0fbeac6d3f
graphics: compact shader keys and hash packed pipeline state
2026-09-29 13:57:32 +04:00
5e4f6afc30
graphics: build color target descriptors in place
2026-09-29 13:57:32 +04:00
37501b5a78
graphics: stream clean guest buffers without backing-store lookups
2026-09-29 13:57:32 +04:00
b43bf9f7fb
graphics: store vertex attribute bindings without duplicated arrays
2026-09-29 13:57:32 +04:00
8e42e99788
graphics: batch release labels without redundant submissions
2026-09-29 13:57:32 +04:00
539c0f7bf8
graphics: restore block image storage usage where the device supports it ( #894 )
2026-09-29 01:57:25 +04:00
8e61798bfd
graphics: honor CPU ownership in image dirty-region queries
2026-09-28 22:17:43 +04:00
6ee1bf9db0
graphics: trust image-local readback validity
2026-09-28 22:17:43 +04:00
4cf456fb77
graphics: retain buffer names across draw bindings
2026-09-28 22:17:43 +04:00
c8baa7b909
shader: derive immutable resource policy once per plan
2026-09-28 18:01:49 +04:00
2016f8e2fe
gpu: address extended guest memory without widening dense cache tables
2026-09-28 18:01:49 +04:00
0a5774be7b
shader: support FP64 conversions used by FighterZ ( #884 )
...
shader: support float and unsigned widening to FP64
Co-authored-by: nmzik <Nmzik@mail.ru >
2026-09-28 17:39:31 +04:00
0791f921f6
UFC 5 in-game ( #883 )
...
* shader: release descriptor dependencies
* shader: simplify shared-exit control flow
* shader: fix scalar memory loads
* shader: fix LDS counter bounds
* renderer: skip inactive pixel shaders
* shader: respect FP32 mode in comparisons
* renderer: fix sampler border colors
* shader: resolve descriptors from control flow
* shader: resolve descriptors before resource planning
* shader: handle scalar guards for image bounds
* shader: handle reduced guards for image loops
* shader: fix wave guards and material indices
* shader: preserve scalar buffer offset alignment and carry
* shader: prove masked loop bounds across iteration transitions
* shader: preserve source and IR before resource tracking failures
* shader: track material keys selected from active lanes
* shader: remove obsolete post-dominator analysis
* shader: follow bounds guards through control-flow joins
2026-09-28 16:03:05 +04:00
9229c04ebf
samplerCache: handle reserved sampler anisotropy ratios
...
Co-authored-by: EmK530 <admin@emk530.net >
Co-authored-by: Hamza Shakir <60213466+hamzashakir99@users.noreply.github.com >
2026-09-27 15:46:25 +04:00
0f1ff37f23
Graphics: materialize CMASK clears before publishing expanded metadata
2026-09-27 15:05:46 +04:00
da33a1c4a3
Graphics: respect physical tile layout when resolving depth aliases
2026-09-27 15:05:46 +04:00
f53f0ca483
Graphics: preserve rendered contents across 1D and 2D texture aliases
2026-09-27 15:05:46 +04:00
7b6bfdec64
Graphics: share canonical padded layouts for single-sample color targets
2026-09-27 15:05:46 +04:00
a88181b897
Graphics: share texture layout for linear render-target mip chains
2026-09-27 11:10:02 +04:00
041874f663
Graphics: resolve equivalent terminal mip views without expanding backing
2026-09-27 11:04:19 +04:00
496432bbb4
Shader: skip identity image remapping on materialization hits
2026-09-27 10:47:18 +04:00
bec67b7863
Fix HITMAN 3 boot, layered presentation, and socket imports ( #851 )
...
* videoout: synchronize layered flips with premultiplied composition
* shader: support unsigned FFBH subword sources
* shader: apply cube-face result scaling
* shader: prune buffer reads proven out of bounds
* net: implement send and receive exports with shared socket handling
---------
Co-authored-by: nmzik <Nmzik@mail.ru >
2026-09-27 02:13:30 +04:00
81f312638f
graphics: encode packed UNorm buffer stores before writing skinning normals
2026-09-26 23:42:19 +04:00
16b83a034c
Shader: execute RDNA2 FP64 shadow arithmetic and log denorm limits
...
Shader: disable FP64 denorm preservation controls for now
2026-09-26 15:15:35 +04:00
cf268af839
Shader: implement RDNA2 image atomic float maximum
...
Shader: implement RDNA2 image atomic float minimum
Co-authored-by: foufouadi <attar.foued@gmail.com >
Co-authored-by: frans <francois.att@gmail.com >
Co-authored-by: fxpw <fxpw@outlook.com >
Co-authored-by: Matthew Hurley <171001439+theantipopau@users.noreply.github.com >
2026-09-26 15:15:35 +04:00
cda236dbb3
Shader recompiler: accept V_NOT_B32 SDWA partial dst with any source; allow 64 buffers
...
SDWA source extraction and destination insertion are independent. Cover the reported word1-to-word0 preserve form and byte-source partial destinations in compute tests. Verify 64 distinct compute buffers survive resource tracking and binding layout, and remove the obsolete CFG rejection.
(cherry picked from commit 9e74df7dc0
2026-09-26 01:58:55 +04:00
cf423df624
shader: remove per-draw vertex diagnostic atomics
2026-09-25 21:15:41 +04:00
0ec43a8d3d
graphics: name Vulkan images and views only on creation
2026-09-25 16:15:05 +04:00
bfdbba3aa4
graphics: share EOP clock and immediate write handling
...
Co-authored-by: Mac <me@itsmemac.com >
2026-09-25 16:14:40 +04:00
3585cd8f03
shader: simplify translator dispatch to void handlers
2026-09-25 14:27:09 +04:00
ff54608569
shader: add V_CMPX_O_F32 opcode
2026-09-25 14:27:09 +04:00
6bb68a3fd9
shader: stop repeated CFG merge gateway splitting
2026-09-25 14:27:09 +04:00
93185953f1
shader: fuse image specialization setup with materialization
2026-09-25 14:27:09 +04:00
5a705dd15f
shader: support V_CMPX_EQ_U16 ( #816 )
...
* shader: support V_CMPX_EQ_U16
Decode gfx11 VOPC 0xba and lower it as an unsigned 16-bit equality
compare with CMPX EXEC-mask semantics.
🤖 Generated with Codebuff 🤖
Co-Authored-By: Codebuff <noreply@codebuff.com >
* shader: correct CMPX EQ U16 runtime expectations
Remove the added CFG tests and correct two EXEC expectations in the compute regression case.
---------
Co-authored-by: Matthew Hurley <171001439+theantipopau@users.noreply.github.com >
Co-authored-by: Codebuff <noreply@codebuff.com >
Co-authored-by: nmzik <Nmzik@mail.ru >
2026-09-25 02:27:44 +04:00
a20fb7f9f8
agc: trace per-frame packet parameters only with graphics debug dump
...
The per-frame ACB submit, indirect dispatch, reset-queue and patch-address
parameter dumps, and the flip-pending poll, are logged only with the graphics
debug dump, the way the DCB submit path already is. Otherwise they were about
7.5 MB of log a minute in the Spider-Man world.
2026-09-25 00:03:08 +04:00
d646fd92d1
graphics: hoist loop-invariant checks out of draw/attrib hot paths ( #807 )
...
* graphics: hoist loop-invariant checks out of draw/attrib hot paths
DrawIndirectMulti recomputed the index_type_and_size switch on every
sub-draw of a multi-draw-indirect call, and ShaderApplyAttribSemantics
re-checked the debug-dump config flag on every vertex attribute. Both
values are invariant across their respective loops, so compute them
once before iterating instead.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com >
* graphics: cache vertex buffer descriptor size in AcquireVertexBuffers
VertexBufferDescriptorSize was computed twice per vertex-buffer slot
on every draw call: once while collecting guest ranges, and again
while rebuilding slot bindings. Both calls use identical inputs, so
cache the first pass's result and reuse it in the second.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com >
---------
Co-authored-by: Claude Sonnet 5 <noreply@anthropic.com >
2026-09-24 21:02:23 +04:00
d72a79af2d
graphics: skip compute dispatches with BVH instructions
...
Co-authored-by: Mac <me@itsmemac.com >
2026-09-24 20:46:04 +04:00
dc9280d75d
shader: add GLC/DLC buffer cache policy support
...
Co-authored-by: Mac <me@itsmemac.com >
2026-09-24 20:46:04 +04:00
6a9ae4ae43
shader: add SDWA support for V_MAX_I32
2026-09-24 20:46:04 +04:00
392f39e2f6
shader: support indirect BUFFER_LOAD_DWORDX3
2026-09-24 20:46:04 +04:00
cce0cd950c
videoout: add RGB10A2 PQ buffer support
...
Co-authored-by: Mac <me@itsmemac.com >
2026-09-24 20:46:04 +04:00
e43c242683
shader: add S_MEMREALTIME opcode
...
Co-authored-by: Maxime Allanic <maxime@allanic.me >
Co-authored-by: Mac <me@itsmemac.com >
2026-09-24 20:46:04 +04:00
732057b072
videoout: fix VRR status import signature
...
Co-authored-by: Mac <me@itsmemac.com >
2026-09-24 20:46:04 +04:00
2aaf0c9ba3
graphics: clamp raster depth after polygon offset
...
Enable native Vulkan depth clamping independently of guest depth clipping
2026-09-24 14:09:02 +04:00
fcf0f3b67e
shader: fold the lane test after a pixel shader's entry s_wqm ( #801 )
...
Preserve live lane predicates through RDNA2 whole-quad expansion
Keep the source-live predicate when WQM expands a scalar mask, so entry masks remain known live without an instruction pre-scan. Preserve scalar mask values, SCC, half writes, and raw-source behavior.
Cover entry pixel masks, cross-half copies, and scalar/high-word sources with existing shader regression suites.
Co-authored-by: nmzik <Nmzik@mail.ru >
Co-authored-by: Douglas <douglasproducoes21@gmail.com >
2026-09-24 12:02:19 +04:00
a6248c7c7c
Convert formatted half-float buffer stores from F32
...
Co-authored-by: TarkusR <90155059+TarkusR@users.noreply.github.com >
2026-09-24 11:13:33 +04:00
3bd5de646d
Reuse prepared shader bindings across draws and dispatches
2026-09-24 11:13:33 +04:00
963a0817dc
Bound uniformized image keys by guarded material mask
...
Co-authored-by: TarkusR <90155059+TarkusR@users.noreply.github.com >
2026-09-24 11:13:33 +04:00
1617ee77e5
Share CFG reachability for descriptor bounds analysis
2026-09-24 11:13:33 +04:00
66cc2fe26d
Track depth and stencil attachment feedback across graphics stages
...
Co-authored-by: TarkusR <90155059+TarkusR@users.noreply.github.com >
2026-09-24 11:13:33 +04:00
nmzik