[LLVMdev] Bug in opt

[Joe armstrong]

I have a problem.

I'm writing a C compiler in my favorite programming language (don't ask :-)

I have made a .s file, which can be correctly assembled
and run with lli. But when I optimize it I get no errors
from the optimizer, but the resultant file is incorrect.

Here's what happens:

llvm-as test2_gen.s   %% no errors test2_gen.s.bc is produced

lli test2_gen.s.bc
n=887459712           %% no errors

opt -std-compile-opts -S test2_gen.s.bc > test2_opt.s.bc

%% no errors
%% But now the generated file cannon be disassembled or run 

lli test2_opt.s.bc 
lli: error loading program 'test2_opt.s.bc': Bitcode stream should be a 
multiple
of 4 bytes in length
llvm-dis test2_opt.s.bc 
llvm-dis: Bitcode stream should be a multiple of 4 bytes in length

The generated .s file is as follows:

; ----- start
; Compiled by the amazing Ericsson C->LLVM compiler
; Hand crafted in Erlang
; ModuleID = 'test2.c'

target datalayout =
"e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:32:
64-v64:64:64-v128:128:128-a0:0:64-f80:32:32-n8:16:32"
target triple = "i386-pc-linux-gnu"

; Sock it to me baby

;; globals
declare i32  @printf(i8* , ...)

@main.str1 = private constant [6x i8] c"n=%i\0A\00"

;; code 
define i32 @main() nounwind {
  ;;return register

  %tmp_1  = alloca i32 ,align 4
  %i  = alloca i32 ,align 4
  %max  = alloca i32 ,align 4
  %n  = alloca i32 ,align 4
  %tmp_2  = add i32 0,0
  store i32 %tmp_2 ,i32* %i 
  %tmp_3  = add i32 0,100000000
  store i32 %tmp_3 ,i32* %max 
  %tmp_4  = add i32 0,0
  store i32 %tmp_4 ,i32* %n 
  br label %initfor_1

initfor_1:
  %tmp_5  = add i32 0,0
  store i32 %tmp_5 ,i32* %i 
  br label %testfor_3

updatefor_2:
  %tmp_6  = load i32* %i 
  %tmp_7  = add i32 0,1
  %tmp_8  = add i32 %tmp_6 ,%tmp_7 
  store i32 %tmp_8 ,i32* %i 
  br label %testfor_3

testfor_3:
  %tmp_9  = load i32* %i 
  %tmp_10  = load i32* %max 
  %tmp_11  = icmp slt i32 %tmp_9 ,%tmp_10 
  br i1  %tmp_11 ,label %bodyfor_4,label %endfor_5

bodyfor_4:
  %tmp_12  = load i32* %n 
  %tmp_13  = load i32* %i 
  %tmp_14  = add i32 %tmp_12 ,%tmp_13 
  store i32 %tmp_14 ,i32* %n 
  br label %updatefor_2

endfor_5:
  %tmp_15  = getelementptr [6 x i8]* @main.str1, i32 0, i32 0
  %tmp_16  = load i32* %n 
  %tmp_17  = call i32  (i8* , ...)* @printf(i8*  %tmp_15 , i32  %tmp_16 )
  %tmp_18  = add i32 0,0
  ret i32  %tmp_18 
}

The C code was as follows:

int printf(const char * format, ...);

int main()
{
  int i=0, max=100000000,n=0;
  for(i = 0; i < max; i = i + 1){
    n  = n + i;
    }
  printf("n=%i\n", n);
  return(0);
}

/Joe