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 out and back in during LTO) but also
the cfun->has_unroll flag.
cfun->has_unroll, however, is not currently streamed during LTO, so this
patch attempts to recover it by setting it on any function containing a
loop with loop->unroll > 1.
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.
As per the comment in the PR, a more conservative fix might explicitly
stream out cfun->has_unroll and stream it back in again, but this patch
it simpler and I can't currently see a reason against inferring the
value of the flag like this (comments welcome).
gcc/ChangeLog:
PR libstdc++/116140
* lto-streamer-in.cc (input_cfg): Set fn->has_unroll if fn
contains a loop with requested unrolling.
gcc/testsuite/ChangeLog:
PR libstdc++/116140
* g++.dg/ext/pragma-unroll-lambda-lto.C: New test.
---
gcc/lto-streamer-in.cc | 2 ++
.../g++.dg/ext/pragma-unroll-lambda-lto.C | 32 +++++++++++++++++++
2 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 2e592be8082..93877065d86 100644
--- a/gcc/lto-streamer-in.cc
+++ b/gcc/lto-streamer-in.cc
@@ -1136,6 +1136,8 @@ input_cfg (class lto_input_block *ib, class data_in *data_in,
/* Read OMP SIMD related info. */
loop->safelen = streamer_read_hwi (ib);
loop->unroll = streamer_read_hwi (ib);
+ if (loop->unroll > 1)
+ fn->has_unroll = true;
loop->owned_clique = streamer_read_hwi (ib);
loop->dont_vectorize = streamer_read_hwi (ib);
loop->force_vectorize = streamer_read_hwi (ib);
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" } }
