bit.  This fixes Regression/Transforms/TailDup/MergeTest.ll

llvm-svn: 30237

For Transforms/TailDup/if-tail-dup.ll, f.e., it produces:

_foo:
        movl 8(%esp), %eax
        movl 4(%esp), %ecx
        testl $1, %ecx
        je LBB1_2       #cond_next
LBB1_1: #cond_true
        movl $1, (%eax)
LBB1_2: #cond_next
        testl $2, %ecx
        je LBB1_4       #cond_next10
LBB1_3: #cond_true6
        movl $1, 4(%eax)
LBB1_4: #cond_next10
        testl $4, %ecx
        je LBB1_6       #cond_next18
LBB1_5: #cond_true14
        movl $1, 8(%eax)
LBB1_6: #cond_next18
        testl $8, %ecx
        je LBB1_8       #return
LBB1_7: #cond_true22
        movl $1, 12(%eax)
        ret
LBB1_8: #return
        ret

instead of:

_foo:
        movl 4(%esp), %eax
        testl $2, %eax
        sete %cl
        movl 8(%esp), %edx
        testl $1, %eax
        je LBB1_2       #cond_next
LBB1_1: #cond_true
        movl $1, (%edx)
        testb %cl, %cl
        jne LBB1_4      #cond_next10
        jmp LBB1_3      #cond_true6
LBB1_2: #cond_next
        testb %cl, %cl
        jne LBB1_4      #cond_next10
LBB1_3: #cond_true6
        movl $1, 4(%edx)
        testl $4, %eax
        je LBB1_6       #cond_next18
        jmp LBB1_5      #cond_true14
LBB1_4: #cond_next10
        testl $4, %eax
        je LBB1_6       #cond_next18
LBB1_5: #cond_true14
        movl $1, 8(%edx)
        testl $8, %eax
        je LBB1_8       #return
        jmp LBB1_7      #cond_true22
LBB1_6: #cond_next18
        testl $8, %eax
        je LBB1_8       #return
LBB1_7: #cond_true22
        movl $1, 12(%edx)
        ret
LBB1_8: #return
        ret

llvm-svn: 30158

llvm-svn: 29925

llvm-svn: 25514

llvm-svn: 21427

llvm-svn: 18110

#define CL0(a) case a: f(); goto c;
 #define CL1(a) CL0(a##0) CL0(a##1) CL0(a##2) CL0(a##3) CL0(a##4) CL0(a##5) \
 CL0(a##6) CL0(a##7) CL0(a##8) CL0(a##9)
 #define CL2(a) CL1(a##0) CL1(a##1) CL1(a##2) CL1(a##3) CL1(a##4) CL1(a##5) \
 CL1(a##6) CL1(a##7) CL1(a##8) CL1(a##9)
 #define CL3(a) CL2(a##0) CL2(a##1) CL2(a##2) CL2(a##3) CL2(a##4) CL2(a##5) \
 CL2(a##6) CL2(a##7) CL2(a##8) CL2(a##9)
 #define CL4(a) CL3(a##0) CL3(a##1) CL3(a##2) CL3(a##3) CL3(a##4) CL3(a##5) \
 CL3(a##6) CL3(a##7) CL3(a##8) CL3(a##9)

 void f();

 void a() {
     int b;
  c: switch (b) {
         CL4(1)
     }
 }

This comes from GCC PR 15524

llvm-svn: 17390

an instruction if it can be hoisted to a common dominator of the block.
This implements: test/Regression/Transforms/TailDup/MergeTest.ll

llvm-svn: 16758

llvm-svn: 16432

Patch contributed by Paolo Invernizzi. Thanks Paolo!

llvm-svn: 16368

Move include/Config and include/Support into include/llvm/Config,
include/llvm/ADT and include/llvm/Support. From here on out, all LLVM
public header files must be under include/llvm/.

llvm-svn: 16137

llvm-svn: 15328

llvm-svn: 13750

llvm-svn: 13025

llvm-svn: 12458

as it is making effectively arbitrary modifications to the CFG and we don't
have a domset/domfrontier implementations that can handle the dynamic updates.
Instead of having a bunch of code that doesn't actually work in practice,
just demote any potentially tricky values to the stack (causing the problem
to go away entirely).  Later invocations of mem2reg will rebuild SSA for us.

This fixes all of the major performance regressions with tail duplication
from LLVM 1.1.  For example, this loop:

---
int popcount(int x) {
  int result = 0;
  while (x != 0) {
    result = result + (x & 0x1);
    x = x >> 1;
  }
  return result;
}
---
Used to be compiled into:

int %popcount(int %X) {
entry:
	br label %loopentry

loopentry:		; preds = %entry, %no_exit
	%x.0 = phi int [ %X, %entry ], [ %tmp.9, %no_exit ]		; <int> [#uses=3]
	%result.1.0 = phi int [ 0, %entry ], [ %tmp.6, %no_exit ]		; <int> [#uses=2]
	%tmp.1 = seteq int %x.0, 0		; <bool> [#uses=1]
	br bool %tmp.1, label %loopexit, label %no_exit

no_exit:		; preds = %loopentry
	%tmp.4 = and int %x.0, 1		; <int> [#uses=1]
	%tmp.6 = add int %tmp.4, %result.1.0		; <int> [#uses=1]
	%tmp.9 = shr int %x.0, ubyte 1		; <int> [#uses=1]
	br label %loopentry

loopexit:		; preds = %loopentry
	ret int %result.1.0
}

And is now compiled into:

int %popcount(int %X) {
entry:
        br label %no_exit

no_exit:                ; preds = %entry, %no_exit
        %x.0.0 = phi int [ %X, %entry ], [ %tmp.9, %no_exit ]          ; <int> [#uses=2]
        %result.1.0.0 = phi int [ 0, %entry ], [ %tmp.6, %no_exit ]             ; <int> [#uses=1]
        %tmp.4 = and int %x.0.0, 1              ; <int> [#uses=1]
        %tmp.6 = add int %tmp.4, %result.1.0.0          ; <int> [#uses=2]
        %tmp.9 = shr int %x.0.0, ubyte 1                ; <int> [#uses=2]
        %tmp.1 = seteq int %tmp.9, 0            ; <bool> [#uses=1]
        br bool %tmp.1, label %loopexit, label %no_exit

loopexit:               ; preds = %no_exit
        ret int %tmp.6
}

llvm-svn: 12457

llvm-svn: 12441

llvm-svn: 12021

Note that this is a band-aid put over a band-aid.  This just undisables
tail duplication in on very specific case that it seems to work in.

llvm-svn: 11989

hot 164.gzip loop.

llvm-svn: 11702

llvm-svn: 11052

llvm-svn: 10725

llvm-svn: 9903

Header files will be on the way.

llvm-svn: 9298

llvm-svn: 8276

llvm-svn: 8078

llvm-svn: 7492

llvm-svn: 7243

llvm-svn: 6881

llvm-svn: 6856

llvm-svn: 6852

llvm-svn: 6846