tcg/s390x: Optimize cmpsel with constant 0/-1 arguments

These can be simplified to and/or/andc/orc,
avoiding the load of the constantinto a register.

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>

3 files changed, 34 insertions, 10 deletions

diff --git a/tcg/s390x/tcg-target-con-set.h b/tcg/s390x/tcg-target-con-set.h
index 670089086d..370e4b1295 100644
--- a/tcg/s390x/tcg-target-con-set.h
+++ b/tcg/s390x/tcg-target-con-set.h
@@ -38,7 +38,8 @@ C_O1_I2(r, rZ, r)
 C_O1_I2(v, v, r)
 C_O1_I2(v, v, v)
 C_O1_I3(v, v, v, v)
-C_O1_I4(v, v, v, v, v)
+C_O1_I4(v, v, v, vZ, v)
+C_O1_I4(v, v, v, vZM, v)
 C_O1_I4(r, r, ri, rI, r)
 C_O1_I4(r, r, rC, rI, r)
 C_O2_I1(o, m, r)
diff --git a/tcg/s390x/tcg-target-con-str.h b/tcg/s390x/tcg-target-con-str.h
index 745f6c0df5..3e574e0662 100644
--- a/tcg/s390x/tcg-target-con-str.h
+++ b/tcg/s390x/tcg-target-con-str.h
@@ -20,6 +20,7 @@ CONST('C', TCG_CT_CONST_CMP)
 CONST('I', TCG_CT_CONST_S16)
 CONST('J', TCG_CT_CONST_S32)
 CONST('K', TCG_CT_CONST_P32)
+CONST('M', TCG_CT_CONST_M1)
 CONST('N', TCG_CT_CONST_INV)
 CONST('R', TCG_CT_CONST_INVRISBG)
 CONST('U', TCG_CT_CONST_U32)
diff --git a/tcg/s390x/tcg-target.c.inc b/tcg/s390x/tcg-target.c.inc
index e044168826..a5d57197a4 100644
--- a/tcg/s390x/tcg-target.c.inc
+++ b/tcg/s390x/tcg-target.c.inc
@@ -36,6 +36,7 @@
 #define TCG_CT_CONST_INV        (1 << 13)
 #define TCG_CT_CONST_INVRISBG   (1 << 14)
 #define TCG_CT_CONST_CMP        (1 << 15)
+#define TCG_CT_CONST_M1         (1 << 16)
 
 #define ALL_GENERAL_REGS     MAKE_64BIT_MASK(0, 16)
 #define ALL_VECTOR_REGS      MAKE_64BIT_MASK(32, 32)
@@ -607,6 +608,9 @@ static bool tcg_target_const_match(int64_t val, int ct,
     if ((ct & TCG_CT_CONST_ZERO) && val == 0) {
         return true;
     }
+    if ((ct & TCG_CT_CONST_M1) && val == -1) {
+        return true;
+    }
 
     if (ct & TCG_CT_CONST_INV) {
         val = ~val;
@@ -2904,15 +2908,30 @@ static void tcg_out_cmp_vec(TCGContext *s, unsigned vece, TCGReg a0,
 }
 
 static void tcg_out_cmpsel_vec(TCGContext *s, unsigned vece, TCGReg a0,
-                               TCGReg c1, TCGReg c2,
-                               TCGReg v3, TCGReg v4, TCGCond cond)
+                               TCGReg c1, TCGReg c2, TCGArg v3,
+                               int const_v3, TCGReg v4, TCGCond cond)
 {
-    if (tcg_out_cmp_vec_noinv(s, vece, TCG_VEC_TMP0, c1, c2, cond)) {
-        TCGReg swap = v3;
-        v3 = v4;
-        v4 = swap;
+    bool inv = tcg_out_cmp_vec_noinv(s, vece, TCG_VEC_TMP0, c1, c2, cond);
+
+    if (!const_v3) {
+        if (inv) {
+            tcg_out_insn(s, VRRe, VSEL, a0, v4, v3, TCG_VEC_TMP0);
+        } else {
+            tcg_out_insn(s, VRRe, VSEL, a0, v3, v4, TCG_VEC_TMP0);
+        }
+    } else if (v3) {
+        if (inv) {
+            tcg_out_insn(s, VRRc, VOC, a0, v4, TCG_VEC_TMP0, 0);
+        } else {
+            tcg_out_insn(s, VRRc, VO, a0, v4, TCG_VEC_TMP0, 0);
+        }
+    } else {
+        if (inv) {
+            tcg_out_insn(s, VRRc, VN, a0, v4, TCG_VEC_TMP0, 0);
+        } else {
+            tcg_out_insn(s, VRRc, VNC, a0, v4, TCG_VEC_TMP0, 0);
+        }
     }
-    tcg_out_insn(s, VRRe, VSEL, a0, v3, v4, TCG_VEC_TMP0);
 }
 
 static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
@@ -3036,7 +3055,8 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
         tcg_out_cmp_vec(s, vece, a0, a1, a2, args[3]);
         break;
     case INDEX_op_cmpsel_vec:
-        tcg_out_cmpsel_vec(s, vece, a0, a1, a2, args[3], args[4], args[5]);
+        tcg_out_cmpsel_vec(s, vece, a0, a1, a2, args[3], const_args[3],
+                           args[4], args[5]);
         break;
 
     case INDEX_op_s390_vuph_vec:
@@ -3388,7 +3408,9 @@ static TCGConstraintSetIndex tcg_target_op_def(TCGOpcode op)
     case INDEX_op_bitsel_vec:
         return C_O1_I3(v, v, v, v);
     case INDEX_op_cmpsel_vec:
-        return C_O1_I4(v, v, v, v, v);
+        return (TCG_TARGET_HAS_orc_vec
+                ? C_O1_I4(v, v, v, vZM, v)
+                : C_O1_I4(v, v, v, vZ, v));
 
     default:
         g_assert_not_reached();