This is a v2 of:
https://gcc.gnu.org/pipermail/gcc-patches/2024-August/659969.html
this version just streams the flag as requested.
Bootstrapped/tested as a series on aarch64-linux-gnu (both with and
without LTO), OK for trunk?
Thanks,
Alex
-- >8 --
When #pragma GCC unroll is processed in
tree-cfg.cc:replace_loop_annotate_in_block, we set both the loop->unroll
field (which is currently streamed during LTO) but also the
cfun->has_unroll flag.
cfun->has_unroll, however, is not currently streamed during LTO. This
patch fixes that.
Prior to this patch, loops marked with #pragma GCC unroll that would be
unrolled by RTL loop2_unroll in a non-LTO compilation didn't get
unrolled under LTO.
gcc/ChangeLog:
PR libstdc++/116140
* lto-streamer-in.cc (input_struct_function_base): Stream in
fn->has_unroll.
* lto-streamer-out.cc (output_struct_function_base): Stream out
fn->has_unroll.
gcc/testsuite/ChangeLog:
PR libstdc++/116140
* g++.dg/ext/pragma-unroll-lambda-lto.C: New test.
---
gcc/lto-streamer-in.cc | 1 +
gcc/lto-streamer-out.cc | 1 +
.../g++.dg/ext/pragma-unroll-lambda-lto.C | 32 +++++++++++++++++++
3 files changed, 34 insertions(+)
create mode 100644 gcc/testsuite/g++.dg/ext/pragma-unroll-lambda-lto.C
diff --git a/gcc/lto-streamer-in.cc b/gcc/lto-streamer-in.cc
index 64f75807328..9d0ec5d589c 100644
--- a/gcc/lto-streamer-in.cc
+++ b/gcc/lto-streamer-in.cc
@@ -1326,6 +1326,7 @@ input_struct_function_base (struct function *fn, class data_in *data_in,
fn->has_force_vectorize_loops = bp_unpack_value (&bp, 1);
fn->has_simduid_loops = bp_unpack_value (&bp, 1);
fn->has_musttail = bp_unpack_value (&bp, 1);
+ fn->has_unroll = bp_unpack_value (&bp, 1);
fn->assume_function = bp_unpack_value (&bp, 1);
fn->va_list_fpr_size = bp_unpack_value (&bp, 8);
fn->va_list_gpr_size = bp_unpack_value (&bp, 8);
diff --git a/gcc/lto-streamer-out.cc b/gcc/lto-streamer-out.cc
index 523d6dad221..52d0d737330 100644
--- a/gcc/lto-streamer-out.cc
+++ b/gcc/lto-streamer-out.cc
@@ -2283,6 +2283,7 @@ output_struct_function_base (struct output_block *ob, struct function *fn)
bp_pack_value (&bp, fn->has_force_vectorize_loops, 1);
bp_pack_value (&bp, fn->has_simduid_loops, 1);
bp_pack_value (&bp, fn->has_musttail, 1);
+ bp_pack_value (&bp, fn->has_unroll, 1);
bp_pack_value (&bp, fn->assume_function, 1);
bp_pack_value (&bp, fn->va_list_fpr_size, 8);
bp_pack_value (&bp, fn->va_list_gpr_size, 8);
diff --git a/gcc/testsuite/g++.dg/ext/pragma-unroll-lambda-lto.C b/gcc/testsuite/g++.dg/ext/pragma-unroll-lambda-lto.C
new file mode 100644
index 00000000000..144c4c32692
--- /dev/null
+++ b/gcc/testsuite/g++.dg/ext/pragma-unroll-lambda-lto.C
@@ -0,0 +1,32 @@
+// { dg-do link { target c++11 } }
+// { dg-options "-O2 -flto -fdump-rtl-loop2_unroll" }
+
+#include <cstdlib>
+
+template<typename Iter, typename Pred>
+inline Iter
+my_find(Iter first, Iter last, Pred pred)
+{
+#pragma GCC unroll 4
+ while (first != last && !pred(*first))
+ ++first;
+ return first;
+}
+
+__attribute__((noipa))
+short *use_find(short *p)
+{
+ auto pred = [](short x) { return x == 42; };
+ return my_find(p, p + 1024, pred);
+}
+
+int main(void)
+{
+ short a[1024];
+ for (int i = 0; i < 1024; i++)
+ a[i] = rand ();
+
+ return use_find (a) - a;
+}
+
+// { dg-final { scan-ltrans-rtl-dump-times "Unrolled loop 3 times" 1 "loop2_unroll" } }
