Also note that a similar problem occurs for hadamard8:
gcc-4.5 -c hadamard8.c -O3 -ffast-math -ftree-vectorizer-verbose=7 -msse2
[...]
hadamard8_diff.c:44: note: not vectorized: unhandled data-ref 
hadamard8_diff.c:26: note: not vectorized: data ref analysis failed D.2771_12 = *D.2770_11;

For which we fail to analyze one of the data references as well.
Note that ICC 11.0 does vectorize this kernel.


typedef unsigned char uint8_t;
typedef unsigned long int uint64_t;
typedef long int x86_reg;

#define BUTTERFLY2(o1,o2,i1,i2) \
o1= (i1)+(i2);\
o2= (i1)-(i2);

#define BUTTERFLY1(x,y) \
{\
    int a,b;\
    a= x;\
    b= y;\
    x= a+b;\
    y= a-b;\
}

#define BUTTERFLYA(x,y) (FFABS((x)+(y)) + FFABS((x)-(y)))

int hadamard8_diff8x8_c(void *s, uint8_t *dst, uint8_t *src, int stride, int h)
{
    int i;
    int temp[64];
    int sum=0;

    for(i=0; i<8; i++){
        //FIXME try pointer walks
        BUTTERFLY2(temp[8*i+0], temp[8*i+1], src[stride*i+0]-dst[stride*i+0],src[stride*i+1]-dst[stride*i+1]);
        BUTTERFLY2(temp[8*i+2], temp[8*i+3], src[stride*i+2]-dst[stride*i+2],src[stride*i+3]-dst[stride*i+3]);
        BUTTERFLY2(temp[8*i+4], temp[8*i+5], src[stride*i+4]-dst[stride*i+4],src[stride*i+5]-dst[stride*i+5]);
        BUTTERFLY2(temp[8*i+6], temp[8*i+7], src[stride*i+6]-dst[stride*i+6],src[stride*i+7]-dst[stride*i+7]);

        BUTTERFLY1(temp[8*i+0], temp[8*i+2]);
        BUTTERFLY1(temp[8*i+1], temp[8*i+3]);
        BUTTERFLY1(temp[8*i+4], temp[8*i+6]);
        BUTTERFLY1(temp[8*i+5], temp[8*i+7]);

        BUTTERFLY1(temp[8*i+0], temp[8*i+4]);
        BUTTERFLY1(temp[8*i+1], temp[8*i+5]);
        BUTTERFLY1(temp[8*i+2], temp[8*i+6]);
        BUTTERFLY1(temp[8*i+3], temp[8*i+7]);
    }

    for(i=0; i<8; i++){
        BUTTERFLY1(temp[8*0+i], temp[8*1+i]);
        BUTTERFLY1(temp[8*2+i], temp[8*3+i]);
        BUTTERFLY1(temp[8*4+i], temp[8*5+i]);
        BUTTERFLY1(temp[8*6+i], temp[8*7+i]);

        BUTTERFLY1(temp[8*0+i], temp[8*2+i]);
        BUTTERFLY1(temp[8*1+i], temp[8*3+i]);
        BUTTERFLY1(temp[8*4+i], temp[8*6+i]);
        BUTTERFLY1(temp[8*5+i], temp[8*7+i]);

        sum +=
             BUTTERFLYA(temp[8*0+i], temp[8*4+i])
            +BUTTERFLYA(temp[8*1+i], temp[8*5+i])
            +BUTTERFLYA(temp[8*2+i], temp[8*6+i])
            +BUTTERFLYA(temp[8*3+i], temp[8*7+i]);
    }
    return sum;
}

(In reply to comment #0)

> sub_hfyu_median_prediction.c:18: note: not vectorized: unhandled data-ref 
> 
> Looking with GDB at it, I get:
> (gdb) p debug_data_references (datarefs)
> (Data Ref: 
>   stmt: D.2736_16 = *D.2735_15;
>   ref: *D.2735_15;
>   base_object: *src1_14(D);
>   Access function 0: {0B, +, 1}_1
> )
> (Data Ref: 
>   stmt: 
>   ref: 
>   base_object: 
> )
> 
> I think it is the dst data ref that is NULL.  Might be an aliasing
> problem for the data dep analysis, but still, the data ref should be
> analyzed correctly first.

Data refs analysis fails because of the function call in the loop.

The vectorizer should check the return value of compute_data_dependences_for_loop() and print some better error message though.

(In reply to comment #1)

> hadamard8_diff.c:44: note: not vectorized: unhandled data-ref 

There is a function call in this loop as well.

> hadamard8_diff.c:26: note: not vectorized: data ref analysis failed D.2771_12 =
> *D.2770_11;

Scalar evolution analysis fails here with:
failed: evolution of base is not affine.

  D.2768_8 = i_361 * stride_7(D);
  D.2769_9 = (long unsigned int) D.2768_8;
  D.2770_11 = src_10(D) + D.2769_9;
  D.2771_12 = *D.2770_11;

stride is function parameter.

What about fixing the diagnostic message like this:

diff --git a/gcc/tree-vect-data-refs.c b/gcc/tree-vect-data-refs.c
index 37ae9b5..44248b3 100644
--- a/gcc/tree-vect-data-refs.c
+++ b/gcc/tree-vect-data-refs.c
@@ -1866,10 +1866,21 @@ vect_analyze_data_refs (loop_vec_info loop_vinfo, bb_vec_info bb_vinfo)
 
   if (loop_vinfo)
     {
+      bool res;
+
       loop = LOOP_VINFO_LOOP (loop_vinfo);
-      compute_data_dependences_for_loop (loop, true,
-                                         &LOOP_VINFO_DATAREFS (loop_vinfo),
-                                         &LOOP_VINFO_DDRS (loop_vinfo));
+      res = compute_data_dependences_for_loop
+	(loop, true, &LOOP_VINFO_DATAREFS (loop_vinfo),
+	 &LOOP_VINFO_DDRS (loop_vinfo));
+
+      if (!res)
+        {
+          if (vect_print_dump_info (REPORT_UNVECTORIZED_LOCATIONS))
+	    fprintf (vect_dump, "not vectorized: loop contains function calls"
+		     " or data references that cannot be analyzed");
+          return false;
+        }
+
       datarefs = LOOP_VINFO_DATAREFS (loop_vinfo);
     }
   else

When defining the missing function like this:

static inline int mid_pred(int a, int b, int c)
{
    int t= (a-b)&((a-b)>>31);
    a-=t;
    b+=t;
    b-= (b-c)&((b-c)>>31);
    b+= (a-b)&((a-b)>>31);

    return b;
}

The vectorization reports: "not vectorized: unsupported use in stmt."

When this function is defined like this:
static inline int mid_pred(int a, int b, int c)
{
  if(a>b){
    if(c>b){
      if(c>a) b=a;
      else    b=c;
    }
  }else{
    if(b>c){
      if(c>a) b=c;
      else    b=a;
    }
  }
  return b;
}

the vectorizer stops with: "not vectorized: control flow in loop."

(In reply to comment #4)
> What about fixing the diagnostic message like this:
> 

It would be nice to do the same for SLP (compute_data_dependences_for_bb) for completeness.

Thanks,
Ira

> diff --git a/gcc/tree-vect-data-refs.c b/gcc/tree-vect-data-refs.c
> index 37ae9b5..44248b3 100644
> --- a/gcc/tree-vect-data-refs.c
> +++ b/gcc/tree-vect-data-refs.c
> @@ -1866,10 +1866,21 @@ vect_analyze_data_refs (loop_vec_info loop_vinfo,
> bb_vec_info bb_vinfo)
> 
>    if (loop_vinfo)
>      {
> +      bool res;
> +
>        loop = LOOP_VINFO_LOOP (loop_vinfo);
> -      compute_data_dependences_for_loop (loop, true,
> -                                         &LOOP_VINFO_DATAREFS (loop_vinfo),
> -                                         &LOOP_VINFO_DDRS (loop_vinfo));
> +      res = compute_data_dependences_for_loop
> +       (loop, true, &LOOP_VINFO_DATAREFS (loop_vinfo),
> +        &LOOP_VINFO_DDRS (loop_vinfo));
> +
> +      if (!res)
> +        {
> +          if (vect_print_dump_info (REPORT_UNVECTORIZED_LOCATIONS))
> +           fprintf (vect_dump, "not vectorized: loop contains function calls"
> +                    " or data references that cannot be analyzed");
> +          return false;
> +        }
> +
>        datarefs = LOOP_VINFO_DATAREFS (loop_vinfo);
>      }
>    else
> 

(In reply to comment #5)
> When defining the missing function like this:
> 
> static inline int mid_pred(int a, int b, int c)
> {
>     int t= (a-b)&((a-b)>>31);
>     a-=t;
>     b+=t;
>     b-= (b-c)&((b-c)>>31);
>     b+= (a-b)&((a-b)>>31);
> 
>     return b;
> }
> 
> The vectorization reports: "not vectorized: unsupported use in stmt."

Yes, we have an unsupported cycles for l and lt, since they don't match regular reduction pattern.

> 
> When this function is defined like this:
> static inline int mid_pred(int a, int b, int c)
> {
>   if(a>b){
>     if(c>b){
>       if(c>a) b=a;
>       else    b=c;
>     }
>   }else{
>     if(b>c){
>       if(c>a) b=c;
>       else    b=a;
>     }
>   }
>   return b;
> }
> 
> the vectorizer stops with: "not vectorized: control flow in loop."
> 
 
if-conversion fails with 
l_34 = *D.2750_33;
tree could trap...

Subject: Bug 43436

Author: spop
Date: Mon Mar 29 16:38:34 2010
New Revision: 157800

URL: http://gcc.gnu.org/viewcvs?root=gcc&view=rev&rev=157800
Log:
Improve vectorization diagnostic: loop contains function calls.

2010-03-29  Sebastian Pop  <sebastian.pop@amd.com>

	PR middle-end/43436
	* tree-vect-data-refs.c (vect_analyze_data_refs): When
	compute_data_dependences_for_loop returns false, early exit
	and output an extra diagnostic for the failed data reference
	analysis.

Modified:
    trunk/gcc/ChangeLog
    trunk/gcc/tree-vect-data-refs.c