[i386] APX: Fix ICE due to movti postreload splitter [PR112394]

Message ID 20231107073321.479349-1-hongyu.wang@intel.com
State Unresolved
Headers
Series [i386] APX: Fix ICE due to movti postreload splitter [PR112394] |

Checks

Context Check Description
snail/gcc-patch-check warning Git am fail log

Commit Message

Hongyu Wang Nov. 7, 2023, 7:33 a.m. UTC
  Hi,

When APX EGPR enabled, the TImode move pattern *movti_internal allows
move between gpr and sse reg using constraint pair ("r","Yd"). Then a
post-reload splitter transform such move to vec_extractv2di, while under
-msse4.1 -mno-avx EGPR is not allowed for its enabled alternative, which
caused ICE that insn does not match the constraint. To prevent such ICE,
we need to adjust the constraint correspond to "Yd". Add a new "jc"
constraint to disable EGPR under -mno-avx.

Bootstrapped and regtseted on x86_64-pc-linux-gnu{-m32,}.

OK for trunk?

gcc/ChangeLog:

	PR target/112394
	* config/i386/constraints.md (jc): New constraint that prohibits
	EGPR on -mno-avx.
	* config/i386/i386.md (*movdi_internal): Change r constraint
	corresponds to Yd.
	(*movti_internal): Likewise.

gcc/testsuite/ChangeLog:

	PR target/112394
	* gcc.target/i386/pr112394.c: New test.
---
 gcc/config/i386/constraints.md           |  3 +++
 gcc/config/i386/i386.md                  |  8 ++++----
 gcc/testsuite/gcc.target/i386/pr112394.c | 24 ++++++++++++++++++++++++
 3 files changed, 31 insertions(+), 4 deletions(-)
 create mode 100644 gcc/testsuite/gcc.target/i386/pr112394.c
  

Patch

diff --git a/gcc/config/i386/constraints.md b/gcc/config/i386/constraints.md
index f6275740eb2..74c2f0f2d32 100644
--- a/gcc/config/i386/constraints.md
+++ b/gcc/config/i386/constraints.md
@@ -434,3 +434,6 @@  (define_address_constraint "jb"
   (and (match_operand 0 "vsib_address_operand")
        (not (and (match_test "TARGET_APX_EGPR")
 		 (match_test "x86_extended_rex2reg_mentioned_p (op)")))))
+
+(define_register_constraint  "jc"
+ "TARGET_APX_EGPR && !TARGET_AVX ? GENERAL_GPR16 : GENERAL_REGS")
diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md
index ecc74e9994e..ec39c2dd512 100644
--- a/gcc/config/i386/i386.md
+++ b/gcc/config/i386/i386.md
@@ -2454,8 +2454,8 @@  (define_insn "*movoi_internal_avx"
    (set_attr "mode" "OI")])
 
 (define_insn "*movti_internal"
-  [(set (match_operand:TI 0 "nonimmediate_operand" "=!r ,o ,v,v ,v ,m,?r,?Yd")
-	(match_operand:TI 1 "general_operand"	   "riFo,re,C,BC,vm,v,Yd,r"))]
+  [(set (match_operand:TI 0 "nonimmediate_operand" "=!r ,o ,v,v ,v ,m,?jc,?Yd")
+	(match_operand:TI 1 "general_operand"	   "riFo,re,C,BC,vm,v,Yd,jc"))]
   "(TARGET_64BIT
     && !(MEM_P (operands[0]) && MEM_P (operands[1])))
    || (TARGET_SSE
@@ -2537,9 +2537,9 @@  (define_split
 
 (define_insn "*movdi_internal"
   [(set (match_operand:DI 0 "nonimmediate_operand"
-    "=r  ,o  ,r,r  ,r,m ,*y,*y,?*y,?m,?r,?*y,?Yv,?v,?v,m ,m,?r ,?*Yd,?r,?v,?*y,?*x,*k,*k  ,*r,*m,*k")
+    "=r  ,o  ,r,r  ,r,m ,*y,*y,?*y,?m,?r,?*y,?Yv,?v,?v,m ,m,?jc,?*Yd,?r,?v,?*y,?*x,*k,*k  ,*r,*m,*k")
 	(match_operand:DI 1 "general_operand"
-    "riFo,riF,Z,rem,i,re,C ,*y,Bk ,*y,*y,r  ,C  ,?v,Bk,?v,v,*Yd,r   ,?v,r  ,*x ,*y ,*r,*kBk,*k,*k,CBC"))]
+    "riFo,riF,Z,rem,i,re,C ,*y,Bk ,*y,*y,r  ,C  ,?v,Bk,?v,v,*Yd,jc  ,?v,r  ,*x ,*y ,*r,*kBk,*k,*k,CBC"))]
   "!(MEM_P (operands[0]) && MEM_P (operands[1]))
    && ix86_hardreg_mov_ok (operands[0], operands[1])"
 {
diff --git a/gcc/testsuite/gcc.target/i386/pr112394.c b/gcc/testsuite/gcc.target/i386/pr112394.c
new file mode 100644
index 00000000000..c582f6ea6bd
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr112394.c
@@ -0,0 +1,24 @@ 
+/* PR target/112394 */
+/* { dg-do compile { target { ! ia32 } } } */
+/* { dg-options "-msse4.1 -m64 -O -mapxf" } */
+
+typedef int __attribute__((__vector_size__ (8))) A;
+typedef int __attribute__((__vector_size__ (16))) B;
+typedef char __attribute__((__vector_size__ (4))) C;
+typedef char __attribute__((__vector_size__ (32))) D;
+typedef _Complex __int128 CU;
+typedef _Float16 __attribute__((__vector_size__ (8))) F;
+D d;
+B b;
+CU gcu;
+
+int
+foo (char c, int, int, int, int, CU cu, int x)
+{
+  d /= c | d;
+  F f = __builtin_convertvector (b, F);
+  cu /= gcu;
+  A a = (A) f;
+  int i = cu + x;
+  return ((C) a[0])[1] + i + c;
+}