@steffo Best boss fight!

@steffo I need to measure register spill overhead, and the method we've come up with is to make the stack uncached. This should theoretically be the worst-case where other running threads steal your cache lines... I guess?

I'm writing a LD_PRELOAD program that maps an uncached memory segment as the stack to make your program run slower.

It does a lot of cursed thingies, like live-patching the stack for self-references.
I love doing increasingly weird things.

@steffo Maybe, I have no idea how to calibrate it correctly .
Still, piece of art!

@steffo I think it's for the secondary quests that you unlock later in the game

@steffo Be me, I just bought an HDR screen.
The first level of the game is AWESOME, you just come into the light with grassy vibrant colors and you see the new world you're forced into.

Then the rest of the game is just, really dark?
I know it's not a HDR game but I really looked forward to that brilliant intro. Maybe there's something similar later.

Human you're upset
Stop typing
Timo to zzzzz

#cat #CatsOfMastodon

@steffo me too

@steffo Still fighting steam servers?

@steffo wait, you have an arm sever? Or is it using something like qemu or multiarch?

@steffo I tried to run SANE_DEBUG_AIRSCAN=true scanimage -L and I saw something interesting:

WSDD: HTTP POST http://192.168.1.88:80/WebServices/Device: 200 OK
WSDD: HTTP POST http://192.168.1.88:80/WebServices/Device: OK
WSDD: "Brother MFC-L3740CDW series": IPv6 address expected but not yet discovered
WSDD: "Brother MFC-L3740CDW series": IPv6 address expected but not yet discovered
WSDD: "Brother MFC-L3740CDW series": IPv6 address expected but not yet discovered
...

I guess that sane-airscan saw the IPv4 printer and somehow tried to contact it in IPv6, and it just failed

Do you ever have that incessant feeling of debugging your sane config?
Like, your new scanner worked in NAPS2, but now it only works in SkanLite, scanimage -L doesn't detect it but airscan-discover works fine...

WELL I DID, EVERYTHING IS WORKING NOW.

And the problem was??????
IPv6

@steffo Same thing happened to @fluiddruid today, you need to finish the game again (any ending)

@steffo Yes.

I got an Obsidian page open called "Tessellation Shader". I'm reading 3 blogs, 2 specifications and 1 hour long video.

It's both a live-blogging thing and a cry for help.

Kepler NVK breaks with some tessellation tests, whohoo!

The tests somehow all pass, but the GPU complains in the kernel logs about an out of range memory access.

So, uhm, what is tessellation exactly? (asking for a friend).

Finally made my own Everything machine in Shapez, without following tutorials or guides.

It's not really fast and has a really slow turn over time, but hey, I made that!

#shapez #gaming

@steffo yess!
You just do a reverse next and you can inspect the state of the system before that instruction was executed. It's the holy grail of debugging.

Some emulators might have these commands built-in, but for x86-64 it seems to magically records the changes to the registers and the memory, and when you undo an instruction it enters replay mode.

It should be just like "ohh, my program is trying to fetch code ad 0x0000, press undo, ah here was the jump"

I'm reading gdb manual for the first time after using it blind for ages.

I could've always had access to reverse execution and bookmarks? What?
Why didn't I read this before, I want my hours debugging and restarting weird programs back.

Look ma, I'm on phoronix!

https://www.phoronix.com/news/Nouveau-NAK-Faster-Kepler

@steffo use them on the presentation!