cfgexpand sorts variables by decreasing size, so when merging a later
variable into an earlier one, there's usually no need to update the
merged size.

But for poly_int sizes, the sort function just uses a lexicographical
comparison of the coefficients, so e.g. 2X+2 comes before 0X+32.
Which is bigger depends on the runtime value of X.

This patch therefore takes the upper bound of the two sizes, which
is conservatively correct for variable-length vectors and a no-op
on other targets.

It's probably a bad idea to merge fixed-length and variable-length
variables in practice, but that's really an optimisation decision.
I think we should have this patch as a correctness fix either way.

This is easiest to test using the ACLE, but in principle it could happen
for autovectorised code too, e.g. when using OpenMP vector variables.
It's therefore a regression from GCC 8.

2020-01-22  Richard Sandiford  <richard.sandiford@arm.com>

gcc/
	* cfgexpand.c (union_stack_vars): Update the size.

gcc/testsuite/
	* gcc.target/aarch64/sve/acle/general/stack_vars_1.c: New test.