optimize_insn_for_speed () in assemble output is not aligned with
splitter condition, and it cause an ICE when building SPEC2017
blender_r.
Not sure if ctrl is supposed to be reliable in assemble output, the patch just
remove that as a walkaround.
Bootstrapped and regtested on x86_64-pc-linux-gnu{-m32,}
Ready to push to trunk.
libpng/pngread.c: In function ‘png_read_image’:
libpng/pngread.c:786:1: internal compiler error: in final_scan_insn_1, at
final.cc:2813
786 | }
| ^
0x73ac3d final_scan_insn_1
../../gcc/final.cc:2813
0xb3420b final_scan_insn(rtx_insn*, _IO_FILE*, int, int, int*)
../../gcc/final.cc:2887
0xb344c4 final_1
../../gcc/final.cc:1979
0xb34f64 rest_of_handle_final
../../gcc/final.cc:4240
0xb34f64 execute
../../gcc/final.cc:4318
gcc/ChangeLog:
PR target/110438
* config/i386/sse.md (<mask_codefor>one_cmpl<mode>2<mask_name>):
Remove # from assemble output.
---
gcc/config/i386/sse.md | 4 ----
1 file changed, 4 deletions(-)
diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md
index 6bf9c99a2c1..e1158c5717a 100644
--- a/gcc/config/i386/sse.md
+++ b/gcc/config/i386/sse.md
@@ -17220,10 +17220,6 @@ (define_insn_and_split
"<mask_codefor>one_cmpl<mode>2<mask_name>"
|| <ssescalarmode>mode == SImode
|| <ssescalarmode>mode == DImode)"
{
- if (!<mask_applied> && which_alternative
- && optimize_insn_for_speed_p ())
- return "#";
-
if (TARGET_AVX512VL)
return "vpternlog<ternlogsuffix>\t{$0x55, %1, %0,
%0<mask_operand3>|%0<mask_operand3>, %0, %1, 0x55}";
else
--
2.39.1.388.g2fc9e9ca3c
