Minor doc updates.

Fixed wrong register use on triggering waves regarding the loop offset.

README.md

@@ -41,7 +41,7 @@ please let me know under chrisly@platon42.de. Thank you.
 
 The new replayer comes as a drop-in binary replacement if you wish.
 In this case you will get faster sample generation (about 12%
-faster on 68000) and about 45% less CPU time spent. However, you
+faster on 68000) and about 45% less CPU time spent during playback. However, you
 won't get stuff as song-end detection and precalc progress this way.
 This mode uses the old CPU DMA wait that takes away 8 raster lines.
 
@@ -54,7 +54,7 @@ during the vertical blank.
 
 Please use the documented sizes for the `MySong` and `MyPlayer` data
 structures, which are the symbols `sv_SIZEOF` and `pv_SIZEOF`
-respectively (about 2K and 12K with volume table).
+respectively (about 2KB and 12KB with volume table).
 
 The source needs two common include files to compile (`custom.i` and
 `dmabits.i`). You should leave assembler optimizations enabled.
@@ -69,6 +69,7 @@ The source needs two common include files to compile (`custom.i` and
    - a pointer to chip memory sample buffer in `a1`
    - the pointer to `MySong` in `a2`
    - a pointer to a longword for progress information or null in `a3`
+
    This will create the samples, too.
 4. After that, regularly call `pre_PlayerTick` with `MyPlayer` in `a0`
    and optionally the copperlist in a1 if you're using that mode).
@@ -87,15 +88,19 @@ Raspberry Casket, depending on the features compiled in, is about
 
 So this means that the optimization is not just "on the outside".
 
+About 2.4 KB of the code (and data) are spent for the sample generation,
+the remaining code for playback.
+
 ### Timing
 
-Sample generation is a bit faster (I guess around 10-15%), but most of the time is spent on muls operations, so this is the limiting factor.
+Sample generation is a bit faster (I guess around 10-15%),
+but most of the time is spent on `muls` operations, so this is the limiting factor.
 Raspberry Casket is about twice as fast as the old replayer for playback.
 
 Unfortunately, the replayer is still pretty slow and has high
 jitter compared to other standard music replayers.
 
-This means it may take up to 33 raster lines (14-19 on average)
+This means it may take up to 32 raster lines (13-18 on average)
 which is significant more than a standard Protracker replayer
 (the original one could take about 60 raster lines worst case and
 about 34 on average!).
@@ -117,11 +122,16 @@ solve this problem.
 
 ## Changelog
 
+### V1.x (unreleased)
+- Fixed a bug regarding the copper output mode with looping waves having a loop-offset.
+- Fixed wrong register use on triggering waves regarding the loop offset.
+- Minor code size optimizations.
+
 ### V1.1 (28-Dec-22)
 - Optimized base displacement by reordering variables.
 - Further optimized ADSR code.
 - Optimized wave loop code.
-- Bake in this strange vibrato speed multiplication to precalculated vibrato value (where possible).
+- Baked in this strange vibrato speed multiplication to precalculated vibrato value (where possible).
 - Various small optimizations.
 - Store instrument number * 4 on loading to avoid using two adds every frame.
 - Optimized speed/shuffle code. Idea of using xor turned out to make things too complicated for pattern breaks/jumps.

src/raspberry_casket.asm

@@ -1,5 +1,5 @@
 ;--------------------------------------------------------------------
-; Raspberry Casket Player V1.1 (28-Dec-2022)
+; Raspberry Casket Player V1.1 (30-May-2023)
 ; ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 ;
 ; Provided by Chris 'platon42' Hodges <chrisly@platon42.de>
@@ -97,8 +97,7 @@
 ; of the time is spent on muls operations, so this is the limiting
 ; factor.
 ;
-; Raspberry Casket is about twice as fast as the old replayer for
+; Raspberry Casket is about twice as fast as the old replayer for playback.
-; playback.
 ;
 ; Unfortunately, the replayer is still pretty slow and has high
 ; jitter compared to other standard music replayers.
@@ -814,17 +813,15 @@ pre_SongInit:
         moveq.l #0,d1
         move.b  (a0)+,d1                        ; ii_adsr_attack
         add.w   d1,d1
-        lea     pre_fast_roll_off_16(pc),a5
+        move.w  pre_fast_roll_off_16-pre_vib_delay_table(a5,d1.w),d1
-        move.w  (a5,d1.w),d1
         move.w  d1,uii_adsr_attack(a4)
 
         moveq.l #0,d1
         move.b  (a0)+,d1                        ; ii_adsr_decay
-        lea     pre_ramp_up_16(pc),a5
+        move.b  pre_ramp_up_16-pre_vib_delay_table(a5,d1.w),uii_adsr_decay+1(a4)
-        move.b  (a5,d1.w),uii_adsr_decay+1(a4)
 
         move.b  (a0)+,d1                        ; ii_adsr_sustain
-                    ; what is this? a patch?
+        ; what is this? a patch?
         cmp.b   #15,d1
         bne.s   .dont_patch_sustain
         moveq.l #16,d1
@@ -834,8 +831,7 @@ pre_SongInit:
 
         moveq.l #0,d1
         move.b  (a0)+,d1                        ; ii_adsr_release
-        lea     (pre_ramp_up_16,pc),a5
+        move.b  pre_ramp_up_16-pre_vib_delay_table(a5,d1.w),uii_adsr_release(a4)
-        move.b  (a5,d1.w),uii_adsr_release(a4)
 
         move.b  (a0)+,d1                        ; ii_pattern_steps
         move.b  d1,uii_pattern_steps(a4)
@@ -1257,7 +1253,6 @@ pre_PlayerInit:
 
         moveq.l #0,d3
         move.b  wi_osc_phase_min_b(a3),d3
-
         mulu    d5,d3
         lsl.l   #6,d3
 
@@ -1387,7 +1382,7 @@ pre_PlayerInit:
 
         cmpa.l  #$8000,a5       ; if symmetrical
         beq.s   .gen_noise_centered
-        ; what does this do? (a5 - $8000) (a5 +$7fff)&$8000
+        ; FIXME what does this do? d4 = (a5 - $8000) d1 = (a5 + $7fff)&$ffff8000 -> d4 - d1 == ((a5 - $8000) - ((a5 + $7fff)&$ffff8000)
         move.l  a5,d4
         addi.l  #$FFFF8000,d4
         move.l  a5,d1
@@ -1593,7 +1588,7 @@ pre_PlayerInit:
 .entry_to_filter_loop
         move.l  d0,a6
         move.l  d3,d1       ; flt_speed_b*128
-        adda.l  d1,a6	    ; suppress M68kUnexpectedConditionalInstruction
+        adda.l  d1,a6       ; suppress M68kUnexpectedConditionalInstruction
         bgt.s   .filter_speed_pos
 
 .filter_speed_neg
@@ -3393,7 +3388,7 @@ pre_PlayerTick:
         move.w  wi_chipram_w(a3),d0
         move.w  d0,d6
         subq.w  #1,d6
-        cmp.w   d4,d6
+        cmp.w   d5,d6
         ble.s   .lbC00118E
         sub.w   d5,d0
         bra.s   .lbC000F48
@@ -3407,7 +3402,7 @@ pre_PlayerTick:
 .inst_nowave_has_subloop
         move.l  pv_wave_sample_table(a4),pcd_out_ptr_l(a5)
 
-        move.w  wi_loop_offset_w(a3),d4
+        move.w  wi_loop_offset_w(a3),d5
 .inst_set_no_lof
         move.w  d3,pcd_out_lof_w(a5)
         moveq.l #0,d0
@@ -3415,7 +3410,7 @@ pre_PlayerTick:
         addq.w  #1,d0
         move.w  d0,pcd_inst_subloop_wait_w(a5)
 
-        move.w  d4,pcd_inst_loop_offset_w(a5)
+        move.w  d5,pcd_inst_loop_offset_w(a5)
         st      pcd_inst_ping_pong_dir_b(a5)
 
 .inst_wave_selected
@@ -4002,7 +3997,7 @@ pre_PlayerTick:
         tst.b   ocd_trigger(a0)
         beq.s   .setptrvolper
         move.b  d5,ocd_trigger(a0)
-        sub.l   d2,d6
+        sub.l   d2,d0
 .setptrvolper
         move.w  d0,1*4(a1)  ; ac_ptr (lo)
         swap    d0
@@ -4129,6 +4124,13 @@ pre_vib_depth_table:
 pre_vib_delay_table:
         dc.b    0,4,8,10,12,14,16,18,20,24,32,40,56,96,150,255
 
+pre_ramp_up_16:
+        dc.b    0,1,3,6,7,9,10,11,12,13,14,16,19,35,55,143
+
+pre_fast_roll_off_16:
+        dc.w    $400,$200,$80,$64,$50,$40,$30,$20,$10,14,12,10,8
+        dc.w    4,2,1
+
 pre_roll_off_table:
         dc.w    $400,$200,$180,$140,$100,$C0,$A0,$80,$78,$74,$6E
         dc.w    $69,$64,$5A,$46,$40,$38,$30,$28,$20,$1F,$1E,$1D
@@ -4139,13 +4141,6 @@ pre_roll_off_table:
         dc.w    2,3,3,2,3,3,2,3,2,3,2,3,2,3,2,3,2,2,2,2,2,2,2,2,1
         dc.w    2,1,2,1,2,1,2,1,1,2,1,1,1,2,1
 
-pre_ramp_up_16:
-        dc.b    0,1,3,6,7,9,10,11,12,13,14,16,19,35,55,143
-
-pre_fast_roll_off_16:
-        dc.w    $400,$200,$80,$64,$50,$40,$30,$20,$10,14,12,10,8
-        dc.w    4,2,1
-
 pre_octave_note_offset_table:
         dc.b    1*NOTES_IN_OCTAVE*4,1*NOTES_IN_OCTAVE*4,1*NOTES_IN_OCTAVE*4
         dc.b    2*NOTES_IN_OCTAVE*4,2*NOTES_IN_OCTAVE*4,2*NOTES_IN_OCTAVE*4