[gcn] Work-around libgomp 'error: array subscript 0 is outside array bounds of ‘__lds struct gomp_thread * __lds[0]’ [-Werror=array-bounds]' some more [PR101484]

With yesterday's commit 9f2bc5077debef2b046b6c10d38591ac324ad8b5 "[gcn]
Work-around libgomp 'error: array subscript 0 is outside array bounds of
‘__lds struct gomp_thread * __lds[0]’ [-Werror=array-bounds]' [PR101484]",
I did defuse the "unexpected" '-Werror=array-bounds' diagnostics that we see
as of commit a110855667782dac7b674d3e328b253b3b3c919b "Correct handling of
variable offset minus constant in -Warray-bounds [PR100137]".  However, these
'#pragma GCC diagnostic [...]' directives cause some code generation changes
(that seems unexpected, problematic!), which results in a lot (ten thousands)
of 'GCN team arena exhausted' run-time diagnostics, also leading to a few
FAILs:

    PASS: libgomp.c/../libgomp.c-c++-common/for-11.c (test for excess errors)
    [-PASS:-]{+FAIL:+} libgomp.c/../libgomp.c-c++-common/for-11.c execution test

    PASS: libgomp.c/../libgomp.c-c++-common/for-12.c (test for excess errors)
    [-PASS:-]{+FAIL:+} libgomp.c/../libgomp.c-c++-common/for-12.c execution test

    PASS: libgomp.c/../libgomp.c-c++-common/for-3.c (test for excess errors)
    [-PASS:-]{+FAIL:+} libgomp.c/../libgomp.c-c++-common/for-3.c execution test

    PASS: libgomp.c/../libgomp.c-c++-common/for-5.c (test for excess errors)
    [-PASS:-]{+FAIL:+} libgomp.c/../libgomp.c-c++-common/for-5.c execution test

    PASS: libgomp.c/../libgomp.c-c++-common/for-6.c (test for excess errors)
    [-PASS:-]{+FAIL:+} libgomp.c/../libgomp.c-c++-common/for-6.c execution test

    PASS: libgomp.c/../libgomp.c-c++-common/for-9.c (test for excess errors)
    [-PASS:-]{+FAIL:+} libgomp.c/../libgomp.c-c++-common/for-9.c execution test

Same for 'libgomp.c++'.

It remains to be analyzed how '#pragma GCC diagnostic [...]' directives can
cause code generation changes; for now I'm working around the "unexpected"
'-Werror=array-bounds' diagnostics differently.

Overall, still awaiting a different solution, of course.

	libgomp/
	PR target/101484
	* configure.tgt [amdgcn*-*-*] (XCFLAGS): Add
	'-Wno-error=array-bounds'.
	* config/gcn/team.c: Remove '-Werror=array-bounds' work-around.
	* libgomp.h [__AMDGCN__]: Likewise.

3 files changed, 3 insertions, 15 deletions

diff --git a/libgomp/config/gcn/team.c b/libgomp/config/gcn/team.c
index 94ce2f2..627210e 100644
--- a/libgomp/config/gcn/team.c
+++ b/libgomp/config/gcn/team.c
@@ -65,12 +65,9 @@ gomp_gcn_enter_kernel (void)
       void * __lds *arena_start = (void * __lds *)TEAM_ARENA_START;
       void * __lds *arena_free = (void * __lds *)TEAM_ARENA_FREE;
       void * __lds *arena_end = (void * __lds *)TEAM_ARENA_END;
-# pragma GCC diagnostic push
-# pragma GCC diagnostic ignored "-Warray-bounds" /*TODO PR101484 */
       *arena_start = team_arena;
       *arena_free = team_arena;
       *arena_end = team_arena + TEAM_ARENA_SIZE;
-# pragma GCC diagnostic pop
 
       /* Allocate and initialize the team-local-storage data.  */
       struct gomp_thread *thrs = team_malloc_cleared (sizeof (*thrs)
diff --git a/libgomp/configure.tgt b/libgomp/configure.tgt
index fe2bf1d..d4f1e74 100644
--- a/libgomp/configure.tgt
+++ b/libgomp/configure.tgt
@@ -173,6 +173,9 @@ case "${target}" in
 
   amdgcn*-*-*)
 	config_path="gcn accel"
+
+	#TODO PR101484
+	XCFLAGS="$XCFLAGS -Wno-error=array-bounds"
 	;;
 
   *)
diff --git a/libgomp/libgomp.h b/libgomp/libgomp.h
index 4159cbe..8d25dc8 100644
--- a/libgomp/libgomp.h
+++ b/libgomp/libgomp.h
@@ -128,10 +128,7 @@ team_malloc (size_t size)
        : "=v"(result) : "v"(TEAM_ARENA_FREE), "v"(size), "e"(1L) : "memory");
 
   /* Handle OOM.  */
-# pragma GCC diagnostic push
-# pragma GCC diagnostic ignored "-Warray-bounds" /*TODO PR101484 */
   if (result + size > *(void * __lds *)TEAM_ARENA_END)
-# pragma GCC diagnostic pop
     {
       /* While this is experimental, let's make sure we know when OOM
 	 happens.  */
@@ -162,11 +159,8 @@ team_free (void *ptr)
      However, if we fell back to using heap then we should free it.
      It would be better if this function could be a no-op, but at least
      LDS loads are cheap.  */
-# pragma GCC diagnostic push
-# pragma GCC diagnostic ignored "-Warray-bounds" /*TODO PR101484 */
   if (ptr < *(void * __lds *)TEAM_ARENA_START
       || ptr >= *(void * __lds *)TEAM_ARENA_END)
-# pragma GCC diagnostic pop
     free (ptr);
 }
 #else
@@ -795,19 +789,13 @@ static inline struct gomp_thread *gcn_thrs (void)
 {
   /* The value is at the bottom of LDS.  */
   struct gomp_thread * __lds *thrs = (struct gomp_thread * __lds *)4;
-# pragma GCC diagnostic push
-# pragma GCC diagnostic ignored "-Warray-bounds" /*TODO PR101484 */
   return *thrs;
-# pragma GCC diagnostic pop
 }
 static inline void set_gcn_thrs (struct gomp_thread *val)
 {
   /* The value is at the bottom of LDS.  */
   struct gomp_thread * __lds *thrs = (struct gomp_thread * __lds *)4;
-# pragma GCC diagnostic push
-# pragma GCC diagnostic ignored "-Warray-bounds" /*TODO PR101484 */
   *thrs = val;
-# pragma GCC diagnostic pop
 }
 static inline struct gomp_thread *gomp_thread (void)
 {