[TCP]: cubic optimization

Use willy's work in optimizing cube root by having table for small values.

Signed-off-by: Stephen Hemminger <shemminger@linux-foundation.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 39 insertions, 11 deletions

diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c
index 0e6cdfeb207a..15c580375002 100644
--- a/net/ipv4/tcp_cubic.c
+++ b/net/ipv4/tcp_cubic.c
@@ -91,23 +91,51 @@ static void bictcp_init(struct sock *sk)
                 tcp_sk(sk)->snd_ssthresh = initial_ssthresh;
 }
 
-/*
- * calculate the cubic root of x using Newton-Raphson
+/* calculate the cubic root of x using a table lookup followed by one
+ * Newton-Raphson iteration.
+ * Avg err ~= 0.195%
  */
 static u32 cubic_root(u64 a)
 {
-        u32 x;
-
-        /* Initial estimate is based on:
-         * cbrt(x) = exp(log(x) / 3)
+        u32 x, b, shift;
+        /*
+         * cbrt(x) MSB values for x MSB values in [0..63].
+         * Precomputed then refined by hand - Willy Tarreau
+         *
+         * For x in [0..63],
+         *   v = cbrt(x << 18) - 1
+         *   cbrt(x) = (v[x] + 10) >> 6
          */
-        x = 1u << (fls64(a)/3);
+        static const u8 v[] = {
+                /* 0x00 */    0,   54,   54,   54,  118,  118,  118,  118,
+                /* 0x08 */  123,  129,  134,  138,  143,  147,  151,  156,
+                /* 0x10 */  157,  161,  164,  168,  170,  173,  176,  179,
+                /* 0x18 */  181,  185,  187,  190,  192,  194,  197,  199,
+                /* 0x20 */  200,  202,  204,  206,  209,  211,  213,  215,
+                /* 0x28 */  217,  219,  221,  222,  224,  225,  227,  229,
+                /* 0x30 */  231,  232,  234,  236,  237,  239,  240,  242,
+                /* 0x38 */  244,  245,  246,  248,  250,  251,  252,  254,
+        };
+
+        b = fls64(a);
+        if (b < 7) {
+                /* a in [0..63] */
+                return ((u32)v[(u32)a] + 35) >> 6;
+        }
+
+        b = ((b * 84) >> 8) - 1;
+        shift = (a >> (b * 3));
 
-        /* converges to 32 bits in 3 iterations */
-        x = (2 * x + (u32)div64_64(a, (u64)x*(u64)x)) / 3;
-        x = (2 * x + (u32)div64_64(a, (u64)x*(u64)x)) / 3;
-        x = (2 * x + (u32)div64_64(a, (u64)x*(u64)x)) / 3;
+        x = ((u32)(((u32)v[shift] + 10) << b)) >> 6;
 
+        /*
+         * Newton-Raphson iteration
+         *                         2
+         * x    = ( 2 * x  +  a / x  ) / 3
+         *  k+1          k         k
+         */
+        x = (2 * x + (u32)div64_64(a, (u64)x * (u64)(x - 1)));
+        x = ((x * 341) >> 10);
         return x;
 }