diff mbox series

[PULL,21/27] tcg/s390x: Generalize movcond implementation

Message ID 20230107075118.1814503-22-richard.henderson@linaro.org
State Accepted
Commit 23d1394a6d1962bbbc8b5180e1a696c2895d89c8
Headers show
Series [PULL,01/27] tcg/s390x: Use register pair allocation for div and mulu2 | expand

Commit Message

Richard Henderson Jan. 7, 2023, 7:51 a.m. UTC
Generalize movcond to support pre-computed conditions, and the same
set of arguments at all times.  This will be assumed by a following
patch, which needs to reuse tgen_movcond_int.

Reviewed-by: Ilya Leoshkevich <iii@linux.ibm.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 tcg/s390x/tcg-target-con-set.h |  3 +-
 tcg/s390x/tcg-target.c.inc     | 52 ++++++++++++++++++++++++++--------
 2 files changed, 41 insertions(+), 14 deletions(-)
diff mbox series

Patch

diff --git a/tcg/s390x/tcg-target-con-set.h b/tcg/s390x/tcg-target-con-set.h
index b194ad7f03..8cf8ed4dff 100644
--- a/tcg/s390x/tcg-target-con-set.h
+++ b/tcg/s390x/tcg-target-con-set.h
@@ -33,8 +33,7 @@  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(r, r, ri, r, 0)
-C_O1_I4(r, r, ri, rI, 0)
+C_O1_I4(r, r, ri, rI, r)
 C_O2_I2(o, m, 0, r)
 C_O2_I2(o, m, r, r)
 C_O2_I3(o, m, 0, 1, r)
diff --git a/tcg/s390x/tcg-target.c.inc b/tcg/s390x/tcg-target.c.inc
index a9e3b4a9b9..30c12052f0 100644
--- a/tcg/s390x/tcg-target.c.inc
+++ b/tcg/s390x/tcg-target.c.inc
@@ -1354,19 +1354,49 @@  static void tgen_setcond(TCGContext *s, TCGType type, TCGCond cond,
     tcg_out_insn(s, RRFc, LOCGR, dest, TCG_TMP0, cc);
 }
 
+static void tgen_movcond_int(TCGContext *s, TCGType type, TCGReg dest,
+                             TCGArg v3, int v3const, TCGReg v4,
+                             int cc, int inv_cc)
+{
+    TCGReg src;
+
+    if (v3const) {
+        if (dest == v4) {
+            if (HAVE_FACILITY(LOAD_ON_COND2)) {
+                /* Emit: if (cc) dest = v3. */
+                tcg_out_insn(s, RIEg, LOCGHI, dest, v3, cc);
+                return;
+            }
+            tcg_out_insn(s, RI, LGHI, TCG_TMP0, v3);
+            src = TCG_TMP0;
+        } else {
+            /* LGR+LOCGHI is larger than LGHI+LOCGR. */
+            tcg_out_insn(s, RI, LGHI, dest, v3);
+            cc = inv_cc;
+            src = v4;
+        }
+    } else {
+        if (dest == v4) {
+            src = v3;
+        } else {
+            tcg_out_mov(s, type, dest, v3);
+            cc = inv_cc;
+            src = v4;
+        }
+    }
+
+    /* Emit: if (cc) dest = src. */
+    tcg_out_insn(s, RRFc, LOCGR, dest, src, cc);
+}
+
 static void tgen_movcond(TCGContext *s, TCGType type, TCGCond c, TCGReg dest,
                          TCGReg c1, TCGArg c2, int c2const,
-                         TCGArg v3, int v3const)
+                         TCGArg v3, int v3const, TCGReg v4)
 {
     int cc, inv_cc;
 
     cc = tgen_cmp2(s, type, c, c1, c2, c2const, false, &inv_cc);
-
-    if (v3const) {
-        tcg_out_insn(s, RIEg, LOCGHI, dest, v3, cc);
-    } else {
-        tcg_out_insn(s, RRFc, LOCGR, dest, v3, cc);
-    }
+    tgen_movcond_int(s, type, dest, v3, v3const, v4, cc, inv_cc);
 }
 
 static void tgen_clz(TCGContext *s, TCGReg dest, TCGReg a1,
@@ -2225,7 +2255,7 @@  static inline void tcg_out_op(TCGContext *s, TCGOpcode opc,
         break;
     case INDEX_op_movcond_i32:
         tgen_movcond(s, TCG_TYPE_I32, args[5], args[0], args[1],
-                     args[2], const_args[2], args[3], const_args[3]);
+                     args[2], const_args[2], args[3], const_args[3], args[4]);
         break;
 
     case INDEX_op_qemu_ld_i32:
@@ -2509,7 +2539,7 @@  static inline void tcg_out_op(TCGContext *s, TCGOpcode opc,
         break;
     case INDEX_op_movcond_i64:
         tgen_movcond(s, TCG_TYPE_I64, args[5], args[0], args[1],
-                     args[2], const_args[2], args[3], const_args[3]);
+                     args[2], const_args[2], args[3], const_args[3], args[4]);
         break;
 
     OP_32_64(deposit):
@@ -3114,9 +3144,7 @@  static TCGConstraintSetIndex tcg_target_op_def(TCGOpcode op)
 
     case INDEX_op_movcond_i32:
     case INDEX_op_movcond_i64:
-        return (HAVE_FACILITY(LOAD_ON_COND2)
-                ? C_O1_I4(r, r, ri, rI, 0)
-                : C_O1_I4(r, r, ri, r, 0));
+        return C_O1_I4(r, r, ri, rI, r);
 
     case INDEX_op_div2_i32:
     case INDEX_op_div2_i64: