[committed][nvptx] Workaround sub.u16 driver JIT bug

[Tom de Vries via Gcc-patches]

Hi,

There's a nvidia driver JIT bug that mishandles this code (minimized from
builtin-arith-overflow-15.c):
...
int main (void) {
  signed char r;
  unsigned char y = (unsigned char) 0x80;
  if (__builtin_sub_overflow ((unsigned char)0, (unsigned char)y, &r))
    __builtin_abort ();
  return 0;
}
...
which at ptx level minimizes to:
...
  mov.u16 r22, 0x0080;
  st.local.u16 [frame_var],r22;
  ld.local.u16 r32,[frame_var];
  sub.u16 r33,0x0000,r32;
  cvt.u32.u16 r35,r33;
...
where we expect r35 == 0x0000ff80 but get instead 0xffffff80, and where using
nvptx-none-run -O0 fixes the problem.  [ See also
https://github.com/vries/nvidia-bugs/tree/master/builtin-arith-overflow-15 . ]

Try to workaround the bug by using sub.s16 instead of sub.u16.

Tested on nvptx.

Committed to trunk.

Thanks,
- Tom

[nvptx] Workaround sub.u16 driver JIT bug

gcc/ChangeLog:

2022-02-07  Tom de Vries  <tdevr...@suse.de>

        PR target/97005
        * config/nvptx/nvptx.md (define_insn "sub<mode>3"): Workaround
        driver JIT bug by using sub.s16 instead of sub.u16.

---
 gcc/config/nvptx/nvptx.md | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/gcc/config/nvptx/nvptx.md b/gcc/config/nvptx/nvptx.md
index bb0c0b3b9a5..cced68e0d4a 100644
--- a/gcc/config/nvptx/nvptx.md
+++ b/gcc/config/nvptx/nvptx.md
@@ -506,7 +506,14 @@ (define_insn "sub<mode>3"
        (minus:HSDIM (match_operand:HSDIM 1 "nvptx_register_operand" "R")
                     (match_operand:HSDIM 2 "nvptx_register_operand" "R")))]
   ""
-  "%.\\tsub%t0\\t%0, %1, %2;")
+  {
+    if (GET_MODE (operands[0]) == HImode)
+      /* Workaround https://developer.nvidia.com/nvidia_bug/3527713.
+        See PR97005.  */
+      return "%.\\tsub.s16\\t%0, %1, %2;";
+
+    return "%.\\tsub%t0\\t%0, %1, %2;";
+  })
 
 (define_insn "mul<mode>3"
   [(set (match_operand:HSDIM 0 "nvptx_register_operand" "=R")