Hi, v1: https://gcc.gnu.org/pipermail/gcc-patches/2021-May/569790.html
This is the updated version with one new parameter costing_for_scalar passed by init_cost hook, instead of checking the passed data point identity. Bootstrapped/regtested on powerpc64le-linux-gnu P9. Is it ok for trunk? BR, Kewen ----- gcc/ChangeLog: * config/rs6000/rs6000.c (struct rs6000_cost_data): New member costing_for_scalar. (rs6000_density_test): Early return if costing_for_scalar is true. (rs6000_init_cost): Init costing_for_scalar of rs6000_cost_data.
--- gcc/config/rs6000/rs6000.c | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/gcc/config/rs6000/rs6000.c b/gcc/config/rs6000/rs6000.c index 88f16b909a3..4981597a10e 100644 --- a/gcc/config/rs6000/rs6000.c +++ b/gcc/config/rs6000/rs6000.c @@ -5234,6 +5234,8 @@ typedef struct _rs6000_cost_data /* For each vectorized loop, this var holds TRUE iff a non-memory vector instruction is needed by the vectorization. */ bool vect_nonmem; + /* Indicates costing for the scalar version of a loop or block. */ + bool costing_for_scalar; } rs6000_cost_data; /* Test for likely overcommitment of vector hardware resources. If a @@ -5255,6 +5257,12 @@ rs6000_density_test (rs6000_cost_data *data) int vec_cost = data->cost[vect_body], not_vec_cost = 0; int i, density_pct; + /* This density test only cares about the cost of vector version of the + loop, early return if it's costing for the scalar version (namely + computing single scalar iteration cost). */ + if (data->costing_for_scalar) + return; + for (i = 0; i < nbbs; i++) { basic_block bb = bbs[i]; @@ -5292,7 +5300,7 @@ rs6000_density_test (rs6000_cost_data *data) /* Implement targetm.vectorize.init_cost. */ static void * -rs6000_init_cost (struct loop *loop_info, bool) +rs6000_init_cost (struct loop *loop_info, bool costing_for_scalar) { rs6000_cost_data *data = XNEW (struct _rs6000_cost_data); data->loop_info = loop_info; @@ -5300,6 +5308,7 @@ rs6000_init_cost (struct loop *loop_info, bool) data->cost[vect_body] = 0; data->cost[vect_epilogue] = 0; data->vect_nonmem = false; + data->costing_for_scalar = costing_for_scalar; return data; } -- 2.17.1