search for: no_exit

...n ------------------------------------------------------------- Interval Contents: entry: load int* %i ; <int>:0 [#uses=1] load int* %j ; <int>:1 [#uses=1] %tmp.24 = setgt int %k, 0 ; <bool> [#uses=1] %tmp.35 = load int* %i ; <int> [#uses=2] br bool %tmp.24, label %no_exit.preheader, label %loopexit no_exit: ; preds = %no_exit, %no_exit.preheader %indvar = phi uint [ 0, %no_exit.preheader ], [ %indvar.next, %no_exit ] ; <uint> [#uses=2] %j.tmp.1 = phi int [ %j.promoted, %no_exit.preheader ], [ %tmp.8, %no_exit ] ; <int> [#uses=1] %tmp.3.0 = phi in...

...g with the > following simple example: > > int main() > { > int r(0); > for (int i = 0; i < 100; ++i) > r += i; > ; > return r; > } When I compiled it, I got the following LLVM code: int %main() { entry: call void %__main( ) br label %no_exit no_exit: ; preds = %entry, %no_exit %i.0.0 = phi int [ 0, %entry ], [ %inc, %no_exit ] %r.0.0 = phi int [ 0, %entry ], [ %tmp.4, %no_exit ] %tmp.4 = add int %r.0.0, %i.0.0 ; <int> [#uses=2] %inc = add int %i.0.0, 1 ; <int> [#uses=2] %tmp.1 = setgt int %inc, 99 ; <bool> [...

Hello, I've just downloaded the latest release of LLVM, and playing with the following simple example: int main() { int r(0); for (int i = 0; i < 100; ++i) r += i; ; return r; } I compile it and then run: analyze -indvars x.bc which prints: Printing analysis 'Induction Variable Analysis' for function 'main': and nothing else. It is a

...clude "stdio.h" #define N 40 void func1() { int a[N]; int i,j; for (i=0; i<N; i++) { if (i==0) a[i] = i*N; else a[i] = i*i; } } Test.ll: void %func1() { entry: %a = alloca [40 x int] ; <[40 x int]*> [#uses=1] br label %no_exit no_exit: ; preds = %else, %then, %entry %i.0.0 = phi int [ 0, %entry ], [ %inc9, %then ], [ %inc, %else ] ; <int> [#uses=7] %tmp.4 = seteq int %i.0.0, 0 ; <bool> [#uses=1] %tmp.7 = getelementptr [40 x int]* %a, int 0, int %i.0.0...

...ng the code below? It is creating assembly like this one below. Block LBB1_9 was inserted to break the critical edge between blocks LBB1_3 and LBB1_8. But it changes the semantics of the original program, because, before, LBB1_8 was falling through LBB1_4, and now it is falling on LBB1_9. LBB1_3: ;no_exit lis r4, 21845 ori r4, r4, 21846 mulhw r4, r2, r4 addi r5, r2, -1 li r6, -1 srwi r6, r4, 31 add r4, r4, r6 mulli r4, r4, 3 li r6, 1 subf r2, r4, r2 cmpwi cr0, r2, 0 beq cr0, LBB1_9 ;no_exit LBB1_7: ;no_ex...

...est(unsigned N, complex double *P) { for (; N != 0; --N) *P++ = 0; } We compile it to this LLVM code: void %test(uint %N, "complex long double"* %P) { entry: %tmp.15 = seteq uint %N, 0 ; <bool> [#uses=1] br bool %tmp.15, label %return, label %no_exit no_exit: ; preds = %no_exit, %entry %indvar = phi uint [ %indvar.next, %no_exit ], [ 0, %entry ] ; <uint> [#uses=3] %tmp.4 = getelementptr "complex long double"* %P, uint %indvar, uint 0 ; <double*> [#uses=1] store...

...) { >> if (i==0) >> a[i] = i*N; >> else >> a[i] = i*i; >> } >> } >> >> Test.ll: >> void %func1() { >> entry: >> %a = alloca [40 x int] ; <[40 x int]*> [#uses=1] >> br label %no_exit >> >> no_exit: ; preds = %else, %then, %entry >> %i.0.0 = phi int [ 0, %entry ], [ %inc9, %then ], [ %inc, %else ] >> ; <int> [#uses=7] >> %tmp.4 = seteq int %i.0.0, 0 ; <bool> [#uses=1] >> %tmp.7 = gete...

...a[N]; > int i,j; > for (i=0; i<N; i++) { > if (i==0) > a[i] = i*N; > else > a[i] = i*i; > } > } > > Test.ll: > void %func1() { > entry: > %a = alloca [40 x int] ; <[40 x int]*> [#uses=1] > br label %no_exit > > no_exit: ; preds = %else, %then, %entry > %i.0.0 = phi int [ 0, %entry ], [ %inc9, %then ], [ %inc, %else ] ; <int> [#uses=7] > %tmp.4 = seteq int %i.0.0, 0 ; <bool> [#uses=1] > %tmp.7 = getelementptr [40 x int]* %a...

...for (; N != 0; --N) > *P++ = 0; > } > > We compile it to this LLVM code: > > void %test(uint %N, "complex long double"* %P) { > entry: > %tmp.15 = seteq uint %N, 0 ; <bool> [#uses=1] > br bool %tmp.15, label %return, label %no_exit > > no_exit: ; preds = %no_exit, %entry > %indvar = phi uint [ %indvar.next, %no_exit ], [ 0, %entry > ] ; <uint> [#uses=3] > %tmp.4 = getelementptr "complex long double"* %P, uint > %indvar, uint 0 ; <double*...

...rget pointersize = 32 %struct..TorRec = type { int, void ()* } %struct.TorRec = type { int, void ()* } %.str_1 = internal constant [13 x sbyte] c"hello world\0A\00" ; <[13 x sbyte]*> [#uses=1] implementation ; Functions: int %main() { entry: br label %no_exit.i1 no_exit.i1: ; preds = %entry, %no_exit.i1 %Str.0.i = phi sbyte* [ %inc.i, %no_exit.i1 ], [ getelementptr ([13 x sbyte]* %.str_1, long 0, long 0), %entry ] ; <sbyte*> [#uses=2] %inc.i = getelementptr sbyte* %Str.0.i, long 1 ; <sb...

...+i) > > r += i; > > ; > > return r; > > } > > When I compiled it, I got the following LLVM code: The code I get is somewhat different: int %main() { entry: %tmp.1.i = load bool* %Initialized.0__ ; <bool> [#uses=1] br bool %tmp.1.i, label %no_exit, label %endif.0.i endif.0.i: ; preds = %entry store bool true, bool* %Initialized.0__ br label %no_exit no_exit: ; preds = %entry, %endif.0.i, %no_exit %i.0.0 = phi int [ %inc, %no_exit ], [ 0, %endif.0.i ], [ 0, %entry ] ; <int> [#uses=2] %r.0.0 = phi int [ %tmp.4, %no_exit ], [ 0,...

...a[i] = i*N; >>> else >>> a[i] = i*i; >>> } >>> } >>> >>> Test.ll: >>> void %func1() { >>> entry: >>> %a = alloca [40 x int] ; <[40 x int]*> [#uses=1] >>> br label %no_exit >>> >>> no_exit: ; preds = %else, %then, %entry >>> %i.0.0 = phi int [ 0, %entry ], [ %inc9, %then ], [ %inc, %else ] ; >>> <int> [#uses=7] >>> %tmp.4 = seteq int %i.0.0, 0 ; <bool> [#uses=1] >>...

...= 0; >> } >> >> We compile it to this LLVM code: >> >> void %test(uint %N, "complex long double"* %P) { >> entry: >> %tmp.15 = seteq uint %N, 0 ; <bool> [#uses=1] >> br bool %tmp.15, label %return, label %no_exit >> >> no_exit: ; preds = %no_exit, %entry >> %indvar = phi uint [ %indvar.next, %no_exit ], [ 0, %entry ] >> ; <uint> [#uses=3] >> %tmp.4 = getelementptr "complex long double"* %P, uint %indvar, >> uint 0...

...creating assembly like this one below. Block LBB1_9 was > inserted to break the critical edge between blocks LBB1_3 and LBB1_8. But > it changes the semantics of the original program, because, before, LBB1_8 > was falling through LBB1_4, and now it is falling on LBB1_9. > > LBB1_3: ;no_exit > lis r4, 21845 > ori r4, r4, 21846 > mulhw r4, r2, r4 > addi r5, r2, -1 > li r6, -1 > srwi r6, r4, 31 > add r4, r4, r6 > mulli r4, r4, 3 > li r6, 1 > subf r2, r4, r2 > cmpwi cr0, r2, 0 &gt...

...t be splitted, right? the instruction like 'phi..'. If so, how could we check this instruction to see if it can be splitted or not. 3) Here is a piece of code char a[]="hello world"; int i; for(i=0;i<10;i++){ a[i]=a[i]+1; } And I got IR code like the following no_exit: ; preds = %strlen.entry, %no_exit %indvar = phi uint [ %indvar.next, %no_exit ], [ 0, %strlen.entry ] ; <uint> [#uses=3] %i.0.0 = cast uint %indvar to int ; <int> [#uses=1] %tmp.24 = getelementptr [12 x sbyte]* %a, int 0, uint %indvar ; <sbyte*> [#uses=2] %tmp.28 = load...

I noticed that fourinarow is one of the programs in which LLVM is much slower than GCC, so I decided to take a look and see why that is so. The program has many loops that look like this: #define ROWS 6 #define COLS 7 void init_board(char b[COLS][ROWS+1]) { int i,j; for (i=0;i<COLS;i++) for (j=0;j<ROWS;j++) b[i][j]='.';

.... I am getting a very > weird dataflow graph (even without the Break Critical edges pass). The > dataflow generated by MachineFunction::dump() for the program below is > given here: > http://compilers.cs.ucla.edu/fernando/projects/soc/images/loop_no_crit2.pdf ... > The problem is the no_exit block. I think it was changed by one of the > optimization passes, and was split into three basic blocks. But now there > is a phi function where both the parameters are defined in the same basic > block. Any of you guys now which pass I should cut off if I want to avoid > this optimiza...

> If you don't want critical edges in the machine code CFG, you're going to > have to write a machine code CFG critical edge splitting pass: LLVM > doesn't currently have one. > > -Chris Hey guys, I've coded a pass to break the critical edges of the machine control flow graph. The program works fine, but I am sure it is not the right way of implementing it.

OK, thanks Chris, I've found that running opt -loopsimplify -instcombine -indvars -stats gives me the setup I need for this transformation, and a small patch makes it happen in the simple case we discussed. However, I'm having some trouble when things get a bit more complicated with 3 nesting levels: int A[3000000], B[20000], C[100], Z; int main() { int i, j, k, *a, *b,

...block option: $ ~/llvm/utils/profile.pl -block Output/em3d.llvm.bc <all of the stuff from before> ===-------------------------------------------------------------------------=== Top 20 most frequently executed basic blocks: ## %% Frequency 1. 4.60% 393/8545 make_neighbors() - no_exit.2 2. 4.56% 390/8545 make_neighbors() - loopentry.2 3. 4.56% 390/8545 make_neighbors() - endif.1 4. 4.56% 390/8545 make_neighbors() - endif.2 5. 4.56% 390/8545 make_neighbors() - loopexit.3 6. 4.56% 390/8545 check_percent() - entry 7. 4.53% 387/8545 make_neighbors...