Wunk

Update units of memory from decimal to binary prefixes

1

`MB` and `GB` can either be interpreted as having base-10 units, or base-2. `MiB` and `GiB` removes this discrepancy so that units of memory are always interpreted using base-2 units....

ARMeilleure: Add initial support for AVX512(EVEX encoding)

6

The first sample use-case being a single-instruction alternative to the vector-`NOT` instruction by utilizing the [vpternlogd instruction](https://www.felixcloutier.com/x86/vpternlogd:vpternlogq). Implements enough of the EVEX encoding features to utilize AVX512 instructions for a...

ARMeilleure: Add `gfni` acceleration

3

[Galois Field New Instructions](https://builders.intel.com/docs/networkbuilders/galois-field-new-instructions-gfni-technology-guide.pdf) were intended for cryptography but the `gf2p8affineqb` can be used to do general purpose bit-shuffling within 8-bit elements of a simd vector for cases such as...

Uses the single-instruction AVX512 `vperm*` instructions to accelerate the `INT8_TYPE` and `INT16_TYPE` permutation opcodes. The `INT8_TYPE` is accelerated using `AVX512VBMI` subset of AVX512. Available since Icelake(Intel) and Zen4(AMD). Passes the...

Passes the `vsubuws` and `vsubsws` unit-tests from https://github.com/xenia-project/xenia/pull/1348

AVX512 Validation

5

This isn't so much an issue as much as it is a tip. But you mention not having access to an AVX512 machine: > This algorithm should map fairly nicely...

ARMeilleure: Add initial support for AVX512(EVEX encoding) (cont)

1

Continuation of https://github.com/Ryujinx/Ryujinx/pull/3663 This PR addresses an issue in register-indexing, register-designations, and other issues the original PR was found to have. `vpternlogd` is now utilized for `mvn`, `orn`, and `not`

Option to _disable_ Anti-Aliasing

1

**Description** I like to make short "explainer gifs" when making a big write-up and have great interest in motion-canvas. I come from utilizing Adobe After Effects to make gifs such...

I believe right now all image-arithmetic is operating upon image color values that are within the non-linear [sRGB](https://en.wikipedia.org/wiki/SRGB) color-space. So operations upon them like sums and averages and conversions may...

shader_jit: Add optimizations up to `x86-64-v4`

5

Adds architecture-specific accelerations to some shader_jit functions up to the `x86-64-v4` ISA, including AVX, AVX512{F,VL,DQ}, SSE41, FMA. Passes unit tests on my i9-7900x. Verification can also be done using Intel's...