From: Tom de Vries <tdevries@suse.de>
Date: Tue, 22 Sep 2020 11:16:39 +0000 (+0200)
Subject: [nvptx] Handle move from DF subreg to DF reg in nvptx_output_mov_insn
X-Git-Url: https://git.libre-soc.org/?a=commitdiff_plain;h=ca52f937fff52c494ef2951490c1654750ef8157;p=gcc.git

[nvptx] Handle move from DF subreg to DF reg in nvptx_output_mov_insn

When compiling test-case gcc.dg/atomic/c11-atomic-exec-1.c, we run into
these ptxas errors:
...
line 100; error: Rounding modifier required for instruction 'cvt'
line 105; error: Rounding modifier required for instruction 'cvt'
...

The problem is that this move:
...
//(insn 13 11 14 2
//      (set (reg:DF 28 [ _9 ])
//           (subreg:DF (reg:TI 22 [ _1 ]) 0)) 9 {*movdf_insn}
//       (nil))
                cvt.f64.u64     %r28, %r22$0;
...
is emitted as cvt.f64.u64, while it should be a mov.b64 instead.

Fix this by handling this case in nvptx_output_mov_insn.

Tested on nvptx.

gcc/ChangeLog:

	PR target/97158
	* config/nvptx/nvptx.c (nvptx_output_mov_insn): Handle move from
	DF subreg to DF reg.
---

diff --git a/gcc/config/nvptx/nvptx.c b/gcc/config/nvptx/nvptx.c
index 0c590d8d1f6..54b1fdf669b 100644
--- a/gcc/config/nvptx/nvptx.c
+++ b/gcc/config/nvptx/nvptx.c
@@ -2349,6 +2349,7 @@ const char *
 nvptx_output_mov_insn (rtx dst, rtx src)
 {
   machine_mode dst_mode = GET_MODE (dst);
+  machine_mode src_mode = GET_MODE (src);
   machine_mode dst_inner = (GET_CODE (dst) == SUBREG
 			    ? GET_MODE (XEXP (dst, 0)) : dst_mode);
   machine_mode src_inner = (GET_CODE (src) == SUBREG
@@ -2375,7 +2376,7 @@ nvptx_output_mov_insn (rtx dst, rtx src)
   if (GET_MODE_SIZE (dst_inner) == GET_MODE_SIZE (src_inner))
     {
       if (GET_MODE_BITSIZE (dst_mode) == 128
-	  && GET_MODE_BITSIZE (GET_MODE (src)) == 128)
+	  && GET_MODE_BITSIZE (src_mode) == 128)
 	{
 	  /* mov.b128 is not supported.  */
 	  if (dst_inner == V2DImode && src_inner == TImode)
@@ -2388,6 +2389,10 @@ nvptx_output_mov_insn (rtx dst, rtx src)
       return "%.\tmov.b%T0\t%0, %1;";
     }
 
+  if (GET_MODE_BITSIZE (src_inner) == 128
+      && GET_MODE_BITSIZE (src_mode) == 64)
+    return "%.\tmov.b%T0\t%0, %1;";
+
   return "%.\tcvt%t0%t1\t%0, %1;";
 }