llvm dev - Apr 2006 - [LLVMdev] floating point exception and SSE2 instructions

Hi,

I'm building a little JIT that creates functions to do array manipulations,
eg. sum all the elements of a double* array. I'm writing this in python,
generating
llvm assembly intructions and piping that through a call to ParseAssemblyString,
ExecutionEngine, etc.

It's working OK on integer values, but i'm getting nasty floating point
exceptions
when i try this on double* values. I've seen this behaviour before on this
platform
(debian Intel P4) when I tried using ATLAS with sse2. I'm pretty sure
it's
valid assembly; the code still causes exceptions when i try using the output
from the llvm demo website. And it works fine on an AMD machine.

What is LLVM doing with my code ? Does it generate SSE2 instructions ?

thanks!

Simon.

double sum_d(double*mem,int n)
{
  double val=0.0;
  while(n)
  { val += *mem; mem++; n--; }
  return val;
}


-- 
Simon Burton, B.Sc.
Licensed PO Box 8066
ANU Canberra 2601
Australia
Ph. 61 02 6249 6940
http://arrowtheory.com

Hi Simon,

The x86 backend does generate scalar SSE2 instructions. For your  
example, it should emit something like:

         .text
         .align  4
         .globl  _sum_d
_sum_d:
         subl $12, %esp
         movl 20(%esp), %eax
         movl 16(%esp), %ecx
         cmpl $0, %eax
         jne LBB_sum_d_2 # cond_true.preheader
LBB_sum_d_1:    # entry.bb9_crit_edge
         pxor %xmm0, %xmm0
         jmp LBB_sum_d_5 # bb9
LBB_sum_d_2:    # cond_true.preheader
         pxor %xmm0, %xmm0
         xorl %edx, %edx
LBB_sum_d_3:    # cond_true
         addsd (%ecx), %xmm0
         addl $8, %ecx
         incl %edx
         cmpl %eax, %edx
         jne LBB_sum_d_3 # cond_true
LBB_sum_d_4:    # bb9.loopexit
LBB_sum_d_5:    # bb9
         movsd %xmm0, (%esp)
         fldl (%esp)
         addl $12, %esp
         ret

There is nothing here that should cause an exception. Are you using a  
release or cvs?

Evan

On Apr 18, 2006, at 11:17 PM, Simon Burton wrote:
>
> Hi,
>
> I'm building a little JIT that creates functions to do array  
> manipulations,
> eg. sum all the elements of a double* array. I'm writing this in  
> python, generating
> llvm assembly intructions and piping that through a call to  
> ParseAssemblyString,
> ExecutionEngine, etc.
>
> It's working OK on integer values, but i'm getting nasty floating  
> point exceptions
> when i try this on double* values. I've seen this behaviour before  
> on this platform
> (debian Intel P4) when I tried using ATLAS with sse2. I'm pretty  
> sure it's
> valid assembly; the code still causes exceptions when i try using  
> the output
> from the llvm demo website. And it works fine on an AMD machine.
>
> What is LLVM doing with my code ? Does it generate SSE2 instructions ?
>
> thanks!
>
> Simon.
>
> double sum_d(double*mem,int n)
> {
>   double val=0.0;
>   while(n)
>   { val += *mem; mem++; n--; }
>   return val;
> }
>
>
> -- 
> Simon Burton, B.Sc.
> Licensed PO Box 8066
> ANU Canberra 2601
> Australia
> Ph. 61 02 6249 6940
> http://arrowtheory.com
>
> _______________________________________________
> LLVM Developers mailing list
> LLVMdev at cs.uiuc.edu         http://llvm.cs.uiuc.edu
> http://lists.cs.uiuc.edu/mailman/listinfo/llvmdev

On Tue, 18 Apr 2006 23:27:39 -0700
Evan Cheng <evan.cheng at apple.com> wrote:
> Hi Simon,
> 
> The x86 backend does generate scalar SSE2 instructions. For your  
> example, it should emit something like:
Oh, how did you get this ?

[...]
> 
> There is nothing here that should cause an exception. Are you using a  
> release or cvs?
CVS.
>From what I remember, this is a bug in debian libc:
some floating point flags are set incorrectly causing SIGFPE.
Can't find the bug report ATM.

Thanks,

Simon.



-- 
Simon Burton, B.Sc.
Licensed PO Box 8066
ANU Canberra 2601
Australia
Ph. 61 02 6249 6940
http://arrowtheory.com