Lines Matching +full:run +full:- +full:shader +full:- +full:db
6 but they can sometimes be useful for debugging end-user issues.
9 ---------------------------
42 - using a VK driver which has no WSI implementation for your display server
43 - profiling the DRI frontend against your VK driver's WSI implementation
50 - running xrdp
51 - using a VK driver which doesn't support modifiers
54 -------------------------------
69 following comma-separated list of named flags, which adds extra
99 ``GL_EXT_foo -GL_EXT_bar`` will enable the ``GL_EXT_foo`` extension
107 or before year X will be reported. This is to work-around a bug in
108 some games where the extension string is copied into a fixed-size
110 buffer overrun can cause the game to crash. This is a work-around for
118 - The format should be ``MAJOR.MINOR[FC|COMPAT]``
119 - ``FC`` is an optional suffix that indicates a forward compatible
121 - ``COMPAT`` is an optional suffix that indicates a compatibility
124 - GL versions <= 3.0 are set to a compatibility (non-Core) profile
125 - GL versions = 3.1, depending on the driver, it may or may not have
127 - GL versions >= 3.2 are set to a Core profile
128 - Examples:
131 select a compatibility (non-Core) profile with GL version 2.1.
133 select a compatibility (non-Core) profile with GL version 3.0.
151 - Mesa may not really implement all the features of the given
159 - The format should be ``MAJOR.MINOR``
160 - Examples: ``2.0``, ``3.0``, ``3.1``
161 - Mesa may not really implement all the features of the given
180 if set to ``true``, disables the on-disk shader cache. If set to
181 ``false``, enables the on-disk shader cache when it is disabled by
183 if on-disk shader cache is disabled.
187 if set, determines the maximum size of the on-disk cache of compiled
188 shader programs. Should be set to a number optionally followed by
202 if set, determines the directory to be used for the on-disk cache of
203 compiled shader programs. If this variable is not set, then the cache
210 if set to ``true``, keeps hit/miss statistics for the shader cache.
215 if set to 1, enables the single file Fossilize DB on-disk shader
216 cache implementation instead of the default Mesa-DB cache
229 if set to 1, enables the multi file on-disk shader cache implementation
230 instead of the default Mesa-DB cache implementation.
240 a string of comma separated file paths to read only Fossilize DB
241 shader caches for loading at initialization. The file paths are
243 referencing both the cache DB and its index file. E.g.
250 specifies number of mesa-db cache parts, default is 50.
254 Mesa-DB cache eviction algorithm calculates weighted score for the
262 a text file that contains a new-line separated list of read only
263 Fossilize DB shader caches to load. The list file is modifiable at
275 if set to 1, enables simultaneous use of :abbr:`RW (read-write)` and
276 :abbr:`RW (read-write)` Fossilize DB caches. At first, data will be
294 see :ref:`Experimenting with Shader Replacements <replacement>`
298 see :ref:`Experimenting with Shader Replacements <replacement>`
305 - The format should be ``MAJOR.MINOR[.PATCH]``
306 - This will not let you force a version higher than the driver's
308 - This can be very useful for debugging but some features may not be
332 not they ever see a wait-before-signal condition.
336 print debug info about device selection decision-making
340 A comma-separated list of trace types used for offline analysis. The
346 .. list-table::
347 :header-rows: 1
349 * - File extension
350 - Offline analysis tool
351 - Supported drivers
352 * - ``rmv``
353 - Radeon Memory Visualizer
354 - ``RADV``
355 * - ``rgp``
356 - Radeon GPU Profiler
357 - ``RADV``
358 * - ``rra``
359 - Radeon Raytracing Analyzer
360 - ``RADV``
361 * - ``ctxroll``
362 - Context rolls
363 - ``RADV``
365 - Creating RMV captures requires the ``scripts/setup.sh`` script in the
366 Radeon Developer Tools folder to be run beforehand
370 Enables per-submit capture for compute-only workload. Disabled by default
390 print debug info about device selection decision-making
399 - ``DRI_PRIME=N``: selects the Nth non-default GPU (N > 0).
400 - ``DRI_PRIME=pci-0000_02_00_0``: selects the GPU connected to this PCIe bus
401 - ``DRI_PRIME=vendor_id:device_id``: selects the first GPU matching these ids.
408 ``lspci -nn | grep VGA`` can be used to know the PCIe bus or ids to use.
412 If set, overrides the global search-directories used when searching for
413 drirc config files. The user-local one will still be used. Mostly useful for
417 --------------------------------
425 a comma-separated list of debug options to apply to NIR
430 a comma-separated list of optimization/lowering passes to skip.
433 --------------------------------------
464 -------------------------------------
477 automated test-runs.
487 ----------------------------------------------------
497 a comma-separated list of named flags, which do various things:
513 ``capture-all``
522 dump shader assembly for compute shaders
524 generate compute shader SIMD32 programs even if workgroup size
535 dump shader assembly for fragment shaders
537 dump shader assembly for geometry shaders
545 dump shader assembly for mesh shaders
547 don't generate SIMD8 fragment shader
549 suppress generation of 16-wide fragment shaders. useful for
552 suppress generation of 32-wide fragment shaders. useful for
554 ``no-oaconfig``
556 related to i915-perf (useful when running on simulation)
560 suppress generation of dual-object geometry shader code
566 dump shader assembly to files at each optimization pass and
574 ``perf-symbol-names``
581 dump shader assembly for ray tracing shaders
585 ``shader-print``
606 ``swsb-stall``
609 dump shader assembly for task shaders
611 dump shader assembly for tessellation control shaders
613 force usage of 8-patches tessellation control shaders (only
614 for gfx 9-11)
616 dump shader assembly for tessellation evaluation shaders
622 dump shader assembly for vertex shaders
624 dump shader assembly for fragment shaders (same as ``fs``)
625 ``cl-quiet``
626 quiets the OpenCL warnings recommending use of Intel compute-runtime
630 a comma-separated list of enable/disable flags configuring the
632 ``INTEL_DECODE=+color,-floats``) :
655 A comma-separated list of device probe override values. The basic
656 format is ``<pci-id>[,<pci-id>,...]``. The wildcard value of ``*``
707 To capture frames 15-37, stopping before frame 38:
721 ``$ echo -1 > path/to/control.fifo``
774 if set, determines the directory to be used for overriding shader
777 The SHA-1 of a shader assembly is printed when assembly is dumped via
778 corresponding :envvar:`INTEL_DEBUG` flag (e.g. ``vs`` for vertex shader).
781 dumping of corresponding shader stages via :envvar:`INTEL_DEBUG`.
783 dumping and overriding shader assemblies.
785 overrode shader with sha1 <SHA-1>" in stderr replacing the original
790 if set, determines the directory to be used for overriding shader
793 The SHA-1 of a shader assembly is printed when assembly is dumped via
794 corresponding :envvar:`INTEL_DEBUG` flag (e.g. ``vs`` for vertex shader).
797 dumping of corresponding shader stages via :envvar:`INTEL_DEBUG`.
799 dumping and overriding shader assemblies.
801 overrode shader with sha1 <SHA-1>" in stderr replacing the original
812 Unlike the text form of shader dumping, :envvar:`INTEL_DEBUG`
819 a comma-separated list of named flags, which control simd dispatch widths:
822 allow generation of SIMD8 fragment shader
824 allow generation of SIMD16 fragment shader
826 allow generation of SIMD32 fragment shader
828 allow generation of SIMD8 compute shader
830 allow generation of SIMD16 compute shader
832 allow generation of SIMD32 compute shader
834 allow generation of SIMD8 task shader
836 allow generation of SIMD16 task shader
838 allow generation of SIMD32 task shader
840 allow generation of SIMD8 mesh shader
842 allow generation of SIMD16 mesh shader
844 allow generation of SIMD32 mesh shader
846 allow generation of SIMD8 ray-tracing shader
848 allow generation of SIMD16 ray-tracing shader
850 allow generation of SIMD32 ray-tracing shader
852 If none of widths for particular shader stage was specified, then all
856 ---------------------------------------
884 effect on hardware that doesn't support soft-pinning (Ivybridge,
913 -------------------------
921 -----------------------------------------------------
939 -------------------------
945 -----------------------------
951 :envvar:`GALLIUM_HUD` to ``help`` and run e.g. ``glxgears`` for more info.
964 control background opacity as an integer percentage (1-100), defaults to 66%.
973 ``kill -10 <pid>`` to toggle the HUD as desired.
1001 specifies an alternate search directory for pipe-loader which overrides
1002 the compile-time path based on the install location.
1006 if non-zero, print all the Gallium environment variables which are
1031 if non-zero, print information about the CPU on start-up
1040 Enable fetch-shade-emit middle-end even though its not correct (e.g.
1045 Disable fetch-shade-emit middle-end even when it is correct
1070 ----------------------------
1117 .. _rusticl-env-var:
1120 -----------------------------
1134 a comma-separated list of drivers to enable CL on. An optional list of
1135 comma-separated integers can be passed per driver to specify which devices
1138 - ``RUSTICL_ENABLE=iris`` (enables all iris devices)
1139 - ``RUSTICL_ENABLE=iris:1,radeonsi:0,2`` (enables second iris and first
1153 a comma-separated list of features to enable. Those are disabled by default
1156 - ``fp16`` enables OpenCL half support
1157 - ``fp64`` enables OpenCL double support
1161 a comma-separated list of debug channels to enable.
1163 - ``allow_invalid_spirv`` disables validation of any input SPIR-V
1164 - ``clc`` dumps all OpenCL C source being compiled
1165 - ``nir`` dumps nirs in various compilation stages. Might print nothing if shader caching is
1167 - ``no_reuse_context`` pipe_contexts are not recycled
1168 - ``no_variants`` disable kernel variants (e.g. specialized binaries for offsets == 0)
1169 - ``perf`` prints a warning when hitting slow paths once
1170 - ``perfspam`` same as perf, but doesn't skip same warnings
1171 - ``program`` dumps compilation logs to stderr
1172 - ``sync`` waits on the GPU to complete after every event
1173 - ``validate`` validates any internally generated SPIR-Vs, e.g. through compiling OpenCL C code
1177 Limits the amount of threads per dimension in a work-group. Useful for splitting up long running
1180 .. _clc-env-var:
1183 -----------------------------
1187 a comma-separated list of debug channels to enable.
1189 - ``dump_llvm`` Dumps all generated LLVM IRs
1190 - ``dump_spirv`` Dumps all compiled, linked and specialized SPIR-Vs
1191 - ``verbose`` Enable debug logging of clc code
1194 -----------------------------------
1202 a comma-separated list of named flags that do debugging things.
1211 a comma-separated list of named flags, which do alternate shader handling.
1216 a comma-separated list of named flags that do various things.
1220 -------------------------------------
1224 a comma-separated list of named flags, which do various things:
1227 Dump vertex shader assembly to stderr
1229 Dump fragment shader assembly to stderr
1231 Dump geometry shader assembly to stderr
1233 Dump compute shader assembly to stderr
1241 -------------------------------------
1245 if set LLVMpipe will no-op rasterization
1249 a comma-separated list of debug options is accepted. See the source
1254 a comma-separated list of options to selectively no-op various parts
1264 ----------------------------------------
1290 See the driver code for other, lesser-used variables.
1292 VA-API environment variables
1293 ----------------------------
1297 enable MPEG4 for VA-API, disabled by default.
1300 --------------------------------
1304 a comma-separated list of named flags, which do various things. Use
1308 -------------------------------------
1312 a comma-separated list of debug options. Use ``V3D_DEBUG=help`` to
1316 .. _radv env-vars:
1319 ---------------------------------
1323 a comma-separated list of named flags, which do various things:
1330 validate the LLVM IR before LLVM compiles the shader
1332 dump the trap handler shader
1334 dump fragment shader epilogs
1346 show GPU-related information
1348 Mark geometry-affecting outputs as invariant. This works around a common
1371 disable FMASK compression on MSAA images (GFX6-GFX10.3)
1377 disable directly recording command buffers in GPU-visible memory
1379 disable mesh shader support on GFX10.3+
1390 disable TC-compat CMASK for MSAA surfaces
1399 dump vertex shader prologs
1405 dump shader statistics
1409 dump SPIR-V
1411 split application-provided fused multiply-add in geometry stages
1435 Dump NIR for selected shader stages.
1437 Dump backend IR (ACO or LLVM) for selected shader stages.
1439 Dump shader disassembly for selected shader stages.
1447 allow to force per-pipeline vertex VRS rates on GFX10.3+. This is only
1458 a comma-separated list of named flags, which do various things:
1467 upload shaders to invisible VRAM (might be useful for non-resizable BAR systems)
1469 forces ray-tracing to be emulated in software on GFX10_3+ and enables
1478 cache per-stage NIR for graphics pipelines
1486 enable wave64 for ray tracing shaders (GFX10-10.3)
1522 a comma-separated list of named flags to configure the trap handler
1557 force the shader clock to its minimum level
1565 a comma-separated list of named flags, which do various things:
1574 ``force-waitcnt``
1576 ``force-waitdeps``
1583 disable pre-RA, ILP and VOPD instruction scheduling
1584 ``nosched-ilp``
1586 ``nosched-vopd``
1594 -------------------------------------
1610 a comma-separated list of named flags, which do various things:
1631 Disable Hyper-Z
1675 Enable additional sanity checks on shader IR
1677 Use old-style monolithic shaders compiled on demand
1679 Disable compiling optimized shader variants.
1681 Use ACO as shader compiler when possible
1695 Program WD/IA to switch on end-of-packet.
1697 Disable out-of-order rasterization
1704 ---------------------------------
1708 a comma-separated list of named flags, which do various things:
1725 Use sb disassembler for shader dumps
1763 Enable additional sanity checks on shader IR
1765 Disable compiling optimized shader variants.
1773 Invoke a shader VM fault test and exit.
1777 Disable Hyper-Z
1785 Program WD/IA to switch on end-of-packet.
1789 Compile one shader variant at shader creation.
1795 Enable unsafe math shader optimizations
1799 if set to ``true``, various compute-related debug information will
1813 a comma-separated list of named flags, which do various things:
1822 Don't log shader conversion errors
1824 Log shader info (non-zero values)
1828 Log shader in and output
1843 ---------------------------------
1847 a comma-separated list of named flags, which do various things:
1858 Log SWTCL-specific info
1886 Disable shader optimizations
1906 ----------------------------------
1910 a comma-separated list of named flags, which do various things:
1918 Disable 16-bit floating point support. This may workaround application
1921 possible) or added in the Mesa-wide driconf (if closed source).
1925 Disable write-combining (force all allocations to be write-through). This
1927 buffers may still be write-combined.
1931 a comma-separated list of named flags, which do various things:
1949 .. _imagination env-vars:
1952 ------------------------------------------------
1956 A comma-separated list of debug options. Use ``PVR_DEBUG=help`` to
1961 a comma-separated list of named flags for the Rogue compiler,
1987 A comma-separated list of named flags for the PCO compiler,
1998 A comma-separated list of passes to skip.
2002 A comma-separated list of named flags for the PCO compiler,
2014 Print the IR for internal shader types.
2033 ---------------------------------
2048 --------------------------------------
2054 ----
2061 -----------------------------------
2064 <https://github.com/KhronosGroup/Vulkan-Loader>`__, *not by Mesa*, but they
2077 A comma-delimited list of globs to search for in known layers and used to
2093 …tps://github.com/KhronosGroup/Vulkan-Loader/blob/main/docs/LoaderInterfaceArchitecture.md#table-of…
2094 …https://github.com/KhronosGroup/Vulkan-Loader/blob/main/docs/LoaderInterfaceArchitecture.md#deprec…