[PATCH v3 07/16] tcg/s390x: Implement tcg_out_dup*_vec

[Richard Henderson <richard.henderson@linaro.org>]

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 tcg/s390x/tcg-target.c.inc | 122 ++++++++++++++++++++++++++++++++++++-
 1 file changed, 119 insertions(+), 3 deletions(-)

diff --git a/tcg/s390x/tcg-target.c.inc b/tcg/s390x/tcg-target.c.inc
index 439ab5a359..ff28d84f95 100644
--- a/tcg/s390x/tcg-target.c.inc
+++ b/tcg/s390x/tcg-target.c.inc
@@ -265,13 +265,20 @@ typedef enum S390Opcode {
     RX_STC      = 0x42,
     RX_STH      = 0x40,
 
+    VRIa_VGBM   = 0xe744,
+    VRIa_VREPI  = 0xe745,
+    VRIb_VGM    = 0xe746,
+    VRIc_VREP   = 0xe74d,
+
     VRRa_VLR    = 0xe756,
+    VRRf_VLVGP  = 0xe762,
 
     VRSb_VLVG   = 0xe722,
     VRSc_VLGV   = 0xe721,
 
     VRX_VL      = 0xe706,
     VRX_VLLEZ   = 0xe704,
+    VRX_VLREP   = 0xe705,
     VRX_VST     = 0xe70e,
     VRX_VSTEF   = 0xe70b,
     VRX_VSTEG   = 0xe70a,
@@ -551,6 +558,34 @@ static int RXB(TCGReg v1, TCGReg v2, TCGReg v3, TCGReg v4)
          | ((v4 & 16) << (4 - 3));
 }
 
+static void tcg_out_insn_VRIa(TCGContext *s, S390Opcode op,
+                              TCGReg v1, uint16_t i2, int m3)
+{
+    tcg_debug_assert(v1 >= TCG_REG_V0 && v1 <= TCG_REG_V31);
+    tcg_out16(s, (op & 0xff00) | ((v1 & 15) << 4));
+    tcg_out16(s, i2);
+    tcg_out16(s, (op & 0x00ff) | RXB(v1, 0, 0, 0) | (m3 << 12));
+}
+
+static void tcg_out_insn_VRIb(TCGContext *s, S390Opcode op,
+                              TCGReg v1, uint8_t i2, uint8_t i3, int m4)
+{
+    tcg_debug_assert(v1 >= TCG_REG_V0 && v1 <= TCG_REG_V31);
+    tcg_out16(s, (op & 0xff00) | ((v1 & 15) << 4));
+    tcg_out16(s, (i2 << 8) | (i3 & 0xff));
+    tcg_out16(s, (op & 0x00ff) | RXB(v1, 0, 0, 0) | (m4 << 12));
+}
+
+static void tcg_out_insn_VRIc(TCGContext *s, S390Opcode op,
+                              TCGReg v1, uint16_t i2, TCGReg v3, int m4)
+{
+    tcg_debug_assert(v1 >= TCG_REG_V0 && v1 <= TCG_REG_V31);
+    tcg_debug_assert(v3 >= TCG_REG_V0 && v3 <= TCG_REG_V31);
+    tcg_out16(s, (op & 0xff00) | ((v1 & 15) << 4) | (v3 & 15));
+    tcg_out16(s, i2);
+    tcg_out16(s, (op & 0x00ff) | RXB(v1, 0, v3, 0) | (m4 << 12));
+}
+
 static void tcg_out_insn_VRRa(TCGContext *s, S390Opcode op,
                               TCGReg v1, TCGReg v2, int m3)
 {
@@ -560,6 +595,17 @@ static void tcg_out_insn_VRRa(TCGContext *s, S390Opcode op,
     tcg_out32(s, (op & 0x00ff) | RXB(v1, v2, 0, 0) | (m3 << 12));
 }
 
+static void tcg_out_insn_VRRf(TCGContext *s, S390Opcode op,
+                              TCGReg v1, TCGReg r2, TCGReg r3)
+{
+    tcg_debug_assert(v1 >= TCG_REG_V0 && v1 <= TCG_REG_V31);
+    tcg_debug_assert(r2 <= TCG_REG_R15);
+    tcg_debug_assert(r3 <= TCG_REG_R15);
+    tcg_out16(s, (op & 0xff00) | ((v1 & 15) << 4) | r2);
+    tcg_out16(s, r3 << 12);
+    tcg_out16(s, (op & 0x00ff) | RXB(v1, 0, 0, 0));
+}
+
 static void tcg_out_insn_VRSb(TCGContext *s, S390Opcode op, TCGReg v1,
                               intptr_t d2, TCGReg b2, TCGReg r3, int m4)
 {
@@ -2467,19 +2513,89 @@ static inline void tcg_out_op(TCGContext *s, TCGOpcode opc,
 static bool tcg_out_dup_vec(TCGContext *s, TCGType type, unsigned vece,
                             TCGReg dst, TCGReg src)
 {
-    g_assert_not_reached();
+    if (src < 16) {
+        /* Replicate general register into two MO_64. */
+        tcg_out_insn(s, VRRf, VLVGP, dst, src, src);
+        if (vece == MO_64) {
+            return true;
+        }
+    }
+
+    /*
+     * Recall that the "standard" integer, within a vector, is the
+     * rightmost element of the leftmost doubleword, a-la VLLEZ.
+     */
+    tcg_out_insn(s, VRIc, VREP, dst, (8 >> vece) - 1, src, vece);
+    return true;
 }
 
 static bool tcg_out_dupm_vec(TCGContext *s, TCGType type, unsigned vece,
                              TCGReg dst, TCGReg base, intptr_t offset)
 {
-    g_assert_not_reached();
+    tcg_out_vrx_mem(s, VRX_VLREP, dst, base, TCG_REG_NONE, offset, vece);
+    return true;
 }
 
 static void tcg_out_dupi_vec(TCGContext *s, TCGType type, unsigned vece,
                              TCGReg dst, int64_t val)
 {
-    g_assert_not_reached();
+    int i, mask, msb, lsb;
+
+    /* Look for int16_t elements.  */
+    if (vece <= MO_16 ||
+        (vece == MO_32 ? (int32_t)val : val) == (int16_t)val) {
+        tcg_out_insn(s, VRIa, VREPI, dst, val, vece);
+        return;
+    }
+
+    /* Look for bit masks.  */
+    if (vece == MO_32) {
+        if (risbg_mask((int32_t)val)) {
+            /* Handle wraparound by swapping msb and lsb.  */
+            if ((val & 0x80000001u) == 0x80000001u) {
+                msb = 32 - ctz32(~val);
+                lsb = clz32(~val) - 1;
+            } else {
+                msb = clz32(val);
+                lsb = 31 - ctz32(val);
+            }
+            tcg_out_insn(s, VRIb, VGM, dst, lsb, msb, MO_32);
+            return;
+        }
+    } else {
+        if (risbg_mask(val)) {
+            /* Handle wraparound by swapping msb and lsb.  */
+            if ((val & 0x8000000000000001ull) == 0x8000000000000001ull) {
+                /* Handle wraparound by swapping msb and lsb.  */
+                msb = 64 - ctz64(~val);
+                lsb = clz64(~val) - 1;
+            } else {
+                msb = clz64(val);
+                lsb = 63 - ctz64(val);
+            }
+            tcg_out_insn(s, VRIb, VGM, dst, lsb, msb, MO_64);
+            return;
+        }
+    }
+
+    /* Look for all bytes 0x00 or 0xff.  */
+    for (i = mask = 0; i < 8; i++) {
+        uint8_t byte = val >> (i * 8);
+        if (byte == 0xff) {
+            mask |= 1 << i;
+        } else if (byte != 0) {
+            break;
+        }
+    }
+    if (i == 8) {
+        tcg_out_insn(s, VRIa, VGBM, dst, mask * 0x0101, 0);
+        return;
+    }
+
+    /* Otherwise, stuff it in the constant pool.  */
+    tcg_out_insn(s, RIL, LARL, TCG_TMP0, 0);
+    new_pool_label(s, val, R_390_PC32DBL, s->code_ptr - 2, 2);
+    tcg_out_insn(s, VRX, VLREP, dst, TCG_TMP0, TCG_REG_NONE, 0, MO_64);
 }
 
 static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
-- 
2.25.1