[Qemu-devel] [PATCH v5 06/35] target/arm: Implement SVE floating-point arithmetic (predicated)

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

Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
 target/arm/helper-sve.h    | 77 +++++++++++++++++++++++++++++++++
 target/arm/sve_helper.c    | 89 ++++++++++++++++++++++++++++++++++++++
 target/arm/translate-sve.c | 46 ++++++++++++++++++++
 target/arm/sve.decode      | 17 ++++++++
 4 files changed, 229 insertions(+)

diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h
index 185112e1d2..4097b55f0e 100644
--- a/target/arm/helper-sve.h
+++ b/target/arm/helper-sve.h
@@ -720,6 +720,83 @@ 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_6(sve_fadd_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sve_fadd_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sve_fadd_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_6(sve_fsub_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sve_fsub_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sve_fsub_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_6(sve_fmul_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sve_fmul_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sve_fmul_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_6(sve_fdiv_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sve_fdiv_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sve_fdiv_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_6(sve_fmin_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sve_fmin_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sve_fmin_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_6(sve_fmax_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sve_fmax_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sve_fmax_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_6(sve_fminnum_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sve_fminnum_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sve_fminnum_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_6(sve_fmaxnum_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sve_fmaxnum_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sve_fmaxnum_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_6(sve_fabd_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sve_fabd_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sve_fabd_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_6(sve_fscalbn_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sve_fscalbn_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sve_fscalbn_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_6(sve_fmulx_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sve_fmulx_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sve_fmulx_d, TCG_CALL_NO_RWG,
+                   void, ptr, 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,
diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c
index a2f034820a..6bf30a3e66 100644
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -2811,6 +2811,95 @@ uint32_t HELPER(sve_while)(void *vd, uint32_t count, uint32_t pred_desc)
     return predtest_ones(d, oprsz, esz_mask);
 }
 
+/* Fully general three-operand expander, controlled by a predicate,
+ * With the extra float_status parameter.
+ */
+#define DO_ZPZZ_FP(NAME, TYPE, H, OP)                           \
+void HELPER(NAME)(void *vd, void *vn, void *vm, 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 mm = *(TYPE *)(vm + H(i));                 \
+                *(TYPE *)(vd + H(i)) = OP(nn, mm, status);      \
+            }                                                   \
+        } while (i & 63);                                       \
+    } while (i != 0);                                           \
+}
+
+DO_ZPZZ_FP(sve_fadd_h, uint16_t, H1_2, float16_add)
+DO_ZPZZ_FP(sve_fadd_s, uint32_t, H1_4, float32_add)
+DO_ZPZZ_FP(sve_fadd_d, uint64_t,     , float64_add)
+
+DO_ZPZZ_FP(sve_fsub_h, uint16_t, H1_2, float16_sub)
+DO_ZPZZ_FP(sve_fsub_s, uint32_t, H1_4, float32_sub)
+DO_ZPZZ_FP(sve_fsub_d, uint64_t,     , float64_sub)
+
+DO_ZPZZ_FP(sve_fmul_h, uint16_t, H1_2, float16_mul)
+DO_ZPZZ_FP(sve_fmul_s, uint32_t, H1_4, float32_mul)
+DO_ZPZZ_FP(sve_fmul_d, uint64_t,     , float64_mul)
+
+DO_ZPZZ_FP(sve_fdiv_h, uint16_t, H1_2, float16_div)
+DO_ZPZZ_FP(sve_fdiv_s, uint32_t, H1_4, float32_div)
+DO_ZPZZ_FP(sve_fdiv_d, uint64_t,     , float64_div)
+
+DO_ZPZZ_FP(sve_fmin_h, uint16_t, H1_2, float16_min)
+DO_ZPZZ_FP(sve_fmin_s, uint32_t, H1_4, float32_min)
+DO_ZPZZ_FP(sve_fmin_d, uint64_t,     , float64_min)
+
+DO_ZPZZ_FP(sve_fmax_h, uint16_t, H1_2, float16_max)
+DO_ZPZZ_FP(sve_fmax_s, uint32_t, H1_4, float32_max)
+DO_ZPZZ_FP(sve_fmax_d, uint64_t,     , float64_max)
+
+DO_ZPZZ_FP(sve_fminnum_h, uint16_t, H1_2, float16_minnum)
+DO_ZPZZ_FP(sve_fminnum_s, uint32_t, H1_4, float32_minnum)
+DO_ZPZZ_FP(sve_fminnum_d, uint64_t,     , float64_minnum)
+
+DO_ZPZZ_FP(sve_fmaxnum_h, uint16_t, H1_2, float16_maxnum)
+DO_ZPZZ_FP(sve_fmaxnum_s, uint32_t, H1_4, float32_maxnum)
+DO_ZPZZ_FP(sve_fmaxnum_d, uint64_t,     , float64_maxnum)
+
+static inline float16 abd_h(float16 a, float16 b, float_status *s)
+{
+    return float16_abs(float16_sub(a, b, s));
+}
+
+static inline float32 abd_s(float32 a, float32 b, float_status *s)
+{
+    return float32_abs(float32_sub(a, b, s));
+}
+
+static inline float64 abd_d(float64 a, float64 b, float_status *s)
+{
+    return float64_abs(float64_sub(a, b, s));
+}
+
+DO_ZPZZ_FP(sve_fabd_h, uint16_t, H1_2, abd_h)
+DO_ZPZZ_FP(sve_fabd_s, uint32_t, H1_4, abd_s)
+DO_ZPZZ_FP(sve_fabd_d, uint64_t,     , abd_d)
+
+static inline float64 scalbn_d(float64 a, int64_t b, float_status *s)
+{
+    int b_int = MIN(MAX(b, INT_MIN), INT_MAX);
+    return float64_scalbn(a, b_int, s);
+}
+
+DO_ZPZZ_FP(sve_fscalbn_h, int16_t, H1_2, float16_scalbn)
+DO_ZPZZ_FP(sve_fscalbn_s, int32_t, H1_4, float32_scalbn)
+DO_ZPZZ_FP(sve_fscalbn_d, int64_t,     , scalbn_d)
+
+DO_ZPZZ_FP(sve_fmulx_h, uint16_t, H1_2, helper_advsimd_mulxh)
+DO_ZPZZ_FP(sve_fmulx_s, uint32_t, H1_4, helper_vfp_mulxs)
+DO_ZPZZ_FP(sve_fmulx_d, uint64_t,     , helper_vfp_mulxd)
+
+#undef DO_ZPZZ_FP
+
 /* Fully general two-operand expander, controlled by a predicate,
  * With the extra float_status parameter.
  */
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index 7639e589f5..4df5360da9 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -3425,6 +3425,52 @@ DO_FP3(FRSQRTS, rsqrts)
 
 #undef DO_FP3
 
+/*
+ *** SVE Floating Point Arithmetic - Predicated Group
+ */
+
+static bool do_zpzz_fp(DisasContext *s, arg_rprr_esz *a,
+                       gen_helper_gvec_4_ptr *fn)
+{
+    if (fn == NULL) {
+        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),
+                           pred_full_reg_offset(s, a->pg),
+                           status, vsz, vsz, 0, fn);
+        tcg_temp_free_ptr(status);
+    }
+    return true;
+}
+
+#define DO_FP3(NAME, name) \
+static bool trans_##NAME(DisasContext *s, arg_rprr_esz *a, uint32_t insn) \
+{                                                                   \
+    static gen_helper_gvec_4_ptr * const fns[4] = {                 \
+        NULL, gen_helper_sve_##name##_h,                            \
+        gen_helper_sve_##name##_s, gen_helper_sve_##name##_d        \
+    };                                                              \
+    return do_zpzz_fp(s, a, fns[a->esz]);                           \
+}
+
+DO_FP3(FADD_zpzz, fadd)
+DO_FP3(FSUB_zpzz, fsub)
+DO_FP3(FMUL_zpzz, fmul)
+DO_FP3(FMIN_zpzz, fmin)
+DO_FP3(FMAX_zpzz, fmax)
+DO_FP3(FMINNM_zpzz, fminnum)
+DO_FP3(FMAXNM_zpzz, fmaxnum)
+DO_FP3(FABD, fabd)
+DO_FP3(FSCALE, fscalbn)
+DO_FP3(FDIV, fdiv)
+DO_FP3(FMULX, fmulx)
+
+#undef DO_FP3
 
 /*
  *** SVE Floating Point Unary Operations Prediated Group
diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index 3abdb87cf5..636212a638 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -684,6 +684,23 @@ 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 Arithmetic Predicated Group
+
+# SVE floating-point arithmetic (predicated)
+FADD_zpzz       01100101 .. 00 0000 100 ... ..... .....    @rdn_pg_rm
+FSUB_zpzz       01100101 .. 00 0001 100 ... ..... .....    @rdn_pg_rm
+FMUL_zpzz       01100101 .. 00 0010 100 ... ..... .....    @rdn_pg_rm
+FSUB_zpzz       01100101 .. 00 0011 100 ... ..... .....    @rdm_pg_rn # FSUBR
+FMAXNM_zpzz     01100101 .. 00 0100 100 ... ..... .....    @rdn_pg_rm
+FMINNM_zpzz     01100101 .. 00 0101 100 ... ..... .....    @rdn_pg_rm
+FMAX_zpzz       01100101 .. 00 0110 100 ... ..... .....    @rdn_pg_rm
+FMIN_zpzz       01100101 .. 00 0111 100 ... ..... .....    @rdn_pg_rm
+FABD            01100101 .. 00 1000 100 ... ..... .....    @rdn_pg_rm
+FSCALE          01100101 .. 00 1001 100 ... ..... .....    @rdn_pg_rm
+FMULX           01100101 .. 00 1010 100 ... ..... .....    @rdn_pg_rm
+FDIV            01100101 .. 00 1100 100 ... ..... .....    @rdm_pg_rn # FDIVR
+FDIV            01100101 .. 00 1101 100 ... ..... .....    @rdn_pg_rm
+
 ### SVE FP Unary Operations Predicated Group
 
 # SVE integer convert to floating-point
-- 
2.17.1