s390: Emulate vec_cmp{eq,gt,gtu} for 128-bit integers

Mode iterator V_HW enables V1TI for target VXE which means
vec_cmpv1tiv1ti becomes available which leads to an ICE since there is
no corresponding insn.

Fixed by emulating comparisons and enabling mode V1TI unconditionally
for V_HW.  For the sake of symmetry, I also added TI mode to V_HW since
TF mode is already included.  As a consequence the consumers of V_HW
vec_{splat,slb,sld,sldw,sldb,srdb,srab,srb,test_mask_int,test_mask}
also become available for 128-bit integers.

This fixes gcc.c-torture/execute/pr105613.c and gcc.dg/pr106063.c.

gcc/ChangeLog:

	* config/s390/vector.md (V_HW): Enable V1TI unconditionally and
	add TI.
	(vec_cmpu<VIT_HW:mode><VIT_HW:mode>): Add 128-bit integer
	variants.
	(*vec_cmpeq<mode><mode>_nocc_emu): Emulate operation.
	(*vec_cmpgt<mode><mode>_nocc_emu): Emulate operation.
	(*vec_cmpgtu<mode><mode>_nocc_emu): Emulate operation.

gcc/testsuite/ChangeLog:

	* gcc.target/s390/vector/vec-cmp-emu-1.c: New test.
	* gcc.target/s390/vector/vec-cmp-emu-2.c: New test.
	* gcc.target/s390/vector/vec-cmp-emu-3.c: New test.

4 files changed, 171 insertions, 12 deletions

diff --git a/gcc/config/s390/vector.md b/gcc/config/s390/vector.md
index 6367885..7560117 100644
--- a/gcc/config/s390/vector.md
+++ b/gcc/config/s390/vector.md
@@ -30,7 +30,7 @@
 ; V_HW2 is for having two iterators expanding independently e.g. vcond.
 ; It's similar to V_HW, but not fully identical: V1TI is not included, because
 ; there are no 128-bit compares.
-(define_mode_iterator V_HW  [V16QI V8HI V4SI V2DI (V1TI "TARGET_VXE") V2DF
+(define_mode_iterator V_HW  [V16QI V8HI V4SI V2DI V1TI TI V2DF
 			     (V4SF "TARGET_VXE") (V1TF "TARGET_VXE")
 			     (TF "TARGET_VXE")])
 (define_mode_iterator V_HW2 [V16QI V8HI V4SI V2DI V2DF (V4SF "TARGET_VXE")
@@ -50,6 +50,7 @@
 (define_mode_iterator VI_HW_HSDT [V8HI V4SI V2DI V1TI TI])
 (define_mode_iterator VI_HW_HS  [V8HI  V4SI])
 (define_mode_iterator VI_HW_QH  [V16QI V8HI])
+(define_mode_iterator VI_HW_T   [V1TI TI])
 
 ; Directly supported vector modes with a certain number of elements
 (define_mode_iterator V_HW_2   [V2DI V2DF])
@@ -151,7 +152,7 @@
 			    (V1HI "V1HI") (V2HI "V2HI") (V4HI "V4HI") (V8HI "V8HI")
 			    (V1SI "V1SI") (V2SI "V2SI") (V4SI "V4SI")
 			    (V1DI "V1DI") (V2DI "V2DI")
-			    (V1TI "V1TI")
+			    (V1TI "V1TI") (TI "V1TI")
 			    (V1SF "V1SI") (V2SF "V2SI") (V4SF "V4SI")
 			    (V1DF "V1DI") (V2DF "V2DI")
 			    (V1TF "V1TI") (TF "V1TI")])
@@ -160,7 +161,7 @@
 			    (V1HI "v1hi") (V2HI "v2hi") (V4HI "v4hi") (V8HI "v8hi")
 			    (V1SI "v1si") (V2SI "v2si") (V4SI "v4si")
 			    (V1DI "v1di") (V2DI "v2di")
-			    (V1TI "v1ti")
+			    (V1TI "v1ti") (TI "v1ti")
 			    (V1SF "v1si") (V2SF "v2si") (V4SF "v4si")
 			    (V1DF "v1di") (V2DF "v2di")
 			    (V1TF "v1ti") (TF   "v1ti")])
@@ -1960,11 +1961,11 @@
   DONE;
 })
 
-(define_expand "vec_cmpu<VI_HW:mode><VI_HW:mode>"
-  [(set (match_operand:VI_HW    0 "register_operand" "")
-	(match_operator:VI_HW   1 ""
-	  [(match_operand:VI_HW 2 "register_operand" "")
-	   (match_operand:VI_HW 3 "register_operand" "")]))]
+(define_expand "vec_cmpu<VIT_HW:mode><VIT_HW:mode>"
+  [(set (match_operand:VIT_HW    0 "register_operand" "")
+	(match_operator:VIT_HW   1 ""
+	  [(match_operand:VIT_HW 2 "register_operand" "")
+	   (match_operand:VIT_HW 3 "register_operand" "")]))]
   "TARGET_VX"
 {
   s390_expand_vec_compare (operands[0], GET_CODE(operands[1]), operands[2], operands[3]);
@@ -1979,6 +1980,94 @@
   "vc<VICMP_HW_OP:insn_cmp_op><VI:bhfgq>\t%v2,%v0,%v1"
   [(set_attr "op_type" "VRR")])
 
+(define_insn_and_split "*vec_cmpeq<mode><mode>_nocc_emu"
+  [(set (match_operand:VI_HW_T             0 "register_operand" "=v")
+	(eq:VI_HW_T (match_operand:VI_HW_T 1 "register_operand"  "v")
+		    (match_operand:VI_HW_T 2 "register_operand"  "v")))]
+  "TARGET_VX"
+  "#"
+  "&& can_create_pseudo_p ()"
+  [(set (match_dup 3)
+	(eq:V2DI (match_dup 1) (match_dup 2)))
+   (set (match_dup 4)
+	(vec_select:V2DI (match_dup 3) (parallel [(const_int 1) (const_int 0)])))
+   (set (match_dup 3)
+	(and:V2DI (match_dup 3) (match_dup 4)))
+   (set (match_dup 0)
+	(subreg:<MODE> (match_dup 3) 0))]
+{
+  operands[1] = simplify_gen_subreg (V2DImode, operands[1], <MODE>mode, 0);
+  operands[2] = simplify_gen_subreg (V2DImode, operands[2], <MODE>mode, 0);
+  operands[3] = gen_reg_rtx (V2DImode);
+  operands[4] = gen_reg_rtx (V2DImode);
+})
+
+(define_insn_and_split "*vec_cmpgt<mode><mode>_nocc_emu"
+  [(set (match_operand:VI_HW_T             0 "register_operand" "=v")
+	(gt:VI_HW_T (match_operand:VI_HW_T 1 "register_operand"  "v")
+		    (match_operand:VI_HW_T 2 "register_operand"  "v")))]
+  "TARGET_VX"
+  "#"
+  "&& can_create_pseudo_p ()"
+  [(set (match_dup 3)
+	(gt:V2DI (match_dup 1) (match_dup 2)))
+   (set (match_dup 4)
+	(eq:V2DI (match_dup 1) (match_dup 2)))
+   (set (match_dup 5)
+	(gtu:V2DI (match_dup 1) (match_dup 2)))
+   (set (match_dup 5)
+	(vec_select:V2DI (match_dup 5) (parallel [(const_int 1) (const_int 0)])))
+   (set (match_dup 4)
+	(and:V2DI (match_dup 4) (match_dup 5)))
+   (set (match_dup 4)
+	(ior:V2DI (match_dup 3) (match_dup 4)))
+   (set (match_dup 4)
+	(vec_duplicate:V2DI
+	 (vec_select:DI
+	  (match_dup 4)
+	  (parallel [(const_int 1)]))))
+   (set (match_dup 0)
+	(subreg:<MODE> (match_dup 4) 0))]
+{
+  operands[1] = simplify_gen_subreg (V2DImode, operands[1], <MODE>mode, 0);
+  operands[2] = simplify_gen_subreg (V2DImode, operands[2], <MODE>mode, 0);
+  operands[3] = gen_reg_rtx (V2DImode);
+  operands[4] = gen_reg_rtx (V2DImode);
+  operands[5] = gen_reg_rtx (V2DImode);
+})
+
+(define_insn_and_split "*vec_cmpgtu<mode><mode>_nocc_emu"
+  [(set (match_operand:VI_HW_T              0 "register_operand" "=v")
+	(gtu:VI_HW_T (match_operand:VI_HW_T 1 "register_operand"  "v")
+		     (match_operand:VI_HW_T 2 "register_operand"  "v")))]
+  "TARGET_VX"
+  "#"
+  "&& can_create_pseudo_p ()"
+  [(set (match_dup 3)
+	(gtu:V2DI (match_dup 1) (match_dup 2)))
+   (set (match_dup 4)
+	(eq:V2DI (match_dup 1) (match_dup 2)))
+   (set (match_dup 5)
+	(vec_select:V2DI (match_dup 3) (parallel [(const_int 1) (const_int 0)])))
+   (set (match_dup 4)
+	(and:V2DI (match_dup 4) (match_dup 5)))
+   (set (match_dup 4)
+	(ior:V2DI (match_dup 3) (match_dup 4)))
+   (set (match_dup 4)
+	(vec_duplicate:V2DI
+	 (vec_select:DI
+	  (match_dup 4)
+	  (parallel [(const_int 1)]))))
+   (set (match_dup 0)
+	(subreg:<MODE> (match_dup 4) 0))]
+{
+  operands[1] = simplify_gen_subreg (V2DImode, operands[1], <MODE>mode, 0);
+  operands[2] = simplify_gen_subreg (V2DImode, operands[2], <MODE>mode, 0);
+  operands[3] = gen_reg_rtx (V2DImode);
+  operands[4] = gen_reg_rtx (V2DImode);
+  operands[5] = gen_reg_rtx (V2DImode);
+})
+
 
 ;;
 ;; Floating point compares
@@ -2315,12 +2404,12 @@
 
 ; op0 = op3 == 0 ? op1 : op2
 (define_insn "*vec_sel0<mode>"
-  [(set (match_operand:V 0 "register_operand" "=v")
-	(if_then_else:V
+  [(set (match_operand:VT 0 "register_operand" "=v")
+	(if_then_else:VT
 	 (eq (match_operand:<TOINTVEC> 3 "register_operand" "v")
 	     (match_operand:<TOINTVEC> 4 "const0_operand" ""))
-	 (match_operand:V 1 "register_operand" "v")
-	 (match_operand:V 2 "register_operand" "v")))]
+	 (match_operand:VT 1 "register_operand" "v")
+	 (match_operand:VT 2 "register_operand" "v")))]
   "TARGET_VX"
   "vsel\t%v0,%2,%1,%3"
   [(set_attr "op_type" "VRR")])
diff --git a/gcc/testsuite/gcc.target/s390/vector/vec-cmp-emu-1.c b/gcc/testsuite/gcc.target/s390/vector/vec-cmp-emu-1.c
new file mode 100644
index 0000000..c92a2b4
--- /dev/null
+++ b/gcc/testsuite/gcc.target/s390/vector/vec-cmp-emu-1.c
@@ -0,0 +1,35 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mzarch -march=z13" } */
+/* { dg-require-effective-target int128 } */
+/* { dg-final { check-function-bodies "**" "" "" } } */
+
+typedef __attribute__ ((vector_size (16))) signed __int128 v1ti;
+typedef __attribute__ ((vector_size (16))) unsigned __int128 uv1ti;
+
+/*
+** eq:
+**	vceqg	(%v[0-9]+),%v[0-9]+,%v[0-9]+
+**	vpdi	(%v[0-9]+),\1,\1,4
+**	vn	%v24,(\1,\2|\2,\1)
+**	br	%r14
+*/
+
+v1ti
+eq (v1ti x, v1ti y)
+{
+  return x == y;
+}
+
+/*
+** ueq:
+**	vceqg	(%v[0-9]+),%v[0-9]+,%v[0-9]+
+**	vpdi	(%v[0-9]+),\1,\1,4
+**	vn	%v24,(\1,\2|\2,\1)
+**	br	%r14
+*/
+
+uv1ti
+ueq (uv1ti x, uv1ti y)
+{
+  return x == y;
+}
diff --git a/gcc/testsuite/gcc.target/s390/vector/vec-cmp-emu-2.c b/gcc/testsuite/gcc.target/s390/vector/vec-cmp-emu-2.c
new file mode 100644
index 0000000..b3ee319
--- /dev/null
+++ b/gcc/testsuite/gcc.target/s390/vector/vec-cmp-emu-2.c
@@ -0,0 +1,18 @@
+/* { dg-do compile } */
+/* { dg-options "-O3 -mzarch -march=z13" } */
+/* { dg-require-effective-target int128 } */
+/* { dg-final { scan-assembler-times {\tvchg\t} 1 } } */
+/* { dg-final { scan-assembler-times {\tvchlg\t} 1 } } */
+/* { dg-final { scan-assembler-times {\tvceqg\t} 1 } } */
+/* { dg-final { scan-assembler-times {\tvpdi\t} 1 } } */
+/* { dg-final { scan-assembler-times {\tvn\t} 1 } } */
+/* { dg-final { scan-assembler-times {\tvo\t} 1 } } */
+/* { dg-final { scan-assembler-times {\tvrepg\t} 1 } } */
+
+typedef __attribute__ ((vector_size (16))) __int128 v1ti;
+
+v1ti
+gt (v1ti x, v1ti y)
+{
+  return x > y;
+}
diff --git a/gcc/testsuite/gcc.target/s390/vector/vec-cmp-emu-3.c b/gcc/testsuite/gcc.target/s390/vector/vec-cmp-emu-3.c
new file mode 100644
index 0000000..8887814
--- /dev/null
+++ b/gcc/testsuite/gcc.target/s390/vector/vec-cmp-emu-3.c
@@ -0,0 +1,17 @@
+/* { dg-do compile } */
+/* { dg-options "-O3 -mzarch -march=z13" } */
+/* { dg-require-effective-target int128 } */
+/* { dg-final { scan-assembler-times {\tvchlg\t} 1 } } */
+/* { dg-final { scan-assembler-times {\tvceqg\t} 1 } } */
+/* { dg-final { scan-assembler-times {\tvpdi\t} 1 } } */
+/* { dg-final { scan-assembler-times {\tvn\t} 1 } } */
+/* { dg-final { scan-assembler-times {\tvo\t} 1 } } */
+/* { dg-final { scan-assembler-times {\tvrepg\t} 1 } } */
+
+typedef __attribute__ ((vector_size (16))) unsigned __int128 uv1ti;
+
+uv1ti
+gt (uv1ti x, uv1ti y)
+{
+  return x > y;
+}