target-arm: A64: Implement SADDLP, UADDLP, SADALP, UADALP

Implement the SADDLP, UADDLP, SADALP and UADALP instructions
in the SIMD 2-reg misc category.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <rth@twiddle.net>
Message-id: 1394822294-14837-8-git-send-email-peter.maydell@linaro.org

1 files changed, 61 insertions, 0 deletions

diff --git a/target-arm/helper-a64.c b/target-arm/helper-a64.c
index 8f53223cee..c31c45e729 100644
--- a/target-arm/helper-a64.c
+++ b/target-arm/helper-a64.c
@@ -293,3 +293,64 @@ float64 HELPER(rsqrtsf_f64)(float64 a, float64 b, void *fpstp)
     }
     return float64_muladd(a, b, float64_three, float_muladd_halve_result, fpst);
 }
+
+/* Pairwise long add: add pairs of adjacent elements into
+ * double-width elements in the result (eg _s8 is an 8x8->16 op)
+ */
+uint64_t HELPER(neon_addlp_s8)(uint64_t a)
+{
+    uint64_t nsignmask = 0x0080008000800080ULL;
+    uint64_t wsignmask = 0x8000800080008000ULL;
+    uint64_t elementmask = 0x00ff00ff00ff00ffULL;
+    uint64_t tmp1, tmp2;
+    uint64_t res, signres;
+
+    /* Extract odd elements, sign extend each to a 16 bit field */
+    tmp1 = a & elementmask;
+    tmp1 ^= nsignmask;
+    tmp1 |= wsignmask;
+    tmp1 = (tmp1 - nsignmask) ^ wsignmask;
+    /* Ditto for the even elements */
+    tmp2 = (a >> 8) & elementmask;
+    tmp2 ^= nsignmask;
+    tmp2 |= wsignmask;
+    tmp2 = (tmp2 - nsignmask) ^ wsignmask;
+
+    /* calculate the result by summing bits 0..14, 16..22, etc,
+     * and then adjusting the sign bits 15, 23, etc manually.
+     * This ensures the addition can't overflow the 16 bit field.
+     */
+    signres = (tmp1 ^ tmp2) & wsignmask;
+    res = (tmp1 & ~wsignmask) + (tmp2 & ~wsignmask);
+    res ^= signres;
+
+    return res;
+}
+
+uint64_t HELPER(neon_addlp_u8)(uint64_t a)
+{
+    uint64_t tmp;
+
+    tmp = a & 0x00ff00ff00ff00ffULL;
+    tmp += (a >> 8) & 0x00ff00ff00ff00ffULL;
+    return tmp;
+}
+
+uint64_t HELPER(neon_addlp_s16)(uint64_t a)
+{
+    int32_t reslo, reshi;
+
+    reslo = (int32_t)(int16_t)a + (int32_t)(int16_t)(a >> 16);
+    reshi = (int32_t)(int16_t)(a >> 32) + (int32_t)(int16_t)(a >> 48);
+
+    return (uint32_t)reslo | (((uint64_t)reshi) << 32);
+}
+
+uint64_t HELPER(neon_addlp_u16)(uint64_t a)
+{
+    uint64_t tmp;
+
+    tmp = a & 0x0000ffff0000ffffULL;
+    tmp += (a >> 16) & 0x0000ffff0000ffffULL;
+    return tmp;
+}