Subject: Re: [stella] some more optimization tips From: "Andrew Davie" <adavie@xxxxxxxxxxxxxxxxx> Date: Sat, 9 May 1998 14:31:25 +1000 |
>PLA might certainly be preferable over LDA, though. If for some reason you >need to make, say, 12 TIA writes from a variable place in ROM, copying >those 12 bytes into RAM offscreen and looping PLA/STA in the kernel is >faster than doing LDA indirect indexed/STA. Yes, true. But If I was that desperate, I'd try very hard to use self-modifying code in zero-page. That way you'd come down to just 5 cycles for each load/store rather than 11 for indexed indirect or 7 for PLA/STA. In the 12 byte example, you'd need a scratchpad space of 48 bytes - expensive, though :) Nonetheless, you offset it by the 12 bytes of stack you're proposing, and its penalty is 36 bytes. Time to dig out that old multiple variable area overlays assembler, mmh? Cheers A -- Archives (includes files) at http://www.biglist.com/lists/stella/archives/ Unsub & more at http://www.biglist.com/lists/stella/stella.html
Current Thread |
---|
|
<- Previous | Index | Next -> |
---|---|---|
Re: [stella] some more optimization, Jim Nitchals | Thread | Re: [stella] some more optimization, Andrew Davie |
Re: [stella] Six-sprite slot machin, Eric Fischer | Date | Re: [stella] Six-sprite slot machin, Glenn Saunders |
Month |