[gcc r12-249] [omp, simt] Fix expand_GOMP_SIMT_*

[gcc r12-249] [omp, simt] Fix expand_GOMP_SIMT_*

[Tom de Vries]

https://gcc.gnu.org/g:4d7c874e2c64ebf7631049ace642d246843febae

commit r12-249-g4d7c874e2c64ebf7631049ace642d246843febae
Author: Tom de Vries <tdevries@suse.de>
Date:   Wed Apr 28 16:00:01 2021 +0200

    [omp, simt] Fix expand_GOMP_SIMT_*
    
    When running the test-case included in this patch using an
    nvptx accelerator, it fails in execution.
    
    The problem is that the expansion of GOMP_SIMT_XCHG_BFLY is optimized away
    during pass_jump as "trivially dead insns".
    
    This is caused by this code in expand_GOMP_SIMT_XCHG_BFLY:
    ...
      class expand_operand ops[3];
      create_output_operand (&ops[0], target, mode);
      ...
      expand_insn (targetm.code_for_omp_simt_xchg_bfly, 3, ops);
    ...
    which doesn't guarantee that target is assigned to by the expanded insn.
    
    F.i., if target is:
    ...
    (gdb) call debug_rtx ( target )
    (subreg/s/u:QI (reg:SI 40 [ _61 ]) 0)
    ...
    then after expand_insn, we have:
    ...
    (gdb) call debug_rtx ( ops[0].value )
    (reg:QI 57)
    ...
    
    See commit 3af3bec2e4d "internal-fn: Avoid dropping the lhs of some
    calls [PR94941]" for a similar problem.
    
    Fix this in the same way, by adding:
    ...
      if (!rtx_equal_p (target, ops[0].value))
        emit_move_insn (target, ops[0].value);
    ...
    where applicable in the expand_GOMP_SIMT_* functions.
    
    Tested libgomp on x86_64 with nvptx accelerator.
    
    gcc/ChangeLog:
    
    2021-04-28  Tom de Vries  <tdevries@suse.de>
    
            PR target/100232
            * internal-fn.c (expand_GOMP_SIMT_ENTER_ALLOC)
            (expand_GOMP_SIMT_LAST_LANE, expand_GOMP_SIMT_ORDERED_PRED)
            (expand_GOMP_SIMT_VOTE_ANY, expand_GOMP_SIMT_XCHG_BFLY)
            (expand_GOMP_SIMT_XCHG_IDX): Ensure target is assigned to.

Diff:
---
 gcc/internal-fn.c                       | 12 ++++++++++++
 libgomp/testsuite/libgomp.c/target-43.c | 24 ++++++++++++++++++++++++
 2 files changed, 36 insertions(+)

diff --git a/gcc/internal-fn.c b/gcc/internal-fn.c
index dd7173126fb..d209a52f823 100644
--- a/gcc/internal-fn.c
+++ b/gcc/internal-fn.c
@@ -243,6 +243,8 @@ expand_GOMP_SIMT_ENTER_ALLOC (internal_fn, gcall *stmt)
   create_input_operand (&ops[2], align, Pmode);
   gcc_assert (targetm.have_omp_simt_enter ());
   expand_insn (targetm.code_for_omp_simt_enter, 3, ops);
+  if (!rtx_equal_p (target, ops[0].value))
+    emit_move_insn (target, ops[0].value);
 }
 
 /* Deallocate per-lane storage and leave non-uniform execution region.  */
@@ -300,6 +302,8 @@ expand_GOMP_SIMT_LAST_LANE (internal_fn, gcall *stmt)
   create_input_operand (&ops[1], cond, mode);
   gcc_assert (targetm.have_omp_simt_last_lane ());
   expand_insn (targetm.code_for_omp_simt_last_lane, 2, ops);
+  if (!rtx_equal_p (target, ops[0].value))
+    emit_move_insn (target, ops[0].value);
 }
 
 /* Non-transparent predicate used in SIMT lowering of OpenMP "ordered".  */
@@ -319,6 +323,8 @@ expand_GOMP_SIMT_ORDERED_PRED (internal_fn, gcall *stmt)
   create_input_operand (&ops[1], ctr, mode);
   gcc_assert (targetm.have_omp_simt_ordered ());
   expand_insn (targetm.code_for_omp_simt_ordered, 2, ops);
+  if (!rtx_equal_p (target, ops[0].value))
+    emit_move_insn (target, ops[0].value);
 }
 
 /* "Or" boolean reduction across SIMT lanes: return non-zero in all lanes if
@@ -339,6 +345,8 @@ expand_GOMP_SIMT_VOTE_ANY (internal_fn, gcall *stmt)
   create_input_operand (&ops[1], cond, mode);
   gcc_assert (targetm.have_omp_simt_vote_any ());
   expand_insn (targetm.code_for_omp_simt_vote_any, 2, ops);
+  if (!rtx_equal_p (target, ops[0].value))
+    emit_move_insn (target, ops[0].value);
 }
 
 /* Exchange between SIMT lanes with a "butterfly" pattern: source lane index
@@ -361,6 +369,8 @@ expand_GOMP_SIMT_XCHG_BFLY (internal_fn, gcall *stmt)
   create_input_operand (&ops[2], idx, SImode);
   gcc_assert (targetm.have_omp_simt_xchg_bfly ());
   expand_insn (targetm.code_for_omp_simt_xchg_bfly, 3, ops);
+  if (!rtx_equal_p (target, ops[0].value))
+    emit_move_insn (target, ops[0].value);
 }
 
 /* Exchange between SIMT lanes according to given source lane index.  */
@@ -382,6 +392,8 @@ expand_GOMP_SIMT_XCHG_IDX (internal_fn, gcall *stmt)
   create_input_operand (&ops[2], idx, SImode);
   gcc_assert (targetm.have_omp_simt_xchg_idx ());
   expand_insn (targetm.code_for_omp_simt_xchg_idx, 3, ops);
+  if (!rtx_equal_p (target, ops[0].value))
+    emit_move_insn (target, ops[0].value);
 }
 
 /* This should get expanded in adjust_simduid_builtins.  */
diff --git a/libgomp/testsuite/libgomp.c/target-43.c b/libgomp/testsuite/libgomp.c/target-43.c
new file mode 100644
index 00000000000..46b1cfc5b20
--- /dev/null
+++ b/libgomp/testsuite/libgomp.c/target-43.c
@@ -0,0 +1,24 @@
+/* { dg-do run } */
+#include <stdlib.h>
+
+#define N 32
+#define TYPE char
+
+int
+main (void)
+{
+  TYPE result = 1;
+  TYPE a[N];
+  for (int x = 0; x < N; ++x)
+    a[x] = 1;
+
+#pragma omp target map(tofrom: result) map(to:a)
+#pragma omp for simd reduction(&&:result)
+  for (int x = 0; x < N; ++x)
+    result = result && a[x];
+
+  if (result != 1)
+    abort ();
+
+  return 0;
+}