shader-db statistics on Broadwell:
total instructions in shared programs: 8963409 -> 8962455 (-0.01%)
instructions in affected programs: 60858 -> 59904 (-1.57%)
helped: 318
HURT: 0
total cycles in shared programs: 71408022 -> 71406276 (-0.00%)
cycles in affected programs: 398416 -> 396670 (-0.44%)
helped: 199
HURT: 51
GAINED: 1
The only shaders affected were in Dota 2 Reborn.
It also sets up for the next optimization.
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Matt Turner <mattst88@gmail.com>
This better reflects what it does. I plan to add other ALU
optimizations as well, so the old name would be confusing.
In preparation for that, also move the file comments about csels
above the opt_undef_csel function, and delete the ones about there
not being other optimizations.
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Matt Turner <mattst88@gmail.com>
According to Timothy, using program_string_id == 0 to identify the
passthrough TCS is going to be problematic for his shader cache work.
So, change it to strcmp() the name at visitor creation time.
Signed-off-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Matt Turner <mattst88@gmail.com>
Fix windows in 32-bit mode when hyperthreading is disabled on Xeons.
Some support for asymmetric processor topologies.
Reviewed-by: Bruce Cherniak <bruce.cherniak@intel.com>
This tells LLVM to always use SMEM loads for descriptors. It fixes a
regression in piglit's arb_shader_storage_buffer_object/execution/indirect.shader_test
that was caused by LLVM r268259 (but the proper fix is really here in Mesa).
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Beginning with commit 7b208a73, Unigine Valley began hanging the GPU on
Gen >= 8 platforms.
Evidently that commit allowed the scheduler to make different choices
that somehow finally ran afoul of a hardware bug in which POW and FDIV
instructions may not be followed by an instruction with two destination
registers (including compressed instructions). I presume the conditions
are more complex than that, but the internal hardware bug report (BDWGFX
bug_de 1696294) does not contain much more information.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=94924
Reviewed-by: Topi Pohjolainen <topi.pohjolainen@intel.com> [v1]
Tested-by: Mark Janes <mark.a.janes@intel.com> [v1]
Reviewed-by: Francisco Jerez <currojerez@riseup.net>
When gathering query results, swr_gather_stats was
unnecessarily stalling the entire pipeline. Results are now
collected asynchronously, with a fence marking completion.
Reviewed-By: George Kyriazis <george.kyriazis@intel.com>
We already are a GLintptr, casting won't help.
Reviewed-by: Alejandro Piñeiro <apinheiro@igalia.com>
Reviewed-by: Anuj Phogat <anuj.phogat@gmail.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
The assert was null checking dest_arr_parent twice. The intention
seems to be to check both dest_ and src_.
Added in d3636da9
Reviewed-by: Eduardo Lima Mitev <elima@igalia.com>
The function returns GLuint, not GLfloat values.
v2: also fix the OES function
Cc: "11.2" <mesa-stable@lists.freedesktop.org>
Reviewed-by: Charmaine Lee <charmainel@vmware.com>
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>
Silences warnings with 32-bit Linux gcc builds and MinGW which doesn't
recognize the ‘t’ conversion character.
Reviewed-by: Sinclair Yeh <syeh@vmware.com>
v2:
* Declare loop index variable at loop site (idr)
* Make arrays of MI_MATH instructions 'static const' (idr)
* Remove commented debug code (idr)
* Updated comment in set_query_availability (Ken)
* Replace switch with if/else in hsw_result_to_gpr0 (Ken)
* Only divide GL_FRAGMENT_SHADER_INVOCATIONS_ARB by 4 on
hsw and gen8 (Ken)
Signed-off-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
This matches the byte based offset of brw_load_register_mem*.
The function is also moved into intel_batchbuffer.c like
brw_load_register_mem*.
Signed-off-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Pretty much only happens if shader variant compile fails. But in this
case, if we haven't emitted cmdstream, we don't want to set needs_flush.
Signed-off-by: Rob Clark <robclark@freedesktop.org>
This was always a bit overly complicated, and had some issues (like
ctx->prog.dirty not getting reset at the end of the batch). It also
required some special hacks to avoid resetting dirty state on binning
pass. So just move it all into ctx->dirty (leaving some free bits
for future shader stages), and make FD_DIRTY_PROG just be the union
of all FD_SHADER_DIRTY_*.
Signed-off-by: Rob Clark <robclark@freedesktop.org>
Ofc won't catch *all* faults, but at least helpful for catching offsets
which are completely bogus.
Signed-off-by: Rob Clark <robclark@freedesktop.org>
Now that the opc's encode the instruction category (making them unique)
we no longer need to check the category in addition to the opc.
Signed-off-by: Rob Clark <robclark@freedesktop.org>
The instruction encoding allows for more registers, but at least on
a3xx/a4xx they don't actually exist.
Signed-off-by: Rob Clark <robclark@freedesktop.org>
Helps reduce register pressure and instruction counts for immediates
that would otherwise require a mov into gpr.
total instructions in shared programs: 4455332 -> 4369297 (-1.93%)
total dwords in shared programs: 8807872 -> 8614432 (-2.20%)
total full registers used in shared programs: 263062 -> 250846 (-4.64%)
total half registers used in shader programs: 9845 -> 9845 (0.00%)
total const registers used in shared programs: 1029735 -> 1466993 (42.46%)
half full const instr dwords
helped 0 10415 0 17861 5912
hurt 0 1157 21458 947 33
Signed-off-by: Rob Clark <robclark@freedesktop.org>
Copied from linux kernel (where it is called MAINTAINERS and
get_maintainer.pl), with minimal changes to script (to recognize
mesa src tree rather than linux kernel src tree, and to avoid
accidentaly CC'ing Linus Torvalds on mesa patches), and slimmed
down MAINTAINER file syntax to recognize that we don't really have
subsystem "maintainers" in the same sense as the linux kernel (ie. no
different mailing lists and git trees per subsystem).
The main point is to automate slapping on the correct CC's for patches
via git's --cc-cmd feature, more than anything else.
I didn't attempt to fully populate the REVIEWERS file, by a long shot.
This is an opt-in system and anyone else can add their own entries.
To utilize:
git send-email --cc-cmd ./scripts/get_reviewer.pl ...
or to configure it to be the default:
git config sendemail.cccmd ./scripts/get_reviewer.pl
Signed-off-by: Rob Clark <robclark@freedesktop.org>
The kernel is now more strict with the class ids it exposes, so we need
to check the G98 and MCP89 classes as well as the GT215 class. This
effectively caused us to decide there were no decoding capabilities on
newer kernel for VP3 chips.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=95251
Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Cc: "11.2" <mesa-stable@lists.freedesktop.org>
When computing the offset in the uniform storage table, take into account
the size multiplier so double precision matrices are handled correctly.
Signed-off-by: Juan A. Suarez Romero <jasuarez@igalia.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Split 32-bit and 64-bit fmod lowering as the drivers might need to
lower them separately inside NIR depending on the HW support.
Signed-off-by: Samuel Iglesias Gonsálvez <siglesias@igalia.com>
Reviewed-by: Jordan Justen <jordan.l.justen@intel.com>
