From: Richard Sandiford Date: Wed, 13 Nov 2019 09:12:17 +0000 (+0000) Subject: Account for the cost of generating loop masks X-Git-Url: https://git.libre-soc.org/?a=commitdiff_plain;h=61e5f2df0345bcc1f7675125922692d727e20603;p=gcc.git Account for the cost of generating loop masks We didn't take the cost of generating loop masks into account, and so tended to underestimate the cost of loops that need multiple masks. 2019-11-13 Richard Sandiford gcc/ * tree-vect-loop.c (vect_estimate_min_profitable_iters): Include the cost of generating loop masks. gcc/testsuite/ * gcc.target/aarch64/sve/mask_struct_store_3.c: Add -fno-vect-cost-model. * gcc.target/aarch64/sve/mask_struct_store_3_run.c: Likewise. * gcc.target/aarch64/sve/peel_ind_2.c: Likewise. * gcc.target/aarch64/sve/peel_ind_2_run.c: Likewise. * gcc.target/aarch64/sve/peel_ind_3.c: Likewise. * gcc.target/aarch64/sve/peel_ind_3_run.c: Likewise. From-SVN: r278125 --- diff --git a/gcc/ChangeLog b/gcc/ChangeLog index e7b04334fb5..047052835f0 100644 --- a/gcc/ChangeLog +++ b/gcc/ChangeLog @@ -1,3 +1,8 @@ +2019-11-13 Richard Sandiford + + * tree-vect-loop.c (vect_estimate_min_profitable_iters): Include + the cost of generating loop masks. + 2019-11-13 Richard Sandiford * tree-vectorizer.h (vect_apply_runtime_profitability_check_p): diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog index a253a5397cc..834c17a6d7f 100644 --- a/gcc/testsuite/ChangeLog +++ b/gcc/testsuite/ChangeLog @@ -1,3 +1,13 @@ +2019-11-13 Richard Sandiford + + * gcc.target/aarch64/sve/mask_struct_store_3.c: Add + -fno-vect-cost-model. + * gcc.target/aarch64/sve/mask_struct_store_3_run.c: Likewise. + * gcc.target/aarch64/sve/peel_ind_2.c: Likewise. + * gcc.target/aarch64/sve/peel_ind_2_run.c: Likewise. + * gcc.target/aarch64/sve/peel_ind_3.c: Likewise. + * gcc.target/aarch64/sve/peel_ind_3_run.c: Likewise. + 2019-11-13 Richard Sandiford PR c++/92206 diff --git a/gcc/testsuite/gcc.target/aarch64/sve/mask_struct_store_3.c b/gcc/testsuite/gcc.target/aarch64/sve/mask_struct_store_3.c index 001f5be8ff5..1765d54a483 100644 --- a/gcc/testsuite/gcc.target/aarch64/sve/mask_struct_store_3.c +++ b/gcc/testsuite/gcc.target/aarch64/sve/mask_struct_store_3.c @@ -1,5 +1,5 @@ /* { dg-do compile } */ -/* { dg-options "-O2 -ftree-vectorize -ffast-math" } */ +/* { dg-options "-O2 -ftree-vectorize -ffast-math -fno-vect-cost-model" } */ #include diff --git a/gcc/testsuite/gcc.target/aarch64/sve/mask_struct_store_3_run.c b/gcc/testsuite/gcc.target/aarch64/sve/mask_struct_store_3_run.c index 31d661b6594..4dbe0335c72 100644 --- a/gcc/testsuite/gcc.target/aarch64/sve/mask_struct_store_3_run.c +++ b/gcc/testsuite/gcc.target/aarch64/sve/mask_struct_store_3_run.c @@ -1,5 +1,5 @@ /* { dg-do run { target aarch64_sve_hw } } */ -/* { dg-options "-O2 -ftree-vectorize -ffast-math" } */ +/* { dg-options "-O2 -ftree-vectorize -ffast-math -fno-vect-cost-model" } */ #include "mask_struct_store_3.c" diff --git a/gcc/testsuite/gcc.target/aarch64/sve/peel_ind_2.c b/gcc/testsuite/gcc.target/aarch64/sve/peel_ind_2.c index e792cdf2cad..df82d58ea77 100644 --- a/gcc/testsuite/gcc.target/aarch64/sve/peel_ind_2.c +++ b/gcc/testsuite/gcc.target/aarch64/sve/peel_ind_2.c @@ -1,7 +1,7 @@ /* { dg-do compile } */ /* Pick an arbitrary target for which unaligned accesses are more expensive. */ -/* { dg-options "-O3 -msve-vector-bits=256 -mtune=thunderx" } */ +/* { dg-options "-O3 -msve-vector-bits=256 -mtune=thunderx -fno-vect-cost-model" } */ #define N 512 #define START 7 diff --git a/gcc/testsuite/gcc.target/aarch64/sve/peel_ind_2_run.c b/gcc/testsuite/gcc.target/aarch64/sve/peel_ind_2_run.c index 9c5ae1bd068..b9785356d18 100644 --- a/gcc/testsuite/gcc.target/aarch64/sve/peel_ind_2_run.c +++ b/gcc/testsuite/gcc.target/aarch64/sve/peel_ind_2_run.c @@ -1,6 +1,6 @@ /* { dg-do run { target aarch64_sve_hw } } */ /* { dg-options "-O3 -mtune=thunderx" } */ -/* { dg-options "-O3 -mtune=thunderx -msve-vector-bits=256" { target aarch64_sve256_hw } } */ +/* { dg-options "-O3 -mtune=thunderx -msve-vector-bits=256 -fno-vect-cost-model" { target aarch64_sve256_hw } } */ #include "peel_ind_2.c" diff --git a/gcc/testsuite/gcc.target/aarch64/sve/peel_ind_3.c b/gcc/testsuite/gcc.target/aarch64/sve/peel_ind_3.c index 441589eef60..1707f02fe92 100644 --- a/gcc/testsuite/gcc.target/aarch64/sve/peel_ind_3.c +++ b/gcc/testsuite/gcc.target/aarch64/sve/peel_ind_3.c @@ -1,7 +1,7 @@ /* { dg-do compile } */ /* Pick an arbitrary target for which unaligned accesses are more expensive. */ -/* { dg-options "-O3 -msve-vector-bits=256 -mtune=thunderx" } */ +/* { dg-options "-O3 -msve-vector-bits=256 -mtune=thunderx -fno-vect-cost-model" } */ #define N 32 #define MAX_START 8 diff --git a/gcc/testsuite/gcc.target/aarch64/sve/peel_ind_3_run.c b/gcc/testsuite/gcc.target/aarch64/sve/peel_ind_3_run.c index 384a38eb8ec..98389675d79 100644 --- a/gcc/testsuite/gcc.target/aarch64/sve/peel_ind_3_run.c +++ b/gcc/testsuite/gcc.target/aarch64/sve/peel_ind_3_run.c @@ -1,6 +1,6 @@ /* { dg-do run { target aarch64_sve_hw } } */ -/* { dg-options "-O3 -mtune=thunderx" } */ -/* { dg-options "-O3 -mtune=thunderx -msve-vector-bits=256" { target aarch64_sve256_hw } } */ +/* { dg-options "-O3 -mtune=thunderx -fno-vect-cost-model" } */ +/* { dg-options "-O3 -mtune=thunderx -msve-vector-bits=256 -fno-vect-cost-model" { target aarch64_sve256_hw } } */ #include "peel_ind_3.c" diff --git a/gcc/tree-vect-loop.c b/gcc/tree-vect-loop.c index 83fb8486640..005fa308911 100644 --- a/gcc/tree-vect-loop.c +++ b/gcc/tree-vect-loop.c @@ -3291,6 +3291,32 @@ vect_estimate_min_profitable_iters (loop_vec_info loop_vinfo, si->kind, si->stmt_info, si->misalign, vect_epilogue); } + + /* Calculate how many masks we need to generate. */ + unsigned int num_masks = 0; + rgroup_masks *rgm; + unsigned int num_vectors_m1; + FOR_EACH_VEC_ELT (LOOP_VINFO_MASKS (loop_vinfo), num_vectors_m1, rgm) + if (rgm->mask_type) + num_masks += num_vectors_m1 + 1; + gcc_assert (num_masks > 0); + + /* In the worst case, we need to generate each mask in the prologue + and in the loop body. One of the loop body mask instructions + replaces the comparison in the scalar loop, and since we don't + count the scalar comparison against the scalar body, we shouldn't + count that vector instruction against the vector body either. + + Sometimes we can use unpacks instead of generating prologue + masks and sometimes the prologue mask will fold to a constant, + so the actual prologue cost might be smaller. However, it's + simpler and safer to use the worst-case cost; if this ends up + being the tie-breaker between vectorizing or not, then it's + probably better not to vectorize. */ + (void) add_stmt_cost (target_cost_data, num_masks, vector_stmt, + NULL, 0, vect_prologue); + (void) add_stmt_cost (target_cost_data, num_masks - 1, vector_stmt, + NULL, 0, vect_body); } else if (npeel < 0) {