| Message ID | 87wp50me3l.fsf@linaro.org |
|---|---|
| State | New |
| Headers | show |
| Series | Fix an SVE failure in the Fortran matmul* tests | expand |
On 09/15/2017 04:49 AM, Richard Sandiford wrote: > The vectoriser was calling vect_get_smallest_scalar_type without > having proven that the type actually is a scalar. This seems to > be the intended behaviour: the ultimate test of whether the type > is interesting (and hence scalar) is whether an associated vector > type exists, but this is only tested later. > > The patch simply makes the function cope gracefully with non-scalar > inputs. > > Tested on aarch64-linux-gnu, x86_64-linux-gnu and powerpc64le-linux-gnu. > OK to install? > > Richard > > > 2017-09-15 Richard Sandiford <richard.sandiford@linaro.org> > Alan Hayward <alan.hayward@arm.com> > David Sherwood <david.sherwood@arm.com> > > gcc/ > * tree-vect-data-refs.c (vect_get_smallest_scalar_type): Cope > with types that aren't in fact scalar. OK. jeff
Index: gcc/tree-vect-data-refs.c =================================================================== --- gcc/tree-vect-data-refs.c 2017-09-14 17:35:26.634355297 +0100 +++ gcc/tree-vect-data-refs.c 2017-09-15 11:41:22.764283196 +0100 @@ -118,6 +118,11 @@ vect_get_smallest_scalar_type (gimple *s tree scalar_type = gimple_expr_type (stmt); HOST_WIDE_INT lhs, rhs; + /* During the analysis phase, this function is called on arbitrary + statements that might not have scalar results. */ + if (!tree_fits_uhwi_p (TYPE_SIZE_UNIT (scalar_type))) + return scalar_type; + lhs = rhs = TREE_INT_CST_LOW (TYPE_SIZE_UNIT (scalar_type)); if (is_gimple_assign (stmt)