From a7e74927701cdf22ab185f9fd0eb358b0d29974b Mon Sep 17 00:00:00 2001 From: lkcl Date: Tue, 8 Oct 2019 12:13:49 +0100 Subject: [PATCH] --- simple_v_extension/vector_ops.mdwn | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/simple_v_extension/vector_ops.mdwn b/simple_v_extension/vector_ops.mdwn index ce4c370cc..394e5b24d 100644 --- a/simple_v_extension/vector_ops.mdwn +++ b/simple_v_extension/vector_ops.mdwn @@ -37,8 +37,9 @@ may also be run in either "vector" mode or "rotation" mode. See [[discussion]] CORDIC can also be used for performing DCT. See -vx, vy = CORDIC(vx, vy, coordinate\_mode, beta) +CORDIC has several RADIX-4 papers for efficient pipelining. Each stage requires its own ROM tables which can get costly. Two combinatorial blocks may be chained together to double the RADIX and halve the pipeline depth, at the cost of doubling the latency. +Also, to get good accuracy, particularly at the limits of CORDIC input range, requires double the bitwidth of the output in internal computations. This similar to how MUL requires double the bitwidth to compute. Links: -- 2.30.2