gcc 4.0.0 generates slower code than gcc 3.4.3 for the BLAS "axpy" operation.
(This is no doubt specific to IA32, and perhaps also to the processor version.)
The program is below, here are the timing results:

                   gcc 3.4.3    gcc 4.0.0
Method              cpu secs     cpu secs
z[]=x[]+alpha*y[]     1.45         1.72
z[]=z[]+alpha*y[]     1.47         2.03
z[]=z[]+y[]           1.44         1.57
                                                                                
The second method is a common special case of the first,
so it is unfortunate that gcc 4 does poorly on it.

========
The program is in two files to defeat inlining: rzvaxpy.c and zvaxpy.c
and here is the script I used to compile/run them:

for m in METH1 METH2 METH3
do
   for cc in gcc343 gcc400
   do
      $cc -march=i686 -O3 -D$m rzvaxpy.c zvaxpy.c
      echo $cc $m `(time a.out)2>&1`
   done
done

==== zvaxpy.c

void
zvaxpy(double *z, double *x, double *y, int n, double alpha)
{
   int i;
                                                                                
#if defined(METH1)
   for (i = 0; i < n; i++) z[i] = x[i] + alpha * y[i];
#elif defined(METH2)
   for (i = 0; i < n; i++) z[i] = z[i] + alpha * y[i];
#else
   for (i = 0; i < n; i++) z[i] = z[i] +  y[i];
#endif
}

==== rzvaxpy.c

#include <stdio.h>
                                                                                
#define N 100
#define NITER ((300*1000*1000)/N)
double a[100], b[100];
                                                                                
extern void zvaxpy(double *, double *, double *, int, double);
                                                                                
int
main()
{
   int i;
   double sum;
   for (i = 0; i < 100; i++) { a[i] = 0; b[i] = 1; }
   for (i = 0; i < NITER; i++) zvaxpy(a,a, b, N, 1.1);
   sum = 0; for (i = 0; i < N; i++) sum += a[i];
   printf("sum %g\n", sum);
   return 0;
}