------- Comment #4 from changpeng dot fang at amd dot com 2010-07-28 18:22
-------
Andrew's example is exactly what the prefetch sees for the test case (in the
bug description). Unfortunately, the prefetch pass could not recognize that
vect_pa.6_24 and vect_pa.20_38 are exactly the same address:
<bb 2>:
pretmp.2_18 = (float) beta_4(D);
vect_pa.9_22 = (vector(4) float *) &a;
vect_pa.6_23 = vect_pa.9_22;
vect_cst_.12_27 = {pretmp.2_18, pretmp.2_18, pretmp.2_18, pretmp.2_18};
vect_pb.16_29 = (vector(4) float *) &b;
vect_pb.13_30 = vect_pb.16_29;
vect_pa.23_36 = (vector(4) float *) &a;
vect_pa.20_37 = vect_pa.23_36;
<bb 3>:
# vect_pa.6_24 = PHI <vect_pa.6_25(4), vect_pa.6_23(2)>
# vect_pb.13_31 = PHI <vect_pb.13_32(4), vect_pb.13_30(2)>
# vect_pa.20_38 = PHI <vect_pa.20_39(4), vect_pa.20_37(2)>
# ivtmp.24_40 = PHI <ivtmp.24_41(4), 0(2)>
vect_var_.10_26 = *vect_pa.6_24;
vect_var_.11_28 = vect_cst_.12_27;
vect_var_.17_33 = *vect_pb.13_31;
vect_var_.18_34 = vect_var_.11_28 * vect_var_.17_33;
vect_var_.19_35 = vect_var_.10_26 + vect_var_.18_34;
*vect_pa.20_38 = vect_var_.19_35;
vect_pa.6_25 = vect_pa.6_24 + 16;
vect_pb.13_32 = vect_pb.13_31 + 16;
vect_pa.20_39 = vect_pa.20_38 + 16;
ivtmp.24_41 = ivtmp.24_40 + 1;
if (ivtmp.24_41 < 256)
goto <bb 4>;
else
goto <bb 5>;
<bb 4>:
goto <bb 3>;
--
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=45021
