Most tools looking at shader stats assume that there is only a single
resulting binary shader out of a single input. On Intel HW this is not
always the case. So having a statistic on each variant that reports
the maximum dispatch width helps showing improvement on a single
shader in terms of how large we manage to compile it.
For shaders that can be compiled in multiple SIMD width (like fragment
shaders), this will report the maximum dispatch width in the
statistics of each variants.
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Sagar Ghuge <sagar.ghuge@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22014>
When enabled, on gfx12 plus, we will add the sync nop instruction after
each instruction to make sure that current instruction depends on the
previous instruction explicitly.
This option will help us to get a hint if something is missing or broken
in software scoreboard pass.
Signed-off-by: Sagar Ghuge <sagar.ghuge@intel.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21797>
This mainly lets the software scoreboarding pass correctly mark the
instructions, without needing to resort to fragile manual handling in
the generator.
We can also make small improvements. On Gfx 8LP-12.0, we no longer have
the restrictions about DWord alignment, so we can simply write each half
into its intended location, rather than writing it to the low DWord and
then shifting it in place.
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Sagar Ghuge <sagar.ghuge@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21783>
We can lower FS_OPCODE_UNIFORM_PULL_CONSTANT_LOAD into other more
generic sends and drop this internal opcode.
The idea behind this change is to allow bindless surfaces to be used
for UBO pulls and why it's interesting to be able to reuse
setup_surface_descriptors(). But that will come in a later change.
No shader-db changes on TGL & DG2.
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/20416>
For cases with lots of very small primitives, this may improve
performance because we're not executing those dead channels all the
time.
Shader-db reports no instruction or cycle-count changes. However, by
hacking up the driver to report when this optimization triggers, it
appears to affect about 10% of shader-db.
v2 (Kenneth Graunke): Always enable VMask prior to XeHP for now,
because using VMask on those platforms allows us to perform the
eliminate_find_live_channel() optimization. However, XeHP doesn't
seem to have packed fragment shader dispatch, so we lose that
optimization regardless, and there's no reason not to avoid vmask.
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/1054>
Originally, we had virtual opcodes for scratch access, and let the
generator count spills/fills separately from other sends. Later, we
started using the generic SHADER_OPCODE_SEND for spills/fills on some
generations of hardware, and simply detected stateless messages there.
But then we started using stateless messages for other things:
- anv uses stateless messages for the buffer device address feature.
- nir_opt_large_constants generates stateless messages.
- XeHP curbe setup can generate stateless messages.
So counting stateless messages is not accurate. Instead, we move the
spill/fill accounting to the register allocator, as it generates such
things, as well as the load/store_scratch intrinsic handling, as those
are basically spill/fills, just at a higher level.
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/16691>
We haven't exposed this intrinsic as it doesn't directly correspond to
anything in SPIR-V. However, it's used internally by some NIR passes,
namely nir_opt_uniform_atomics().
We reuse most of the infrastructure in brw_find_live_channel, but with
LZD/ADD instead of FBL. A new SHADER_OPCODE_FIND_LAST_LIVE_CHANNEL is
like SHADER_OPCODE_FIND_LIVE_CHANNEL but from the other side.
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Caio Oliveira <caio.oliveira@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/15484>
We'll want different types of IDs based on topology. Let's make this
more flexible and also move the bit shifting code a layer above where
it's easier to do bitshifting operations, especially if you need to
stash things into temporary registers.
v2: Keep previous comment.
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Caio Oliveira <caio.oliveira@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13719>
This fixes a bug in the CLUSTER_BROADCAST code generation that causes
the original IR region to be ignored, this will be a problem when we
start lowering 64-bit CLUSTER_BROADCAST instructions at the IR level,
since it will lead to instructions with non-trivial regioning.
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/14273>
One of the two SHUFFLE implementations wasn't taking into account the
destination stride at all, and the other (more commonly used) one was
taking it into account incorrectly since brw_reg::hstride represents
the stride logarithmically, so we need to use a left-shift operator
instead of product. Found by inspection.
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/14273>
This fixes a bug in the handcrafted SIMD lowering done by the SHUFFLE
code generation, which wasn't taking into account the source and
destination region strides while deciding whether it needs to split an
instruction.
v2: Use new element_sz() helper instead of left shift. (Lionel)
Fixes: 90c9f29518 ("i965/fs: Add support for nir_intrinsic_shuffle")
Reviewed-by: Caio Oliveira <caio.oliveira@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/14273>
Having an integer destination type instead of a float destination type
confuses the SWSB code. This causes problems on some Intel GPUs. Fix
this by using the correct type in the destination of the F32TOF16
opcode.
Gfx7 doesn't have the HF type, so continue to emit W on that platform.
The assertions in brw_F32TO16 (brw_eu_emit.c) are updated to reflect
this. In scalar mode, UD is never emitted as a destination type for
this opcode, so remove it from the allowed types in the assertion.
I also condidered doing something like de55fd358f ("intel/fs/xehp:
Teach SWSB pass about the exec pipeline of
FS_OPCODE_PACK_HALF_2x16_SPLIT."), but Curro recommended that just using
the correct types is a better fix. I agree.
v2: Add missing changes to fs_generator::generate_pack_half_2x16_split.
I'm not sure how I (and the Intel CI) missed that the first time. :(
v3: Fix copy-and-paste issue in the v2 fix. Noticed by Tapani.
Reviewed-by: Francisco Jerez <currojerez@riseup.net> [v1]
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/14181>
There are two problems with the current architecture.
In OpenGL, the id is supposed to be a unique identifier for a particular
log source. This is done so that applications can (theoretically)
filter particular log messages. The debug callback infrastructure in
Mesa assigns a uniqe value when a value of 0 is passed in. This causes
the id to get set once to a unique value for each message.
By passing a stack variable that is initialized to 0 on every call,
every time the same message is logged, it will have a different id.
This isn't great, but it's also not catastrophic.
When threaded shader compiles are used, the id *pointer* is saved and
dereferenced at a possibly much later time on a possibly different
thread. This causes one thread to access the stack from a different
thread... and that stack frame might not be valid any more. :(
This fixes shader-db crashes of various kinds on Iris with threaded
shader compiles enabled.
Fixes: 42c34e1ac8 ("iris: Enable threaded shader compilation")
Reviewed-by: Matt Turner <mattst88@gmail.com>
Reviewed-by: Anuj Phogat <anuj.phogat@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12136>
Right now the accumulator-clearing move emitted by the generator for
Wa_14010017096 inherits the SWSB field from the previous instruction.
This can lead to redundant synchronization, or possibly more serious
issues if the previous instruction had a TGL_SBID_SET SWSB
synchronization mode. Take the SWSB synchronization information from
the IR.
Fixes: a27542c5dd ("intel/compiler: Clear accumulator register before EOT")
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11433>
Instead of depending on the driver to compile each resume shader
separately, we compile them all in one go in the back-end and build an
SBT as part of the shader program. Shader relocs are used to make the
entries in the SBT point point to the correct resume shader.
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8637>
Those helpers exist primarily to sort out some of the weirdness around
Gen4-6 dataport access. On Gen5 and earlier, everything was called
"dataport" and, instead of the SFID we have today there was a "target
cache" parameter in the descriptor. There are also some bits that moved
around on various gens depending on read vs. write. Starting with Gen6,
most things which target one of the data cache SFIDs should use
brw_dp_desc() instead.
v2: Drop backward comment (Ken)
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/7455>
