[Qemu-devel] [PATCH v2 57/67] target/arm: Implement SVE floating-point compare vectors

[Richard Henderson]

Signed-off-by: Richard Henderson <address@hidden>
---
 target/arm/helper-sve.h    | 49 +++++++++++++++++++++++++++++++++++
 target/arm/sve_helper.c    | 64 ++++++++++++++++++++++++++++++++++++++++++++++
 target/arm/translate-sve.c | 41 +++++++++++++++++++++++++++++
 target/arm/sve.decode      | 11 ++++++++
 4 files changed, 165 insertions(+)

diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h
index 3cb7ab9ef2..30373e3fc7 100644
--- a/target/arm/helper-sve.h
+++ b/target/arm/helper-sve.h
@@ -839,6 +839,55 @@ DEF_HELPER_FLAGS_5(sve_ucvt_ds, TCG_CALL_NO_RWG,
 DEF_HELPER_FLAGS_5(sve_ucvt_dd, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, i32)
 
+DEF_HELPER_FLAGS_6(sve_fcmge_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sve_fcmge_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sve_fcmge_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_6(sve_fcmgt_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sve_fcmgt_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sve_fcmgt_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_6(sve_fcmeq_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sve_fcmeq_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sve_fcmeq_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_6(sve_fcmne_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sve_fcmne_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sve_fcmne_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_6(sve_fcmuo_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sve_fcmuo_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sve_fcmuo_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_6(sve_facge_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sve_facge_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sve_facge_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_6(sve_facgt_h, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sve_facgt_s, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_6(sve_facgt_d, TCG_CALL_NO_RWG,
+                   void, ptr, ptr, ptr, ptr, ptr, i32)
+
 DEF_HELPER_FLAGS_3(sve_fmla_zpzzz_h, TCG_CALL_NO_RWG, void, env, ptr, i32)
 DEF_HELPER_FLAGS_3(sve_fmla_zpzzz_s, TCG_CALL_NO_RWG, void, env, ptr, i32)
 DEF_HELPER_FLAGS_3(sve_fmla_zpzzz_d, TCG_CALL_NO_RWG, void, env, ptr, i32)
diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c
index 4edd3d4367..ace613684d 100644
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -3100,6 +3100,70 @@ DO_FMLA(sve_fnmls_zpzzz_d, 64, , 1, 1)
 
 #undef DO_FMLA
 
+/* Two operand floating-point comparison controlled by a predicate.
+ * Unlike the integer version, we are not allowed to optimistically
+ * compare operands, since the comparison may have side effects wrt
+ * the FPSR.
+ */
+#define DO_FPCMP_PPZZ(NAME, TYPE, H, OP)                                \
+void HELPER(NAME)(void *vd, void *vn, void *vm, void *vg,               \
+                  void *status, uint32_t desc)                          \
+{                                                                       \
+    intptr_t opr_sz = simd_oprsz(desc);                                 \
+    intptr_t i = opr_sz, j = ((opr_sz - 1) & -64) >> 3;                 \
+    do {                                                                \
+        uint64_t out = 0;                                               \
+        uint64_t pg = *(uint64_t *)(vg + j);                            \
+        do {                                                            \
+            i -= sizeof(TYPE), out <<= sizeof(TYPE);                    \
+            if ((pg >> (i & 63)) & 1) {                                 \
+                TYPE nn = *(TYPE *)(vn + H(i));                         \
+                TYPE mm = *(TYPE *)(vm + H(i));                         \
+                out |= OP(TYPE, nn, mm, status);                        \
+            }                                                           \
+        } while (i & 63);                                               \
+        *(uint64_t *)(vd + j) = out;                                    \
+        j -= 8;                                                         \
+    } while (i > 0);                                                    \
+}
+
+#define DO_FPCMP_PPZZ_H(NAME, OP) \
+    DO_FPCMP_PPZZ(NAME##_h, float16, H1_2, OP)
+#define DO_FPCMP_PPZZ_S(NAME, OP) \
+    DO_FPCMP_PPZZ(NAME##_s, float32, H1_4, OP)
+#define DO_FPCMP_PPZZ_D(NAME, OP) \
+    DO_FPCMP_PPZZ(NAME##_d, float64,     , OP)
+
+#define DO_FPCMP_PPZZ_ALL(NAME, OP) \
+    DO_FPCMP_PPZZ_H(NAME, OP)   \
+    DO_FPCMP_PPZZ_S(NAME, OP)   \
+    DO_FPCMP_PPZZ_D(NAME, OP)
+
+#define DO_FCMGE(TYPE, X, Y, ST)  TYPE##_compare(Y, X, ST) <= 0
+#define DO_FCMGT(TYPE, X, Y, ST)  TYPE##_compare(Y, X, ST) < 0
+#define DO_FCMEQ(TYPE, X, Y, ST)  TYPE##_compare_quiet(X, Y, ST) == 0
+#define DO_FCMNE(TYPE, X, Y, ST)  TYPE##_compare_quiet(X, Y, ST) != 0
+#define DO_FCMUO(TYPE, X, Y, ST)  \
+    TYPE##_compare_quiet(X, Y, ST) == float_relation_unordered
+#define DO_FACGE(TYPE, X, Y, ST)  \
+    TYPE##_compare(TYPE##_abs(Y), TYPE##_abs(X), ST) <= 0
+#define DO_FACGT(TYPE, X, Y, ST)  \
+    TYPE##_compare(TYPE##_abs(Y), TYPE##_abs(X), ST) < 0
+
+DO_FPCMP_PPZZ_ALL(sve_fcmge, DO_FCMGE)
+DO_FPCMP_PPZZ_ALL(sve_fcmgt, DO_FCMGT)
+DO_FPCMP_PPZZ_ALL(sve_fcmeq, DO_FCMEQ)
+DO_FPCMP_PPZZ_ALL(sve_fcmne, DO_FCMNE)
+DO_FPCMP_PPZZ_ALL(sve_fcmuo, DO_FCMUO)
+DO_FPCMP_PPZZ_ALL(sve_facge, DO_FACGE)
+DO_FPCMP_PPZZ_ALL(sve_facgt, DO_FACGT)
+
+#undef DO_FPCMP_PPZZ_ALL
+#undef DO_FPCMP_PPZZ_D
+#undef DO_FPCMP_PPZZ_S
+#undef DO_FPCMP_PPZZ_H
+#undef DO_FPCMP_PPZZ
+
 /*
  * Load contiguous data, protected by a governing predicate.
  */
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index 0241e8e707..8fcb9dd2be 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -3265,6 +3265,47 @@ DO_FP3(FMULX, fmulx)
 
 #undef DO_FP3
 
+static void do_fp_cmp(DisasContext *s, arg_rprr_esz *a,
+                      gen_helper_gvec_4_ptr *fn)
+{
+    unsigned vsz = vec_full_reg_size(s);
+    TCGv_ptr status;
+
+    if (fn == NULL) {
+        unallocated_encoding(s);
+        return;
+    }
+
+    status = get_fpstatus_ptr(a->esz == MO_16);
+    tcg_gen_gvec_4_ptr(pred_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);
+}
+
+#define DO_FPCMP(NAME, name) \
+static void trans_##NAME##_ppzz(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          \
+    };                                                                \
+    do_fp_cmp(s, a, fns[a->esz]);                                     \
+}
+
+DO_FPCMP(FCMGE, fcmge)
+DO_FPCMP(FCMGT, fcmgt)
+DO_FPCMP(FCMEQ, fcmeq)
+DO_FPCMP(FCMNE, fcmne)
+DO_FPCMP(FCMUO, fcmuo)
+DO_FPCMP(FACGE, facge)
+DO_FPCMP(FACGT, facgt)
+
+#undef DO_FPCMP
+
 typedef void gen_helper_sve_fmla(TCGv_env, TCGv_ptr, TCGv_i32);
 
 static void do_fmla(DisasContext *s, arg_rprrr_esz *a, gen_helper_sve_fmla *fn)
diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index 6ccb4289fc..f82cef2d7e 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -321,6 +321,17 @@ UXTH               00000100 .. 010 011 101 ... ..... ..... 
        @rd_pg_rn
 SXTW           00000100 .. 010 100 101 ... ..... .....         @rd_pg_rn
 UXTW           00000100 .. 010 101 101 ... ..... .....         @rd_pg_rn
 
+### SVE Floating Point Compare - Vectors Group
+
+# SVE floating-point compare vectors
+FCMGE_ppzz     01100101 .. 0 ..... 010 ... ..... 0 ....        @pd_pg_rn_rm
+FCMGT_ppzz     01100101 .. 0 ..... 010 ... ..... 1 ....        @pd_pg_rn_rm
+FCMEQ_ppzz     01100101 .. 0 ..... 011 ... ..... 0 ....        @pd_pg_rn_rm
+FCMNE_ppzz     01100101 .. 0 ..... 011 ... ..... 1 ....        @pd_pg_rn_rm
+FCMUO_ppzz     01100101 .. 0 ..... 110 ... ..... 0 ....        @pd_pg_rn_rm
+FACGE_ppzz     01100101 .. 0 ..... 110 ... ..... 1 ....        @pd_pg_rn_rm
+FACGT_ppzz     01100101 .. 0 ..... 111 ... ..... 1 ....        @pd_pg_rn_rm
+
 ### SVE Integer Multiply-Add Group
 
 # SVE integer multiply-add writing addend (predicated)
-- 
2.14.3