Hi,

With GOMP_NVPTX_JIT=-00 and -mptx=3.1, I run into:
...
FAIL: libgomp.oacc-c/../libgomp.oacc-c-c++-common/acc_prof-version-1.c \
  -DACC_DEVICE_TYPE_nvidia=1 -DACC_MEM_SHARED=0 -foffload=nvptx-none  -O2 \
  execution test
...

The problem is that we're generating a diverging branch around nothing:
...
        {
                .reg.u32        %x;
                mov.u32 %x, %tid.x;
                setp.ne.u32     %r23, %x, 0;
        }
        @%r23   bra     $L2;
$L2:
...
which the driver JIT has problems with at -O0, so consequently we run into the
nvptx_uniform_warp_check.

Fix this by handling asm ("") and alike in prevent_branch_around_nothing.

Tested on x86_64 with nvptx accelerator.

Committed to trunk.

Thanks,
- Tom

[nvptx] Handle asm insn in prevent_branch_around_nothing

gcc/ChangeLog:

2022-02-10  Tom de Vries  <tdevr...@suse.de>

        PR target/104456
        * config/nvptx/nvptx.cc (prevent_branch_around_nothing): Handle asm
        insn.

---
 gcc/config/nvptx/nvptx.cc | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/gcc/config/nvptx/nvptx.cc b/gcc/config/nvptx/nvptx.cc
index 5b26c0f4c7d..afbad5bdde6 100644
--- a/gcc/config/nvptx/nvptx.cc
+++ b/gcc/config/nvptx/nvptx.cc
@@ -5257,6 +5257,14 @@ prevent_branch_around_nothing (void)
            case CODE_FOR_nvptx_join:
            case CODE_FOR_nop:
              continue;
+           case -1:
+             /* Handle asm ("") and similar.  */
+             if (GET_CODE (PATTERN (insn)) == ASM_INPUT
+                 || GET_CODE (PATTERN (insn)) == ASM_OPERANDS
+                 || (GET_CODE (PATTERN (insn)) == PARALLEL
+                     && asm_noperands (PATTERN (insn)) >= 0))
+               continue;
+             /* FALLTHROUGH.  */
            default:
              seen_label = NULL;
              continue;

Reply via email to