From f93a0258df2ec4f4f42da7185bc8202c6811607e Mon Sep 17 00:00:00 2001
From: Mark Borgerding <mark@borgerding.net>
Date: Sat, 11 Oct 2003 22:45:35 +0000
Subject: [PATCH] Simplified some inner loop calcs

'make test' output:
### testing SNR for  1024 point FFTs
#### DOUBLE
snr_t2f = 295.34
snr_f2t = 308.77
#### FLOAT
snr_t2f = 146.93
snr_f2t = 143.56
#### SHORT
snr_t2f = 54.799
snr_f2t = 24.562

#### timing 10000 x 1024 point FFTs
#### DOUBLE
Elapsed:0:10.69 user:8.71 sys:0.20
#### FLOAT
Elapsed:0:04.40 user:3.42 sys:0.11
#### SHORT
Elapsed:0:05.62 user:4.77 sys:0.04
---
 kiss_fft.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/kiss_fft.c b/kiss_fft.c
index 16107d3..b3d4b1e 100644
--- a/kiss_fft.c
+++ b/kiss_fft.c
@@ -100,18 +100,19 @@ void fft_work(
     }
 
     for ( u=0; u<m; ++u ) {
+        k=u;
         for ( q1=0 ; q1<p ; ++q1 ) {
+            scratch[q1] = Fout[ k  ];
 #ifdef FIXED_POINT
-            scratch[q1].r = Fout[ u+q1*m  ].r>>1;
-            scratch[q1].i = Fout[ u+q1*m  ].i>>1;
-#else
-            scratch[q1] = Fout[ u+q1*m  ];
+            scratch[q1].r = Fout[ k  ].r>>1;
+            scratch[q1].i = Fout[ k  ].i>>1;
 #endif            
+            k += m;
         }
 
+        k=u;
         for ( q1=0 ; q1<p ; ++q1 ) {
             int twidx=0;
-            k=q1*m+u;
             Fout[ k ] = scratch[0];
             for (q=1;q<p;++q ) {
                 twidx += fstride * k;
@@ -121,6 +122,7 @@ void fft_work(
                 Fout[ k ].r += t.r;
                 Fout[ k ].i += t.i;
             }
+            k += m;
         }
     }
 }