[Qemu-devel] [PATCH v6 05/35] target/arm: Implement SVE integer convert to floating-point

[Richard Henderson <richard.henderson@linaro.org>]

Reviewed-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/arm/helper-sve.h    | 30 +++++++++++++
 target/arm/sve_helper.c    | 38 ++++++++++++++++
 target/arm/translate-sve.c | 90 ++++++++++++++++++++++++++++++++++++++
 target/arm/sve.decode      | 22 ++++++++++
 4 files changed, 180 insertions(+)

diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h
index b768128951..185112e1d2 100644
--- a/target/arm/helper-sve.h
+++ b/target/arm/helper-sve.h
@@ -720,6 +720,36 @@ DEF_HELPER_FLAGS_5(gvec_rsqrts_s, TCG_CALL_NO_RWG,
 DEF_HELPER_FLAGS_5(gvec_rsqrts_d, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, i32)
 
+DEF_HELPER_FLAGS_5(sve_scvt_hh, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve_scvt_sh, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve_scvt_dh, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve_scvt_ss, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve_scvt_sd, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve_scvt_ds, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve_scvt_dd, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(sve_ucvt_hh, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve_ucvt_sh, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve_ucvt_dh, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve_ucvt_ss, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve_ucvt_sd, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve_ucvt_ds, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve_ucvt_dd, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, i32)
+
 DEF_HELPER_FLAGS_4(sve_ld1bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
 DEF_HELPER_FLAGS_4(sve_ld2bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
 DEF_HELPER_FLAGS_4(sve_ld3bb_r, TCG_CALL_NO_WG, void, env, ptr, tl, i32)
diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c
index bd874e6fa2..031bec22df 100644
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -2811,6 +2811,44 @@ uint32_t HELPER(sve_while)(void *vd, uint32_t count, uint32_t pred_desc)
     return predtest_ones(d, oprsz, esz_mask);
 }
 
+/* Fully general two-operand expander, controlled by a predicate,
+ * With the extra float_status parameter.
+ */
+#define DO_ZPZ_FP(NAME, TYPE, H, OP)                                  \
+void HELPER(NAME)(void *vd, void *vn, void *vg, void *status, uint32_t desc) \
+{                                                                     \
+    intptr_t i = simd_oprsz(desc);                                    \
+    uint64_t *g = vg;                                                 \
+    do {                                                              \
+        uint64_t pg = g[(i - 1) >> 6];                                \
+        do {                                                          \
+            i -= sizeof(TYPE);                                        \
+            if (likely((pg >> (i & 63)) & 1)) {                       \
+                TYPE nn = *(TYPE *)(vn + H(i));                       \
+                *(TYPE *)(vd + H(i)) = OP(nn, status);                \
+            }                                                         \
+        } while (i & 63);                                             \
+    } while (i != 0);                                                 \
+}
+
+DO_ZPZ_FP(sve_scvt_hh, uint16_t, H1_2, int16_to_float16)
+DO_ZPZ_FP(sve_scvt_sh, uint32_t, H1_4, int32_to_float16)
+DO_ZPZ_FP(sve_scvt_ss, uint32_t, H1_4, int32_to_float32)
+DO_ZPZ_FP(sve_scvt_sd, uint64_t,     , int32_to_float64)
+DO_ZPZ_FP(sve_scvt_dh, uint64_t,     , int64_to_float16)
+DO_ZPZ_FP(sve_scvt_ds, uint64_t,     , int64_to_float32)
+DO_ZPZ_FP(sve_scvt_dd, uint64_t,     , int64_to_float64)
+
+DO_ZPZ_FP(sve_ucvt_hh, uint16_t, H1_2, uint16_to_float16)
+DO_ZPZ_FP(sve_ucvt_sh, uint32_t, H1_4, uint32_to_float16)
+DO_ZPZ_FP(sve_ucvt_ss, uint32_t, H1_4, uint32_to_float32)
+DO_ZPZ_FP(sve_ucvt_sd, uint64_t,     , uint32_to_float64)
+DO_ZPZ_FP(sve_ucvt_dh, uint64_t,     , uint64_to_float16)
+DO_ZPZ_FP(sve_ucvt_ds, uint64_t,     , uint64_to_float32)
+DO_ZPZ_FP(sve_ucvt_dd, uint64_t,     , uint64_to_float64)
+
+#undef DO_ZPZ_FP
+
 /*
  * Load contiguous data, protected by a governing predicate.
  */
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index 83de87ee0e..7639e589f5 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -3425,6 +3425,96 @@ DO_FP3(FRSQRTS, rsqrts)
 
 #undef DO_FP3
 
+
+/*
+ *** SVE Floating Point Unary Operations Prediated Group
+ */
+
+static bool do_zpz_ptr(DisasContext *s, int rd, int rn, int pg,
+                       bool is_fp16, gen_helper_gvec_3_ptr *fn)
+{
+    if (sve_access_check(s)) {
+        unsigned vsz = vec_full_reg_size(s);
+        TCGv_ptr status = get_fpstatus_ptr(is_fp16);
+        tcg_gen_gvec_3_ptr(vec_full_reg_offset(s, rd),
+                           vec_full_reg_offset(s, rn),
+                           pred_full_reg_offset(s, pg),
+                           status, vsz, vsz, 0, fn);
+        tcg_temp_free_ptr(status);
+    }
+    return true;
+}
+
+static bool trans_SCVTF_hh(DisasContext *s, arg_rpr_esz *a, uint32_t insn)
+{
+    return do_zpz_ptr(s, a->rd, a->rn, a->pg, true, gen_helper_sve_scvt_hh);
+}
+
+static bool trans_SCVTF_sh(DisasContext *s, arg_rpr_esz *a, uint32_t insn)
+{
+    return do_zpz_ptr(s, a->rd, a->rn, a->pg, true, gen_helper_sve_scvt_sh);
+}
+
+static bool trans_SCVTF_dh(DisasContext *s, arg_rpr_esz *a, uint32_t insn)
+{
+    return do_zpz_ptr(s, a->rd, a->rn, a->pg, true, gen_helper_sve_scvt_dh);
+}
+
+static bool trans_SCVTF_ss(DisasContext *s, arg_rpr_esz *a, uint32_t insn)
+{
+    return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve_scvt_ss);
+}
+
+static bool trans_SCVTF_ds(DisasContext *s, arg_rpr_esz *a, uint32_t insn)
+{
+    return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve_scvt_ds);
+}
+
+static bool trans_SCVTF_sd(DisasContext *s, arg_rpr_esz *a, uint32_t insn)
+{
+    return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve_scvt_sd);
+}
+
+static bool trans_SCVTF_dd(DisasContext *s, arg_rpr_esz *a, uint32_t insn)
+{
+    return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve_scvt_dd);
+}
+
+static bool trans_UCVTF_hh(DisasContext *s, arg_rpr_esz *a, uint32_t insn)
+{
+    return do_zpz_ptr(s, a->rd, a->rn, a->pg, true, gen_helper_sve_ucvt_hh);
+}
+
+static bool trans_UCVTF_sh(DisasContext *s, arg_rpr_esz *a, uint32_t insn)
+{
+    return do_zpz_ptr(s, a->rd, a->rn, a->pg, true, gen_helper_sve_ucvt_sh);
+}
+
+static bool trans_UCVTF_dh(DisasContext *s, arg_rpr_esz *a, uint32_t insn)
+{
+    return do_zpz_ptr(s, a->rd, a->rn, a->pg, true, gen_helper_sve_ucvt_dh);
+}
+
+static bool trans_UCVTF_ss(DisasContext *s, arg_rpr_esz *a, uint32_t insn)
+{
+    return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve_ucvt_ss);
+}
+
+static bool trans_UCVTF_ds(DisasContext *s, arg_rpr_esz *a, uint32_t insn)
+{
+    return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve_ucvt_ds);
+}
+
+static bool trans_UCVTF_sd(DisasContext *s, arg_rpr_esz *a, uint32_t insn)
+{
+    return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve_ucvt_sd);
+}
+
+static bool trans_UCVTF_dd(DisasContext *s, arg_rpr_esz *a, uint32_t insn)
+{
+    return do_zpz_ptr(s, a->rd, a->rn, a->pg, false, gen_helper_sve_ucvt_dd);
+}
+
 /*
  *** SVE Memory - 32-bit Gather and Unsized Contiguous Group
  */
diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index 606c4f623c..3abdb87cf5 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -133,6 +133,9 @@
 @rd_pg_rn       ........ esz:2 ... ... ... pg:3 rn:5 rd:5       &rpr_esz
 @rd_pg4_pn      ........ esz:2 ... ... .. pg:4 . rn:4 rd:5      &rpr_esz
 
+# One register operand, with governing predicate, no vector element size
+@rd_pg_rn_e0    ........ .. ... ... ... pg:3 rn:5 rd:5          &rpr_esz esz=0
+
 # Two register operands with a 6-bit signed immediate.
 @rd_rn_i6       ........ ... rn:5 ..... imm:s6 rd:5             &rri
 
@@ -681,6 +684,25 @@ FTSMUL          01100101 .. 0 ..... 000 011 ..... .....         @rd_rn_rm
 FRECPS          01100101 .. 0 ..... 000 110 ..... .....         @rd_rn_rm
 FRSQRTS         01100101 .. 0 ..... 000 111 ..... .....         @rd_rn_rm
 
+### SVE FP Unary Operations Predicated Group
+
+# SVE integer convert to floating-point
+SCVTF_hh        01100101 01 010 01 0 101 ... ..... .....        @rd_pg_rn_e0
+SCVTF_sh        01100101 01 010 10 0 101 ... ..... .....        @rd_pg_rn_e0
+SCVTF_dh        01100101 01 010 11 0 101 ... ..... .....        @rd_pg_rn_e0
+SCVTF_ss        01100101 10 010 10 0 101 ... ..... .....        @rd_pg_rn_e0
+SCVTF_sd        01100101 11 010 00 0 101 ... ..... .....        @rd_pg_rn_e0
+SCVTF_ds        01100101 11 010 10 0 101 ... ..... .....        @rd_pg_rn_e0
+SCVTF_dd        01100101 11 010 11 0 101 ... ..... .....        @rd_pg_rn_e0
+
+UCVTF_hh        01100101 01 010 01 1 101 ... ..... .....        @rd_pg_rn_e0
+UCVTF_sh        01100101 01 010 10 1 101 ... ..... .....        @rd_pg_rn_e0
+UCVTF_dh        01100101 01 010 11 1 101 ... ..... .....        @rd_pg_rn_e0
+UCVTF_ss        01100101 10 010 10 1 101 ... ..... .....        @rd_pg_rn_e0
+UCVTF_sd        01100101 11 010 00 1 101 ... ..... .....        @rd_pg_rn_e0
+UCVTF_ds        01100101 11 010 10 1 101 ... ..... .....        @rd_pg_rn_e0
+UCVTF_dd        01100101 11 010 11 1 101 ... ..... .....        @rd_pg_rn_e0
+
 ### SVE Memory - 32-bit Gather and Unsized Contiguous Group
 
 # SVE load predicate register
-- 
2.17.1