| .. |
|
BranchPastEndpgm.cpp
|
fix(shader): keep decoding past an s_endpgm while a branch targets later code
|
2026-10-04 17:03:31 +02:00 |
|
BufferAtomicCsub.cpp
|
feat(shader): implement buffer_atomic_csub
|
2026-10-05 02:15:47 +02:00 |
|
BufferAtomics.cpp
|
feat(shader): implement buffer_atomic_inc/dec and the 64-bit integer buffer atomics
|
2026-10-04 22:56:09 +02:00 |
|
BufferAtomicsFloat.cpp
|
feat(shader): implement the float and 64-bit inc/dec buffer atomics
|
2026-10-04 22:56:09 +02:00 |
|
BufferAtomicsIncDec64.cpp
|
feat(shader): implement the float and 64-bit inc/dec buffer atomics
|
2026-10-04 22:56:09 +02:00 |
|
BufferAtomicsOrSwap64.cpp
|
test(shader): execute buffer_atomic_or_x2 and buffer_atomic_swap_x2 against hardware results
|
2026-10-05 03:54:49 +02:00 |
|
BufferIntegerAtomics.cpp
|
test(shader): execute the untested buffer byte/short/dwordx2/x3 loads and stores and the 32-bit integer buffer atomics against values measured on RDNA
|
2026-10-04 18:37:45 +02:00 |
|
BufferLoadStore.cpp
|
test(shader): execute the untested buffer byte/short/dwordx2/x3 loads and stores and the 32-bit integer buffer atomics against values measured on RDNA
|
2026-10-04 18:37:45 +02:00 |
|
Bvh64IntersectRay.cpp
|
feat(shader): implement image_bvh64_intersect_ray
|
2026-10-05 00:26:32 +00:00 |
|
CacheControl.cpp
|
feat(shader): decode cache invalidations and performance hints as no-ops
|
2026-10-01 22:45:25 +02:00 |
|
D16Memory.cpp
|
feat(shader): implement the D16 byte/short loads and high-half stores
|
2026-10-03 11:37:07 +02:00 |
|
DivFixupF16.cpp
|
feat(shader): implement v_div_fixup_f16
|
2026-10-03 09:19:46 +02:00 |
|
Division.cpp
|
fix(shader): choose v_div_scale_f32/v_div_fmas_f32 NaNs on the bits and refuse s_denorm_mode
|
2026-10-04 12:05:33 +02:00 |
|
DivisionResultModifiers.cpp
|
feat(shader): accept clamp on v_div_fmas/fixup and omod on their f64 forms
|
2026-10-05 05:19:06 +02:00 |
|
Dpp8.cpp
|
feat(shader): decode DPP8 on VOP1 and VOP2
|
2026-10-05 03:32:30 +02:00 |
|
Dpp16InactiveSource.cpp
|
fix(shader): DPP16 lanes whose source lane is inactive
|
2026-10-05 03:32:41 +02:00 |
|
Dpp16Operands.cpp
|
fix(shader): DPP16 operands of v_pk_fmac_f16 and the relative moves
|
2026-10-04 22:35:51 +02:00 |
|
DppNoForm.cpp
|
fix(shader): refuse DPP16 on opcodes with no DPP form
|
2026-10-05 03:33:06 +02:00 |
|
DsPermute.cpp
|
feat(shader): implement ds_permute_b32
|
2026-10-04 08:19:43 +02:00 |
|
DsSwizzle.cpp
|
test(shader): execute ds_swizzle_b32 in all three offset modes
|
2026-10-05 04:34:00 +02:00 |
|
F32MinMaxNan.cpp
|
fix(shader): return src0 when both f32 min/max sources are NaN
|
2026-10-05 00:00:40 +02:00 |
|
F32OutputModifier.cpp
|
fix(shader): apply the f32 output modifier on the bits like the hardware
|
2026-10-05 05:00:29 +02:00 |
|
F32ResultClamp.cpp
|
fix(shader): clamp f32 results to +0 for NaN and -0
|
2026-10-04 12:16:07 +02:00 |
|
F64Arithmetic.cpp
|
feat(shader): implement basic f64 VALU ops
|
2026-10-04 08:52:14 +02:00 |
|
F64Conversions.cpp
|
feat(shader): implement basic f64 VALU ops
|
2026-10-04 08:52:14 +02:00 |
|
F64Division.cpp
|
feat(shader): implement v_div_scale_f64, v_div_fmas_f64 and v_div_fixup_f64
|
2026-10-05 03:37:13 +02:00 |
|
F64DivisionModifiers.cpp
|
feat(shader): implement v_div_scale_f64, v_div_fmas_f64 and v_div_fixup_f64
|
2026-10-05 03:37:13 +02:00 |
|
F64NanConversions.cpp
|
fix(shader): build f32/f64 conversion NaNs from the bits
|
2026-10-04 08:52:14 +02:00 |
|
F64Rounding.cpp
|
feat(shader): implement basic f64 VALU ops
|
2026-10-04 08:52:14 +02:00 |
|
F64Transcendental.cpp
|
feat(shader): implement v_rcp/rsq/sqrt_f64 and v_trig_preop_f64
|
2026-10-05 03:36:14 +02:00 |
|
FlatCacheBits.cpp
|
test(shader): keep the flat cache bits test within CI's time limit
|
2026-10-05 16:54:53 +02:00 |
|
FlatD16Loads.cpp
|
test(shader): execute the flat D16 loads against hardware results
|
2026-10-05 03:50:30 +02:00 |
|
FlatGlobalLoads.cpp
|
test(shader): execute flat and global loads against hardware results
|
2026-10-04 19:09:54 +02:00 |
|
FlatStore.cpp
|
feat(shader): store through flat and global addresses
|
2026-10-05 05:05:03 +02:00 |
|
Float16Dot.cpp
|
fix(shader): refuse v_dot2_f32_f16 without op_sel_hi on the accumulator
|
2026-10-04 18:47:31 -05:00 |
|
Float16Misc.cpp
|
feat(shader): implement f16 ldexp/frexp/norm/class, v_sat_pk_u8_i16 and v_mul/mac_legacy_f32
|
2026-10-02 06:46:26 +02:00 |
|
Float16ResultModifiers.cpp
|
test(shader): compare f16 sine results within the Vulkan error bound
|
2026-10-05 03:38:07 +02:00 |
|
Float16Rounding.cpp
|
fix(shader): round f32 to f16 to nearest even on every driver
|
2026-10-02 06:40:10 +02:00 |
|
FmaLegacy.cpp
|
fix(shader): apply the DX9 zero rule to v_fma_legacy_f32
|
2026-10-04 21:47:22 -03:00 |
|
FmaRounding.cpp
|
fix(shader): keep fused multiply-adds fused and v_mad/v_mac_f32 rounded twice
|
2026-10-02 06:41:03 +02:00 |
|
FormatD16.cpp
|
feat(shader): implement the D16 format buffer loads
|
2026-10-03 11:37:10 +02:00 |
|
FormatD16Store.cpp
|
feat(shader): implement the D16 format buffer stores
|
2026-10-03 11:37:15 +02:00 |
|
FormattedStore.cpp
|
fix(shader): convert formatted buffer stores to the element format
|
2026-10-03 11:37:12 +02:00 |
|
GlobalAtomics.cpp
|
feat(shader): implement the integer flat and global atomics
|
2026-10-05 05:05:03 +02:00 |
|
GlobalAtomicsFloat.cpp
|
feat(shader): implement the float and 64-bit inc/dec flat and global atomics
|
2026-10-05 05:05:10 +02:00 |
|
GlobalLoadAddtid.cpp
|
feat(shader): implement global_load_dword_addtid
|
2026-10-04 17:09:25 +02:00 |
|
GlobalStoreAddtid.cpp
|
feat(shader): implement global_store_dword_addtid
|
2026-10-05 08:41:19 +02:00 |
|
ImageAtomics.cpp
|
feat(shader): implement the missing integer image atomics
|
2026-10-02 17:39:14 +02:00 |
|
ImageAtomicsFloat.cpp
|
feat(shader): implement image_atomic_fmin, fmax and fcmpswap
|
2026-10-04 23:01:27 +02:00 |
|
ImageCacheBits.cpp
|
feat(shader): accept the dlc cache bit on MIMG
|
2026-10-04 22:54:05 +02:00 |
|
ImageLoadPacked.cpp
|
feat(shader): implement image_load_pck and image_load_mip_pck with signed variants
|
2026-10-04 22:32:13 +02:00 |
|
ImageSampleBiasA16.cpp
|
fix(shader): give the a16 bias of image samples its own address dword
|
2026-10-05 01:30:17 +02:00 |
|
ImageSampleDerivatives.cpp
|
fix(shader): read _cd quad gradients through a lane-varying permute
|
2026-10-05 03:39:58 +02:00 |
|
ImageSampleLodClamp.cpp
|
feat(shader): decode image_sample_d_cl_o
|
2026-10-02 19:07:30 +02:00 |
|
ImageStorePacked.cpp
|
feat(shader): implement image_store_pck and image_store_mip_pck
|
2026-10-04 22:46:58 +02:00 |
|
ImageTexelStatus.cpp
|
feat(shader): accept tfe and lwe on MIMG loads, stores and samples
|
2026-10-05 08:25:57 +02:00 |
|
IntegerDot.cpp
|
feat(shader): implement the integer dot products
|
2026-10-02 19:01:57 +02:00 |
|
LdsAddtid.cpp
|
test(shader): execute the untested LDS reads, writes and integer atomics against values measured on RDNA
|
2026-10-04 22:35:58 +02:00 |
|
LdsAtomics.cpp
|
feat(shader): implement the missing 32-bit LDS atomics and fix ds_min/max_f32
|
2026-10-02 07:11:48 +02:00 |
|
LdsAtomics64.cpp
|
test(shader): order the contended LDS 64-bit atomics with barriers
|
2026-10-04 18:46:54 -05:00 |
|
LdsIntegerAtomics.cpp
|
test(shader): execute the untested LDS reads, writes and integer atomics against values measured on RDNA
|
2026-10-04 22:35:58 +02:00 |
|
LdsReadWrite.cpp
|
test(shader): execute the untested LDS reads, writes and integer atomics against values measured on RDNA
|
2026-10-04 22:35:58 +02:00 |
|
MixPrecision.cpp
|
ci: run the shader execution tests on lavapipe
|
2026-10-01 22:45:25 +02:00 |
|
PackedIntegerClamp.cpp
|
fix(shader): VOP3P integer clamp on v_pk_mad/add/sub_{i16,u16}
|
2026-10-04 12:33:38 +02:00 |
|
Permlane16.cpp
|
fix(shader): keep v_permlane16 lanes whose source lane is inactive
|
2026-10-05 04:38:40 +02:00 |
|
PixelHelperLanes.cpp
|
fix(shader): isolate wave32 operations in wide host subgroups
|
2026-10-04 21:02:46 -03:00 |
|
PixelLds.cpp
|
test(agc): validate pixel LDS and expose pipeline statistics
|
2026-10-04 23:04:39 -03:00 |
|
PixelLdsLaneSlots.cpp
|
perf(recompiler): index lane-strided per-invocation LDS by constant slots
|
2026-10-05 18:18:29 +13:00 |
|
ReadFirstLane.cpp
|
fix(recompiler): v_readfirstlane_b32 of an empty EXEC reads lane 0
|
2026-10-03 20:16:35 +13:00 |
|
ReadLane.cpp
|
fix(shader): wrap the v_readlane_b32 lane select at the wave size
|
2026-10-02 18:23:56 +13:00 |
|
RelativeIndexing.cpp
|
feat(shader): implement v_movrelsd_b32, v_movrelsd_2_b32, v_swap_b32 and v_swaprel_b32
|
2026-10-03 11:37:02 +02:00 |
|
ScalarBitCount.cpp
|
feat(shader): implement s_bcnt0_i32_b64, s_ff0_i32_b64, s_flbit_i32(_i64), s_quadmask_b32
|
2026-10-02 09:59:47 +02:00 |
|
ScalarGetreg.cpp
|
docs: record that s_getreg_b32 reads round to nearest even after s_setreg_b32
|
2026-10-04 18:48:04 -05:00 |
|
ScalarProgramEnd.cpp
|
test(agc): discard the results of recompiles expected to be refused
|
2026-10-05 07:12:32 +00:00 |
|
ScalarProgramEndSaved.cpp
|
fix(shader): translate s_round_mode only for round to nearest even
|
2026-10-05 03:34:37 +02:00 |
|
ScalarProgramFlow.cpp
|
fix(shader): wave-wide exec and vcc branch conditions
|
2026-10-05 04:56:35 +02:00 |
|
ScalarRelativeIndexing.cpp
|
feat(shader): implement s_movrels/s_movreld (b32, b64) and s_movrelsd_2_b32
|
2026-10-02 09:59:59 +02:00 |
|
ScalarSetpc.cpp
|
fix(shader): refuse s_setpc_b64 after s_sub with the immediate first
|
2026-10-05 04:45:57 +02:00 |
|
ScalarSop1.cpp
|
fix(shader): s_wqm SCC and s_andn{1,2}_wrexec destination
|
2026-10-04 16:56:48 +02:00 |
|
ScalarSop2.cpp
|
fix(shader): s_lshlN_add SCC and s_bfe_[iu]32 fields past bit 31
|
2026-10-04 22:35:45 +02:00 |
|
ScalarSopkCompare.cpp
|
test(shader): cover the s_cmpk compares
|
2026-10-02 17:06:50 +02:00 |
|
ScalarSopkMisc.cpp
|
test(agc): discard the results of recompiles expected to be refused
|
2026-10-05 07:12:32 +00:00 |
|
ScalarSopkWaitcnt.cpp
|
test(shader): cover the SOPK s_waitcnt counters and count them as decoded
|
2026-10-04 17:13:18 +02:00 |
|
ScalarWideLoads.cpp
|
fix(shader): return zero when an s_buffer_load offset passes 2^32
|
2026-10-05 04:29:33 +02:00 |
|
SdwaDestination.cpp
|
fix(shader): v_mov_b32 SDWA writes byte destinations
|
2026-10-04 11:44:10 +02:00 |
|
SdwaIntegerClamp.cpp
|
feat(shader): saturate VOP2 integer SDWA results on clamp
|
2026-10-04 13:36:35 +02:00 |
|
SdwaIntegerSelectors.cpp
|
feat(shader): accept every SDWA selector on VOP2 integer ops
|
2026-10-04 13:29:20 +02:00 |
|
ShaderClock.cpp
|
feat(shader): implement s_memtime and s_memrealtime
|
2026-10-02 07:58:41 +02:00 |
|
TbufferFormatD16.cpp
|
test(shader): execute tbuffer_load_format_d16_xyzw against hardware results
|
2026-10-05 04:01:05 +02:00 |
|
ViewPastLastMip.cpp
|
fix(agc): address texture views that start past the surface's last mip
|
2026-10-04 19:52:04 +13:00 |
|
Vop1Control.cpp
|
test(shader): cover the operand-less decoding of v_nop, v_pipeflush and v_clrexcp
|
2026-10-02 17:50:53 +02:00 |
|
Vop1FloatUnary.cpp
|
fix(shader): choose unary f32/f16 special results on the bits, as RDNA does
|
2026-10-05 03:38:12 +02:00 |
|
Vop1Vop2Integer.cpp
|
fix(shader): v_cvt_rpi/flr_i32_f32 NaN and exact round-half-up
|
2026-10-04 22:35:56 +02:00 |
|
Vop2ModifierForms.cpp
|
feat(shader): accept float modifiers on v_cndmask_b32, v_mul_legacy_f32 and v_ldexp_f16
|
2026-10-05 04:59:40 +02:00 |
|
Vop3Aliases.cpp
|
feat(shader): decode VOP3 v_max/min_f16 and v_cvt_f32_f16/ubyte, accept abs/neg on f16 binaries
|
2026-10-01 22:45:25 +02:00 |
|
Vop3AlignOpSel.cpp
|
fix(shader): VOP3 op_sel on v_alignbit/alignbyte_b32 and 16-bit max3/min3/med3
|
2026-10-04 12:41:07 +02:00 |
|
Vop3CarryOut.cpp
|
test(shader): cover the VOP3 carry-out add and subtracts and count v_sub_co_u32 as decoded
|
2026-10-04 17:01:01 +02:00 |
|
Vop3CompareModifiers.cpp
|
fix(shader): accept neg on VOP3-encoded float compares
|
2026-10-01 22:45:25 +02:00 |
|
Vop3CubeClamp.cpp
|
feat(shader): accept clamp on v_cube*_f32 and match their zero and subnormal results
|
2026-10-05 10:57:27 +02:00 |
|
Vop3Integer.cpp
|
feat(shader): implement VOP3 v_add/sub_nc_i32 with clamp, v_mul_lo_u16, v_mad_u16/i16/u32_u16/i32_i16, v_ashrrev_i64
|
2026-10-01 22:45:25 +02:00 |
|
Vop3Integer16TernaryOpSel.cpp
|
fix(shader): VOP3 op_sel on v_alignbit/alignbyte_b32 and 16-bit max3/min3/med3
|
2026-10-04 12:41:07 +02:00 |
|
Vop3LegacySourceModifiers.cpp
|
fix(shader): v_mullit_f32 legacy rules, v_cvt_pk_u8_f32 rounding and VOP3 neg/abs
|
2026-10-05 10:53:50 +02:00 |
|
Vop3Lerp.cpp
|
feat(shader): implement v_lerp_u8
|
2026-10-02 18:57:06 +02:00 |
|
Vop3MadClamp.cpp
|
feat(shader): implement clamp on v_mad_u64_u32 and v_mad_i64_i32
|
2026-10-05 04:59:15 +02:00 |
|
Vop3MadI64.cpp
|
feat(shader): implement v_mad_i64_i32
|
2026-10-04 09:17:12 +02:00 |
|
Vop3PackLdexp.cpp
|
fix(shader): compute v_cvt_pknorm_*_f32, v_ldexp_f32 and v_pack_b32_f16 on the bits
|
2026-10-05 03:42:08 +02:00 |
|
Vop3QuadSad.cpp
|
feat(shader): implement v_qsad_pk_u16_u8 and the mqsad ops
|
2026-10-04 08:22:25 +02:00 |
|
Vop3Sad.cpp
|
feat(shader): implement v_sad_u8, v_sad_hi_u8, v_sad_u16 and v_msad_u8
|
2026-10-02 18:25:22 +02:00 |
|
VopcCompare.cpp
|
fix(shader): lower f16 NLE comparisons through swapped unordered less-than
|
2026-10-02 21:17:18 +03:00 |
|
VopcCompareF64.cpp
|
feat(shader): implement the VOPC f64 compares
|
2026-10-02 17:16:32 +02:00 |
|
VopcCompareTable.cpp
|
test(shader): execute every non-f64 VOPC compare against values measured on RDNA
|
2026-10-04 18:12:35 +02:00 |
|
VulkanTestDevice.hpp
|
ci: run the shader execution tests on lavapipe
|
2026-10-01 22:45:25 +02:00 |
|
Wave32Subgroup.cpp
|
fix(shader): isolate wave32 operations in wide host subgroups
|
2026-10-04 21:02:46 -03:00 |
|
WaveIdInWorkgroup.cpp
|
feat(shader): implement s_get_waveid_in_workgroup
|
2026-10-02 18:08:46 +02:00 |
|
WaveSleep.cpp
|
feat(shader): decode s_wakeup as a no-op
|
2026-10-02 18:10:07 +02:00 |
|
WaveUniform.cpp
|
perf(recompiler): emit wave-uniform values once for both lanes of a two-lane invocation
|
2026-10-03 20:00:38 +13:00 |
|
WriteLane.cpp
|
fix(shader): v_writelane_b32 ignores EXEC
|
2026-10-02 23:42:49 +02:00 |
4066e6dd29