Tag: gaming

Posted on by — Leave a comment

benchmark: disable CPU & RAM mitigations to speed up Linux gaming

i ran Monster Hunter Wilds benchmark 4k ultra with no frame gen, via steam store on Linux, on Xorg display server with “teafree” enabled, running the open-source amdgpu kernel driver:

68.51 FPS average | 23243 score ::: regular Linux Kernel
71.87 FPS average | 24526 score ::: Kernel boot options: mitigations=off init_on_alloc=0 init_on_free=0 randomize_kstack_offset=0

7900XTX GPU
3800X CPU

Linux 6.14.0 built using:
clang +full LTO, debian defaut kernel config as make oldconfig with some things already tweaked at build time such as changing timer frequency to 1000Hz, disabling non-essential debug stuf the kernel documentation says has “minimal runtime overhead”, etc, intel components, etc removed due to running on AMD.

mitigations=off,init_on_alloc=0,init_on_free=0, etc are optionally disabled at runtime as a benchmark (mitigations is something that is _always_ on, by default on every linux distro and default kernel. init_on_alloc/free are enabled by default varying by distro, some have either one or the other enabled, or both on)

this is a system-wide speed improvement, and reduces latency, speeds up the CPU and also the memory operations by sacrificing security operations. register zeroing is also a newer kernel CPU security option we can choose to enable/disable (security/speed)

it will be nice to test this with ntsync now it is mainlined into the kernel! ^-^: ttps://www.kernel.org/doc/html/v6.14-rc7/userspace-api/ntsync.html

besides other kernel memory & cpu options, another potential kernel-level improvement we can get is from AutoFDO when building the kernel using clang (though, i probably need to upgrade from my Zen 2 gen CPU for a start):
https://www.kernel.org/doc/html/next/dev-tools/autofdo.html

“AutoFDO (Auto-Feedback-Directed Optimization) is a type of profile-guided optimization (PGO) used to enhance the performance of binary executables. It gathers information about the frequency of execution of various code paths within a binary using hardware sampling. This data is then used to guide the compiler’s optimization decisions, resulting in a more efficient binary. AutoFDO is a powerful optimization technique, and data indicates that it can significantly improve kernel performance. It’s especially beneficial for workloads affected by front-end stalls.

For AutoFDO builds, unlike non-FDO builds, the user must supply a profile. Acquiring an AutoFDO profile can be done in several ways. AutoFDO profiles are created by converting hardware sampling using the “perf” tool. It is crucial that the workload used to create these perf files is representative; they must exhibit runtime characteristics similar to the workloads that are intended to be optimized. Failure to do so will result in the compiler optimizing for the wrong objective. […]

Posted on by — Leave a comment

here’s why RPGs such as the original FFVII have power, immersion & magick that modern voice-acted RPGs absolutely lack.

One of the key reasons classic text-based RPGs such as the legendary FFVII were/are so powerful:

The ability to enter your own name as the protagonist (“cloud”), in a text-based RPG, enables the game to speak to the role-player’s conscious mind, subconscious mind, and unconscious mind.

This powerful key feature is *absolutely* absent from modern voice-acted RPGs and the remake.

I’ve said before that they should at least attempt to use modern voice synthesis which is able to SPEAK the player’s name, alongside the voice acting. This is the only way to even get close to such dimension of what an RPG is supposed to feel like. A role-player could even use their own voice to train a “deepfake” machine-learned “A.I.” voice for the protagonist.

in the case of the original FFVII in particular for example, the game exploits this further by eventually revealing to the role-player that “cloud” is not who he thinks he is, his memories of his past are false, and he falls into the life stream and has to find his “true self”.


You were telling people before that you were EX-SOLDIER 1st class …? No… that was Zack… remember? Zack died… you picked up his sword though … that wasn’t you in that old photo you remember … that was also Zack …

Thus, the role-player experiences “oh… this is who i really am”, and continues the role-playing game from there.

This is of course even more effective to younger players as they may still be developing their sense of “true self” and identity in the real world.

In various parts of the game, a high frequency constant tone may sound like tinitus, the screen may flash, fade or suddenly switch to a pure black or pure white screen, then dialogue text appearing, speaking to the role-player’s mind, akin to an inner voice inside one’s head, but other times as an external voice speaking into the mind … JENOVA? Sephiroth? Cloud’s consciousness? Are you a puppet? Hmm? Who are you? Are your memories real?

In this way, it was a true masterpiece which exhibits and exploits techniques which yield powerful experiences and effects to the role-player which is impossible for voice-acted RPGs to achieve… unless they implement realistic voice synthesis to speak the role-player’s inputted name, and exploit “deepfake” machine-learning for the protagonist to mimic their real voice.

so, when will we get good voice synthesis for RPGs? machine-learned player voice? wen FFVII remake voice synth mod? enter your real friend’s names as the other party members? train their voice etc?

let’s mosey
(where to? the knowlespole? or temple of the ancients? let’s maybe talk to the JENOVA’s witnesses, where have all the Cetra people gone anyway… ?)