[PULL 20/23] tcg/ppc: Update vector support for v3.00 Altivec

[Richard Henderson]

These new instructions are conditional only on MSR.VEC and
are thus part of the Altivec instruction set, and not VSX.
This includes negation and compare not equal.

Reviewed-by: Aleksandar Markovic <address@hidden>
Signed-off-by: Richard Henderson <address@hidden>
---
 tcg/ppc/tcg-target.h     |  2 +-
 tcg/ppc/tcg-target.inc.c | 23 +++++++++++++++++++++++
 2 files changed, 24 insertions(+), 1 deletion(-)

diff --git a/tcg/ppc/tcg-target.h b/tcg/ppc/tcg-target.h
index 13197eddce..4fa21f0e71 100644
--- a/tcg/ppc/tcg-target.h
+++ b/tcg/ppc/tcg-target.h
@@ -159,7 +159,7 @@ extern bool have_vsx;
 #define TCG_TARGET_HAS_andc_vec         1
 #define TCG_TARGET_HAS_orc_vec          have_isa_2_07
 #define TCG_TARGET_HAS_not_vec          1
-#define TCG_TARGET_HAS_neg_vec          0
+#define TCG_TARGET_HAS_neg_vec          have_isa_3_00
 #define TCG_TARGET_HAS_abs_vec          0
 #define TCG_TARGET_HAS_shi_vec          0
 #define TCG_TARGET_HAS_shs_vec          0
diff --git a/tcg/ppc/tcg-target.inc.c b/tcg/ppc/tcg-target.inc.c
index 840464aab5..bd9259c60f 100644
--- a/tcg/ppc/tcg-target.inc.c
+++ b/tcg/ppc/tcg-target.inc.c
@@ -499,6 +499,9 @@ static int tcg_target_const_match(tcg_target_long val, 
TCGType type,
 #define VSUBUWM    VX4(1152)
 #define VSUBUDM    VX4(1216)      /* v2.07 */
 
+#define VNEGW      (VX4(1538) | (6 << 16))  /* v3.00 */
+#define VNEGD      (VX4(1538) | (7 << 16))  /* v3.00 */
+
 #define VMAXSB     VX4(258)
 #define VMAXSH     VX4(322)
 #define VMAXSW     VX4(386)
@@ -528,6 +531,9 @@ static int tcg_target_const_match(tcg_target_long val, 
TCGType type,
 #define VCMPGTUH   VX4(582)
 #define VCMPGTUW   VX4(646)
 #define VCMPGTUD   VX4(711)       /* v2.07 */
+#define VCMPNEB    VX4(7)         /* v3.00 */
+#define VCMPNEH    VX4(71)        /* v3.00 */
+#define VCMPNEW    VX4(135)       /* v3.00 */
 
 #define VSLB       VX4(260)
 #define VSLH       VX4(324)
@@ -2976,6 +2982,8 @@ int tcg_can_emit_vec_op(TCGOpcode opc, TCGType type, 
unsigned vece)
     case INDEX_op_shri_vec:
     case INDEX_op_sari_vec:
         return vece <= MO_32 || have_isa_2_07 ? -1 : 0;
+    case INDEX_op_neg_vec:
+        return vece >= MO_32 && have_isa_3_00;
     case INDEX_op_mul_vec:
         switch (vece) {
         case MO_8:
@@ -3090,7 +3098,9 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
     static const uint32_t
         add_op[4] = { VADDUBM, VADDUHM, VADDUWM, VADDUDM },
         sub_op[4] = { VSUBUBM, VSUBUHM, VSUBUWM, VSUBUDM },
+        neg_op[4] = { 0, 0, VNEGW, VNEGD },
         eq_op[4]  = { VCMPEQUB, VCMPEQUH, VCMPEQUW, VCMPEQUD },
+        ne_op[4]  = { VCMPNEB, VCMPNEH, VCMPNEW, 0 },
         gts_op[4] = { VCMPGTSB, VCMPGTSH, VCMPGTSW, VCMPGTSD },
         gtu_op[4] = { VCMPGTUB, VCMPGTUH, VCMPGTUW, VCMPGTUD },
         ssadd_op[4] = { VADDSBS, VADDSHS, VADDSWS, 0 },
@@ -3132,6 +3142,11 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
     case INDEX_op_sub_vec:
         insn = sub_op[vece];
         break;
+    case INDEX_op_neg_vec:
+        insn = neg_op[vece];
+        a2 = a1;
+        a1 = 0;
+        break;
     case INDEX_op_mul_vec:
         tcg_debug_assert(vece == MO_32 && have_isa_2_07);
         insn = VMULUWM;
@@ -3194,6 +3209,9 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
         case TCG_COND_EQ:
             insn = eq_op[vece];
             break;
+        case TCG_COND_NE:
+            insn = ne_op[vece];
+            break;
         case TCG_COND_GT:
             insn = gts_op[vece];
             break;
@@ -3276,6 +3294,10 @@ static void expand_vec_cmp(TCGType type, unsigned vece, 
TCGv_vec v0,
     case TCG_COND_GTU:
         break;
     case TCG_COND_NE:
+        if (have_isa_3_00 && vece <= MO_32) {
+            break;
+        }
+        /* fall through */
     case TCG_COND_LE:
     case TCG_COND_LEU:
         need_inv = true;
@@ -3599,6 +3621,7 @@ static const TCGTargetOpDef *tcg_target_op_def(TCGOpcode 
op)
     case INDEX_op_dup2_vec:
         return &v_v_v;
     case INDEX_op_not_vec:
+    case INDEX_op_neg_vec:
     case INDEX_op_dup_vec:
         return &v_v;
     case INDEX_op_ld_vec:
-- 
2.17.1