tcg/ppc: Add support for vector saturated add/subtract

Add support for vector saturated add/subtract using Altivec
instructions:
VADDSBS, VADDSHS, VADDSWS, VADDUBS, VADDUHS, VADDUWS, and
VSUBSBS, VSUBSHS, VSUBSWS, VSUBUBS, VSUBUHS, VSUBUWS.

Tested-by: Mark Cave-Ayland <mark.cave-ayland@ilande.co.uk>
Reviewed-by: Aleksandar Markovic <amarkovic@wavecomp.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Aleksandar Markovic <amarkovic@wavecomp.com>

diff --git a/tcg/ppc/tcg-target.h b/tcg/ppc/tcg-target.h
index 13699f1..3ebbbfa 100644 (file)
--- a/tcg/ppc/tcg-target.h
+++ b/tcg/ppc/tcg-target.h
@@ -163,7 +163,7 @@ extern bool have_altivec;
 #define TCG_TARGET_HAS_shv_vec          0
 #define TCG_TARGET_HAS_cmp_vec          1
 #define TCG_TARGET_HAS_mul_vec          0
-#define TCG_TARGET_HAS_sat_vec          0
+#define TCG_TARGET_HAS_sat_vec          1
 #define TCG_TARGET_HAS_minmax_vec       1
 #define TCG_TARGET_HAS_bitsel_vec       0
 #define TCG_TARGET_HAS_cmpsel_vec       0

diff --git a/tcg/ppc/tcg-target.inc.c b/tcg/ppc/tcg-target.inc.c
index 6cfc78b..a116520 100644 (file)
--- a/tcg/ppc/tcg-target.inc.c
+++ b/tcg/ppc/tcg-target.inc.c
@@ -471,12 +471,24 @@ static int tcg_target_const_match(tcg_target_long val, TCGType type,
 #define STVX       XO31(231)
 #define STVEWX     XO31(199)
 
+#define VADDSBS    VX4(768)
+#define VADDUBS    VX4(512)
 #define VADDUBM    VX4(0)
+#define VADDSHS    VX4(832)
+#define VADDUHS    VX4(576)
 #define VADDUHM    VX4(64)
+#define VADDSWS    VX4(896)
+#define VADDUWS    VX4(640)
 #define VADDUWM    VX4(128)
 
+#define VSUBSBS    VX4(1792)
+#define VSUBUBS    VX4(1536)
 #define VSUBUBM    VX4(1024)
+#define VSUBSHS    VX4(1856)
+#define VSUBUHS    VX4(1600)
 #define VSUBUHM    VX4(1088)
+#define VSUBSWS    VX4(1920)
+#define VSUBUWS    VX4(1664)
 #define VSUBUWM    VX4(1152)
 
 #define VMAXSB     VX4(258)
@@ -2844,6 +2856,10 @@ int tcg_can_emit_vec_op(TCGOpcode opc, TCGType type, unsigned vece)
     case INDEX_op_smin_vec:
     case INDEX_op_umax_vec:
     case INDEX_op_umin_vec:
+    case INDEX_op_ssadd_vec:
+    case INDEX_op_sssub_vec:
+    case INDEX_op_usadd_vec:
+    case INDEX_op_ussub_vec:
         return vece <= MO_32;
     case INDEX_op_cmp_vec:
         return vece <= MO_32 ? -1 : 0;
@@ -2945,6 +2961,10 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
         eq_op[4]  = { VCMPEQUB, VCMPEQUH, VCMPEQUW, 0 },
         gts_op[4] = { VCMPGTSB, VCMPGTSH, VCMPGTSW, 0 },
         gtu_op[4] = { VCMPGTUB, VCMPGTUH, VCMPGTUW, 0 },
+        ssadd_op[4] = { VADDSBS, VADDSHS, VADDSWS, 0 },
+        usadd_op[4] = { VADDUBS, VADDUHS, VADDUWS, 0 },
+        sssub_op[4] = { VSUBSBS, VSUBSHS, VSUBSWS, 0 },
+        ussub_op[4] = { VSUBUBS, VSUBUHS, VSUBUWS, 0 },
         umin_op[4] = { VMINUB, VMINUH, VMINUW, 0 },
         smin_op[4] = { VMINSB, VMINSH, VMINSW, 0 },
         umax_op[4] = { VMAXUB, VMAXUH, VMAXUW, 0 },
@@ -2971,6 +2991,18 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
     case INDEX_op_sub_vec:
         insn = sub_op[vece];
         break;
+    case INDEX_op_ssadd_vec:
+        insn = ssadd_op[vece];
+        break;
+    case INDEX_op_sssub_vec:
+        insn = sssub_op[vece];
+        break;
+    case INDEX_op_usadd_vec:
+        insn = usadd_op[vece];
+        break;
+    case INDEX_op_ussub_vec:
+        insn = ussub_op[vece];
+        break;
     case INDEX_op_smin_vec:
         insn = smin_op[vece];
         break;
@@ -3277,6 +3309,10 @@ static const TCGTargetOpDef *tcg_target_op_def(TCGOpcode op)
     case INDEX_op_andc_vec:
     case INDEX_op_orc_vec:
     case INDEX_op_cmp_vec:
+    case INDEX_op_ssadd_vec:
+    case INDEX_op_sssub_vec:
+    case INDEX_op_usadd_vec:
+    case INDEX_op_ussub_vec:
     case INDEX_op_smax_vec:
     case INDEX_op_smin_vec:
     case INDEX_op_umax_vec: