fdo-mirrors/mesa
1
0
Fork 0
mirror of https://gitlab.freedesktop.org/mesa/mesa.git synced 2026-05-19 02:48:07 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 2
220438 commits 66 branches 935 tags 954 MiB
Commit graph

85 commits

Author SHA1 Message Date
Georg Lehmann
47599b2c38 aco/opt_postRA: remove try_convert_fma_to_vop2 
This is now done directly in the VOPD scheduler.

Foz-DB GFX1201:
Totals from 600 (0.52% of 114655) affected shaders:
no stats changed

Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/40225>
 2026-03-10 14:21:56 +00:00
Georg Lehmann
fc7b5d7eed aco/opt_postRA: don't optimize across calls 
Could do better by checking which registers are clobbered/preserved,
but that's unlikely to be useful anyway.

Backport-to: 26.0

Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39801>
 2026-02-11 11:34:29 +00:00
Georg Lehmann
2d38da94d4 aco: allow v_cmpx with DPP 
The wording in the RDNA3 ISA doc was since clarified, v_cmpx with DPP
behaves exactly like one would expect:
FI controls whether the source value can be read from inactive lanes,
but inactive lanes always write a 0 bit. The same applies to v_cmp with DPP.

Foz-DB Navi48:
Totals from 987 (1.20% of 82405) affected shaders:
Instrs: 517003 -> 516445 (-0.11%); split: -0.11%, +0.00%
CodeSize: 2782688 -> 2780508 (-0.08%); split: -0.08%, +0.00%
Latency: 2059169 -> 2056327 (-0.14%); split: -0.14%, +0.00%
InvThroughput: 365374 -> 365328 (-0.01%); split: -0.03%, +0.01%
Copies: 64669 -> 65616 (+1.46%)
SALU: 70693 -> 70652 (-0.06%)

Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39516>
 2026-01-27 20:42:51 +00:00
Georg Lehmann
1c1bd9d090 aco: only apply DPP with 3 or less uses 
Creating many new DPP instructions increases code size and decreases throughput.

Foz-DB Navi48:
Totals from 2196 (2.67% of 82179) affected shaders:
MaxWaves: 59930 -> 59960 (+0.05%); split: +0.08%, -0.03%
Instrs: 3718514 -> 3718298 (-0.01%); split: -0.08%, +0.07%
CodeSize: 20593544 -> 20507660 (-0.42%); split: -0.43%, +0.02%
VGPRs: 135924 -> 135744 (-0.13%); split: -0.17%, +0.04%
Latency: 33174704 -> 33163001 (-0.04%); split: -0.07%, +0.04%
InvThroughput: 6500723 -> 6491382 (-0.14%); split: -0.15%, +0.01%
VClause: 72348 -> 72343 (-0.01%); split: -0.06%, +0.05%
SClause: 83160 -> 83165 (+0.01%); split: -0.03%, +0.04%
Copies: 286592 -> 285575 (-0.35%); split: -0.45%, +0.09%
Branches: 99970 -> 99971 (+0.00%); split: -0.00%, +0.00%
PreSGPRs: 103280 -> 103279 (-0.00%)
PreVGPRs: 95590 -> 95440 (-0.16%); split: -0.30%, +0.14%
VALU: 1931369 -> 1931725 (+0.02%); split: -0.08%, +0.09%
SALU: 637663 -> 636780 (-0.14%); split: -0.15%, +0.01%
VOPD: 65236 -> 65589 (+0.54%); split: +0.91%, -0.37%

Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39516>
 2026-01-27 20:42:51 +00:00
Georg Lehmann
d4c0318f48 aco: apply DPP with scalar src1 on gfx11.5+ 
Foz-DB Navi48:
Totals from 6261 (7.62% of 82179) affected shaders:
MaxWaves: 176284 -> 176236 (-0.03%); split: +0.01%, -0.03%
Instrs: 5850185 -> 5828451 (-0.37%); split: -0.41%, +0.04%
CodeSize: 31363324 -> 31419904 (+0.18%); split: -0.08%, +0.26%
VGPRs: 328284 -> 328200 (-0.03%); split: -0.07%, +0.05%
SpillSGPRs: 2268 -> 2256 (-0.53%)
Latency: 50235516 -> 50218816 (-0.03%); split: -0.06%, +0.03%
InvThroughput: 8256243 -> 8242036 (-0.17%); split: -0.22%, +0.05%
VClause: 81000 -> 80975 (-0.03%); split: -0.11%, +0.08%
SClause: 136376 -> 136387 (+0.01%); split: -0.11%, +0.11%
Copies: 414021 -> 417894 (+0.94%); split: -0.13%, +1.07%
Branches: 105301 -> 105298 (-0.00%); split: -0.00%, +0.00%
PreSGPRs: 291360 -> 291432 (+0.02%)
PreVGPRs: 238593 -> 238729 (+0.06%); split: -0.02%, +0.08%
VALU: 3425446 -> 3403463 (-0.64%); split: -0.65%, +0.01%
SALU: 815505 -> 819372 (+0.47%); split: -0.02%, +0.50%

Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39516>
 2026-01-27 20:42:51 +00:00
Georg Lehmann
903d940fa9 aco: don't convert VOP3P to VOP3 when applying DPP 
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39516>
 2026-01-27 20:42:50 +00:00
Georg Lehmann
8ac7b9fc37 aco: undo operand swap if applying DPP fails 
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/39516>
 2026-01-27 20:42:50 +00:00
Georg Lehmann
39a61502e5 aco/opt_postRA: allow v_cmpx to clobber exec before nop split/create vector 
Kind of ugly, but I really hate seeing this in every rt traversal loop:

image_bvh64_intersect_ray v[56:59], [v40, v41, v42, v47, v48, v49, v50, v51, v52, v53, v54, v55], s[44:47]
v_cmp_class_f32_e64 s57, 0xff800000, v12
s_and_b32 exec_lo, s57, exec_lo
s_cbranch_execz BB219

Foz-DB Navi21:
Totals from 3394 (3.48% of 97591) affected shaders:
Instrs: 9536259 -> 9533592 (-0.03%)
CodeSize: 51657072 -> 51640120 (-0.03%); split: -0.03%, +0.00%
Latency: 109493553 -> 109513317 (+0.02%); split: -0.01%, +0.02%
InvThroughput: 29125525 -> 29131876 (+0.02%); split: -0.00%, +0.02%
Copies: 815888 -> 818219 (+0.29%); split: -0.01%, +0.30%
Branches: 277451 -> 277449 (-0.00%)
SALU: 1217642 -> 1214976 (-0.22%)

Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/38697>
 2025-11-29 08:02:24 +00:00
Antonio Ospite
ddf2aa3a4d build: avoid redefining unreachable() which is standard in C23 
In the C23 standard unreachable() is now a predefined function-like
macro in <stddef.h>

See https://android.googlesource.com/platform/bionic/+/HEAD/docs/c23.md#is-now-a-predefined-function_like-macro-in

And this causes build errors when building for C23:

-----------------------------------------------------------------------
In file included from ../src/util/log.h:30,
                 from ../src/util/log.c:30:
../src/util/macros.h:123:9: warning: "unreachable" redefined
  123 | #define unreachable(str)    \
      |         ^~~~~~~~~~~
In file included from ../src/util/macros.h:31:
/usr/lib/gcc/x86_64-linux-gnu/14/include/stddef.h:456:9: note: this is the location of the previous definition
  456 | #define unreachable() (__builtin_unreachable ())
      |         ^~~~~~~~~~~
-----------------------------------------------------------------------

So don't redefine it with the same name, but use the name UNREACHABLE()
to also signify it's a macro.

Using a different name also makes sense because the behavior of the
macro was extending the one of __builtin_unreachable() anyway, and it
also had a different signature, accepting one argument, compared to the
standard unreachable() with no arguments.

This change improves the chances of building mesa with the C23 standard,
which for instance is the default in recent AOSP versions.

All the instances of the macro, including the definition, were updated
with the following command line:

  git grep -l '[^_]unreachable(' -- "src/**" | sort | uniq | \
  while read file; \
  do \
    sed -e 's/\([^_]\)unreachable(/\1UNREACHABLE(/g' -i "$file"; \
  done && \
  sed -e 's/#undef unreachable/#undef UNREACHABLE/g' -i src/intel/isl/isl_aux_info.c

Reviewed-by: Erik Faye-Lund <erik.faye-lund@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/36437>
 2025-07-31 17:49:42 +00:00
Georg Lehmann
cd4c0bc58e aco: don't use constant_bits when not applying constants 
This is incorrect for 16bit integer operands.

Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/35020>
 2025-05-19 13:05:48 +00:00
Georg Lehmann
f98d20fec6 aco: replace get_operand_size with get_operand_type 
To not use constant_bits everywhere.

Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/35020>
 2025-05-19 13:05:48 +00:00
Georg Lehmann
2d68efd9f3 aco/opt_postRA: remove scc == 0 for more opcodes 
Convert special case to s_cselect

Foz-DB Navi21:
Totals from 42 (0.05% of 79789) affected shaders:
Instrs: 91826 -> 91690 (-0.15%)
CodeSize: 496304 -> 495680 (-0.13%)
Latency: 1631974 -> 1631948 (-0.00%); split: -0.00%, +0.00%
InvThroughput: 278772 -> 278766 (-0.00%)
SALU: 10627 -> 10491 (-1.28%)

Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/33734>
 2025-03-04 21:36:17 +00:00
Georg Lehmann
83247ffa30 aco/opt_postRA: remove scc != 0 with multiple uses 
These can always be removed.

Foz-DB Navi21:
Totals from 39 (0.05% of 79789) affected shaders:
Instrs: 138352 -> 138299 (-0.04%)
CodeSize: 710424 -> 710272 (-0.02%)
Latency: 468276 -> 468254 (-0.00%); split: -0.01%, +0.00%
InvThroughput: 108970 -> 108973 (+0.00%)
SALU: 18785 -> 18732 (-0.28%)

Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/33734>
 2025-03-04 21:36:17 +00:00
Georg Lehmann
6445ba0f05 aco/opt_postRA: allow try_optimize_scc_nocompare for all instructions 
If the old SCC source worked, the new one will too.

Foz-DB Navi21:
Totals from 106 (0.13% of 79789) affected shaders:
Instrs: 255233 -> 254825 (-0.16%)
CodeSize: 1337308 -> 1335692 (-0.12%)
Latency: 1455208 -> 1454524 (-0.05%); split: -0.05%, +0.00%
InvThroughput: 385624 -> 385612 (-0.00%); split: -0.00%, +0.00%
SALU: 53976 -> 53568 (-0.76%)

Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/33734>
 2025-03-04 21:36:17 +00:00
Georg Lehmann
3386ea09d4 aco/opt_postRA: split try_optimize_scc_nocompare in two functions 
These are two independent steps, no real reason why they should be in the same
function.

No FOZ-DB changes.

Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/33734>
 2025-03-04 21:36:17 +00:00
Friedrich Vock
71392fff25 aco: Fix dead instruction/index handling for try_insert_saveexec_out_of_loop 
The loop checking if exec is overwritten didn't check for NULL
instructions, and didn't fix up reg write indices after inserting
instructions.

Fixes: fcd94a8c ("aco: move try_optimize_branching_sequence() to postRA optimizations")
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32746>
 2025-01-08 10:48:01 +00:00
Georg Lehmann
6a6b26dfa5 aco: create v_cmpx with s_andn2(exec, v_cmp) 
Foz-DB Navi21:
Totals from 3928 (4.95% of 79395) affected shaders:
Instrs: 1155370 -> 1151154 (-0.36%)
CodeSize: 6332192 -> 6314616 (-0.28%)
Latency: 11955231 -> 11933281 (-0.18%); split: -0.18%, +0.00%
InvThroughput: 1842283 -> 1841822 (-0.03%); split: -0.03%, +0.00%
SALU: 175431 -> 171215 (-2.40%)

Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Daniel Schürmann <None>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32731>
 2024-12-30 13:05:23 +00:00
Daniel Schürmann
fcd94a8ca7 aco: move try_optimize_branching_sequence() to postRA optimizations 
Totals from 196 (0.25% of 79206) affected shaders: (Navi31)

Instrs: 534343 -> 534438 (+0.02%); split: -0.00%, +0.02%
CodeSize: 2774852 -> 2775420 (+0.02%); split: -0.00%, +0.02%
Latency: 7103512 -> 7103021 (-0.01%); split: -0.01%, +0.00%
InvThroughput: 959477 -> 959447 (-0.00%)
Copies: 42646 -> 42648 (+0.00%)
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32330>
 2024-12-12 08:11:21 +00:00
Daniel Schürmann
95d44c7ce0 aco/optimizer_postRA: set branch()->never_taken if exec is constant non-zero 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32330>
 2024-12-12 08:11:21 +00:00
Daniel Schürmann
1ff9a0fe80 aco: remove Pseudo_instruction::tmp_in_scc 
This information is redundant, now.

No fossil-changes.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32217>
 2024-11-20 11:04:32 +00:00
Daniel Schürmann
a1a4a6061c aco/ra: explicitly assign scratch SGPR for linear phis 
We are about to remove the branch definitions which previously
served this purpose. Also remove Block::scc_live_out.
Some changes due to round-robin RA.

Totals from 939 (1.18% of 79395) affected shaders: (Navi31)

Instrs: 5038786 -> 5038611 (-0.00%); split: -0.01%, +0.00%
CodeSize: 26153412 -> 26152904 (-0.00%); split: -0.00%, +0.00%
Latency: 41649989 -> 41650120 (+0.00%); split: -0.00%, +0.00%
InvThroughput: 6447508 -> 6447536 (+0.00%); split: -0.00%, +0.00%
SClause: 131319 -> 131276 (-0.03%); split: -0.03%, +0.00%
Copies: 359362 -> 359256 (-0.03%); split: -0.05%, +0.02%
SALU: 639275 -> 639169 (-0.02%); split: -0.03%, +0.01%
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/32217>
 2024-11-20 11:04:32 +00:00
Daniel Schürmann
e2705a9d85 aco: set Precolored flag before register allocation 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/31387>
 2024-10-22 12:29:18 +00:00
Rhys Perry
39270a8be3 aco: preserve SSA in try_eliminate_scc_copy 
Otherwise, there is no definition of this temporary. Fixes fail in future
validation.

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/30440>
 2024-08-21 10:47:20 +00:00
Samuel Pitoiset
7a69d78ba2 aco: use SPDX-License-Identifier 
Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28622>
 2024-04-08 15:49:25 +00:00
Timur Kristóf
b9b557f2e7 aco/optimizer_postRA: Remove a check from SCC no-compare optimization. 
Not all code paths of this optimization depend on there being only
one user of the first operand; and those code paths already have
their own check for this.

Fossil DB stats on Navi 21:

Totals from 477 (0.60% of 79395) affected shaders:
Instrs: 995901 -> 995341 (-0.06%); split: -0.06%, +0.00%
CodeSize: 5218856 -> 5216816 (-0.04%); split: -0.04%, +0.00%
Latency: 16340256 -> 16338799 (-0.01%); split: -0.01%, +0.00%
InvThroughput: 3044975 -> 3044871 (-0.00%); split: -0.00%, +0.00%
Copies: 95047 -> 95071 (+0.03%)
SALU: 150345 -> 149785 (-0.37%); split: -0.38%, +0.01%

Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Georg Lehmann <dadschoorse@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28545>
 2024-04-04 00:50:11 +00:00
Daniel Schürmann
a863c7951e aco: remove create_instruction() template parameter 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28370>
 2024-03-28 11:25:43 +00:00
Daniel Schürmann
1187189235 aco: unify different SALU types into single struct SALU_instruction 
This removes
- SOP1_instruction
- SOP2_instruction
- SOPC_instruction
- SOPK_instruction
- SOPP_instruction

and their corresponding methods.

Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28370>
 2024-03-28 11:25:43 +00:00
Timur Kristóf
58e3b1f930 aco: Allow passing constant operand to is_overwritten_since. 
This is to make it more intuitive and also consistent
with last_writer_idx which does allow constant operands.

Signed-off-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Georg Lehmann <dadschoorse@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28046>
 2024-03-19 20:50:12 +00:00
Daniel Schürmann
9bbb9f1104 aco: use small_vec as Block::edge_vec for predecessors and successors 
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27984>
 2024-03-19 13:06:58 +00:00
Rhys Perry
dea8b02b03 aco: don't pass constant to is_overwritten_since() 
Fixes usage of uninitialised value in dead_space/065515347dca4851 and
other dead_space shaders.

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Georg Lehmann <dadschoorse@gmail.com>
Fixes: def0c275c4 ("aco: Eliminate SCC copies when possible.")
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/28011>
 2024-03-07 12:17:39 +00:00
Timur Kristóf
def0c275c4 aco: Eliminate SCC copies when possible. 
Foz-DB Navi31:
Totals from 2517 (3.22% of 78112) affected shaders:
Instrs: 5992126 -> 5972611 (-0.33%); split: -0.33%, +0.00%
CodeSize: 30986404 -> 30914536 (-0.23%); split: -0.23%, +0.00%
Latency: 43221112 -> 43217422 (-0.01%); split: -0.02%, +0.01%
InvThroughput: 6675983 -> 6674598 (-0.02%); split: -0.02%, +0.00%
SClause: 181987 -> 181976 (-0.01%); split: -0.01%, +0.00%
Copies: 538852 -> 519419 (-3.61%)

Co-authored-by: Georg Lehmann <dadschoorse@gmail.com>
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27072>
 2024-03-05 22:51:01 +00:00
Georg Lehmann
e7d6cd9216 aco/post-ra: track pseudo scratch sgpr/scc clobber 
Foz-DB Navi31:
Totals from 1439 (1.84% of 78112) affected shaders:
Instrs: 1994854 -> 1996650 (+0.09%)
CodeSize: 11376864 -> 11383384 (+0.06%)
Latency: 14996299 -> 14999317 (+0.02%); split: -0.00%, +0.02%
InvThroughput: 2061294 -> 2061518 (+0.01%); split: -0.00%, +0.01%

Cc: mesa-stable

Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27855>
 2024-03-05 20:16:21 +00:00
Georg Lehmann
bd93e8372d aco/post-ra: assume scc is going to be overwritten by phis at end of blocks 
Cc: mesa-stable
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27855>
 2024-03-05 20:16:21 +00:00
Georg Lehmann
a5056b2f93 aco/post-ra: rename overwritten_subdword to allow additional uses 
Cc: mesa-stable
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27855>
 2024-03-05 20:16:21 +00:00
Georg Lehmann
ad5fbc4407 aco: use fmamk/ak instead of fma with inline constant for more VOPD 
Foz-DB navi31, forced wave32:
Totals from 24438 (31.29% of 78112) affected shaders:
Instrs: 21632788 -> 21551766 (-0.37%); split: -0.38%, +0.01%
CodeSize: 126181860 -> 126083848 (-0.08%); split: -0.10%, +0.02%
Latency: 162491062 -> 162516234 (+0.02%); split: -0.05%, +0.07%
InvThroughput: 31121194 -> 31002125 (-0.38%); split: -0.40%, +0.02%
VClause: 420176 -> 420169 (-0.00%); split: -0.00%, +0.00%
SClause: 791844 -> 791762 (-0.01%); split: -0.01%, +0.00%

Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27523>
 2024-02-15 12:38:55 +01:00
Georg Lehmann
e36235e6d5 aco: reassign split vector to SOPC 
Foz-DB Navi21:
Totals from 2669 (3.42% of 78112) affected shaders:
Instrs: 3570360 -> 3562026 (-0.23%)
CodeSize: 19049784 -> 19017092 (-0.17%)
Latency: 25343555 -> 25337767 (-0.02%); split: -0.03%, +0.00%
InvThroughput: 6191344 -> 6191079 (-0.00%); split: -0.01%, +0.00%
VClause: 90803 -> 90802 (-0.00%)
SClause: 114858 -> 114842 (-0.01%); split: -0.03%, +0.01%
Copies: 269287 -> 260999 (-3.08%)

Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/27046>
 2024-01-13 11:03:09 +00:00
Georg Lehmann
576afa8540 aco: don't optimize DPP across more than one block 
Register write tracking doesn't work for inactive lanes, so this was unsafe.

Foz-DB Navi31:
Totals from 8 (0.01% of 78196) affected shaders:
Instrs: 11513 -> 11515 (+0.02%)
CodeSize: 61056 -> 61064 (+0.01%)

Cc: mesa-stable
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/10197
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/26373>
 2023-11-28 12:48:56 +00:00
Rhys Perry
0e79f76aa5 aco: add fetch_inactive field to DPP instructions 
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Georg Lehmann <dadschoorse@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25525>
 2023-10-04 18:53:43 +00:00
Rhys Perry
26fce534b5 aco: shrink DPP8_instruction 
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Georg Lehmann <dadschoorse@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25525>
 2023-10-04 18:53:43 +00:00
Rhys Perry
ea633c128c aco/optimizer_postRA: don't combine DPP across exec on GFX8/9 
GFX8/9 seem to use FI=0 behaviour.

fossil-db (vega10):
Totals from 1 (0.00% of 63053) affected shaders:
Instrs: 542 -> 570 (+5.17%)
CodeSize: 2928 -> 3040 (+3.83%)
Latency: 2087 -> 2118 (+1.49%)
InvThroughput: 1103 -> 1143 (+3.63%)

Affected shader is from Cyberpunk 2077 fossil.

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Georg Lehmann <dadschoorse@gmail.com>
Cc: 23.2 <mesa-stable>
Closes: https://gitlab.freedesktop.org/mesa/mesa/-/issues/9784
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25471>
 2023-09-29 18:23:21 +00:00
Rhys Perry
ac48334ecd aco/optimizer_postRA: check overwritten_subdword in is_overwritten_since() 
Fixes crash for
dEQP-VK.mesh_shader.ext.in_out.with_f16.permutation_0.mesh_only and
similar tests on GFX11.

Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Fixes: 3d29779a25 ("aco/optimizer_postRA: Distinguish overwritten untrackable and subdword.")
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/25223>
 2023-09-18 10:26:16 +00:00
Georg Lehmann
476149f90d aco: use can_use_input_modifiers helper 
Foz-DB GFX1100:
Totals from 80 (0.06% of 132657) affected shaders:
CodeSize: 504500 -> 503660 (-0.17%)
Instrs: 95033 -> 94824 (-0.22%)
Latency: 629695 -> 629235 (-0.07%)
InvThroughput: 97105 -> 97008 (-0.10%)
VClause: 1779 -> 1777 (-0.11%)
Copies: 3233 -> 3236 (+0.09%); split: -0.03%, +0.12%

Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/23059>
 2023-05-18 22:57:24 +00:00
Georg Lehmann
644c5e95a0 aco: use get_operand_size for dpp opt 
This matters now that v_fma_mixlo_f16/v_fma_mixhi_f16 can use dpp.

Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/23059>
 2023-05-18 22:57:24 +00:00
Georg Lehmann
6a53af3fc8 aco: introduce helper to swap valu operands with modifiers 
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/23059>
 2023-05-18 22:57:23 +00:00
Georg Lehmann
04976beac7 aco: don't apply dpp if the alu instr uses the operand twice 
CP77 has a ton of fma(dpp(a), dpp(a), b).

Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22698>
 2023-05-12 13:31:16 +00:00
Georg Lehmann
151bcc1e8b aco: use VOP3+DPP 
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22698>
 2023-05-12 13:31:16 +00:00
Georg Lehmann
2a1e6a140d aco: also reassign p_extract_vector post ra 
Foz-DB Navi21:
Totals from 1223 (0.91% of 134864) affected shaders:
CodeSize: 6923888 -> 6913516 (-0.15%)
Instrs: 1293744 -> 1291151 (-0.20%)
Latency: 16928653 -> 16925035 (-0.02%); split: -0.02%, +0.00%
InvThroughput: 2985304 -> 2984775 (-0.02%); split: -0.02%, +0.00%
VClause: 32260 -> 32319 (+0.18%)
SClause: 54952 -> 54949 (-0.01%)
Copies: 83968 -> 81377 (-3.09%)

Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22821>
 2023-05-11 10:26:24 +00:00
Georg Lehmann
c1cf40da8a aco: Assert that operands have the same byte offset when reassigning split vectors 
This can not happen because the post-RA optimizer doesn't support sub dword
writes at the moment, but everytime I look at this I wonder if there might
be a bug here.

Reviewed-by: Timur Kristóf <timur.kristof@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22821>
 2023-05-11 10:26:24 +00:00
Georg Lehmann
a60b9313d3 aco: swap opsel when swapping VOP2/C operands 
Reviewed-by: Rhys Perry <pendingchaos02@gmail.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/22069>
 2023-03-30 03:34:34 +00:00
Georg Lehmann
de4805f25f aco: use bitfield array helpers for valu modifiers 
Reviewed-by: Daniel Schürmann <daniel@schuermann.dev>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/21023>
 2023-03-07 11:53:23 +00:00