[PATCH RFC] target/arm: Implement SVE2 fp multiply-add long

[Stephen Long]

Implements FMLALB, FMLALT, FMLSLB, FMLSLT

Signed-off-by: Stephen Long <address@hidden>
---
 target/arm/helper-sve.h    |  5 ++++
 target/arm/sve.decode      |  6 ++++
 target/arm/sve_helper.c    | 27 ++++++++++++++++++
 target/arm/translate-sve.c | 58 ++++++++++++++++++++++++++++++++++++++
 4 files changed, 96 insertions(+)

diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h
index 0a62eef94e..803df6e973 100644
--- a/target/arm/helper-sve.h
+++ b/target/arm/helper-sve.h
@@ -2731,3 +2731,8 @@ DEF_HELPER_FLAGS_5(sve2_sqrdcmlah_idx_h, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_5(sve2_sqrdcmlah_idx_s, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_6(sve2_fmlal_zzzw_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sve2_fmlsl_zzzw_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, i32)
diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index 3cf824bac5..89554fe46c 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -1568,3 +1568,9 @@ SM4E            01000101 00 10001 1 11100 0 ..... .....  
@rdn_rm_e0
 # SVE2 crypto constructive binary operations
 SM4EKEY         01000101 00 1 ..... 11110 0 ..... .....  @rd_rn_rm_e0
 RAX1            01000101 00 1 ..... 11110 1 ..... .....  @rd_rn_rm_e0
+
+### SVE2 floating-point multiply-add long
+FMLALB_zzzw     01100100 .. 1 ..... 10 0 00 0 ..... .....  @rda_rn_rm
+FMLALT_zzzw     01100100 .. 1 ..... 10 0 00 1 ..... .....  @rda_rn_rm
+FMLSLB_zzzw     01100100 .. 1 ..... 10 1 00 0 ..... .....  @rda_rn_rm
+FMLSLT_zzzw     01100100 .. 1 ..... 10 1 00 1 ..... .....  @rda_rn_rm
diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c
index aa94df302a..c3192aa223 100644
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -7622,3 +7622,30 @@ void HELPER(fmmla_d)(void *vd, void *va, void *vn, void 
*vm,
         d[3] = float64_add(a[3], float64_add(p0, p1, status), status);
     }
 }
+
+void HELPER(sve2_fmlal_zzzw_s)(void *vd, void *vn, void *vm, void *va,
+                  void *status, uint32_t desc)
+{
+    intptr_t i, opr_sz = simd_oprsz(desc);
+    intptr_t sel1 = simd_data(desc) * sizeof(float16);
+    for (i = 0; i < opr_sz; i += sizeof(float32)) {
+        float32 nn = *(float16 *)(vn + H1_2(i + sel1));
+        float32 mm = *(float16 *)(vm + H1_2(i + sel1));
+        float32 aa = *(float32 *)(va + H1_4(i));
+        *(float32 *)(vd + H1_4(i)) = float32_muladd(nn, mm, aa, 0, status);
+    }
+}
+
+void HELPER(sve2_fmlsl_zzzw_s)(void *vd, void *vn, void *vm, void *va,
+                  void *status, uint32_t desc)
+{
+    intptr_t i, opr_sz = simd_oprsz(desc);
+    intptr_t sel1 = simd_data(desc) * sizeof(float16);
+    for (i = 0; i < opr_sz; i += sizeof(float32)) {
+        float32 nn = *(float16 *)(vn + H1_2(i + sel1));
+        float32 mm = *(float16 *)(vm + H1_2(i + sel1));
+        float32 aa = *(float32 *)(va + H1_4(i));
+        nn = float32_set_sign(nn, float32_is_neg(nn) ^ 1);
+        *(float32 *)(vd + H1_4(i)) = float32_muladd(nn, mm, aa, 0, status);
+    }
+}
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index a8e57ea5f4..0dc35b601a 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -8253,3 +8253,61 @@ static bool trans_RAX1(DisasContext *s, arg_rrr_esz *a)
     }
     return true;
 }
+
+/*
+ * SVE2 Floating Point Multiply-Add Vector Group
+ */
+static bool do_sve2_zzzz_fp(DisasContext *s, arg_rrrr_esz *a,
+                       gen_helper_gvec_4_ptr *fn, int data)
+{
+    if (fn == NULL || !dc_isar_feature(aa64_sve2, s)) {
+        return false;
+    }
+    if (sve_access_check(s)) {
+        unsigned vsz = vec_full_reg_size(s);
+        TCGv_ptr status = get_fpstatus_ptr(a->esz == MO_16);
+        tcg_gen_gvec_4_ptr(vec_full_reg_offset(s, a->rd),
+                           vec_full_reg_offset(s, a->rn),
+                           vec_full_reg_offset(s, a->rm),
+                           vec_full_reg_offset(s, a->ra),
+                           status, vsz, vsz, data, fn);
+        tcg_temp_free_ptr(status);
+    }
+    return true;
+}
+
+static bool do_sve2_fmlal_zzzw(DisasContext *s, arg_rrrr_esz *a, bool sel)
+{
+    if (!dc_isar_feature(aa64_sve2, s) || a->esz != 2) {
+        return false;
+    }
+    return do_sve2_zzzz_fp(s, a, gen_helper_sve2_fmlal_zzzw_s, sel);
+}
+
+static bool trans_FMLALB_zzzw(DisasContext *s, arg_rrrr_esz *a)
+{
+    return do_sve2_fmlal_zzzw(s, a, false);
+}
+
+static bool trans_FMLALT_zzzw(DisasContext *s, arg_rrrr_esz *a)
+{
+    return do_sve2_fmlal_zzzw(s, a, true);
+}
+
+static bool do_sve2_fmlsl_zzzw(DisasContext *s, arg_rrrr_esz *a, bool sel)
+{
+    if (!dc_isar_feature(aa64_sve2, s) || a->esz != 2) {
+        return false;
+    }
+    return do_sve2_zzzz_fp(s, a, gen_helper_sve2_fmlsl_zzzw_s, sel);
+}
+
+static bool trans_FMLSLB_zzzw(DisasContext *s, arg_rrrr_esz *a)
+{
+    return do_sve2_fmlsl_zzzw(s, a, false);
+}
+
+static bool trans_FMLSLT_zzzw(DisasContext *s, arg_rrrr_esz *a)
+{
+    return do_sve2_fmlsl_zzzw(s, a, true);
+}
-- 
2.17.1