[PULL 24/28] tcg/s390x: Implement vector shift operations

[Richard Henderson]

Reviewed-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 tcg/s390x/tcg-target-con-set.h |  1 +
 tcg/s390x/tcg-target.h         | 12 ++---
 tcg/s390x/tcg-target.c.inc     | 93 +++++++++++++++++++++++++++++++++-
 3 files changed, 99 insertions(+), 7 deletions(-)

diff --git a/tcg/s390x/tcg-target-con-set.h b/tcg/s390x/tcg-target-con-set.h
index cb953896d5..49b98f33b9 100644
--- a/tcg/s390x/tcg-target-con-set.h
+++ b/tcg/s390x/tcg-target-con-set.h
@@ -24,6 +24,7 @@ C_O1_I2(r, 0, rI)
 C_O1_I2(r, 0, rJ)
 C_O1_I2(r, r, ri)
 C_O1_I2(r, rZ, r)
+C_O1_I2(v, v, r)
 C_O1_I2(v, v, v)
 C_O1_I4(r, r, ri, r, 0)
 C_O1_I4(r, r, ri, rI, 0)
diff --git a/tcg/s390x/tcg-target.h b/tcg/s390x/tcg-target.h
index 1c581a2f60..d7d204b782 100644
--- a/tcg/s390x/tcg-target.h
+++ b/tcg/s390x/tcg-target.h
@@ -148,12 +148,12 @@ extern uint64_t s390_facilities[3];
 #define TCG_TARGET_HAS_not_vec        1
 #define TCG_TARGET_HAS_neg_vec        1
 #define TCG_TARGET_HAS_abs_vec        1
-#define TCG_TARGET_HAS_roti_vec       0
-#define TCG_TARGET_HAS_rots_vec       0
-#define TCG_TARGET_HAS_rotv_vec       0
-#define TCG_TARGET_HAS_shi_vec        0
-#define TCG_TARGET_HAS_shs_vec        0
-#define TCG_TARGET_HAS_shv_vec        0
+#define TCG_TARGET_HAS_roti_vec       1
+#define TCG_TARGET_HAS_rots_vec       1
+#define TCG_TARGET_HAS_rotv_vec       1
+#define TCG_TARGET_HAS_shi_vec        1
+#define TCG_TARGET_HAS_shs_vec        1
+#define TCG_TARGET_HAS_shv_vec        1
 #define TCG_TARGET_HAS_mul_vec        1
 #define TCG_TARGET_HAS_sat_vec        0
 #define TCG_TARGET_HAS_minmax_vec     0
diff --git a/tcg/s390x/tcg-target.c.inc b/tcg/s390x/tcg-target.c.inc
index 85178c93d3..98c0cd5091 100644
--- a/tcg/s390x/tcg-target.c.inc
+++ b/tcg/s390x/tcg-target.c.inc
@@ -277,6 +277,10 @@ typedef enum S390Opcode {
     VRRc_VCEQ   = 0xe7f8,   /* we leave the m5 cs field 0 */
     VRRc_VCH    = 0xe7fb,   /* " */
     VRRc_VCHL   = 0xe7f9,   /* " */
+    VRRc_VERLLV = 0xe773,
+    VRRc_VESLV  = 0xe770,
+    VRRc_VESRAV = 0xe77a,
+    VRRc_VESRLV = 0xe778,
     VRRc_VML    = 0xe7a2,
     VRRc_VN     = 0xe768,
     VRRc_VNC    = 0xe769,
@@ -287,6 +291,10 @@ typedef enum S390Opcode {
     VRRc_VX     = 0xe76d,
     VRRf_VLVGP  = 0xe762,
 
+    VRSa_VERLL  = 0xe733,
+    VRSa_VESL   = 0xe730,
+    VRSa_VESRA  = 0xe73a,
+    VRSa_VESRL  = 0xe738,
     VRSb_VLVG   = 0xe722,
     VRSc_VLGV   = 0xe721,
 
@@ -643,6 +651,18 @@ static void tcg_out_insn_VRRf(TCGContext *s, S390Opcode op,
     tcg_out16(s, (op & 0x00ff) | RXB(v1, 0, 0, 0));
 }
 
+static void tcg_out_insn_VRSa(TCGContext *s, S390Opcode op, TCGReg v1,
+                              intptr_t d2, TCGReg b2, TCGReg v3, int m4)
+{
+    tcg_debug_assert(is_vector_reg(v1));
+    tcg_debug_assert(d2 >= 0 && d2 <= 0xfff);
+    tcg_debug_assert(is_general_reg(b2));
+    tcg_debug_assert(is_vector_reg(v3));
+    tcg_out16(s, (op & 0xff00) | ((v1 & 0xf) << 4) | (v3 & 0xf));
+    tcg_out16(s, b2 << 12 | d2);
+    tcg_out16(s, (op & 0x00ff) | RXB(v1, 0, v3, 0) | (m4 << 12));
+}
+
 static void tcg_out_insn_VRSb(TCGContext *s, S390Opcode op, TCGReg v1,
                               intptr_t d2, TCGReg b2, TCGReg r3, int m4)
 {
@@ -2710,6 +2730,43 @@ static void tcg_out_vec_op(TCGContext *s, TCGOpcode opc,
         tcg_out_insn(s, VRRc, VX, a0, a1, a2, 0);
         break;
 
+    case INDEX_op_shli_vec:
+        tcg_out_insn(s, VRSa, VESL, a0, a2, TCG_REG_NONE, a1, vece);
+        break;
+    case INDEX_op_shri_vec:
+        tcg_out_insn(s, VRSa, VESRL, a0, a2, TCG_REG_NONE, a1, vece);
+        break;
+    case INDEX_op_sari_vec:
+        tcg_out_insn(s, VRSa, VESRA, a0, a2, TCG_REG_NONE, a1, vece);
+        break;
+    case INDEX_op_rotli_vec:
+        tcg_out_insn(s, VRSa, VERLL, a0, a2, TCG_REG_NONE, a1, vece);
+        break;
+    case INDEX_op_shls_vec:
+        tcg_out_insn(s, VRSa, VESL, a0, 0, a2, a1, vece);
+        break;
+    case INDEX_op_shrs_vec:
+        tcg_out_insn(s, VRSa, VESRL, a0, 0, a2, a1, vece);
+        break;
+    case INDEX_op_sars_vec:
+        tcg_out_insn(s, VRSa, VESRA, a0, 0, a2, a1, vece);
+        break;
+    case INDEX_op_rotls_vec:
+        tcg_out_insn(s, VRSa, VERLL, a0, 0, a2, a1, vece);
+        break;
+    case INDEX_op_shlv_vec:
+        tcg_out_insn(s, VRRc, VESLV, a0, a1, a2, vece);
+        break;
+    case INDEX_op_shrv_vec:
+        tcg_out_insn(s, VRRc, VESRLV, a0, a1, a2, vece);
+        break;
+    case INDEX_op_sarv_vec:
+        tcg_out_insn(s, VRRc, VESRAV, a0, a1, a2, vece);
+        break;
+    case INDEX_op_rotlv_vec:
+        tcg_out_insn(s, VRRc, VERLLV, a0, a1, a2, vece);
+        break;
+
     case INDEX_op_cmp_vec:
         switch ((TCGCond)args[3]) {
         case TCG_COND_EQ:
@@ -2744,10 +2801,23 @@ int tcg_can_emit_vec_op(TCGOpcode opc, TCGType type, 
unsigned vece)
     case INDEX_op_not_vec:
     case INDEX_op_or_vec:
     case INDEX_op_orc_vec:
+    case INDEX_op_rotli_vec:
+    case INDEX_op_rotls_vec:
+    case INDEX_op_rotlv_vec:
+    case INDEX_op_sari_vec:
+    case INDEX_op_sars_vec:
+    case INDEX_op_sarv_vec:
+    case INDEX_op_shli_vec:
+    case INDEX_op_shls_vec:
+    case INDEX_op_shlv_vec:
+    case INDEX_op_shri_vec:
+    case INDEX_op_shrs_vec:
+    case INDEX_op_shrv_vec:
     case INDEX_op_sub_vec:
     case INDEX_op_xor_vec:
         return 1;
     case INDEX_op_cmp_vec:
+    case INDEX_op_rotrv_vec:
         return -1;
     case INDEX_op_mul_vec:
         return vece < MO_64;
@@ -2810,7 +2880,7 @@ void tcg_expand_vec_op(TCGOpcode opc, TCGType type, 
unsigned vece,
                        TCGArg a0, ...)
 {
     va_list va;
-    TCGv_vec v0, v1, v2;
+    TCGv_vec v0, v1, v2, t0;
 
     va_start(va, a0);
     v0 = temp_tcgv_vec(arg_temp(a0));
@@ -2822,6 +2892,13 @@ void tcg_expand_vec_op(TCGOpcode opc, TCGType type, 
unsigned vece,
         expand_vec_cmp(type, vece, v0, v1, v2, va_arg(va, TCGArg));
         break;
 
+    case INDEX_op_rotrv_vec:
+        t0 = tcg_temp_new_vec(type);
+        tcg_gen_neg_vec(vece, t0, v2);
+        tcg_gen_rotlv_vec(vece, v0, v1, t0);
+        tcg_temp_free_vec(t0);
+        break;
+
     default:
         g_assert_not_reached();
     }
@@ -2978,6 +3055,10 @@ static TCGConstraintSetIndex tcg_target_op_def(TCGOpcode 
op)
     case INDEX_op_abs_vec:
     case INDEX_op_neg_vec:
     case INDEX_op_not_vec:
+    case INDEX_op_rotli_vec:
+    case INDEX_op_sari_vec:
+    case INDEX_op_shli_vec:
+    case INDEX_op_shri_vec:
         return C_O1_I1(v, v);
     case INDEX_op_add_vec:
     case INDEX_op_sub_vec:
@@ -2988,7 +3069,17 @@ static TCGConstraintSetIndex tcg_target_op_def(TCGOpcode 
op)
     case INDEX_op_xor_vec:
     case INDEX_op_cmp_vec:
     case INDEX_op_mul_vec:
+    case INDEX_op_rotlv_vec:
+    case INDEX_op_rotrv_vec:
+    case INDEX_op_shlv_vec:
+    case INDEX_op_shrv_vec:
+    case INDEX_op_sarv_vec:
         return C_O1_I2(v, v, v);
+    case INDEX_op_rotls_vec:
+    case INDEX_op_shls_vec:
+    case INDEX_op_shrs_vec:
+    case INDEX_op_sars_vec:
+        return C_O1_I2(v, v, r);
 
     default:
         g_assert_not_reached();
-- 
2.25.1