exitStub
LBB1_4: #label.0
cmpl $257, %ecx
je LBB1_2 #codeRepl5.exitStub
LBB1_1: #label.0.no_exit.1_crit_edge.exitStub
movl $1, %eax
movl (%esp), %ebx
movl 4(%esp), %esi
addl $8, %esp
ret
LBB1_2: #codeRepl5.exitStub
xorl %eax, %eax
movl (%esp), %ebx
movl 4(%esp), %esi
addl $8, %esp
ret
instead of:
_loadAndRLEsource_no_exit_2E_1_label_2E_0:
subl $8, %esp
movl %esi, 4(%esp)
movl %ebx, (%esp)
movl 16(%esp), %eax
movl 12(%esp), %ecx
jmp LBB1_3 #label.0
LBB1_1: #label.0.no_exit.1_crit_edge.exitStub
movl $1, %eax
movl (%esp), %ebx
movl 4(%esp), %esi
addl $8, %esp
ret
LBB1_2: #codeRepl5.exitStub
xorl %eax, %eax
movl (%esp), %ebx
movl 4(%esp), %esi
addl $8, %esp
ret
LBB1_3: #label.0
movl _last, %edx
movl %edx, %esi
incl %esi
movl %esi, _last
movl %ecx, %ebx
# TRUNCATE movb %bl, %bl
movl _block, %esi
movb %bl, 1(%esi,%edx)
cmpl %eax, _last
jge LBB1_2 #codeRepl5.exitStub
LBB1_4: #label.0
cmpl $257, %ecx
jne LBB1_1 #label.0.no_exit.1_crit_edge.exitStub
jmp LBB1_2 #codeRepl5.exitStub
... which is much better layout :)
llvm-svn: 31282
|
| |
|
|
| |
llvm-svn: 31281
|
| |
|
|
|
|
| |
used by comparisons in the main block.
llvm-svn: 31279
|
| |
|
|
| |
llvm-svn: 31276
|
| |
|
|
| |
llvm-svn: 31275
|
| |
|
|
|
|
|
|
| |
edges whose destinations are not phi nodes don't bother us. Also, share
split edges, since the split edge can't have a phi. This significantly
reduces the complexity of generated code in some cases.
llvm-svn: 31274
|
| |
|
|
|
|
| |
jump tables that are dead.
llvm-svn: 31273
|
| |
|
|
| |
llvm-svn: 31269
|
| |
|
|
| |
llvm-svn: 31267
|
| |
|
|
| |
llvm-svn: 31266
|
| |
|
|
|
|
| |
the pred block doesn't fall through into them if it's a jumptable.
llvm-svn: 31263
|
| |
|
|
| |
llvm-svn: 31261
|
| |
|
|
|
|
|
|
|
| |
being inserted on unsplit critical edges, which introduces (sometimes large
amounts of) partially dead spill code.
This also fixes PR925 + CodeGen/Generic/switch-crit-edge-constant.ll
llvm-svn: 31260
|
| |
|
|
| |
llvm-svn: 31254
|
| |
|
|
| |
llvm-svn: 31243
|
| |
|
|
|
|
|
|
|
|
| |
(CodeGen/Generic/2006-10-27-CondFolding.ll).
Add many fewer CFG edges and PHI node entries. If there is a switch which has
the same block as multiple destinations, only add that block once as a successor/phi
node (in the jumptable case)
llvm-svn: 31242
|
| |
|
|
| |
llvm-svn: 31240
|
| |
|
|
| |
llvm-svn: 31233
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
PowerPC/and-branch.ll to:
cmpwi cr0, r4, 4
bgt cr0, LBB1_2 ;UnifiedReturnBlock
LBB1_3: ;entry
cmplwi cr0, r3, 0
bne cr0, LBB1_2 ;UnifiedReturnBlock
instead of:
cmpwi cr7, r4, 4
mfcr r2
addic r4, r3, -1
subfe r3, r4, r3
rlwinm r2, r2, 30, 31, 31
or r2, r2, r3
cmplwi cr0, r2, 0
bne cr0, LBB1_2 ;UnifiedReturnBlock
LBB1_1: ;cond_true
llvm-svn: 31232
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
This compiles Regression/CodeGen/X86/or-branch.ll into:
_foo:
subl $12, %esp
call L_bar$stub
movl 20(%esp), %eax
movl 16(%esp), %ecx
cmpl $5, %eax
jl LBB1_1 #cond_true
LBB1_3: #entry
testl %ecx, %ecx
jne LBB1_2 #UnifiedReturnBlock
LBB1_1: #cond_true
call L_bar$stub
addl $12, %esp
ret
LBB1_2: #UnifiedReturnBlock
addl $12, %esp
ret
instead of:
_foo:
subl $12, %esp
call L_bar$stub
movl 20(%esp), %eax
movl 16(%esp), %ecx
cmpl $4, %eax
setg %al
testl %ecx, %ecx
setne %cl
testb %cl, %al
jne LBB1_2 #UnifiedReturnBlock
LBB1_1: #cond_true
call L_bar$stub
addl $12, %esp
ret
LBB1_2: #UnifiedReturnBlock
addl $12, %esp
ret
And on ppc to:
cmpwi cr0, r29, 5
blt cr0, LBB1_1 ;cond_true
LBB1_3: ;entry
cmplwi cr0, r30, 0
bne cr0, LBB1_2 ;UnifiedReturnBlock
instead of:
cmpwi cr7, r4, 4
mfcr r2
addic r4, r3, -1
subfe r30, r4, r3
rlwinm r29, r2, 30, 31, 31
and r2, r29, r30
cmplwi cr0, r2, 0
bne cr0, LBB1_2 ;UnifiedReturnBlock
llvm-svn: 31230
|
| |
|
|
| |
llvm-svn: 31209
|
| |
|
|
|
|
|
|
| |
Make necessary changes to support DIV -> [SUF]Div. This changes llvm to
have three division instructions: signed, unsigned, floating point. The
bytecode and assembler are bacwards compatible, however.
llvm-svn: 31195
|
| |
|
|
| |
llvm-svn: 31188
|
| |
|
|
| |
llvm-svn: 31180
|
| |
|
|
| |
llvm-svn: 31179
|
| |
|
|
| |
llvm-svn: 31171
|
| |
|
|
|
|
| |
visitBr to just call visitSwitchCase, eliminating duplicate logic.
llvm-svn: 31167
|
| |
|
|
|
|
|
| |
Rename LHSBB/RHSBB to TrueBB/FalseBB. Allow the RHS value to be null,
in which case the LHS is treated as a bool.
llvm-svn: 31166
|
| |
|
|
| |
llvm-svn: 31161
|
| |
|
|
| |
llvm-svn: 31155
|
| |
|
|
| |
llvm-svn: 31153
|
| |
|
|
| |
llvm-svn: 31152
|
| |
|
|
|
|
|
|
|
|
|
| |
a place more useful. In particular, if we can put them in a place where code
will be able to fall into it, do so. Otherwise, put it in a place it can fall
through into a successor. Otherwise, if preventing a fallthrough, move to the
end of the function, out of the way.
This deletes several hundred unconditional branches from spass.
llvm-svn: 31149
|
| |
|
|
| |
llvm-svn: 31145
|
| |
|
|
| |
llvm-svn: 31140
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
movl 32(%esp), %eax
cmpl $1, %eax
je LBB1_1 #bb
LBB1_4: #entry
cmpl $2, %eax
je LBB1_2 #bb2
jmp LBB1_3 #UnifiedReturnBlock
LBB1_1: #bb
notice that we would miss the fall through and emit this instead:
movl 32(%esp), %eax
cmpl $2, %eax
je LBB1_2 #bb2
LBB1_4: #entry
cmpl $1, %eax
jne LBB1_3 #UnifiedReturnBlock
LBB1_1: #bb
llvm-svn: 31130
|
| |
|
|
| |
llvm-svn: 31129
|
| |
|
|
| |
llvm-svn: 31125
|
| |
|
|
| |
llvm-svn: 31124
|
| |
|
|
| |
llvm-svn: 31119
|
| |
|
|
| |
llvm-svn: 31102
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
call L_strcmp$stub
testl %eax, %eax
- jne LBB26_208 #cond_true6020
- jmp LBB26_227 #bb7119
+ je LBB26_227 #bb7119
LBB26_208: #cond_true6020
movl $l31_str14, 4(%esp)
testl %eax, %eax
- jne LBB26_704 #cond_true13042
- jmp LBB26_713 #bb13151
+ je LBB26_713 #bb13151
LBB26_704: #cond_true13042
movl $_str52, 4(%esp)
cmpl 76(%ecx), %eax
- jge LBB26_1628 #cond_false63.i.i
- jmp LBB26_1769 #_Z8makeGridP13mrSurfaceListidiidd.exit.i
+ jl LBB26_1769 #_Z8makeGridP13mrSurfaceListidiidd.exit.i
LBB26_1628: #cond_false63.i.i
movl $0, 48964(%esp)
llvm-svn: 31100
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
jle FOO
jmp BAR
BAR:
into:
jle FOO
BAR:
... whoa!
llvm-svn: 31098
|
| |
|
|
|
|
|
|
|
|
|
|
| |
1. Remove a bunch of ifdef'd code.
2. When a block just contains an uncond branch, change all blocks branching
to it to jump to the destination instead.
3. If branch analysis tells us some edges in the machinecfg are not actually
possible, remove them.
#2 triggers a suprisingly large number of times.
llvm-svn: 31094
|
| |
|
|
|
|
|
| |
This is currently disabled by default and limited in several ways, but does
have a positive effect.
llvm-svn: 31090
|
| |
|
|
| |
llvm-svn: 31088
|
| |
|
|
|
|
| |
output.
llvm-svn: 31067
|
| |
|
|
|
|
|
|
| |
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
|
| |
|
|
|
|
|
|
| |
blocks into the basic block list when lowering the switch inst. into a
binary tree of if-then statements. This allows the "visitSwitchCase" func
to allow for fall-through behavior.
llvm-svn: 31057
|
| |
|
|
| |
llvm-svn: 31040
|