0e61bedf9a
Merge pull request #4162 from Celegans12/fix/shader-wave64-lane-reductions
...
fix(shader): match half-wave reductions over relatively addressed vector registers
2026-10-12 23:54:08 +13:00
b40a0b17dc
Merge pull request #3946 from danzaio/fix/shader-failure-address
...
fix(agc): name the shader address and stage in preparation failures
2026-10-12 23:51:09 +13:00
e9d35d6491
Merge pull request #3636 from JAB-dev/feat/agc-color-target-1-5-5-5
...
feat(agc): render 1_5_5_5 UNORM color targets
2026-10-12 23:48:42 +13:00
eee8541dae
Merge pull request #2904 from Scramblrrrr/codex/depth-storage-reuse
...
fix(graphics): allow storage textures in reused depth memory
2026-10-12 23:46:54 +13:00
2979ae37a3
Merge pull request #4152 from adriadam10/feat/phase-b
...
perf(agc): build shader pipeline libraries when shaders are registered
2026-10-12 10:31:42 +02:00
9bc3623517
Merge pull request #4355 from oneandonlydean/up4/fix-4276-stencil-ref-export
...
fix(agc): export the stencil reference from pixel shaders with VK_EXT_shader_stencil_export
2026-10-12 21:22:09 +13:00
3f80d529da
Merge pull request #4309 from oneandonlydean/up4/fix-2776-msaa-enable-single-sample
...
fix(agc): accept MSAA_ENABLE on a single-sample target sampled at the pixel center
2026-10-12 21:21:26 +13:00
b1ee794a66
test(agc): give the formatted buffer vertex case clip distances and the zero-position pixel shader its push slot
...
Co-Authored-By: Claude <noreply@anthropic.com>
2026-10-12 09:59:23 +02:00
672e43ca67
perf(recompiler): keep compute shaders specialized; only prebuilt vertex and pixel shaders take the registration form
...
Co-Authored-By: Claude <noreply@anthropic.com>
2026-10-12 09:50:41 +02:00
361c7e2024
perf(agc): keep oversized shaders specialized and prebuild libraries on their own thread
...
Co-Authored-By: Claude <noreply@anthropic.com>
2026-10-12 09:50:41 +02:00
67556722e1
perf(recompiler): read vertex attribute component selectors at run time when modules are built at registration
...
Co-Authored-By: Claude <noreply@anthropic.com>
2026-10-12 09:50:41 +02:00
e9def903fd
perf(agc): prebuild each stage's library alone and keep two descriptor sets with pipeline libraries
...
Co-Authored-By: Claude <noreply@anthropic.com>
2026-10-12 09:50:41 +02:00
7f64d14772
perf(agc): build the shader pipeline libraries when graphics stages are resolved at registration
...
Co-Authored-By: Claude <noreply@anthropic.com>
2026-10-12 09:50:41 +02:00
baf3437465
perf(recompiler): read depth-compare state and export mappings at run time when modules are built at registration
...
Co-Authored-By: Claude <noreply@anthropic.com>
2026-10-12 09:50:33 +02:00
765ea6a10f
perf(recompiler): keep descriptor heaps uncompacted and read image modes at run time when modules are built at registration
...
Co-Authored-By: Claude <noreply@anthropic.com>
2026-10-12 09:50:32 +02:00
ddb6680667
perf(recompiler): read buffer V# words in the shader when modules are built at registration
...
Co-Authored-By: Claude <noreply@anthropic.com>
2026-10-12 09:50:32 +02:00
22d662eda7
fix(agc): export the stencil reference from pixel shaders with VK_EXT_shader_stencil_export
2026-10-12 19:44:41 +13:00
d06c065657
Merge pull request #3895 from CouchRiv/fix-shader-vcmpx-f32-family
...
fix(shader): keep f32 denormals in compares when denormals are kept
2026-10-12 19:39:34 +13:00
fdfbeba8ad
fix(agc): accept MSAA_ENABLE on a single-sample target sampled at the pixel center
2026-10-12 19:07:15 +13:00
deaa2e3ef6
test(agc): draw into a 1_5_5_5 target and read the 16 bits back
...
Draws 32_ABGR exports into a tiled and a linear format 17 target and compares every texel with
the layout X in bits 0-4, Y in 5-9, Z in 10-14, W in bit 15, including the X/Z-swapped pairs, rounding
edges and texels outside the scissor. Reverting the X/Z exchange fails it.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-10-12 07:59:29 +02:00
9db923e907
fix(shader): clip primitives with an all-zero clip position
2026-10-12 06:46:34 +02:00
768929bb76
test(agc): preparation failures name the shader address and stage
...
FailureCapture now requires the code address and stage in the diagnosed failure, with and without the request dump. Fails before the wrap, passes after. AI-assisted: yes.
2026-10-12 01:33:37 -03:00
32cb3fea95
Merge pull request #3932 from CouchRiv/fix-shader-f16-denorm-flush-family
...
fix(shader): flush f16 denormals in unary, frexp and conversion ops per the float mode
2026-10-12 17:29:43 +13:00
c12cb634f1
Merge pull request #4249 from oneandonlydean/up4/fix-skip-messages
...
test(agc): word the tessellation and oversized dispatch skips as device limitations, as check_skips expects
2026-10-12 16:09:15 +13:00
34a16b7f08
Merge pull request #4159 from MarcZX100/codex/fix-sampled-cache-fixture-4141
...
test(agc): keep sampled cache fixture registrations separate
2026-10-12 15:47:18 +13:00
572e9d9f78
test(agc): word the tessellation and oversized dispatch skips as device limitations, as check_skips expects
2026-10-12 15:06:12 +13:00
20b801b7e8
test(agc): report the packed f16 native skip as a device limitation, as check_skips expects
2026-10-12 14:51:21 +13:00
d0ca839cc9
Merge pull request #4057 from jweidenh/codex/vector-window-stage-inputs
...
fix(recompiler): include implicit inputs in relative vector windows
2026-10-12 14:30:23 +13:00
8938a257f2
test(agc): read lane 63 of the vertex index in the registered workgroup fixture
...
The fixture read lane 63 of v0, which the program never writes. Since #3546 a wave64 vertex program on a narrower host subgroup builds that read as 0, so the synchronous registration the test expects to fail succeeds. v5 holds the vertex index, which is not 0 in lanes 32-63, so the read still throws.
2026-10-12 13:44:23 +13:00
ef218ef928
test(agc): distinguish GPU depth from reused storage bytes
2026-10-11 21:29:59 -03:00
c87c8c229b
test(agc): keep sampled cache fixture registrations separate
2026-10-12 00:12:50 +00:00
364d7cf29f
fix(shader): match half-wave reductions over relatively addressed vector registers
...
A program that uses v_movrels_b32 or v_movreld_b32 keeps every vector
register from the lowest relatively addressed one up in a per-invocation
window array, so its plain register accesses become LoadVectorWindow and
StoreVectorWindow. The half-wave reduction matcher followed only SSA values,
so a wave64 scan, v_permlanex16_b32 join and lane 31/63 read through that
array threw that lane 63 is outside the 32-lane host subgroup.
The matcher now reads a window load at a constant slot as the value of the
last store to that slot earlier in its block, unless a store at a runtime
slot lies in between; each invocation owns its array, so that is the value
the load returns. A store in another block, or a v_movreld_b32 at a runtime
M0 in between, still throws. This was the only refused lane 32-63 read left
among Ghost of Yotei's wave64 graphics programs (one pixel program).
2026-10-12 02:07:50 +02:00
e4575c723e
test(recompiler): keep vector window fixtures observable
2026-10-11 19:23:00 -04:00
c0c86deeb8
test(recompiler): cover implicit inputs in relative vector windows
2026-10-11 19:23:00 -04:00
de54527a8b
fix(shader): keep f32 denormals in compares when denormals are kept
...
With the f32 denormal field of FLOAT_MODE set to keep, v_cmp_X_f32 and
v_cmpx_X_f32 read a denormal operand as zero: NVIDIA, RADV and lavapipe
all flush denormals in their float compares. Compare the operands as
sign-magnitude integers instead, with NaN handled apart. Compares with
flushed denormals are unchanged. This matches RDNA2 (gfx1036) on 256
operand pairs per opcode, with f32 denormals kept and flushed.
Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>
2026-10-11 18:51:37 -04:00
325e0a8bdd
Merge pull request #3741 from jweidenh/codex/optimized-pipeline-readback
...
test(agc): verify graphics output after optimized pipeline binding
2026-10-12 00:50:45 +02:00
3905e7e2c9
Merge pull request #3827 from CouchRiv/fix-shader-combined-cvt-i16-f16-omod
...
fix(shader): accept output modifiers on v_cvt_i16_f16 and ignore them as the hardware does
2026-10-12 00:39:20 +02:00
f9e1d2541c
Merge pull request #3750 from fma-rc/feat/shader-subvector-loop
...
feat(shader): implement s_subvector_loop_begin and s_subvector_loop_end
2026-10-12 00:28:10 +02:00
2b8f151b3f
test(agc): verify optimized pipeline draws and readback
2026-10-12 00:16:28 +02:00
33067ca0c7
Merge pull request #3856 from ErenYeager1836/carry/recompiler-vector-window
...
perf(recompiler): keep relatively addressed vector registers in a window array
2026-10-12 00:10:58 +02:00
825cbd4106
Merge pull request #3531 from karanvora2599/perf/shader-native-packed-f16
...
perf(shader): compute v_pk_add_f16 and v_pk_mul_f16 with native f16 math
2026-10-12 00:10:02 +02:00
c7731cf4d4
Merge pull request #3843 from kr4y4/fix/agc-aniso-override-force-degamma
...
fix(agc): keep FORCE_DEGAMMA paired when ANISO_OVERRIDE rebuilds a sampler
2026-10-12 00:09:01 +02:00
31bf997b53
Merge pull request #3833 from David-cmrg/test/agc-gated-dispatch-short-spins
...
test(agc): split the gated dispatch producer spin into short dispatches
2026-10-12 00:08:18 +02:00
6407626dd1
Merge pull request #3830 from winstrex/fix/agc-flat-apertures-kernel-parts
...
test(agc): split agc_driver_flat_apertures by shader instead of by row
2026-10-12 00:08:14 +02:00
e53c30bcdf
Merge pull request #3828 from CouchRiv/fix-shader-combined-pknorm-f16
...
fix(shader): accept abs, neg and op_sel source modifiers on v_cvt_pknorm_i16_f16 and v_cvt_pknorm_u16_f16
2026-10-12 00:07:49 +02:00
4b355d4e68
Merge pull request #3825 from kr4y4/fix/shader-dpp8-pk-fmac-f16
...
fix(shader): accept DPP8 on v_pk_fmac_f16
2026-10-12 00:07:47 +02:00
1a7b96b5bc
Merge pull request #3822 from object05/test/f32-denormal-flush-split-fma
...
test(shader): accept the split fma sum in F32DenormalFlush
2026-10-12 00:06:56 +02:00
e10f91b305
Merge pull request #3777 from MarcZX100/codex/agc-store-idle-3272
...
fix(agc): store pending storage-image results when queues idle
2026-10-12 00:04:39 +02:00
e05a603771
Merge pull request #3668 from CouchRiv/fix-shader-float-compare-clamp
...
fix(shader): accept the clamp bit on VOP3 float compares
2026-10-11 23:46:41 +02:00
cbd98bbdc1
Merge pull request #3540 from ivica00/fix/srgb-bilinear-cube-zero
...
fix(shader): return 0 for an 8-bit sRGB bilinear cube comparison
2026-10-11 23:45:00 +02:00
Dean
Adrià
Adrià Franch
Dean Galvin
JAB-dev
fma-rc
danzaio
Scramblrrrr
MarcZX100
Celegans12
jweidenh
Alex