47bbd1c7ff
intel/tools/error_decode: Parse HW context in Xe decoder
...
Signed-off-by: José Roberto de Souza <jose.souza@intel.com >
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27888 >
2024-03-21 16:59:09 +00:00
ec3a41960b
intel/tools/error_decode: Add function to print batch in Xe decoder
...
This will be useful to decode HW context in the next patch.
Signed-off-by: José Roberto de Souza <jose.souza@intel.com >
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27888 >
2024-03-21 16:59:09 +00:00
171eb89b75
intel/tools/error_decode: Fix parsing in Xe decoder
...
xe_topic can't be inside of the for loop otherwise it will be set to
TOPIC_INVALID at every iteration.
TOPIC_INVALID was added after it was reviewed by Lionel because CI
complained that xe_topic may be not initialized, turns out leaving it
not initialized was causing the xe_topic value to keep the value set
in the previous interation makeing the parser to work by luck.
Fixes: 90e38bbb3bjose.souza@intel.com >
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27888 >
2024-03-21 16:59:09 +00:00
bfdcddfda9
intel/tools: Make intel_stub_gpu work when using meson devenv
...
When `meson devenv` is used, the shim library that is meant to be
preloaded is not necessarily available at the installation dir. So
when running in that mode both the script and the shim library will
be in the same (build) directory, so adjust the ld_preload to pick
that.
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/10798
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28134 >
2024-03-15 03:25:46 +00:00
f5532f8bab
intel/tools: avoid invalid time and file bits combination
...
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/10780
Fixes: cc41603d6dpedretti.fabio@gmail.com >
Signed-off-by: David Heidelberg <david.heidelberg@collabora.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28081 >
2024-03-08 21:01:38 +00:00
1ba5e9432d
intel/meson: Add dependencies for brw and elk
...
Instead of link_with, use meson dependency for the compilers. Will
be useful later to propagate some extra dependencies.
Acked-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com >
Reviewed-by: Dylan Baker <dylan@pnwbakers.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27865 >
2024-02-29 23:08:16 +00:00
209ae6bd41
intel/tools: Fix compilation in 32 bits
...
u64 is long long in 32 bits.
Fixes: 90e38bbb3bmarkjanes@swizzler.org >
Signed-off-by: José Roberto de Souza <jose.souza@intel.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27854 >
2024-02-28 23:37:43 +00:00
90e38bbb3b
intel/tools/error_decode: Parse Xe KMD error dump file
...
There is more to do but this is able to parse batch buffers, including
fetch and parse other bos like shader programs.
Some functions used by read_i915_data_file() could be shared with Xe
so I have moved those to aubinator_error_decode_lib.c/h.
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com >
Signed-off-by: José Roberto de Souza <jose.souza@intel.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27661 >
2024-02-27 01:04:16 +00:00
7e88176b0b
intel/tools/error_decode: Move code that can be shared between i915 and Xe error decoders
...
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com >
Signed-off-by: José Roberto de Souza <jose.souza@intel.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27661 >
2024-02-27 01:04:16 +00:00
6f83b1dddc
intel/tools: Add extra compiler device sha only for Gfx9+
...
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27563 >
2024-02-24 00:24:32 +00:00
8abfbc9cca
intel/meson: Rename libintel_compiler to libintel_compiler_brw
...
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27563 >
2024-02-24 00:24:32 +00:00
23e0cff907
intel/tools: Add ELK support for intel_hang_viewer
...
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27563 >
2024-02-24 00:24:32 +00:00
d641ca5b86
intel/tools: Add ELK support for aubinator_viewer
...
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27563 >
2024-02-24 00:24:32 +00:00
9d379f08af
intel/tools: Add ELK support for intel_hang_replay
...
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27563 >
2024-02-24 00:24:32 +00:00
c9a6b49b4b
intel/tools: Add ELK support for aubinator_error_decode
...
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27563 >
2024-02-24 00:24:32 +00:00
5338a24fe0
intel/tools: Add ELK support for aubinator
...
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27563 >
2024-02-24 00:24:31 +00:00
0669210ef4
intel/decoder: Add ELK support
...
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com >
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27563 >
2024-02-24 00:24:31 +00:00
341d0fcbf6
intel/tools/error_decode: Detect and split error dump file parsing by KMD
...
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com >
Signed-off-by: José Roberto de Souza <jose.souza@intel.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27728 >
2024-02-21 18:10:54 +00:00
1b07bb12d3
intel/tools/error_decode: Add support to search for Xe KMD error dumps
...
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com >
Signed-off-by: José Roberto de Souza <jose.souza@intel.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27728 >
2024-02-21 18:10:54 +00:00
77484ab6cf
intel/tools/error_decode: Simply error message handling
...
In the code path without arguments it tries 3 different paths and error
messages are overwritten one by other, in this case any of those
error messages are irrelevant.
For the code path with arguments is similar, as it already have a
fprintf(stderr) in the caller of open_error_state_file().
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com >
Signed-off-by: José Roberto de Souza <jose.souza@intel.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27728 >
2024-02-21 18:10:54 +00:00
70e2384f8f
intel/tools/error_decode: Add function to try to open error dump file
...
Just to simply a bit open_error_state_file().
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com >
Signed-off-by: José Roberto de Souza <jose.souza@intel.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27728 >
2024-02-21 18:10:54 +00:00
805d45e916
intel/decoder: Move decoder to a separate module
...
Depends on both intel/common and intel/compiler. Breaks circular
dependency between these two modules.
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27647 >
2024-02-16 16:37:31 +00:00
08176d9d16
intel/tools: add shader compiler hash key to json devinfo format
...
Offline shader compilation will use json as the source configuration
to accurately instantiate mesa for target hardware. Similar platforms
generate identical shader binaries even though intel_device_info
differs inconsequenially.
Include the shader compilation hash key to device info json files, so
these platforms can be deduplicated.
Closes : #6746
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26844 >
2024-02-15 16:59:25 -08:00
aa649dfa5f
intel/tools: move intel_dev_info to intel/tools
...
This is a more sensible home for intel_dev_info.
Offline shader compilation will take intel_dev_info json files as
input. For that use case, the shader compiler hash value is needed in
the json file.
intel_dev_info will depend on intel/compiler, and must be located in
intel/tools to break a circular meson dependency.
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26844 >
2024-02-15 16:59:15 -08:00
0b751a2134
intel: Rename i965_{asm,disasm} tools to brw_{asm,disasm}
...
And move them inside the compiler since they (especially asm) rely on
a bunch of internal types.
Acked-by: Dylan Baker <dylan@pnwbakers.com >
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27579 >
2024-02-15 09:26:46 +00:00
5992185c8d
intel/compiler: Merge intel_disasm.[ch] into corresponding brw files
...
Rename the functions to match the existing ones.
Acked-by: Dylan Baker <dylan@pnwbakers.com >
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27579 >
2024-02-15 09:26:46 +00:00
468a0ffe9c
intel/compiler: Include brw_disasm_info.h where its used
...
Acked-by: Dylan Baker <dylan@pnwbakers.com >
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27579 >
2024-02-15 09:26:46 +00:00
ff95f00883
intel/compiler: Move disassemble functions to own header file
...
Acked-by: Dylan Baker <dylan@pnwbakers.com >
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27579 >
2024-02-15 09:26:46 +00:00
f95b87a3dc
intel/tools: load json device info in drm_shim
...
Enable drm_shim to parse a serialized intel_device_info structure from
json. When overriding the gpu hardware, drm_shim provides the stubbed
intel_device_info structure to mesa through an unused ioctl.
Reviewed-by: Dylan Baker <dylan@pnwbakers.com >
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27557 >
2024-02-13 19:38:36 +00:00
e56f810316
intel/tools: add intel device meson dependencies
...
idep_intel_dev ensures that headers are generated before dependent
source files are compiled. Some tools have been building without that
dependency, and encounter intermittent compilation errors on
sufficiently parallel builds.
Any target which depends on idep_intel_dev will link with
libintel_dev. Redundant link instructions can be removed.
Reviewed-by: Caio Oliveira <caio.oliveira@intel.com >
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/10604
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27600 >
2024-02-13 18:37:19 +00:00
3fd44345c4
intel: Skip ioctls for querying device info when hardware is unsupported
...
While enumerating devices on a system with multiple implementations,
unnecessary ioctls will be issued before a driver checks if it supports a
given device.
This patch makes the driver fail early based on a intel_device_info.ver
check with 2 new parameters added to intel_get_device_info_from_fd.
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27166 >
2024-01-25 09:57:24 +00:00
7e111268f1
intel/hang_viewer: add aux-tt view
...
Allows you to visualize the AUX-TT.
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com >
Reviewed-by: Tapani Pälli <tapani.palli@intel.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27058 >
2024-01-15 11:16:40 +00:00
78a881af43
intel/genxml: add GAM done register description
...
Useful if you encounter some kind of pagefault (including with
AUX-TT).
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com >
Reviewed-by: Tapani Pälli <tapani.palli@intel.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27058 >
2024-01-15 11:16:40 +00:00
8e6d28f473
intel/tools/tests: Add i965_asm tests for gfx12 and gfx12.5
...
Signed-off-by: Sviatoslav Peleshko <sviatoslav.peleshko@globallogic.com >
Reviewed-by: Sagar Ghuge <sagar.ghuge@intel.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25657 >
2024-01-09 11:35:52 +00:00
b87fc2125e
intel/tools/tests: Unbreak i965_asm tests
...
Currently it's searching for test cases in the nonexistent folders, and
because there are none, tests always pass. Point the script onto the
correct ones. And while we're at it, add a check to make sure this
situation won't repeat in the future.
Signed-off-by: Sviatoslav Peleshko <sviatoslav.peleshko@globallogic.com >
Reviewed-by: Sagar Ghuge <sagar.ghuge@intel.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25657 >
2024-01-09 11:35:52 +00:00
bb2083a57c
intel/tools/tests: Fix sends indirect argument in gfx9 test
...
Currently it's in the wrong format. It was fixed in disasm in
98aab272sviatoslav.peleshko@globallogic.com >
Reviewed-by: Sagar Ghuge <sagar.ghuge@intel.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25657 >
2024-01-09 11:35:52 +00:00
98d2461424
intel/tools/i965_asm: Don't set src0 for break and while on gfx12
...
This effectively implements same changes as were done to codegen in
bafc9515sviatoslav.peleshko@globallogic.com >
Reviewed-by: Sagar Ghuge <sagar.ghuge@intel.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25657 >
2024-01-09 11:35:52 +00:00
db4d58fe31
intel/tools/i965_asm: Add dp4a and add3 instructions
...
Signed-off-by: Sviatoslav Peleshko <sviatoslav.peleshko@globallogic.com >
Reviewed-by: Sagar Ghuge <sagar.ghuge@intel.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25657 >
2024-01-09 11:35:52 +00:00
88fcd305be
intel/tools/i965_asm: Implement gfx12 and gfx12.5 send/sendc
...
Signed-off-by: Sviatoslav Peleshko <sviatoslav.peleshko@globallogic.com >
Reviewed-by: Sagar Ghuge <sagar.ghuge@intel.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25657 >
2024-01-09 11:35:52 +00:00
bc46cc7807
intel/tools/i965_asm: Allow src0 and src2 of ternary instructions to be imm
...
Signed-off-by: Sviatoslav Peleshko <sviatoslav.peleshko@globallogic.com >
Reviewed-by: Sagar Ghuge <sagar.ghuge@intel.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25657 >
2024-01-09 11:35:52 +00:00
8eaa0db13f
intel/tools/i965_asm: Don't override flag reg from cond modifier
...
Both predication and conditional modifier use the same flag, but in
assembly it's specified only once. If the instruction already has a
flag from predication we should not override it with zeroes.
Signed-off-by: Sviatoslav Peleshko <sviatoslav.peleshko@globallogic.com >
Reviewed-by: Sagar Ghuge <sagar.ghuge@intel.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25657 >
2024-01-09 11:35:52 +00:00
f96e08f34d
intel/tools/i965_asm: Allow neg and abs modifiers on accumulator register
...
Signed-off-by: Sviatoslav Peleshko <sviatoslav.peleshko@globallogic.com >
Reviewed-by: Sagar Ghuge <sagar.ghuge@intel.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25657 >
2024-01-09 11:35:52 +00:00
98665e024f
intel/tools/i965_asm: Handle sync instruction
...
Signed-off-by: Sviatoslav Peleshko <sviatoslav.peleshko@globallogic.com >
Reviewed-by: Sagar Ghuge <sagar.ghuge@intel.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25657 >
2024-01-09 11:35:52 +00:00
9dd3a6f86f
intel/tools/i965_asm: Handle HF immediates
...
Signed-off-by: Sviatoslav Peleshko <sviatoslav.peleshko@globallogic.com >
Reviewed-by: Sagar Ghuge <sagar.ghuge@intel.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25657 >
2024-01-09 11:35:52 +00:00
0c41a8f5d6
intel/tools/i965_asm: Add SWSB handling
...
Signed-off-by: Sviatoslav Peleshko <sviatoslav.peleshko@globallogic.com >
Reviewed-by: Sagar Ghuge <sagar.ghuge@intel.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25657 >
2024-01-09 11:35:52 +00:00
5a2aa3ff88
intel: Cleanup duplicate ALIGN macro defines
...
Use ALIGN function instead
Signed-off-by: Yonggang Luo <luoyonggang@gmail.com >
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26864 >
2024-01-03 12:46:10 +00:00
8665ce27bc
intel: Use ALIGN_POT instead of ALIGN inside macro define
...
These macro define is compute from literals, so use ALIGN_POT instead of ALIGN function
so that it's can be computed at compile time
Signed-off-by: Yonggang Luo <luoyonggang@gmail.com >
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26864 >
2024-01-03 12:46:10 +00:00
af65af8267
intel/tools: fix compilation of intel_hang_viewer on 32 bits
...
Because gcc was complaining:
../../src/intel/tools/intel_hang_viewer.cpp: In function ‘void display_hang_stats()’:
../../src/intel/tools/intel_hang_viewer.cpp:365:31: error: format ‘%lu’ expects argument of type ‘long unsigned int’, but argument 2 has type ‘std::vector<hang_bo>::size_type’ {aka ‘unsigned int’} [-Werror=format=]
365 | ImGui::Text("BOs: %lu", context.bos.size());
| ~~^ ~~~~~~~~~~~~~~~~~~
| | |
| long unsigned int std::vector<hang_bo>::size_type {aka unsigned int}
| %u
../../src/intel/tools/intel_hang_viewer.cpp:366:31: error: format ‘%lu’ expects argument of type ‘long unsigned int’, but argument 2 has type ‘std::vector<hang_exec>::size_type’ {aka ‘unsigned int’} [-Werror=format=]
366 | ImGui::Text("Execs %lu", context.execs.size());
| ~~^ ~~~~~~~~~~~~~~~~~~~~
| | |
| long unsigned int std::vector<hang_exec>::size_type {aka unsigned int}
| %u
../../src/intel/tools/intel_hang_viewer.cpp:367:31: error: format ‘%lu’ expects argument of type ‘long unsigned int’, but argument 2 has type ‘std::vector<hang_map>::size_type’ {aka ‘unsigned int’} [-Werror=format=]
367 | ImGui::Text("Maps: %lu", context.maps.size());
| ~~^ ~~~~~~~~~~~~~~~~~~~
| | |
| long unsigned int std::vector<hang_map>::size_type {aka unsigned int}
| %u
cc1plus: some warnings being treated as errors
I'm not sure if STL's size_type is defined by the spec to be anything
specific, but for the platforms we care about it seems to be size_t,
so change it to %z.
Fixes: 33fd93f3b1lionel.g.landwerlin@intel.com >
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26581 >
2023-12-08 22:53:03 +00:00
8d6c059bd2
intel/tools: 32bit compile fixes
...
Fixes: 03712579b0lionel.g.landwerlin@intel.com >
Reviewed-by: Tapani Pälli <tapani.palli@intel.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26514 >
2023-12-05 17:45:18 +00:00
344a4948b7
intel/hang_replay: fix compile race with generated files
...
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com >
Fixes: 03712579b0ian.d.romanick@intel.com >
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26510 >
2023-12-05 06:09:52 +00:00
José Roberto de Souza