Henrik RydgårdandClaude Opus 5.5 6245285ca7 SoftGPU: Don't linger in drawing threads on Windows, and less in transform helpers ...

On native Windows (Ryzen 9 9950X3D), lingering only paid in the transform
helpers. With no drawing-thread linger and 100 us for the helpers, wall
time stayed within 1% of 200/300 us in Daxter, GTA VCS, Wipeout Pure,
Tekken 6, Burnout Dominator, LocoRoco and Ridge Racer, with 9-27% less
CPU time. No linger at all cost up to 7% (Daxter), almost all of it from
the transform helpers.

The linger times are now per platform; Linux keeps the WSL2 values.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>

2026-10-10 15:15:03 +02:00

..

Common

SoftGPU: Don't skin in the vertex decoder for the transform unit

2026-10-10 15:01:49 +02:00

D3D11

Compute FIXA/FIXB blends like the GE

2026-10-09 09:09:36 +02:00

Debugger

GE dump recording: Track every VRAM block a range touches

2026-10-09 17:41:30 +02:00

GLES

Read CLUT8 from 16-bit framebuffers in the shader, replacing the SOCOM hack

2026-10-10 01:04:23 +02:00

Software

SoftGPU: Don't linger in drawing threads on Windows, and less in transform helpers

2026-10-10 15:15:03 +02:00

Vulkan

Read CLUT8 from 16-bit framebuffers in the shader, replacing the SOCOM hack

2026-10-10 01:04:23 +02:00

CMakeLists.txt

SoftGPU: Remove the pixel and sampler JITs

2026-10-10 13:44:48 +02:00

ge_constants.h

GPU: Fix draw engine buffer overruns and stale vertex data

2026-09-29 10:33:32 -06:00

GeConstants.cpp

Add the necessary logic to use in-shader CLUT lookups for regular textures

2026-06-11 12:42:16 +02:00

GeDisasm.cpp

Fix the ImGe debugger vertex list

2026-06-02 14:53:37 +02:00

GeDisasm.h

…

GPU.cpp

GE debugger: Fix the stepping request handshake

2026-09-29 09:49:10 -06:00

GPU.h

Read CLUT8 from 16-bit framebuffers in the shader, replacing the SOCOM hack

2026-10-10 01:04:23 +02:00

GPU.vcxproj

SoftGPU: Remove the pixel and sampler JITs

2026-10-10 13:44:48 +02:00

GPU.vcxproj.filters

SoftGPU: Remove the pixel and sampler JITs

2026-10-10 13:44:48 +02:00

GPUCommon.cpp

Merge pull request #22476 from hrydgard/community-security-fixes

2026-10-09 18:55:57 +02:00

GPUCommon.h

GE: Validate display list stack pointers and pending interrupt list IDs on load

2026-10-09 15:32:05 +02:00

GPUCommonHW.cpp

Update the mip bias uniforms when only the bias changes

2026-10-10 01:04:23 +02:00

GPUCommonHW.h

Remove the "Software skinning" option. Now always on.

2026-07-14 17:02:57 +02:00

GPUDefinitions.h

Disable anisotropic filtering for all flat draws.

2026-06-08 15:28:58 +02:00

GPUState.cpp

Vulkan: Apply the texture LOD bias in the shader where samplers ignore it

2026-10-10 01:04:23 +02:00

GPUState.h

Vulkan: Apply the texture LOD bias in the shader where samplers ignore it

2026-10-10 01:04:23 +02:00

GPUStateSIMDUtil.h

Remove the cached UVScale in gstate_c. Conversion is cheap enough to do directly from gstate, no point in caching.

2026-07-03 13:17:35 +02:00

Math3D.cpp

Finish up this cleanup (move _M_SSE compat define out of Common.h)

2024-12-19 16:23:20 +01:00

Math3D.h

SoftGPU: Splat Vec4s in registers, and three more stalls

2026-10-10 15:01:49 +02:00