s390x/tcg: Implement VECTOR ELEMENT ROTATE LEFT LOGICAL

Take care of properly taking the modulo of the count. We might later
want to come back and create a variant of VERLL where the base register
is 0, resulting in an immediate.

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: David Hildenbrand <david@redhat.com>

diff --git a/target/s390x/helper.h b/target/s390x/helper.h
index 20b677917bbcb28305d5364b59f3b7e45a3be54a..b3e15cfe8cc969e590c281eb1fa6ff60d7f1fb08 100644 (file)
--- a/target/s390x/helper.h
+++ b/target/s390x/helper.h
@@ -198,6 +198,10 @@ DEF_HELPER_FLAGS_4(gvec_vmlo16, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
 DEF_HELPER_FLAGS_4(gvec_vmlo32, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
 DEF_HELPER_FLAGS_3(gvec_vpopct8, TCG_CALL_NO_RWG, void, ptr, cptr, i32)
 DEF_HELPER_FLAGS_3(gvec_vpopct16, TCG_CALL_NO_RWG, void, ptr, cptr, i32)
+DEF_HELPER_FLAGS_4(gvec_verllv8, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
+DEF_HELPER_FLAGS_4(gvec_verllv16, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
+DEF_HELPER_FLAGS_4(gvec_verll8, TCG_CALL_NO_RWG, void, ptr, cptr, i64, i32)
+DEF_HELPER_FLAGS_4(gvec_verll16, TCG_CALL_NO_RWG, void, ptr, cptr, i64, i32)
 
 #ifndef CONFIG_USER_ONLY
 DEF_HELPER_3(servc, i32, env, i64, i64)

diff --git a/target/s390x/insn-data.def b/target/s390x/insn-data.def
index 0f786d6ab1c466954d1cc049e5ba106a69f60da8..e765c159411f5ab7129b68a8de8f8a35a5c4bc8b 100644 (file)
--- a/target/s390x/insn-data.def
+++ b/target/s390x/insn-data.def
@@ -1146,6 +1146,9 @@
     F(0xe76f, VOC,     VRR_c, VE,  0, 0, 0, 0, voc, 0, IF_VEC)
 /* VECTOR POPULATION COUNT */
     F(0xe750, VPOPCT,  VRR_a, V,   0, 0, 0, 0, vpopct, 0, IF_VEC)
+/* VECTOR ELEMENT ROTATE LEFT LOGICAL */
+    F(0xe773, VERLLV,  VRR_c, V,   0, 0, 0, 0, verllv, 0, IF_VEC)
+    F(0xe733, VERLL,   VRS_a, V,   la2, 0, 0, 0, verll, 0, IF_VEC)
 
 #ifndef CONFIG_USER_ONLY
 /* COMPARE AND SWAP AND PURGE */

diff --git a/target/s390x/translate_vx.inc.c b/target/s390x/translate_vx.inc.c
index 7e4876247e8144595a60e57febdc1f80edf84b27..0ca3bb3e6a3c23d40713e67751a5b44a44f2d50a 100644 (file)
--- a/target/s390x/translate_vx.inc.c
+++ b/target/s390x/translate_vx.inc.c
@@ -185,6 +185,9 @@ static void get_vec_element_ptr_i64(TCGv_ptr ptr, uint8_t reg, TCGv_i64 enr,
 #define gen_gvec_2(v1, v2, gen) \
     tcg_gen_gvec_2(vec_full_reg_offset(v1), vec_full_reg_offset(v2), \
                    16, 16, gen)
+#define gen_gvec_2s(v1, v2, c, gen) \
+    tcg_gen_gvec_2s(vec_full_reg_offset(v1), vec_full_reg_offset(v2), \
+                    16, 16, c, gen)
 #define gen_gvec_3(v1, v2, v3, gen) \
     tcg_gen_gvec_3(vec_full_reg_offset(v1), vec_full_reg_offset(v2), \
                    vec_full_reg_offset(v3), 16, 16, gen)
@@ -1845,3 +1848,60 @@ static DisasJumpType op_vpopct(DisasContext *s, DisasOps *o)
     gen_gvec_2(get_field(s->fields, v1), get_field(s->fields, v2), &g[es]);
     return DISAS_NEXT;
 }
+
+static void gen_rll_i32(TCGv_i32 d, TCGv_i32 a, TCGv_i32 b)
+{
+    TCGv_i32 t0 = tcg_temp_new_i32();
+
+    tcg_gen_andi_i32(t0, b, 31);
+    tcg_gen_rotl_i32(d, a, t0);
+    tcg_temp_free_i32(t0);
+}
+
+static void gen_rll_i64(TCGv_i64 d, TCGv_i64 a, TCGv_i64 b)
+{
+    TCGv_i64 t0 = tcg_temp_new_i64();
+
+    tcg_gen_andi_i64(t0, b, 63);
+    tcg_gen_rotl_i64(d, a, t0);
+    tcg_temp_free_i64(t0);
+}
+
+static DisasJumpType op_verllv(DisasContext *s, DisasOps *o)
+{
+    const uint8_t es = get_field(s->fields, m4);
+    static const GVecGen3 g[4] = {
+        { .fno = gen_helper_gvec_verllv8, },
+        { .fno = gen_helper_gvec_verllv16, },
+        { .fni4 = gen_rll_i32, },
+        { .fni8 = gen_rll_i64, },
+    };
+
+    if (es > ES_64) {
+        gen_program_exception(s, PGM_SPECIFICATION);
+        return DISAS_NORETURN;
+    }
+
+    gen_gvec_3(get_field(s->fields, v1), get_field(s->fields, v2),
+               get_field(s->fields, v3), &g[es]);
+    return DISAS_NEXT;
+}
+
+static DisasJumpType op_verll(DisasContext *s, DisasOps *o)
+{
+    const uint8_t es = get_field(s->fields, m4);
+    static const GVecGen2s g[4] = {
+        { .fno = gen_helper_gvec_verll8, },
+        { .fno = gen_helper_gvec_verll16, },
+        { .fni4 = gen_rll_i32, },
+        { .fni8 = gen_rll_i64, },
+    };
+
+    if (es > ES_64) {
+        gen_program_exception(s, PGM_SPECIFICATION);
+        return DISAS_NORETURN;
+    }
+    gen_gvec_2s(get_field(s->fields, v1), get_field(s->fields, v3), o->addr1,
+                &g[es]);
+    return DISAS_NEXT;
+}

diff --git a/target/s390x/vec_int_helper.c b/target/s390x/vec_int_helper.c
index fd8162f1f140ce06cb189f60c3d441ee674bb26b..a3c8f09eacc71cd4700166460f6308305493cb66 100644 (file)
--- a/target/s390x/vec_int_helper.c
+++ b/target/s390x/vec_int_helper.c
@@ -478,3 +478,34 @@ void HELPER(gvec_vpopct##BITS)(void *v1, const void *v2, uint32_t desc)        \
 }
 DEF_VPOPCT(8)
 DEF_VPOPCT(16)
+
+#define DEF_VERLLV(BITS)                                                       \
+void HELPER(gvec_verllv##BITS)(void *v1, const void *v2, const void *v3,       \
+                               uint32_t desc)                                  \
+{                                                                              \
+    int i;                                                                     \
+                                                                               \
+    for (i = 0; i < (128 / BITS); i++) {                                       \
+        const uint##BITS##_t a = s390_vec_read_element##BITS(v2, i);           \
+        const uint##BITS##_t b = s390_vec_read_element##BITS(v3, i);           \
+                                                                               \
+        s390_vec_write_element##BITS(v1, i, rol##BITS(a, b));                  \
+    }                                                                          \
+}
+DEF_VERLLV(8)
+DEF_VERLLV(16)
+
+#define DEF_VERLL(BITS)                                                        \
+void HELPER(gvec_verll##BITS)(void *v1, const void *v2, uint64_t count,        \
+                              uint32_t desc)                                   \
+{                                                                              \
+    int i;                                                                     \
+                                                                               \
+    for (i = 0; i < (128 / BITS); i++) {                                       \
+        const uint##BITS##_t a = s390_vec_read_element##BITS(v2, i);           \
+                                                                               \
+        s390_vec_write_element##BITS(v1, i, rol##BITS(a, count));              \
+    }                                                                          \
+}
+DEF_VERLL(8)
+DEF_VERLL(16)