From a31becca488b537cfc24bba7c0f48b2c44726240 Mon Sep 17 00:00:00 2001 From: Andrew Carlotti Date: Thu, 22 Dec 2022 02:09:51 +0000 Subject: Allow build_popcount_expr to use an IFN gcc/ChangeLog: * tree-ssa-loop-niter.cc (build_popcount_expr): Add IFN support. gcc/testsuite/ChangeLog: * g++.dg/tree-ssa/pr86544.C: Add .POPCOUNT to tree scan regex. * gcc.dg/tree-ssa/popcount.c: Likewise. * gcc.dg/tree-ssa/popcount2.c: Likewise. * gcc.dg/tree-ssa/popcount3.c: Likewise. * gcc.target/aarch64/popcount4.c: Likewise. * gcc.target/i386/pr95771.c: Likewise, and... * gcc.target/i386/pr95771-2.c: ...split int128 test from above, since this would emit just a single IFN if a TI optab is added. --- gcc/testsuite/g++.dg/tree-ssa/pr86544.C | 2 +- gcc/testsuite/gcc.dg/tree-ssa/popcount.c | 2 +- gcc/testsuite/gcc.dg/tree-ssa/popcount2.c | 2 +- gcc/testsuite/gcc.dg/tree-ssa/popcount3.c | 2 +- gcc/testsuite/gcc.target/aarch64/popcount4.c | 2 +- gcc/testsuite/gcc.target/i386/pr95771-2.c | 17 +++++++++++++++++ gcc/testsuite/gcc.target/i386/pr95771.c | 17 +---------------- gcc/tree-ssa-loop-niter.cc | 25 ++++++++++++++++++------- 8 files changed, 41 insertions(+), 28 deletions(-) create mode 100644 gcc/testsuite/gcc.target/i386/pr95771-2.c (limited to 'gcc') diff --git a/gcc/testsuite/g++.dg/tree-ssa/pr86544.C b/gcc/testsuite/g++.dg/tree-ssa/pr86544.C index ef43891..50befb3 100644 --- a/gcc/testsuite/g++.dg/tree-ssa/pr86544.C +++ b/gcc/testsuite/g++.dg/tree-ssa/pr86544.C @@ -12,5 +12,5 @@ int PopCount (long b) { return c; } -/* { dg-final { scan-tree-dump-times "__builtin_popcount" 1 "optimized" } } */ +/* { dg-final { scan-tree-dump-times "__builtin_popcount|\\.POPCOUNT" 1 "optimized" } } */ /* { dg-final { scan-tree-dump-times "if" 0 "phiopt4" } } */ diff --git a/gcc/testsuite/gcc.dg/tree-ssa/popcount.c b/gcc/testsuite/gcc.dg/tree-ssa/popcount.c index b469410..efd906a 100644 --- a/gcc/testsuite/gcc.dg/tree-ssa/popcount.c +++ b/gcc/testsuite/gcc.dg/tree-ssa/popcount.c @@ -39,4 +39,4 @@ void PopCount3 (long b1) { } } -/* { dg-final { scan-tree-dump-times "__builtin_popcount" 3 "optimized" } } */ +/* { dg-final { scan-tree-dump-times "__builtin_popcount|\\.POPCOUNT" 3 "optimized" } } */ diff --git a/gcc/testsuite/gcc.dg/tree-ssa/popcount2.c b/gcc/testsuite/gcc.dg/tree-ssa/popcount2.c index ef73e34..ae38a32 100644 --- a/gcc/testsuite/gcc.dg/tree-ssa/popcount2.c +++ b/gcc/testsuite/gcc.dg/tree-ssa/popcount2.c @@ -26,4 +26,4 @@ int main() return 0; } -/* { dg-final { scan-tree-dump-times "__builtin_popcount" 1 "optimized" } } */ +/* { dg-final { scan-tree-dump-times "__builtin_popcount|\\.POPCOUNT" 1 "optimized" } } */ diff --git a/gcc/testsuite/gcc.dg/tree-ssa/popcount3.c b/gcc/testsuite/gcc.dg/tree-ssa/popcount3.c index ef43891..50befb3 100644 --- a/gcc/testsuite/gcc.dg/tree-ssa/popcount3.c +++ b/gcc/testsuite/gcc.dg/tree-ssa/popcount3.c @@ -12,5 +12,5 @@ int PopCount (long b) { return c; } -/* { dg-final { scan-tree-dump-times "__builtin_popcount" 1 "optimized" } } */ +/* { dg-final { scan-tree-dump-times "__builtin_popcount|\\.POPCOUNT" 1 "optimized" } } */ /* { dg-final { scan-tree-dump-times "if" 0 "phiopt4" } } */ diff --git a/gcc/testsuite/gcc.target/aarch64/popcount4.c b/gcc/testsuite/gcc.target/aarch64/popcount4.c index ee55b2e..8aa15ff 100644 --- a/gcc/testsuite/gcc.target/aarch64/popcount4.c +++ b/gcc/testsuite/gcc.target/aarch64/popcount4.c @@ -11,4 +11,4 @@ int PopCount (long b) { return c; } -/* { dg-final { scan-tree-dump-times "__builtin_popcount" 0 "optimized" } } */ +/* { dg-final { scan-tree-dump-times "__builtin_popcount|\\.POPCOUNT" 0 "optimized" } } */ diff --git a/gcc/testsuite/gcc.target/i386/pr95771-2.c b/gcc/testsuite/gcc.target/i386/pr95771-2.c new file mode 100644 index 0000000..1db9dc9 --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/pr95771-2.c @@ -0,0 +1,17 @@ +/* PR tree-optimization/95771 */ +/* { dg-do compile } */ +/* { dg-require-effective-target int128 } */ +/* { dg-options "-O2 -mpopcnt -fdump-tree-optimized" } */ +/* { dg-final { scan-tree-dump " = __builtin_popcount| = \\.POPCOUNT" "optimized" } } */ + +int +corge (unsigned __int128 x) +{ + int i = 0; + while (x) + { + x &= x - 1; + ++i; + } + return i; +} diff --git a/gcc/testsuite/gcc.target/i386/pr95771.c b/gcc/testsuite/gcc.target/i386/pr95771.c index d7b67017..d41be44 100644 --- a/gcc/testsuite/gcc.target/i386/pr95771.c +++ b/gcc/testsuite/gcc.target/i386/pr95771.c @@ -1,8 +1,7 @@ /* PR tree-optimization/95771 */ /* { dg-do compile } */ /* { dg-options "-O2 -mpopcnt -fdump-tree-optimized" } */ -/* { dg-final { scan-tree-dump-times " = __builtin_popcount" 6 "optimized" { target int128 } } } */ -/* { dg-final { scan-tree-dump-times " = __builtin_popcount" 4 "optimized" { target { ! int128 } } } } */ +/* { dg-final { scan-tree-dump-times " = __builtin_popcount| = \\.POPCOUNT" 4 "optimized" } } */ int foo (unsigned char x) @@ -51,17 +50,3 @@ qux (unsigned long long x) } return i; } - -#ifdef __SIZEOF_INT128__ -int -corge (unsigned __int128 x) -{ - int i = 0; - while (x) - { - x &= x - 1; - ++i; - } - return i; -} -#endif diff --git a/gcc/tree-ssa-loop-niter.cc b/gcc/tree-ssa-loop-niter.cc index 26e39ad..65b9604 100644 --- a/gcc/tree-ssa-loop-niter.cc +++ b/gcc/tree-ssa-loop-niter.cc @@ -2033,11 +2033,18 @@ static tree build_popcount_expr (tree src) { tree fn; + bool use_ifn = false; int prec = TYPE_PRECISION (TREE_TYPE (src)); int i_prec = TYPE_PRECISION (integer_type_node); int li_prec = TYPE_PRECISION (long_integer_type_node); int lli_prec = TYPE_PRECISION (long_long_integer_type_node); - if (prec <= i_prec) + + tree utype = unsigned_type_for (TREE_TYPE (src)); + src = fold_convert (utype, src); + + if (direct_internal_fn_supported_p (IFN_POPCOUNT, utype, OPTIMIZE_FOR_BOTH)) + use_ifn = true; + else if (prec <= i_prec) fn = builtin_decl_implicit (BUILT_IN_POPCOUNT); else if (prec == li_prec) fn = builtin_decl_implicit (BUILT_IN_POPCOUNTL); @@ -2046,12 +2053,11 @@ build_popcount_expr (tree src) else return NULL_TREE; - tree utype = unsigned_type_for (TREE_TYPE (src)); - src = fold_convert (utype, src); - if (prec < i_prec) - src = fold_convert (unsigned_type_node, src); tree call; - if (prec == 2 * lli_prec) + if (use_ifn) + call = build_call_expr_internal_loc (UNKNOWN_LOCATION, IFN_POPCOUNT, + integer_type_node, 1, src); + else if (prec == 2 * lli_prec) { tree src1 = fold_convert (long_long_unsigned_type_node, fold_build2 (RSHIFT_EXPR, TREE_TYPE (src), @@ -2064,7 +2070,12 @@ build_popcount_expr (tree src) call = fold_build2 (PLUS_EXPR, integer_type_node, call1, call2); } else - call = build_call_expr (fn, 1, src); + { + if (prec < i_prec) + src = fold_convert (unsigned_type_node, src); + + call = build_call_expr (fn, 1, src); + } return call; } -- cgit v1.1