Recent content by Krille

If you have the hardware for that, why not use the virtual serial drive functionality in XTIDE Universal BIOS? EDIT: BTW, I suspect bad RAM.

Google hasn't indexed the entire forum and it's unlikely that they ever will so I would recommend using a different search engine. I never thought it would come to this but I've started to use Bing instead. Yeah, you know Google has turned into a pathetic joke when you turn to Microsoft for your...

The DOS boot partition should be just 10-15 MB tops. Keep in mind, a 100 MB partition would have been a huge part of a drive back in the day. And a total waste. I'm a CNA for Netware 4.11 and was certified in 1999. Haven't used it since. It's not that I didn't like it, because I did. Netware...

Why do you say that? Only 70 KB/s but you got almost 868 KB/s before? I'm probably missing something. :)

String space corrupt is what usually happens when QB programs become sufficiently large. It's one of the many reasons we love and cherish QB. ;) Think of it as QB:s subtle way of letting you know it's time to optimize the code. :giggle:

This guy on facebook (I don't recall his name but I wouldn't be surprised if he is also a member here) said he was using an Arco Computer Products AC-1075 controller with XUB and he claimed that he had not done any modifications to the code - he was just using the standard 16-bit IDE controller...

Sorry for disappearing on you guys. I've been sick and also busy with other stuff. Thanks for doing all that testing and creating a spread sheet. I bet that was a lot of work. Anyway, I can't explain the loss of performance in r605. The only change that should affect performance is WORD_ALIGN...

The prefetch queue is treated as a buffer of 6 bytes. It must be, because otherwise it would have to redo the instruction fetch for all instructions not aligned on a WORD boundary. That would be a serious design flaw considering that so many instructions have an odd length. So yes, the benefit...

Yeah, my immediate thought when reading your post was that something changed between r604 and r623 that made transfers a lot slower. However, when looking through the changes in each of those revisions I can't find anything that should affect the performance so drastically. It would be great if...

Yeah, it's as fast as it gets then. Still, you might want to upgrade anyway for other reasons, depending on what revision you're using now and if any bugs has been fixed since then. But the performance won't improve.

No, with a V20 you would only get higher performance with XT-IDE cards. That's with the assumption that you are using one of the XT Plus builds of course. If you're not (which would be kind of silly) then yes, you would get higher performance with the newer version with XT-CF cards also.

Thanks for testing Malc! That's more in line with what I expected.

Why would it only help with even-sized instructions? By making sure that instructions start on even addresses we don't waste RAM accesses. Now, there are plenty of alignment directives in the code where we both jump to AND fall through to a label. Those are the ones I feel unsure about whether...

No worries! I don't think the length of the instruction is relevant. On 8086 and V30 CPUs RAM is accessed 16 bits at a time on WORD boundaries. Fetching an instruction from an odd address will waste half of that memory access and will also require an extra memory access to fetch the rest of...

Let's see if you're right! (see below) :) I knew it wouldn't matter on an 8088 but I am curious if it makes a difference on an 8086. That is what FreddyV is testing on after all. Anyway, I've created a couple of new defines that can be used to unroll the transfer loops a bit more...