target-arm: Implement VMULL.P8

Implement VMULL.P8 (the 32x32->64 version of the polynomial multiply
instruction).

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Signed-off-by: Aurelien Jarno <aurelien@aurel32.net>

1 files changed, 30 insertions, 0 deletions

diff --git a/target-arm/neon_helper.c b/target-arm/neon_helper.c
index dc09968c86..ee253bbd2e 100644
--- a/target-arm/neon_helper.c
+++ b/target-arm/neon_helper.c
@@ -895,6 +895,36 @@ uint32_t HELPER(neon_mul_p8)(uint32_t op1, uint32_t op2)
     return result;
 }
 
+uint64_t HELPER(neon_mull_p8)(uint32_t op1, uint32_t op2)
+{
+    uint64_t result = 0;
+    uint64_t mask;
+    uint64_t op2ex = op2;
+    op2ex = (op2ex & 0xff) |
+        ((op2ex & 0xff00) << 8) |
+        ((op2ex & 0xff0000) << 16) |
+        ((op2ex & 0xff000000) << 24);
+    while (op1) {
+        mask = 0;
+        if (op1 & 1) {
+            mask |= 0xffff;
+        }
+        if (op1 & (1 << 8)) {
+            mask |= (0xffffU << 16);
+        }
+        if (op1 & (1 << 16)) {
+            mask |= (0xffffULL << 32);
+        }
+        if (op1 & (1 << 24)) {
+            mask |= (0xffffULL << 48);
+        }
+        result ^= op2ex & mask;
+        op1 = (op1 >> 1) & 0x7f7f7f7f;
+        op2ex <<= 1;
+    }
+    return result;
+}
+
 #define NEON_FN(dest, src1, src2) dest = (src1 & src2) ? -1 : 0
 NEON_VOP(tst_u8, neon_u8, 4)
 NEON_VOP(tst_u16, neon_u16, 2)