[PATCH v3 36/81] target/arm: Implement SVE2 MATCH, NMATCH

[Richard Henderson]

From: Stephen Long <steplong@quicinc.com>

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Stephen Long <steplong@quicinc.com>
Message-Id: <20200415145915.2859-1-steplong@quicinc.com>
[rth: Expanded comment for do_match2]
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
---
v2: Apply esz_mask to input pg to fix output flags.
---
 target/arm/helper-sve.h    | 10 ++++++
 target/arm/sve.decode      |  5 +++
 target/arm/sve_helper.c    | 64 ++++++++++++++++++++++++++++++++++++++
 target/arm/translate-sve.c | 22 +++++++++++++
 4 files changed, 101 insertions(+)

diff --git a/target/arm/helper-sve.h b/target/arm/helper-sve.h
index 923911ca21..7f53287f0d 100644
--- a/target/arm/helper-sve.h
+++ b/target/arm/helper-sve.h
@@ -2509,6 +2509,16 @@ DEF_HELPER_FLAGS_3(sve2_uqrshrnt_h, TCG_CALL_NO_RWG, 
void, ptr, ptr, i32)
 DEF_HELPER_FLAGS_3(sve2_uqrshrnt_s, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
 DEF_HELPER_FLAGS_3(sve2_uqrshrnt_d, TCG_CALL_NO_RWG, void, ptr, ptr, i32)
 
+DEF_HELPER_FLAGS_5(sve2_match_ppzz_b, TCG_CALL_NO_RWG,
+                   i32, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_match_ppzz_h, TCG_CALL_NO_RWG,
+                   i32, ptr, ptr, ptr, ptr, i32)
+
+DEF_HELPER_FLAGS_5(sve2_nmatch_ppzz_b, TCG_CALL_NO_RWG,
+                   i32, ptr, ptr, ptr, ptr, i32)
+DEF_HELPER_FLAGS_5(sve2_nmatch_ppzz_h, TCG_CALL_NO_RWG,
+                   i32, ptr, ptr, ptr, ptr, i32)
+
 DEF_HELPER_FLAGS_6(sve2_faddp_zpzz_h, TCG_CALL_NO_RWG,
                    void, ptr, ptr, ptr, ptr, ptr, i32)
 DEF_HELPER_FLAGS_6(sve2_faddp_zpzz_s, TCG_CALL_NO_RWG,
diff --git a/target/arm/sve.decode b/target/arm/sve.decode
index a50afd40c2..2207693d28 100644
--- a/target/arm/sve.decode
+++ b/target/arm/sve.decode
@@ -1320,6 +1320,11 @@ UQSHRNT         01000101 .. 1 ..... 00 1101 ..... .....  
@rd_rn_tszimm_shr
 UQRSHRNB        01000101 .. 1 ..... 00 1110 ..... .....  @rd_rn_tszimm_shr
 UQRSHRNT        01000101 .. 1 ..... 00 1111 ..... .....  @rd_rn_tszimm_shr
 
+### SVE2 Character Match
+
+MATCH           01000101 .. 1 ..... 100 ... ..... 0 .... @pd_pg_rn_rm
+NMATCH          01000101 .. 1 ..... 100 ... ..... 1 .... @pd_pg_rn_rm
+
 ## SVE2 floating-point pairwise operations
 
 FADDP           01100100 .. 010 00 0 100 ... ..... ..... @rdn_pg_rm
diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c
index aa7ff94812..139dea423f 100644
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -6875,3 +6875,67 @@ void HELPER(sve2_nbsl)(void *vd, void *vn, void *vm, 
void *vk, uint32_t desc)
         d[i] = ~((n[i] & k[i]) | (m[i] & ~k[i]));
     }
 }
+
+/*
+ * Returns true if m0 or m1 contains the low uint8_t/uint16_t in n.
+ * See hasless(v,1) from
+ *   https://graphics.stanford.edu/~seander/bithacks.html#ZeroInWord
+ */
+static inline bool do_match2(uint64_t n, uint64_t m0, uint64_t m1, int esz)
+{
+    int bits = 8 << esz;
+    uint64_t ones = dup_const(esz, 1);
+    uint64_t signs = ones << (bits - 1);
+    uint64_t cmp0, cmp1;
+
+    cmp1 = dup_const(esz, n);
+    cmp0 = cmp1 ^ m0;
+    cmp1 = cmp1 ^ m1;
+    cmp0 = (cmp0 - ones) & ~cmp0;
+    cmp1 = (cmp1 - ones) & ~cmp1;
+    return (cmp0 | cmp1) & signs;
+}
+
+static inline uint32_t do_match(void *vd, void *vn, void *vm, void *vg,
+                                uint32_t desc, int esz, bool nmatch)
+{
+    uint16_t esz_mask = pred_esz_masks[esz];
+    intptr_t opr_sz = simd_oprsz(desc);
+    uint32_t flags = PREDTEST_INIT;
+    intptr_t i, j, k;
+
+    for (i = 0; i < opr_sz; i += 16) {
+        uint64_t m0 = *(uint64_t *)(vm + i);
+        uint64_t m1 = *(uint64_t *)(vm + i + 8);
+        uint16_t pg = *(uint16_t *)(vg + H1_2(i >> 3)) & esz_mask;
+        uint16_t out = 0;
+
+        for (j = 0; j < 16; j += 8) {
+            uint64_t n = *(uint64_t *)(vn + i + j);
+
+            for (k = 0; k < 8; k += 1 << esz) {
+                if (pg & (1 << (j + k))) {
+                    bool o = do_match2(n >> (k * 8), m0, m1, esz);
+                    out |= (o ^ nmatch) << (j + k);
+                }
+            }
+        }
+        *(uint16_t *)(vd + H1_2(i >> 3)) = out;
+        flags = iter_predtest_fwd(out, pg, flags);
+    }
+    return flags;
+}
+
+#define DO_PPZZ_MATCH(NAME, ESZ, INV)                                         \
+uint32_t HELPER(NAME)(void *vd, void *vn, void *vm, void *vg, uint32_t desc)  \
+{                                                                             \
+    return do_match(vd, vn, vm, vg, desc, ESZ, INV);                          \
+}
+
+DO_PPZZ_MATCH(sve2_match_ppzz_b, MO_8, false)
+DO_PPZZ_MATCH(sve2_match_ppzz_h, MO_16, false)
+
+DO_PPZZ_MATCH(sve2_nmatch_ppzz_b, MO_8, true)
+DO_PPZZ_MATCH(sve2_nmatch_ppzz_h, MO_16, true)
+
+#undef DO_PPZZ_MATCH
diff --git a/target/arm/translate-sve.c b/target/arm/translate-sve.c
index 540e926c18..ffb7f5c8a0 100644
--- a/target/arm/translate-sve.c
+++ b/target/arm/translate-sve.c
@@ -7467,6 +7467,28 @@ static bool trans_UQRSHRNT(DisasContext *s, arg_rri_esz 
*a)
     return do_sve2_shr_narrow(s, a, ops);
 }
 
+static bool do_sve2_ppzz_flags(DisasContext *s, arg_rprr_esz *a,
+                               gen_helper_gvec_flags_4 *fn)
+{
+    if (!dc_isar_feature(aa64_sve2, s)) {
+        return false;
+    }
+    return do_ppzz_flags(s, a, fn);
+}
+
+#define DO_SVE2_PPZZ_MATCH(NAME, name)                                      \
+static bool trans_##NAME(DisasContext *s, arg_rprr_esz *a)                  \
+{                                                                           \
+    static gen_helper_gvec_flags_4 * const fns[4] = {                       \
+        gen_helper_sve2_##name##_ppzz_b, gen_helper_sve2_##name##_ppzz_h,   \
+        NULL,                            NULL                               \
+    };                                                                      \
+    return do_sve2_ppzz_flags(s, a, fns[a->esz]);                           \
+}
+
+DO_SVE2_PPZZ_MATCH(MATCH, match)
+DO_SVE2_PPZZ_MATCH(NMATCH, nmatch)
+
 static bool do_sve2_zpzz_fp(DisasContext *s, arg_rprr_esz *a,
                             gen_helper_gvec_4_ptr *fn)
 {
-- 
2.25.1