[Qemu-devel] [PULL SUBSYSTEM s390x 10/40] s390x/tcg: Implement VECTOR COMPARE *

[David Hildenbrand <david@redhat.com>]

To carry out the comparison, we can reuse the existing gvec comparison
function. In case the CC is to be computed, save the result vector
and compute the CC lazily. The result is a vector consisting of all 1's
for elements that matched and 0's for elements that didn't match.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: David Hildenbrand <david@redhat.com>
---
 target/s390x/cc_helper.c        | 17 +++++++++++++++++
 target/s390x/helper.c           |  1 +
 target/s390x/insn-data.def      |  6 ++++++
 target/s390x/internal.h         |  1 +
 target/s390x/translate.c        |  1 +
 target/s390x/translate_vx.inc.c | 28 ++++++++++++++++++++++++++++
 6 files changed, 54 insertions(+)

diff --git a/target/s390x/cc_helper.c b/target/s390x/cc_helper.c
index 0e467bf2b6..a00294f183 100644
--- a/target/s390x/cc_helper.c
+++ b/target/s390x/cc_helper.c
@@ -402,6 +402,20 @@ static uint32_t cc_calc_lcbb(uint64_t dst)
     return dst == 16 ? 0 : 3;
 }
 
+static uint32_t cc_calc_vc(uint64_t low, uint64_t high)
+{
+    if (high == -1ull && low == -1ull) {
+        /* all elements match */
+        return 0;
+    } else if (high == 0 && low == 0) {
+        /* no elements match */
+        return 3;
+    } else {
+        /* some elements but not all match */
+        return 1;
+    }
+}
+
 static uint32_t do_calc_cc(CPUS390XState *env, uint32_t cc_op,
                                   uint64_t src, uint64_t dst, uint64_t vr)
 {
@@ -514,6 +528,9 @@ static uint32_t do_calc_cc(CPUS390XState *env, uint32_t cc_op,
     case CC_OP_LCBB:
         r = cc_calc_lcbb(dst);
         break;
+    case CC_OP_VC:
+        r = cc_calc_vc(src, dst);
+        break;
 
     case CC_OP_NZ_F32:
         r = set_cc_nz_f32(dst);
diff --git a/target/s390x/helper.c b/target/s390x/helper.c
index f957a2c830..3c8f0a7615 100644
--- a/target/s390x/helper.c
+++ b/target/s390x/helper.c
@@ -418,6 +418,7 @@ const char *cc_name(enum cc_op cc_op)
         [CC_OP_SLA_64]    = "CC_OP_SLA_64",
         [CC_OP_FLOGR]     = "CC_OP_FLOGR",
         [CC_OP_LCBB]      = "CC_OP_LCBB",
+        [CC_OP_VC]        = "CC_OP_VC",
     };
 
     return cc_names[cc_op];
diff --git a/target/s390x/insn-data.def b/target/s390x/insn-data.def
index 52e398f515..1d159cb201 100644
--- a/target/s390x/insn-data.def
+++ b/target/s390x/insn-data.def
@@ -1078,6 +1078,12 @@
     F(0xe7db, VEC,     VRR_a, V,   0, 0, 0, 0, vec, cmps64, IF_VEC)
 /* VECTOR ELEMENT COMPARE LOGICAL */
     F(0xe7d9, VECL,    VRR_a, V,   0, 0, 0, 0, vec, cmpu64, IF_VEC)
+/* VECTOR COMPARE EQUAL */
+    E(0xe7f8, VCEQ,    VRR_b, V,   0, 0, 0, 0, vc, 0, TCG_COND_EQ, IF_VEC)
+/* VECTOR COMPARE HIGH */
+    E(0xe7fb, VCH,     VRR_b, V,   0, 0, 0, 0, vc, 0, TCG_COND_GT, IF_VEC)
+/* VECTOR COMPARE HIGH LOGICAL */
+    E(0xe7f9, VCHL,    VRR_b, V,   0, 0, 0, 0, vc, 0, TCG_COND_GTU, IF_VEC)
 
 #ifndef CONFIG_USER_ONLY
 /* COMPARE AND SWAP AND PURGE */
diff --git a/target/s390x/internal.h b/target/s390x/internal.h
index 56534b38e0..9893fc094b 100644
--- a/target/s390x/internal.h
+++ b/target/s390x/internal.h
@@ -200,6 +200,7 @@ enum cc_op {
     CC_OP_SLA_64,               /* Calculate shift left signed (64bit) */
     CC_OP_FLOGR,                /* find leftmost one */
     CC_OP_LCBB,                 /* load count to block boundary */
+    CC_OP_VC,                   /* vector compare result */
     CC_OP_MAX
 };
 
diff --git a/target/s390x/translate.c b/target/s390x/translate.c
index e8e8a79b7d..da8f5b469d 100644
--- a/target/s390x/translate.c
+++ b/target/s390x/translate.c
@@ -572,6 +572,7 @@ static void gen_op_calc_cc(DisasContext *s)
     case CC_OP_SLA_32:
     case CC_OP_SLA_64:
     case CC_OP_NZ_F128:
+    case CC_OP_VC:
         /* 2 arguments */
         gen_helper_calc_cc(cc_op, cpu_env, local_cc_op, cc_src, cc_dst, dummy);
         break;
diff --git a/target/s390x/translate_vx.inc.c b/target/s390x/translate_vx.inc.c
index 4d5af6e3b6..199742fad0 100644
--- a/target/s390x/translate_vx.inc.c
+++ b/target/s390x/translate_vx.inc.c
@@ -1389,3 +1389,31 @@ static DisasJumpType op_vec(DisasContext *s, DisasOps *o)
     read_vec_element_i64(o->in2, get_field(s->fields, v2), enr, es);
     return DISAS_NEXT;
 }
+
+static DisasJumpType op_vc(DisasContext *s, DisasOps *o)
+{
+    const uint8_t es = get_field(s->fields, m4);
+    TCGCond cond = s->insn->data;
+
+    if (es > ES_64) {
+        gen_program_exception(s, PGM_SPECIFICATION);
+        return DISAS_NORETURN;
+    }
+
+    tcg_gen_gvec_cmp(cond, es,
+                     vec_full_reg_offset(get_field(s->fields, v1)),
+                     vec_full_reg_offset(get_field(s->fields, v2)),
+                     vec_full_reg_offset(get_field(s->fields, v3)), 16, 16);
+    if (get_field(s->fields, m5) & 0x1) {
+        TCGv_i64 low = tcg_temp_new_i64();
+        TCGv_i64 high = tcg_temp_new_i64();
+
+        read_vec_element_i64(high, get_field(s->fields, v1), 0, ES_64);
+        read_vec_element_i64(low, get_field(s->fields, v1), 1, ES_64);
+        gen_op_update2_cc_i64(s, CC_OP_VC, low, high);
+
+        tcg_temp_free_i64(low);
+        tcg_temp_free_i64(high);
+    }
+    return DISAS_NEXT;
+}
-- 
2.20.1