diff mbox series

[v1,13/41] s390x/tcg: Implement VECTOR COUNT TRAILING ZEROS

Message ID 20190411100836.646-14-david@redhat.com
State New
Headers show
Series s390x/tcg: Vector Instruction Support Part 2 | expand

Commit Message

David Hildenbrand April 11, 2019, 10:08 a.m. UTC 
Implement it similar to VECTOR COUNT LEADING ZEROS.

Signed-off-by: David Hildenbrand <david@redhat.com>
---
 target/s390x/helper.h           |  2 ++
 target/s390x/insn-data.def      |  2 ++
 target/s390x/translate_vx.inc.c | 28 ++++++++++++++++++++++++++++
 target/s390x/vec_int_helper.c   | 14 ++++++++++++++
 4 files changed, 46 insertions(+)

Comments

Richard Henderson April 12, 2019, 11:23 p.m. UTC | #1 
On 4/11/19 12:08 AM, David Hildenbrand wrote:
> +        s390_vec_write_element##BITS(v1, i, ctz32(a));                         

Wrong result for a == 0.  You need a ? ctz32(a) : BITS.


r~
David Hildenbrand April 16, 2019, 9:07 a.m. UTC | #2 
On 13.04.19 01:23, Richard Henderson wrote:
> a ? ctz32(a) : BITS

Nice catch, thanks!
diff mbox series

Patch

diff --git a/target/s390x/helper.h b/target/s390x/helper.h
index e25e1467ae..83e5070821 100644
--- a/target/s390x/helper.h
+++ b/target/s390x/helper.h
@@ -154,6 +154,8 @@  DEF_HELPER_FLAGS_4(gvec_vavgl8, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
 DEF_HELPER_FLAGS_4(gvec_vavgl16, TCG_CALL_NO_RWG, void, ptr, cptr, cptr, i32)
 DEF_HELPER_FLAGS_3(gvec_vclz8, TCG_CALL_NO_RWG, void, ptr, cptr, i32)
 DEF_HELPER_FLAGS_3(gvec_vclz16, TCG_CALL_NO_RWG, void, ptr, cptr, i32)
+DEF_HELPER_FLAGS_3(gvec_vctz8, TCG_CALL_NO_RWG, void, ptr, cptr, i32)
+DEF_HELPER_FLAGS_3(gvec_vctz16, TCG_CALL_NO_RWG, void, ptr, cptr, 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 be3c07aafb..a355b7f62f 100644
--- a/target/s390x/insn-data.def
+++ b/target/s390x/insn-data.def
@@ -1086,6 +1086,8 @@ 
     E(0xe7f9, VCHL,    VRR_b, V,   0, 0, 0, 0, vc, 0, TCG_COND_GTU, IF_VEC)
 /* VECTOR COUNT LEADING ZEROS */
     F(0xe753, VCLZ,    VRR_a, V,   0, 0, 0, 0, vclz, 0, IF_VEC)
+/* VECTOR COUNT TRAILING ZEROS */
+    F(0xe752, VCTZ,    VRR_a, V,   0, 0, 0, 0, vctz, 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 299924a7cc..23d5870dc5 100644
--- a/target/s390x/translate_vx.inc.c
+++ b/target/s390x/translate_vx.inc.c
@@ -1406,3 +1406,31 @@  static DisasJumpType op_vclz(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_ctz_i32(TCGv_i32 d, TCGv_i32 a)
+{
+    tcg_gen_ctzi_i32(d, a, 32);
+}
+
+static void gen_ctz_i64(TCGv_i64 d, TCGv_i64 a)
+{
+    tcg_gen_ctzi_i64(d, a, 64);
+}
+
+static DisasJumpType op_vctz(DisasContext *s, DisasOps *o)
+{
+    const uint8_t es = get_field(s->fields, m3);
+    static const GVecGen2 g[4] = {
+        { .fno = gen_helper_gvec_vctz8, },
+        { .fno = gen_helper_gvec_vctz16, },
+        { .fni4 = gen_ctz_i32, },
+        { .fni8 = gen_ctz_i64, },
+    };
+
+    if (es > ES_64) {
+        gen_program_exception(s, PGM_SPECIFICATION);
+        return DISAS_NORETURN;
+    }
+    gen_gvec_2(get_field(s->fields, v1), get_field(s->fields, v2), &g[es]);
+    return DISAS_NEXT;
+}
diff --git a/target/s390x/vec_int_helper.c b/target/s390x/vec_int_helper.c
index 366962cfbe..c589f92765 100644
--- a/target/s390x/vec_int_helper.c
+++ b/target/s390x/vec_int_helper.c
@@ -107,3 +107,17 @@  void HELPER(gvec_vclz##BITS)(void *v1, const void *v2, uint32_t desc)          \
 }
 DEF_VCLZ(8)
 DEF_VCLZ(16)
+
+#define DEF_VCTZ(BITS)                                                         \
+void HELPER(gvec_vctz##BITS)(void *v1, const void *v2, 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, ctz32(a));                         \
+    }                                                                          \
+}
+DEF_VCTZ(8)
+DEF_VCTZ(16)