From 3e8db3dffad1d508bf0d9d10d465e7fe1ccced81 Mon Sep 17 00:00:00 2001 From: Clanmaster21 Date: Thu, 10 Oct 2019 07:56:15 +0100 Subject: [PATCH] Doesn't use self-modifying code The number of bytes is the same as my previous attempt, with 11 more cycles in intoHL, so although I don't feel as clever this time it's still a good optimisation. I found an equivalent method for intoDE, however relying on intoHL still allows for `ex (sp), hl` to be used in intoIX, which is smaller and faster. --- kernel/core.asm | 17 +++++++++-------- 1 file changed, 9 insertions(+), 8 deletions(-) diff --git a/kernel/core.asm b/kernel/core.asm index 6ffa452..bf3d8d0 100644 --- a/kernel/core.asm +++ b/kernel/core.asm @@ -26,20 +26,21 @@ addDE: noop: ; piggy backing on the first "ret" we have ret -; copy (HL) into HL, utilising the optimised HL instructions. The first ld -; edits the address of the second ld to now be HL. +; copy (HL) into DE, then exchange the two, utilising the optimised HL instructions. +; ld must be done little endian, so least significant byte first. intoHL: - ld (.load+1), hl -.load: - ld hl, (.load) ; (.load) is just a placeholder so the - ; assembler will assemble the correct opcode + push de + ld e, (hl) + inc hl + ld d, (hl) + ex de, hl + pop de ret intoDE: ex de, hl call intoHL - ex de, hl ; de not affected by intoHL, so no push/pop - ; is necessary + ex de, hl ; de preserved by intoHL, so no push/pop needed ret intoIX: