Skip to content
Snippets Groups Projects
Commit 386d20a5 authored by Eric Kooistra's avatar Eric Kooistra
Browse files

Added remarks on the reorder memories.

parent 583cfe5d
No related branches found
No related tags found
No related merge requests found
...@@ -49,7 +49,7 @@ ...@@ -49,7 +49,7 @@
-- When use_separate = true then the use_fft_shift must be false, because -- When use_separate = true then the use_fft_shift must be false, because
-- fft_shift() only applies to spectra for complex input. -- fft_shift() only applies to spectra for complex input.
-- --
-- Remark: -- Remarks:
-- . This fft_r2_wide does not (yet) support wb_factor = 1 (= only a -- . This fft_r2_wide does not (yet) support wb_factor = 1 (= only a
-- fft_r2_pipe instance) or wb_factor = g_fft.nof_points (= only a -- fft_r2_pipe instance) or wb_factor = g_fft.nof_points (= only a
-- fft_r2_par instance). Fixing this is nice to have, but not essential. -- fft_r2_par instance). Fixing this is nice to have, but not essential.
...@@ -59,6 +59,14 @@ ...@@ -59,6 +59,14 @@
-- . wb_factor = 1 -- . wb_factor = 1
-- . wb_factor > 1 AND wb_factor < g_fft.nof_points -- . wb_factor > 1 AND wb_factor < g_fft.nof_points
-- . wb_factor = g_fft.nof_points. -- . wb_factor = g_fft.nof_points.
-- . This fft_r2_wide uses the use_reorder in the pipeline FFT, in the parallel
-- FFT and also has reorder memory in the fft_sepa_wide instance. The reorder
-- memories in the FFTs can maybe be saved by using only the reorder memory
-- in the fft_sepa_wide instance. This would require changing the indexing in
-- fft_sepa_wide instance.
-- . The reorder memory in the pipeline FFT, parallel FFT and in the
-- fft_sepa_wide could make reuse of a reorder component from the reorder
-- library instead of using a dedicated local solution.
library ieee, common_lib, rTwoSDF_lib; library ieee, common_lib, rTwoSDF_lib;
use IEEE.std_logic_1164.all; use IEEE.std_logic_1164.all;
......
0% Loading or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment