dfe113e846
Merge pull request #17634 from fp64/macro-x86-loadu
...
Streamline x86 SSE workaround
2023-06-27 23:01:41 -07:00
e4229886b7
Merge pull request #17636 from lvonasek/review_openxr
...
OpenXR - Major review
2023-06-27 20:07:42 +02:00
880168ee3c
OpenXR - Fix render glitches caused by wrong mirroring
2023-06-27 18:54:38 +02:00
99ce3125df
[Softgpu] Fix AArch64 oversight
2023-06-27 17:20:11 +02:00
436b49c4f2
Streamline x86 SSE workaround
...
Seems clearer than using #ifdef's at each site. Also rationale
is clearly spelled out, one 'Go to definition' away from any instance.
2023-06-27 00:30:01 -04:00
fedb92b0e9
softgpu: Ensure early depth test uses SIMD.
2023-06-25 10:18:21 -07:00
08d578dce9
Merge pull request #17618 from unknownbrackets/softgpu-opt-cast
...
Optimize casts in softgpu
2023-06-25 07:55:30 +02:00
ec92675c5e
Merge pull request #17619 from unknownbrackets/softgpu-opt-z
...
softgpu: Improve Z interpolation SIMD
2023-06-25 07:55:03 +02:00
d42642edd2
softgpu: Improve Z interpolation SIMD.
2023-06-24 22:17:11 -07:00
15b66ba6c0
softgpu: Make SIMD on x86_32 a bit safer.
2023-06-24 14:49:23 -07:00
ae9d34370e
softgpu: Move wsum_recip out of the triangle loop.
...
Seems like a small benefit, but not seeing any issues from this.
Noticed by fp64.
2023-06-24 12:38:05 -07:00
795de9b164
softgpu: Use SIMD for more Vec4 casts.
...
A number of these were falling back to some pretty terrible code.
Thanks to fp64 for noticing.
2023-06-24 12:36:44 -07:00
76990aec70
Merge pull request #17609 from fp64/optimize-softgpu-tex-linear
...
softgpu: Optimize (bi-)linear texture filtering
2023-06-21 23:39:15 -07:00
159faaa2ec
softgpu: Optimize (bi-)linear texture filtering
...
Seeing as SampleLinearLevel is near the top in the profiler,
optimize actual bilinear filtering using SSE2. Solid win in the
synthetic benchmark (https://godbolt.org/z/fqh3xvbGx , also doubles
as correctness check), no visible difference in actual PPSSPP.
Note: profiler suggests that hot part of SampleLinearLevel is
elsewhere.
2023-06-21 20:02:34 +03:00
7cc8c6cea4
OSD: Add semantics, move the the OSD state to common (while keeping the renderer in the UI).
2023-06-20 14:40:46 +02:00
efd8565ffe
Merge pull request #17592 from fp64/anymask-movemask
...
Use _mm_movemask_ps for AnyMask
2023-06-17 09:48:09 -07:00
ab85c46161
Use _mm_movemask_ps for AnyMask
...
Probably very minor speed improvement, but it's rather neat.
2023-06-17 01:05:02 -04:00
5b4fa06b00
Revert Dot33 on 32-bit x86 only. See #17584
2023-06-16 23:43:33 +02:00
6d4e5a0f3e
Merge pull request #17584 from fp64/sse2-dot33
...
Convert Dot33 to SSE2
2023-06-15 20:08:23 +02:00
def09bf575
Update the uvscale uniform a bit more conservatively on framebuffer changes
...
Plus fixes a few minor oversights
Fixes #17581 and possibly #17522
2023-06-15 11:57:30 +02:00
f0d844a5a3
Convert Dot33 to SSE2
...
Simpler, lower requirements, and doesn't seem to hurt speed. See #17571 .
2023-06-14 22:02:50 -04:00
6d8069dfd1
Vulkan: Remove the remains of the input attachment experiment
...
Haven't been using these for a while.
I've come to the conclusion here that I think it's better to try to
deal with the issues using safe workarounds like copies, instead of
relying on features with somewhat iffy driver support that are not
universal across APIs anyway.
2023-06-13 20:46:27 +02:00
df7bd89b7d
Division->shift. since it's a signed integer, gets rid of a cdq instruction.
2023-06-13 11:57:28 +02:00
0eb3702ecb
Then add the early-outs for NEON too.
2023-06-13 11:48:04 +02:00
9647872a09
Same for NEON, first the refactor...
2023-06-13 11:48:04 +02:00
77da36c03f
SSE addstrip: Add the early-outs.
2023-06-13 11:47:53 +02:00
39034586a4
SSE: Refactor AddStrip to prepare for early out
2023-06-13 11:45:59 +02:00
22632b82bd
Merge pull request #17565 from hrydgard/breakout-vcache-vulkan
...
Vulkan: Breakout the vertex cache logic from DoFlush()
2023-06-13 09:56:52 +02:00
963ca50ba7
Merge pull request #17567 from hrydgard/uvscale-as-argument
...
Pass uvScale in as a fourth argument to the vertex decoder
2023-06-13 09:49:31 +02:00
71a34d4ffc
Merge pull request #17569 from hrydgard/arm64dec-optimize-saved-regs
...
ARM64: Optimize saved registers in vertex decoder.
2023-06-13 09:49:08 +02:00
a7fa37d114
softgpu: Use SIMD more for dot products.
2023-06-12 19:54:32 -07:00
cdcf3b272e
ARM64: Optimize saved registers in vertex decoder.
...
Simplify away some arrays with unused elements
2023-06-13 00:26:38 +02:00
4af6fac726
Nop-align the ARM and ARM64 loops too. Many CPUs benefit somewhat from hot loops being 16-byte aligned.
2023-06-13 00:05:48 +02:00
5ae9c9c64e
Merge pull request #17568 from hrydgard/extract-some-changes
...
Extract some minor changes from #17497
2023-06-12 23:38:14 +02:00
c4e44d66b0
x86/x64: Nop-align the main loop of vertex decoder loops
2023-06-12 20:39:39 +02:00
01cea7f088
Pass uvScale in as an argument to the vertex decoder
...
Cleaner than overwriting/restoring gstate_c.uvScale in the decoder
loop. A small cleanup I've been wanting to do for ages.
Expecting a negligble perf boost if any.
2023-06-12 20:25:18 +02:00
880379c15d
Extract some minor changes from #17497
2023-06-12 20:20:06 +02:00
d957f6b0be
Of course got the check backwards
2023-06-12 19:45:34 +02:00
1a1462ecb0
x86 buildfix, warning fix
2023-06-12 17:46:57 +02:00
c9aa3479a4
Make vertexFullAlpha-in-register work the same as on ARM.
2023-06-12 16:08:14 +02:00
a164f77f47
VertexDecoderX86 (64-bit only): Avoid a memory access per loop iteration for alpha
2023-06-12 15:58:55 +02:00
f5516d3248
Actually switch away from XXH to a custom hash, to de-risk
2023-06-12 14:24:20 +02:00
2f90ec6093
Breakout the vertex caching (just code cleanup)
2023-06-12 13:16:14 +02:00
468757b93a
Add comment about possible UV scale/offset bug. Move loop-max to local.
2023-06-12 13:16:14 +02:00
d90671e877
Add some comments.
2023-06-12 13:16:13 +02:00
186b0f105c
Simplify the vertex cache ID handling
2023-06-12 13:16:13 +02:00
53aa2cc596
Apply stencil writemask when clearing properly again, see #17478
...
Also renames vpAndScissor to vpAndScissor_ for consistency.
2023-06-12 11:49:44 +02:00
e9e95d23ce
VulkanDebug log fix, reduce log spam
2023-05-30 18:32:33 +02:00
49ecc01556
Fix image leak bug when pausing and we're just displaying a framebuffer in memory
2023-05-30 18:29:50 +02:00
7c4b9bac90
Cache textures created by MakePixelsTexture and reuse where appropriate.
2023-05-30 14:07:44 +02:00
Unknown W. Brackets