fdo-mirrors/mesa
1
0
Fork 0
mirror of https://gitlab.freedesktop.org/mesa/mesa.git synced 2025-12-24 21:50:12 +01:00
Code Issues Projects Releases Packages Wiki Activity Actions 1
156922 commits 64 branches 914 tags 1 GiB
Commit graph

97 commits

Author SHA1 Message Date
Rhys Perry
98a65eafb7 aco: use scratch_* for VGPR spill/reload on GFX9+ 
fossil-db (navi21):
Totals from 12 (0.01% of 162293) affected shaders:
Instrs: 122808 -> 122782 (-0.02%); split: -0.11%, +0.09%
CodeSize: 711248 -> 710788 (-0.06%); split: -0.16%, +0.10%
SpillSGPRs: 928 -> 831 (-10.45%)
SpillVGPRs: 1626 -> 1624 (-0.12%)
Latency: 4960285 -> 4932547 (-0.56%)
InvThroughput: 2574083 -> 2559953 (-0.55%)
VClause: 3404 -> 3402 (-0.06%)
Copies: 36992 -> 37181 (+0.51%); split: -0.05%, +0.56%
Branches: 3582 -> 3585 (+0.08%)
PreVGPRs: 3055 -> 3057 (+0.07%)

fossil-db (vega10):
Totals from 12 (0.01% of 161355) affected shaders:
Instrs: 124817 -> 124383 (-0.35%); split: -0.46%, +0.12%
CodeSize: 705116 -> 703664 (-0.21%); split: -0.44%, +0.23%
SpillSGPRs: 1012 -> 898 (-11.26%)
SpillVGPRs: 1632 -> 1624 (-0.49%)
Scratch: 201728 -> 200704 (-0.51%)
Latency: 6160115 -> 6266025 (+1.72%); split: -0.34%, +2.06%
InvThroughput: 6440203 -> 6544595 (+1.62%); split: -0.35%, +1.97%
VClause: 3409 -> 3423 (+0.41%)
Copies: 37929 -> 37748 (-0.48%); split: -1.16%, +0.69%
Branches: 3851 -> 3855 (+0.10%); split: -0.13%, +0.23%
PreVGPRs: 3053 -> 3055 (+0.07%)

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/17079>
 2022-07-08 14:49:03 +00:00
Rhys Perry
7d34044908 aco: refactor VGPR spill/reload lowering 
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/17079>
 2022-07-08 14:49:03 +00:00
Daniel Schürmann
8e41c66639 aco: fix spilling of phis without temp operands 
These were spilled unconditionally.

Cc: mesa-stable
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/16708>
 2022-06-01 09:11:03 +00:00
Timur Kristóf
7761b4d89e aco: Fix scratch with task shaders. 
Task shaders work like compute shaders, their scratch pointer
is currently located at the first two user SGPRs.

Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/16692>
 2022-05-24 12:33:49 +00:00
Marek Olšák
39800f0fa3 amd: change chip_class naming to "enum amd_gfx_level gfx_level" 
This aligns the naming with PAL.

Acked-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Acked-by: Pierre-Eric Pellou-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/16469>
 2022-05-13 14:56:22 -04:00
Samuel Pitoiset
a6e1445d5f aco: do not set RESOURCE_LEVEL for buffer descriptors on GFX11 
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/16369>
 2022-05-12 15:46:20 +00:00
Rhys Perry
cc2894345f aco/spill: use spills_entry instead of spills_exit to kill linear VGPRs 
If a predecessor has only spilled constants (no temporaries), spills_exit
will be empty.

fossil-db (Sienna Cichlid):
Totals from 2 (0.00% of 128647) affected shaders:
Latency: 139106 -> 139104 (-0.00%)

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/5633
Cc: mesa-stable
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13821>
 2021-11-22 19:46:22 +00:00
Tony Wasserka
fa655b6f70 aco/spill: Use std::unordered_map for spills_entry 
fossil-db on Navi14:
Totals from 305 (0.20% of 150305) affected shaders:
CodeSize: 5498340 -> 5498328 (-0.00%)
Instrs: 1009992 -> 1009989 (-0.00%)
Latency: 33922644 -> 33923018 (+0.00%)
InvThroughput: 9302963 -> 9303151 (+0.00%)
VClause: 19004 -> 19001 (-0.02%)

Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11925>
 2021-10-01 09:39:13 +00:00
Tony Wasserka
3fad5efd15 aco/spill: Use unordered_map for spills_exit 
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11925>
 2021-10-01 09:39:13 +00:00
Tony Wasserka
7368f16fe8 aco/spill: Clarify use of long-lived references by adding const 
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11925>
 2021-10-01 09:39:13 +00:00
Tony Wasserka
a3ac3b231f aco/spill: Reduce allocations in next_uses_per_block 
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11925>
 2021-10-01 09:39:13 +00:00
Tony Wasserka
a6bcda6a01 aco/spill: Change worklist to a single integer 
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11925>
 2021-10-01 09:39:13 +00:00
Tony Wasserka
e60a70dde0 aco/spill: Store remat list in an std::unordered_map instead of std::map 
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11925>
 2021-10-01 09:39:13 +00:00
Tony Wasserka
4a78a05247 aco/spill: Replace an std::map to booleans with std::set 
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11925>
 2021-10-01 09:39:13 +00:00
Tony Wasserka
112babc697 aco/spill: Reduce redundant std::map lookups 
The previous code checked for element containment first and then performed
another map lookup upon element access. Instead, map::find can be used to
retrieve an iterator usable for element access with no extra lookup needed.

Furthermore, pure containment checks have been simplified using map::count.

Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11925>
 2021-10-01 09:39:13 +00:00
Tony Wasserka
05163fd4f4 aco/spill: Avoid copying current_spills when not needed 
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11925>
 2021-10-01 09:39:13 +00:00
Tony Wasserka
6650799ea5 aco/spill: Prefer unordered_map over map for next use distances 
This changes the iteration order of next use distances, so some "random"
changes to shader metrics are expected.

fossil-db for Navi14:
Totals from 1239 (0.82% of 150305) affected shaders:
SpillSGPRs: 10559 -> 10562 (+0.03%); split: -0.05%, +0.08%
SpillVGPRs: 1632 -> 1863 (+14.15%)
CodeSize: 19321468 -> 19304164 (-0.09%); split: -0.09%, +0.01%
Instrs: 3593957 -> 3591647 (-0.06%); split: -0.07%, +0.01%
Latency: 103120695 -> 102475647 (-0.63%); split: -0.63%, +0.01%
InvThroughput: 23897614 -> 23575320 (-1.35%); split: -1.36%, +0.02%
VClause: 66406 -> 66943 (+0.81%); split: -0.01%, +0.81%
SClause: 118559 -> 118548 (-0.01%)
Copies: 310871 -> 308950 (-0.62%); split: -0.69%, +0.08%
Branches: 123386 -> 123413 (+0.02%); split: -0.00%, +0.03%

These numbers mostly come from parallel-rdp ubershaders. Small changes are
also found in the rdr2 and rage2 shader metrics, whereas others are not
significantly affected.

Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11925>
 2021-10-01 09:39:13 +00:00
Tony Wasserka
4453bce770 aco/spill: Replace vector<map> with vector<vector> for local_next_use 
While adding/removing elements is faster with std::map, the cost of container
copies (and the involved memory allocations) vastly outweigh that benefit in
this usage pattern.

Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11925>
 2021-10-01 09:39:13 +00:00
Tony Wasserka
92d7a6ab1c aco/spill: Avoid destroying local next use maps over-eagerly 
Recreating these maps in a later block requires allocating fresh memory.
Instead, by never shrinking the containing vector in the first place,
previously allocated map memory is now re-used.

Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11925>
 2021-10-01 09:39:13 +00:00
Tony Wasserka
df6c395095 aco/spill: Persist memory allocations of local next use maps 
The function local_next_uses allocated one next-use map per instruction in
the current block. Since the function is called once per block, this caused
an excessive amount of memory allocations to take place.

With this change, the memory for next-use maps is allocated only once and
then reused for later blocks.

Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11925>
 2021-10-01 09:39:13 +00:00
Tony Wasserka
387b315ea0 aco/spill: Avoid copying next_use maps more often than needed 
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11925>
 2021-10-01 09:39:13 +00:00
Tony Wasserka
276da301e6 aco/spill: Replace map[] with map::insert 
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11925>
 2021-10-01 09:39:13 +00:00
Tony Wasserka
b183bdeabf aco/spill: Remove unused container 
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11925>
 2021-10-01 09:39:13 +00:00
Tony Wasserka
0812d440c7 aco: Use std::vector for the underlying container of std::stack 
By default, std::stack uses std::deque to allocate its elements, which has
poor cache efficiency. std::vector makes appending elements more expensive
(due to potential reallocations), but in the changed contexts the element
count should always be low anyway.

Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11925>
 2021-10-01 09:39:13 +00:00
Tony Wasserka
f81eb2a827 aco/spill: Avoid unneeded copies when iterating over maps 
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11925>
 2021-10-01 09:39:13 +00:00
Rhys Perry
54f83d718a aco/spill: add temporary operands of exec phis to next_use_distances_end 
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Fixes: dfb10e4f4b ("aco/spill: don't count phis as variable access")
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12702>
 2021-09-03 14:01:27 +01:00
Tony Wasserka
66e51dc474 aco: Remove use of deprecated Operand constructors 
This migration was done with libclang-based automatic tooling, which
performed these replacements:
* Operand(uint8_t) -> Operand::c8
* Operand(uint16_t) -> Operand::c16
* Operand(uint32_t, false) -> Operand::c32
* Operand(uint32_t, bool) -> Operand::c32_or_c64
* Operand(uint64_t) -> Operand::c64
* Operand(0) -> Operand::zero(num_bytes)

Casts that were previously used for constructor selection have automatically
been removed (e.g. Operand((uint16_t)1) -> Operand::c16(1)).

Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11653>
 2021-07-13 17:43:26 +00:00
Daniel Schürmann
1e2639026f aco: Format. 
Manually adjusted some comments for more intuitive line breaks.

Reviewed-by: Tony Wasserka <tony.wasserka@gmx.de>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11258>
 2021-07-12 21:27:31 +00:00
Daniel Schürmann
0eea0e55ad aco: add 'common/' and 'llvm/' prefix to #includes 
Reviewed-by: Tony Wasserka <tony.wasserka@gmx.de>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11271>
 2021-07-12 12:09:31 +00:00
Daniel Schürmann
59fdaa1985 aco: reorder and cleanup #includes 
Reviewed-by: Tony Wasserka <tony.wasserka@gmx.de>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/11271>
 2021-07-12 12:09:31 +00:00
Daniel Schürmann
989e9867a6 aco: fix additional register requirements for spilling 
It could happen that VGPR spilling without SGPR spilling
calculated a negative spills_to_vgpr number and then
increasing the VGPR target demand above the limit.

Cc: mesa-stable

Reviewed-by: Tony Wasserka <tony.wasserka@gmx.de>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10756>
 2021-05-12 14:13:24 +00:00
Tony Wasserka
741e84f554 aco/spill: Fix improper handling of exec phis 
The "continue" was placed in the wrong loop, leading to exec being
counted as a spilled register when it wasn't.

Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Fixes: a56ddca4e8 ('aco: make all exec accesses non-temporaries')
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/4533
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10486>
 2021-05-03 10:31:07 +00:00
Rhys Perry
776ba40115 aco: add and use Program::progress 
This is used when printing the program and to avoid updating register
demand during post-RA liveness analysis.

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10315>
 2021-04-21 11:09:33 +00:00
Marek Olšák
ec1ddb976a amd/registers: rename IMG_FORMAT to GFX10_FORMAT to disambiguate the meaning 
Reviewed-by: Bas Nieuwenhuizen <bas@basnieuwenhuizen.nl>
Acked-by: Pierre-Eric Pelloux-Prayer <pierre-eric.pelloux-prayer@amd.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/10261>
 2021-04-17 02:37:49 +00:00
Daniel Schürmann
4a57787006 aco/spill: use correct next_use_distances at loop header 
To decide which variables to spill, we must use the distances at the
beginning of the loop-header, and not the distances at the end of the
loop-preheader. The difference are that the former includes phis which are
viable to be spilled as opposed to the phi operands which would be reloaded
by add_coupling_code(), ending up in potentially too high register pressure
before the loop.

Totals from 206 (0.15% of 136546) affected shaders (Raven):
SpillSGPRs: 5154 -> 5000 (-2.99%)
CodeSize: 3654072 -> 3647184 (-0.19%); split: -0.19%, +0.00%
Instrs: 701482 -> 700526 (-0.14%); split: -0.14%, +0.00%
Latency: 40988780 -> 40872506 (-0.28%); split: -0.29%, +0.00%
InvThroughput: 20364560 -> 20306006 (-0.29%)
SClause: 20192 -> 20198 (+0.03%)
Copies: 77732 -> 77688 (-0.06%); split: -0.08%, +0.03%
Branches: 24204 -> 24050 (-0.64%)

Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9196>
 2021-04-13 18:40:57 +00:00
Daniel Schürmann
b56ea19111 aco/spill: refactor live-in registerDemand calculation 
This also fixes some hypothetical issue for loops without phis
and for loops with higher register pressure at the end of the
loop preheader.

No fossil-db changes.

Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9196>
 2021-04-13 18:40:57 +00:00
Daniel Schürmann
282eacc3e0 aco/spill: refactor some more spill decision taking 
No fossil-db changes.

Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9196>
 2021-04-13 18:40:57 +00:00
Daniel Schürmann
dfb10e4f4b aco/spill: don't count phis as variable access 
This increases the chance of evicting phis
if these have longer next-use distances.

Totals from 6 (0.00% of 146267) affected shaders (Navi10):
CodeSize: 476992 -> 464388 (-2.64%)
Instrs: 81785 -> 79952 (-2.24%)
VClause: 2380 -> 2374 (-0.25%)
Copies: 26836 -> 25131 (-6.35%)
Branches: 2494 -> 2492 (-0.08%)

Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9196>
 2021-04-13 18:40:57 +00:00
Daniel Schürmann
b2a6346df7 aco/spill: spill phi constants and exec directly to VGPR 
This lets us avoid some CSSA copies.

Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9196>
 2021-04-13 18:40:57 +00:00
Daniel Schürmann
99936d7142 aco/spill: reload spilled exec masks directly to exec 
This handles the case of
   exec = p_linear_phi %a, %b
where %a or %b might have been spilled.
By directly reloading these variables into the exec mask register,
we can avoid additional CSSA parallelcopies.

Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9196>
 2021-04-13 18:40:57 +00:00
Daniel Schürmann
beb292343a aco/spill: refactor spill decision taking 
No fossil-db changes.

Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9196>
 2021-04-13 18:40:57 +00:00
Daniel Schürmann
ffebe48013 aco: don't rematerialize exec 
Since exec is not considered a temporary anymore,
we accidentally allowed to rematerialize it.

Fixes: a56ddca4e8 ('aco: make all exec accesses non-temporaries')
Closes: #4327

Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9215>
 2021-02-23 14:41:31 +00:00
Daniel Schürmann
8b793f9567 aco: remove dead code for the handling of exec temporaries 
Totals from 26026 (18.67% of 139391) affected shaders (Navi10):
PreSGPRs: 370993 -> 326177 (-12.08%)

Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8870>
 2021-02-12 22:41:31 +00:00
Daniel Schürmann
5d7b3bf1a7 aco: handle non-temp phi definitions and operands 
This will be necessary as we make exec non-temp.

No fossil-db changes.

Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8870>
 2021-02-12 22:41:31 +00:00
Daniel Schürmann
b98a4d4dd7 aco: refactor GPR limit calculation 
This patch delays the calculation of GPR limits in order to
precisely incorporate extra registers (VCC etc.) and shared VGPRs.

Additionally, the allocation granularity is used to set the config.
This has some effect on the reported SGPR stats.

Totals (Navi10):
SGPRs: 6971787 -> 17753642 (+154.65%)

Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8921>
 2021-02-12 19:00:18 +00:00
Rhys Perry
e115b01948 aco: return references in instruction cast methods 
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8595>
 2021-01-22 14:12:33 +00:00
Rhys Perry
1d245cd18b aco: use format-check methods 
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8595>
 2021-01-22 14:12:32 +00:00
Rhys Perry
70dbcfa1c9 aco: use instruction cast methods 
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8595>
 2021-01-22 14:12:32 +00:00
Timur Kristóf
b75d8052a7 aco: Spill more optimally before loops. 
This further reduces the dead code emitted by the spiller.
Some minimal amount of dead IR is still emitted sometimes,
but that doesn't generate any compiled code at the end.

Totals from 1953 (1.40% of 139391) affected shaders:
VGPRs: 206980 -> 206588 (-0.19%)
SpillSGPRs: 24719 -> 16423 (-33.56%); split: -33.58%, +0.02%
CodeSize: 28448516 -> 28343836 (-0.37%); split: -0.38%, +0.01%
MaxWaves: 8960 -> 8992 (+0.36%)
Instrs: 5422049 -> 5408334 (-0.25%); split: -0.26%, +0.01%
Cycles: 511240864 -> 512460764 (+0.24%); split: -0.02%, +0.26%
VMEM: 346681 -> 346468 (-0.06%); split: +0.27%, -0.33%
SMEM: 124160 -> 122802 (-1.09%); split: +0.33%, -1.42%
VClause: 81102 -> 81163 (+0.08%); split: -0.01%, +0.09%
SClause: 174404 -> 174237 (-0.10%); split: -0.23%, +0.13%
Copies: 530216 -> 532961 (+0.52%); split: -0.90%, +1.42%
Branches: 189114 -> 189221 (+0.06%); split: -0.13%, +0.18%
PreSGPRs: 206017 -> 206526 (+0.25%); split: -0.08%, +0.33%
PreVGPRs: 183103 -> 182964 (-0.08%)

Co-authored-by: Daniel Schürmann <daniel@schuermann.dev>
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8026>
 2021-01-11 12:25:29 +00:00
Timur Kristóf
b03fbec4f1 aco: Keep live-though variables and constants spilled. 
This noticably reduces the amount of dead code emitted by our
spiller, when eg. previously a constant was spilled then
rematerialized before a loop, but then spilled again inside the loop.

Fossil DB changes on Navi 10:
Totals from 263 (0.19% of 139391) affected shaders:
VGPRs: 30044 -> 30028 (-0.05%)
SpillSGPRs: 8800 -> 4948 (-43.77%)
CodeSize: 4496040 -> 4335448 (-3.57%); split: -3.57%, +0.00%
Instrs: 843942 -> 819219 (-2.93%); split: -2.93%, +0.00%
Cycles: 76485744 -> 73549080 (-3.84%); split: -4.04%, +0.20%
VMEM: 38204 -> 38147 (-0.15%); split: +0.08%, -0.23%
SMEM: 17872 -> 17959 (+0.49%)
SClause: 24298 -> 24012 (-1.18%)
Copies: 98023 -> 82960 (-15.37%); split: -15.38%, +0.01%
Branches: 29074 -> 27632 (-4.96%)
PreVGPRs: 25291 -> 25241 (-0.20%)

Co-authored-by: Daniel Schürmann <daniel@schuermann.dev>
Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/8026>
 2021-01-11 12:25:29 +00:00