I brought this subject up earlier, and was told to suggest it again for gcc 9,
so I have attached the preliminary changes.
My studies have show that with generic x86-64 optimization it reduces binary
size with around 0.5%, and when optimizing for x64 targets with SSE4 or
better, it reduces binary size by 2-3% on average. The performance changes are
negligible however*, and I haven't been able to detect changes in compile time
big enough to penetrate general noise on my platform, but perhaps someone has
a better setup for that?
* I believe that is because it currently works best on non-optimized code, it
is better at big basic blocks doing all kinds of things than tightly written
inner loops.
Anythhing else I should test or report?
Best regards
'Allan
diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
index beba295bef5..05851229354 100644
--- a/gcc/doc/invoke.texi
+++ b/gcc/doc/invoke.texi
@@ -7612,6 +7612,7 @@ also turns on the following optimization flags:
-fstore-merging @gol
-fstrict-aliasing @gol
-ftree-builtin-call-dce @gol
+-ftree-slp-vectorize @gol
-ftree-switch-conversion -ftree-tail-merge @gol
-fcode-hoisting @gol
-ftree-pre @gol
@@ -7635,7 +7636,6 @@ by @option{-O2} and also turns on the following
optimization flags:
-floop-interchange @gol
-floop-unroll-and-jam @gol
-fsplit-paths @gol
--ftree-slp-vectorize @gol
-fvect-cost-model @gol
-ftree-partial-pre @gol
-fpeel-loops @gol
@@ -8932,7 +8932,7 @@ Perform loop vectorization on trees. This flag is
enabled by default at
@item -ftree-slp-vectorize
@opindex ftree-slp-vectorize
Perform basic block vectorization on trees. This flag is enabled by default
at
-@option{-O3} and when @option{-ftree-vectorize} is enabled.
+@option{-O2} or higher, and when @option{-ftree-vectorize} is enabled.
@item -fvect-cost-model=@var{model}
@opindex fvect-cost-model
diff --git a/gcc/opts.c b/gcc/opts.c
index 33efcc0d6e7..11027b847e8 100644
--- a/gcc/opts.c
+++ b/gcc/opts.c
@@ -523,6 +523,7 @@ static const struct default_options
default_options_table[] =
{ OPT_LEVELS_2_PLUS, OPT_fipa_ra, NULL, 1 },
{ OPT_LEVELS_2_PLUS, OPT_flra_remat, NULL, 1 },
{ OPT_LEVELS_2_PLUS, OPT_fstore_merging, NULL, 1 },
+ { OPT_LEVELS_2_PLUS, OPT_ftree_slp_vectorize, NULL, 1 },
/* -O3 optimizations. */
{ OPT_LEVELS_3_PLUS, OPT_ftree_loop_distribute_patterns, NULL, 1 },
@@ -539,7 +540,6 @@ static const struct default_options
default_options_table[] =
{ OPT_LEVELS_3_PLUS, OPT_floop_unroll_and_jam, NULL, 1 },
{ OPT_LEVELS_3_PLUS, OPT_fgcse_after_reload, NULL, 1 },
{ OPT_LEVELS_3_PLUS, OPT_ftree_loop_vectorize, NULL, 1 },
- { OPT_LEVELS_3_PLUS, OPT_ftree_slp_vectorize, NULL, 1 },
{ OPT_LEVELS_3_PLUS, OPT_fvect_cost_model_, NULL, VECT_COST_MODEL_DYNAMIC
},
{ OPT_LEVELS_3_PLUS, OPT_fipa_cp_clone, NULL, 1 },
{ OPT_LEVELS_3_PLUS, OPT_ftree_partial_pre, NULL, 1 },
