target/arm: Implement SVE2 MATCH, NMATCH

Reviewed-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Stephen Long <steplong@quicinc.com>
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Message-id: 20210525010358.152808-34-richard.henderson@linaro.org
Message-Id: <20200415145915.2859-1-steplong@quicinc.com>
[rth: Expanded comment for do_match2]
Signed-off-by: Richard Henderson <richard.henderson@linaro.org>
Signed-off-by: Peter Maydell <peter.maydell@linaro.org>

1 files changed, 64 insertions, 0 deletions

diff --git a/target/arm/sve_helper.c b/target/arm/sve_helper.c
index 17889bc316..f3250165da 100644
--- a/target/arm/sve_helper.c
+++ b/target/arm/sve_helper.c
@@ -6847,3 +6847,67 @@ 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