0cbe4dd4c4
pan/bi: Use bi_dontcare for ZS_EMIT
...
This is more portable and avoids special casing.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/15461 >
2022-03-18 18:52:06 +00:00
1b934d5962
pan/bi: Emit arch-specific code for bi_dontcare
...
We use bi_dontcare() to specify any encoding where we don't care about
the value, with a preference for power-efficient encodings. On Bifrost,
a (possibly nonexistant) FAU read is the best encoding. On Valhall, that
encoding doesn't exist so just use a zero. That should be good enough in
practice.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/15461 >
2022-03-18 18:52:06 +00:00
666b714a37
pan/bi: Don't analyze helper reqs in !frag shaders
...
Waste of time, and possibly invalid too.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Cc: mesa-stable
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/15461 >
2022-03-18 18:52:06 +00:00
32ca920023
pan/bi: Use vertex/instance ID helpers
...
Enables portability to Valhall.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/15461 >
2022-03-18 18:52:05 +00:00
53f1e57ee7
pan/bi: Handle non-2D arrays
...
Handle arrays generically by using the last component of the coordinate source
as the array index. That works for both 2D arrays and cube arrays, fixing cube
arrays. Cube arrays were already handled correctly in core Panfrost code.
This code path is not tested in dEQP-GLES31 without exposing OES_cube_map_array,
which depends on OES_geometry_shader, which we don't have. Yet we do expose
PIPE_CAP_CUBE_ARRAY, so ARB_cube_map_array is exposed.
Disabling PIPE_CAP_CUBE_ARRAY would be an easy band-aid fix, but it's easy
enough to handle correctly.
dEQP-GLES31 passes with a hack enabling OES_cube_map_array [without geometry
shaders].
Also fixes 1D arrays on Bifrost for the same reasons.
Fixes: 70d6c5675dhttps://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/15254 >
2022-03-12 17:34:01 +00:00
65db6b0e7c
bifrost: Constant fold after lower_explicit_io
...
nir_lower_explicit_io generates mul+add chains even for constants. One
round of constant folding should get rid of these. This fixes all of
the dEQP-VK.glsl.conversions.* tests on panvk.
GoGoGoGo'd-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/15349 >
2022-03-12 03:51:54 +00:00
1aa120b10f
bifrost: Handle nir_op_frexp* and nir_op_ldexp
...
Reviewed-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/15352 >
2022-03-12 02:27:02 +00:00
d2a09f3dd3
bifrost: Implement fine and coarse derivatives
...
We leave the undecorated ops as fine so we don't disturb panfrost. For
coarse derivatives, we use a lane ID of 0 for the first lane and 1 or 2
for the second depending on axis. This ensures that coarse derivatives
are quad-uniform.
Reviewed-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/15352 >
2022-03-12 02:27:02 +00:00
83010c57a6
bifrost: Simplify derivatives a bit
...
Instead of two magic ternary operations, define a new `axis` temporary
which is 1 for X and 2 for Y. Then define everything else in terms of
this variable. In particular, the mask operation we do on LANE_ID is a
mask so it makes more sense to use ~axis than 1/2 but in the other
order.
Reviewed-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/15352 >
2022-03-12 02:27:02 +00:00
9d4441c71a
panfrost: Fix ubo_mask calculation
...
BITSET_MASK returns ~0 when given an input of zero, when we need it to
return 0 instead.
Fixes shaders with only sysvals but no UBOs when push constants are
disabled.
This breaks when 31 or 32 UBOs are used, but PAN_MAX_CONST_BUFFERS is
currently set to 16.
Fixes: c246af0dd8https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/15250 >
2022-03-05 14:55:00 -05:00
24101d944b
pan/bi: Add documentation for bifrost_nir_lower_store_component
...
Taken from the commit that introduced the function,
95458c4033https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/15250 >
2022-03-05 14:55:00 -05:00
198cb4a77a
panfrost: Disable point size upper limit clamping
...
The hardware already clamps this, there is no need to do it in the
shader.
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/15250 >
2022-03-05 14:50:09 -05:00
e7cfe18099
pan/bi: Run CSE after lowering FAU
...
Lowering FAU can add moves from uniforms. If a uniform is moved out to a
register mulitple times in a basic block, these moves can be CSE'd, saving
instructions at the cost of register pressure.
854 shaders in my shader-db are helped on cycle count (average 2.94% reduction
in cycles). Only 9 shaders have hurt thread count, and there is no change in
spills or fills. Overall, this seems to be a win.
Prevents instruction count regressions from the next commit.
total instructions in shared programs: 2454423 -> 2444690 (-0.40%)
instructions in affected programs: 386274 -> 376541 (-2.52%)
helped: 2105
HURT: 0
helped stats (abs) min: 1.0 max: 116.0 x̄: 4.62 x̃: 2
helped stats (rel) min: 0.04% max: 27.27% x̄: 3.64% x̃: 1.92%
95% mean confidence interval for instructions value: -4.91 -4.33
95% mean confidence interval for instructions %-change: -3.83% -3.45%
Instructions are helped.
total tuples in shared programs: 1963534 -> 1957106 (-0.33%)
tuples in affected programs: 233562 -> 227134 (-2.75%)
helped: 1491
HURT: 117
helped stats (abs) min: 1.0 max: 63.0 x̄: 4.44 x̃: 2
helped stats (rel) min: 0.04% max: 24.53% x̄: 4.39% x̃: 2.59%
HURT stats (abs) min: 1.0 max: 5.0 x̄: 1.61 x̃: 1
HURT stats (rel) min: 0.18% max: 8.33% x̄: 1.44% x̃: 1.05%
95% mean confidence interval for tuples value: -4.28 -3.71
95% mean confidence interval for tuples %-change: -4.20% -3.73%
Tuples are helped.
total clauses in shared programs: 387848 -> 387079 (-0.20%)
clauses in affected programs: 13718 -> 12949 (-5.61%)
helped: 583
HURT: 60
helped stats (abs) min: 1.0 max: 16.0 x̄: 1.42 x̃: 1
helped stats (rel) min: 1.11% max: 25.00% x̄: 8.28% x̃: 6.67%
HURT stats (abs) min: 1.0 max: 1.0 x̄: 1.00 x̃: 1
HURT stats (rel) min: 0.86% max: 20.00% x̄: 4.58% x̃: 4.00%
95% mean confidence interval for clauses value: -1.29 -1.10
95% mean confidence interval for clauses %-change: -7.57% -6.58%
Clauses are helped.
total cycles in shared programs: 201866.21 -> 201682.92 (-0.09%)
cycles in affected programs: 6241.79 -> 6058.50 (-2.94%)
helped: 952
HURT: 98
helped stats (abs) min: 0.04166399999999726 max: 2.625 x̄: 0.20 x̃: 0
helped stats (rel) min: 0.12% max: 26.00% x̄: 4.05% x̃: 2.38%
HURT stats (abs) min: 0.041665999999999315 max: 0.16666700000000034 x̄: 0.07 x̃: 0
HURT stats (rel) min: 0.18% max: 8.70% x̄: 1.60% x̃: 1.43%
95% mean confidence interval for cycles value: -0.19 -0.16
95% mean confidence interval for cycles %-change: -3.80% -3.24%
Cycles are helped.
total arith in shared programs: 74924.00 -> 74660.12 (-0.35%)
arith in affected programs: 9303.67 -> 9039.79 (-2.84%)
helped: 1513
HURT: 118
helped stats (abs) min: 0.04166399999999726 max: 2.625 x̄: 0.18 x̃: 0
helped stats (rel) min: 0.07% max: 33.33% x̄: 4.68% x̃: 2.67%
HURT stats (abs) min: 0.041665999999999315 max: 0.16666800000000137 x̄: 0.07 x̃: 0
HURT stats (rel) min: 0.18% max: 8.70% x̄: 1.55% x̃: 1.37%
95% mean confidence interval for arith value: -0.17 -0.15
95% mean confidence interval for arith %-change: -4.48% -3.98%
Arith are helped.
total quadwords in shared programs: 1757254 -> 1751978 (-0.30%)
quadwords in affected programs: 197399 -> 192123 (-2.67%)
helped: 1464
HURT: 110
helped stats (abs) min: 1.0 max: 51.0 x̄: 3.73 x̃: 2
helped stats (rel) min: 0.04% max: 21.95% x̄: 4.16% x̃: 2.52%
HURT stats (abs) min: 1.0 max: 7.0 x̄: 1.71 x̃: 1
HURT stats (rel) min: 0.21% max: 13.04% x̄: 1.65% x̃: 0.93%
95% mean confidence interval for quadwords value: -3.58 -3.13
95% mean confidence interval for quadwords %-change: -3.97% -3.53%
Quadwords are helped.
total threads in shared programs: 52899 -> 52890 (-0.02%)
threads in affected programs: 18 -> 9 (-50.00%)
helped: 0
HURT: 9
HURT stats (abs) min: 1.0 max: 1.0 x̄: 1.00 x̃: 1
HURT stats (rel) min: 50.00% max: 50.00% x̄: 50.00% x̃: 50.00%
95% mean confidence interval for threads value: -1.00 -1.00
95% mean confidence interval for threads %-change: -50.00% -50.00%
Threads are HURT.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/15239 >
2022-03-04 15:22:04 +00:00
b48236ea3e
pan/bi: Add arithmetic flag to RSHIFT ops
...
Models ops like ARSHIFT_OR.i32 on Valhall without adding piles of new
instructions to the IR.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/15216 >
2022-03-03 00:41:44 +00:00
0b0e74ae82
pan/bi: Extend LD_TILE with a register format
...
Required for Valhall. NIR has the information anyway, pass it along.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/15216 >
2022-03-03 00:41:44 +00:00
5796777889
pan/bi: Model offset for LOAD/STORE
...
Needed to model the immediate offset on Valhall.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/15216 >
2022-03-03 00:41:43 +00:00
20891e75c2
pan/bi: Extend BLEND to take a register format
...
Needed on Valhall.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/15216 >
2022-03-03 00:41:43 +00:00
ffde1f359b
pan/bi: Adapt bi_lower_branch for Valhall
...
Disable the Bifrost optimization; it's not portable.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/15204 >
2022-03-01 19:43:23 +00:00
ec9c1f8fa6
pan/bi: Wire Valhall disassembler into compiler
...
Useful when we grow Valhall support (soon!)
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/15204 >
2022-03-01 19:43:22 +00:00
3154df232b
pan/bi: Use a progress loop for constant folding
...
Needed to fold the dependent patterns produced by texture instructions
during NIR->Valhall.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/15204 >
2022-03-01 19:43:22 +00:00
eb1479bda2
pan/bi: Support message preloading
...
Preload LD_VAR_IMM or VAR_TEX instructions in the first block of fragment
shaders on v7. Preloaded messages write to fixed registers; when replacing
instructions we insert moves from the registers at the start of the program and
hope coalescing goes to town. (Admittedly we don't do any coalescing yet...)
The extra moves hurts instruction count in some cases; the win for cycle count
should cancel this out. When we get smarter copy prop or RA, those moves should
go away anyway.
This optimization may hurt register pressure by extending the lifetime of up to
eight registers written in the first block. This is expected to be acceptable:
on a large shader-db, there are no additional spills/fills, and only two shaders
are hurt on thread count.
This optimization only applies to v7, as the hardware was not introduced on v6
and was removed for Valhall.
total instructions in shared programs: 2451624 -> 2454286 (0.11%)
instructions in affected programs: 909046 -> 911708 (0.29%)
helped: 4719
HURT: 3341
helped stats (abs) min: 1.0 max: 10.0 x̄: 1.49 x̃: 1
helped stats (rel) min: 0.08% max: 33.33% x̄: 6.79% x̃: 3.92%
HURT stats (abs) min: 1.0 max: 50.0 x̄: 2.90 x̃: 2
HURT stats (rel) min: 0.12% max: 66.67% x̄: 6.39% x̃: 3.45%
95% mean confidence interval for instructions value: 0.27 0.39
95% mean confidence interval for instructions %-change: -1.55% -1.11%
Inconclusive result (value mean confidence interval and %-change mean confidence interval disagree).
total tuples in shared programs: 1969529 -> 1963429 (-0.31%)
tuples in affected programs: 601327 -> 595227 (-1.01%)
helped: 5907
HURT: 1297
helped stats (abs) min: 1.0 max: 8.0 x̄: 1.41 x̃: 1
helped stats (rel) min: 0.07% max: 33.33% x̄: 7.25% x̃: 5.26%
HURT stats (abs) min: 1.0 max: 40.0 x̄: 1.73 x̃: 1
HURT stats (rel) min: 0.16% max: 31.75% x̄: 3.38% x̃: 2.02%
95% mean confidence interval for tuples value: -0.88 -0.81
95% mean confidence interval for tuples %-change: -5.52% -5.15%
Tuples are helped.
total clauses in shared programs: 401689 -> 387830 (-3.45%)
clauses in affected programs: 136944 -> 123085 (-10.12%)
helped: 8427
HURT: 4
helped stats (abs) min: 1.0 max: 4.0 x̄: 1.65 x̃: 2
helped stats (rel) min: 0.49% max: 50.00% x̄: 19.88% x̃: 18.18%
HURT stats (abs) min: 1.0 max: 4.0 x̄: 2.50 x̃: 2
HURT stats (rel) min: 1.96% max: 19.05% x̄: 14.18% x̃: 17.86%
95% mean confidence interval for clauses value: -1.66 -1.63
95% mean confidence interval for clauses %-change: -20.15% -19.58%
Clauses are helped.
total cycles in shared programs: 202735.83 -> 201862.21 (-0.43%)
cycles in affected programs: 16295.46 -> 15421.83 (-5.36%)
helped: 3349
HURT: 1962
helped stats (abs) min: 0.041665999999999315 max: 1.0 x̄: 0.32 x̃: 0
helped stats (rel) min: 0.24% max: 100.00% x̄: 40.77% x̃: 33.33%
HURT stats (abs) min: 0.041665999999999315 max: 1.5833329999999997 x̄: 0.10 x̃: 0
HURT stats (rel) min: 0.09% max: 31.40% x̄: 2.95% x̃: 1.94%
95% mean confidence interval for cycles value: -0.17 -0.16
95% mean confidence interval for cycles %-change: -25.48% -23.76%
Cycles are helped.
total arith in shared programs: 74665.50 -> 74920.00 (0.34%)
arith in affected programs: 16059.92 -> 16314.42 (1.58%)
helped: 860
HURT: 3409
helped stats (abs) min: 0.041665999999999315 max: 0.25 x̄: 0.06 x̃: 0
helped stats (rel) min: 0.24% max: 37.50% x̄: 4.73% x̃: 2.56%
HURT stats (abs) min: 0.041665999999999315 max: 1.5833329999999997 x̄: 0.09 x̃: 0
HURT stats (rel) min: 0.09% max: 100.00% x̄: 8.99% x̃: 4.21%
95% mean confidence interval for arith value: 0.06 0.06
95% mean confidence interval for arith %-change: 5.83% 6.62%
Arith are HURT.
total texture in shared programs: 13083.50 -> 11877 (-9.22%)
texture in affected programs: 1663 -> 456.50 (-72.55%)
helped: 2377
HURT: 3
helped stats (abs) min: 0.5 max: 1.0 x̄: 0.51 x̃: 0
helped stats (rel) min: 6.25% max: 100.00% x̄: 87.12% x̃: 100.00%
HURT stats (abs) min: 0.5 max: 0.5 x̄: 0.50 x̃: 0
HURT stats (rel) min: 0.00% max: 25.00% x̄: 16.67% x̃: 25.00%
95% mean confidence interval for texture value: -0.51 -0.50
95% mean confidence interval for texture %-change: -87.98% -86.00%
Texture are helped.
total vary in shared programs: 10220.62 -> 4183.88 (-59.06%)
vary in affected programs: 10126.50 -> 4089.75 (-59.61%)
helped: 8538
HURT: 0
helped stats (abs) min: 0.125 max: 1.0 x̄: 0.71 x̃: 0
helped stats (rel) min: 7.14% max: 100.00% x̄: 74.74% x̃: 87.50%
95% mean confidence interval for vary value: -0.71 -0.70
95% mean confidence interval for vary %-change: -75.32% -74.16%
Vary are helped.
total quadwords in shared programs: 1766717 -> 1757161 (-0.54%)
quadwords in affected programs: 553801 -> 544245 (-1.73%)
helped: 6760
HURT: 711
helped stats (abs) min: 1.0 max: 11.0 x̄: 1.58 x̃: 1
helped stats (rel) min: 0.09% max: 29.41% x̄: 5.31% x̃: 4.84%
HURT stats (abs) min: 1.0 max: 33.0 x̄: 1.54 x̃: 1
HURT stats (rel) min: 0.10% max: 31.13% x̄: 2.53% x̃: 1.61%
95% mean confidence interval for quadwords value: -1.31 -1.25
95% mean confidence interval for quadwords %-change: -4.67% -4.46%
Quadwords are helped.
total threads in shared programs: 52899 -> 52897 (<.01%)
threads in affected programs: 4 -> 2 (-50.00%)
helped: 0
HURT: 2
total preloads in shared programs: 0 -> 116492
preloads in affected programs: 0 -> 116492
helped: 0
HURT: 8604
HURT stats (abs) min: 2.0 max: 24.0 x̄: 13.54 x̃: 14
HURT stats (rel) min: 0.00% max: 0.00% x̄: 0.00% x̃: 0.00%
95% mean confidence interval for preloads value: 13.45 13.63
95% mean confidence interval for preloads %-change: 0.00% 0.00%
Preloads are HURT.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9438 >
2022-02-24 14:09:14 -05:00
c8437cd415
pan/bi: Account for message preloading in shaderdb
...
If a message-passing instruction like LD_VAR is preloaded, it will no longer be
counted in the shader cycle counts. Add a special message preload counter that
approximates the cost of preloading, so this information doesn't get a lost.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/9438 >
2022-02-24 12:51:04 -05:00
6b2eda6b72
pan/bi: Reorder pushed uniforms to avoid moves
...
On Bifrost and Valhall, push uniforms are loaded into Fast Access Uniform
Random Access Memory (FAU-RAM). FAU-RAM is organized as an array of 64-bit
slots. A given tuple (Bifrost) or instruction (Valhall) may access at most a
single 64-bit slot. If an instruction requires uniforms from multiple 64-bit
slots, a uniform-to-register move must be inserted to avoid the hazard. However,
if an instruction requires a pair of 32-bit uniforms from the same 64-bit slot,
no move is required.
To reduce the number of moves we emit, this commit adds an optimization pass
that reorders pushed uniforms, trying to group uniforms used by the same
instruction. The pass works by creating a graph of pushed uniforms, where edges
denote the "both 32-bit uniforms required by the same instruction" relationship.
We perform depth-first search on this graph to find the connected components,
where each connected component is a cluster of uniforms that are used together.
We then select pairs of uniforms from each connected component. The remaining
unpaired uniforms (from components of odd sizes) are paired together
arbitrarily.
In principle, we should weight the graph by number of occurences and choose
pairs that maximize the total selected edge weight. This is left for
future work, as it is nontrivial -- selecting these edges optimally appears to
be NP-hard at first blush.
Implementation note: As position and varying shaders share FAU on Bifrost, extra
care is taken with a `push_offset` shader stage info parameter that ensures
varying shaders do not reorder uniforms selected by the previous position
shader.
total instructions in shared programs: 2503343 -> 2451758 (-2.06%)
instructions in affected programs: 1553309 -> 1501724 (-3.32%)
helped: 14256
HURT: 8
helped stats (abs) min: 1.0 max: 80.0 x̄: 3.62 x̃: 3
helped stats (rel) min: 0.06% max: 36.36% x̄: 7.31% x̃: 6.67%
HURT stats (abs) min: 1.0 max: 2.0 x̄: 1.38 x̃: 1
HURT stats (rel) min: 1.30% max: 12.50% x̄: 4.99% x̃: 3.85%
95% mean confidence interval for instructions value: -3.66 -3.58
95% mean confidence interval for instructions %-change: -7.41% -7.20%
Instructions are helped.
total tuples in shared programs: 2008399 -> 1969627 (-1.93%)
tuples in affected programs: 1146344 -> 1107572 (-3.38%)
helped: 12867
HURT: 147
helped stats (abs) min: 1.0 max: 61.0 x̄: 3.03 x̃: 2
helped stats (rel) min: 0.17% max: 42.86% x̄: 6.79% x̃: 4.65%
HURT stats (abs) min: 1.0 max: 3.0 x̄: 1.20 x̃: 1
HURT stats (rel) min: 0.29% max: 20.00% x̄: 2.12% x̃: 1.19%
95% mean confidence interval for tuples value: -3.03 -2.93
95% mean confidence interval for tuples %-change: -6.82% -6.57%
Tuples are helped.
total clauses in shared programs: 408005 -> 401708 (-1.54%)
clauses in affected programs: 90760 -> 84463 (-6.94%)
helped: 6006
HURT: 164
helped stats (abs) min: 1.0 max: 9.0 x̄: 1.08 x̃: 1
helped stats (rel) min: 0.45% max: 33.33% x̄: 12.44% x̃: 14.29%
HURT stats (abs) min: 1.0 max: 1.0 x̄: 1.00 x̃: 1
HURT stats (rel) min: 1.64% max: 25.00% x̄: 9.81% x̃: 5.26%
95% mean confidence interval for clauses value: -1.03 -1.01
95% mean confidence interval for clauses %-change: -12.03% -11.66%
Clauses are helped.
total cycles in shared programs: 203308.37 -> 202737.83 (-0.28%)
cycles in affected programs: 19264.71 -> 18694.17 (-2.96%)
helped: 3024
HURT: 41
helped stats (abs) min: 0.041665999999999315 max: 2.5416680000000014 x̄: 0.19 x̃: 0
helped stats (rel) min: 0.17% max: 33.33% x̄: 3.83% x̃: 2.83%
HURT stats (abs) min: 0.041665999999999315 max: 0.125 x̄: 0.06 x̃: 0
HURT stats (rel) min: 0.30% max: 5.88% x̄: 1.41% x̃: 0.93%
95% mean confidence interval for cycles value: -0.19 -0.18
95% mean confidence interval for cycles %-change: -3.89% -3.64%
Cycles are helped.
total arith in shared programs: 76265.67 -> 74669.25 (-2.09%)
arith in affected programs: 45001.50 -> 43405.08 (-3.55%)
helped: 12945
HURT: 97
helped stats (abs) min: 0.041665999999999315 max: 2.5416680000000014 x̄: 0.12 x̃: 0
helped stats (rel) min: 0.17% max: 50.00% x̄: 8.06% x̃: 4.88%
HURT stats (abs) min: 0.041665999999999315 max: 0.125 x̄: 0.05 x̃: 0
HURT stats (rel) min: 0.21% max: 33.33% x̄: 2.16% x̃: 0.96%
95% mean confidence interval for arith value: -0.12 -0.12
95% mean confidence interval for arith %-change: -8.16% -7.81%
Arith are helped.
total quadwords in shared programs: 1796563 -> 1766803 (-1.66%)
quadwords in affected programs: 948830 -> 919070 (-3.14%)
helped: 12078
HURT: 219
helped stats (abs) min: 1.0 max: 42.0 x̄: 2.49 x̃: 2
helped stats (rel) min: 0.10% max: 33.33% x̄: 5.57% x̃: 5.26%
HURT stats (abs) min: 1.0 max: 4.0 x̄: 1.21 x̃: 1
HURT stats (rel) min: 0.33% max: 6.67% x̄: 2.00% x̃: 1.14%
95% mean confidence interval for quadwords value: -2.46 -2.38
95% mean confidence interval for quadwords %-change: -5.52% -5.36%
Quadwords are helped.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/14163 >
2022-02-24 01:35:33 +00:00
2e86767370
pan/bi: Add BIFROST_MESA_DEBUG=nosb option
...
To disable the new scoreboarding optimizations when debugging.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/14298 >
2022-02-22 16:57:30 +00:00
606ac8d61e
pan/bi: Enable nir_opt_shrink_vectors
...
total instructions in shared programs: 1939513 -> 1935815 (-0.19%)
instructions in affected programs: 809066 -> 805368 (-0.46%)
helped: 3195
HURT: 865
helped stats (abs) min: 1.0 max: 15.0 x̄: 1.99 x̃: 1
helped stats (rel) min: 0.10% max: 25.00% x̄: 2.26% x̃: 1.28%
HURT stats (abs) min: 1.0 max: 22.0 x̄: 3.09 x̃: 2
HURT stats (rel) min: 0.10% max: 83.33% x̄: 2.67% x̃: 1.39%
95% mean confidence interval for instructions value: -1.00 -0.82
95% mean confidence interval for instructions %-change: -1.34% -1.08%
Instructions are helped.
total tuples in shared programs: 1523194 -> 1521789 (-0.09%)
tuples in affected programs: 745526 -> 744121 (-0.19%)
helped: 2947
HURT: 1844
helped stats (abs) min: 1.0 max: 18.0 x̄: 2.06 x̃: 1
helped stats (rel) min: 0.15% max: 25.00% x̄: 2.65% x̃: 1.59%
HURT stats (abs) min: 1.0 max: 29.0 x̄: 2.54 x̃: 1
HURT stats (rel) min: 0.09% max: 40.00% x̄: 2.32% x̃: 1.52%
95% mean confidence interval for tuples value: -0.39 -0.20
95% mean confidence interval for tuples %-change: -0.85% -0.62%
Tuples are helped.
total clauses in shared programs: 329158 -> 325350 (-1.16%)
clauses in affected programs: 111654 -> 107846 (-3.41%)
helped: 2787
HURT: 498
helped stats (abs) min: 1.0 max: 17.0 x̄: 1.57 x̃: 1
helped stats (rel) min: 0.76% max: 40.00% x̄: 6.92% x̃: 5.26%
HURT stats (abs) min: 1.0 max: 3.0 x̄: 1.14 x̃: 1
HURT stats (rel) min: 0.87% max: 50.00% x̄: 4.73% x̃: 3.77%
95% mean confidence interval for clauses value: -1.21 -1.10
95% mean confidence interval for clauses %-change: -5.39% -4.93%
Clauses are helped.
total cycles in shared programs: 172084.50 -> 166827.62 (-3.05%)
cycles in affected programs: 74698.83 -> 69441.96 (-7.04%)
helped: 3706
HURT: 568
helped stats (abs) min: 0.041665999999999315 max: 19.0 x̄: 1.44 x̃: 1
helped stats (rel) min: 0.24% max: 75.00% x̄: 9.48% x̃: 6.90%
HURT stats (abs) min: 0.041665999999999315 max: 1.0 x̄: 0.15 x̃: 0
HURT stats (rel) min: 0.25% max: 50.00% x̄: 2.21% x̃: 1.42%
95% mean confidence interval for cycles value: -1.28 -1.18
95% mean confidence interval for cycles %-change: -8.18% -7.67%
Cycles are helped.
total arith in shared programs: 57145.04 -> 57211.37 (0.12%)
arith in affected programs: 27595.12 -> 27661.46 (0.24%)
helped: 1933
HURT: 2259
helped stats (abs) min: 0.041665999999999315 max: 0.75 x̄: 0.09 x̃: 0
helped stats (rel) min: 0.16% max: 33.33% x̄: 2.74% x̃: 1.52%
HURT stats (abs) min: 0.04166399999999726 max: 1.3333329999999997 x̄: 0.11 x̃: 0
HURT stats (rel) min: 0.10% max: 100.00% x̄: 2.79% x̃: 1.62%
95% mean confidence interval for arith value: 0.01 0.02
95% mean confidence interval for arith %-change: 0.07% 0.40%
Arith are HURT.
total texture in shared programs: 12857 -> 12857 (0.00%)
texture in affected programs: 0 -> 0
helped: 0
HURT: 0
total vary in shared programs: 11157.75 -> 10222 (-8.39%)
vary in affected programs: 5643 -> 4707.25 (-16.58%)
helped: 3196
HURT: 0
helped stats (abs) min: 0.125 max: 1.875 x̄: 0.29 x̃: 0
helped stats (rel) min: 2.78% max: 75.00% x̄: 18.49% x̃: 15.00%
95% mean confidence interval for vary value: -0.30 -0.29
95% mean confidence interval for vary %-change: -18.88% -18.11%
Vary are helped.
total ldst in shared programs: 146420 -> 140270 (-4.20%)
ldst in affected programs: 66027 -> 59877 (-9.31%)
helped: 2942
HURT: 10
helped stats (abs) min: 1.0 max: 19.0 x̄: 2.09 x̃: 2
helped stats (rel) min: 0.90% max: 100.00% x̄: 16.81% x̃: 8.33%
HURT stats (abs) min: 1.0 max: 1.0 x̄: 1.00 x̃: 1
HURT stats (rel) min: 2.22% max: 50.00% x̄: 13.03% x̃: 3.33%
95% mean confidence interval for ldst value: -2.15 -2.02
95% mean confidence interval for ldst %-change: -17.53% -15.89%
Ldst are helped.
total quadwords in shared programs: 1398329 -> 1392117 (-0.44%)
quadwords in affected programs: 704641 -> 698429 (-0.88%)
helped: 3677
HURT: 1299
helped stats (abs) min: 1.0 max: 26.0 x̄: 2.51 x̃: 1
helped stats (rel) min: 0.10% max: 26.92% x̄: 2.64% x̃: 1.89%
HURT stats (abs) min: 1.0 max: 20.0 x̄: 2.31 x̃: 1
HURT stats (rel) min: 0.11% max: 44.44% x̄: 2.34% x̃: 1.55%
95% mean confidence interval for quadwords value: -1.34 -1.16
95% mean confidence interval for quadwords %-change: -1.44% -1.25%
Quadwords are helped.
total threads in shared programs: 35234 -> 35311 (0.22%)
threads in affected programs: 119 -> 196 (64.71%)
helped: 91
HURT: 14
helped stats (abs) min: 1.0 max: 1.0 x̄: 1.00 x̃: 1
helped stats (rel) min: 100.00% max: 100.00% x̄: 100.00% x̃: 100.00%
HURT stats (abs) min: 1.0 max: 1.0 x̄: 1.00 x̃: 1
HURT stats (rel) min: 50.00% max: 50.00% x̄: 50.00% x̃: 50.00%
95% mean confidence interval for threads value: 0.60 0.87
95% mean confidence interval for threads %-change: 70.08% 89.92%
Threads are helped.
total loops in shared programs: 125 -> 125 (0.00%)
loops in affected programs: 0 -> 0
helped: 0
HURT: 0
total spills in shared programs: 149 -> 144 (-3.36%)
spills in affected programs: 22 -> 17 (-22.73%)
helped: 1
HURT: 0
total fills in shared programs: 966 -> 956 (-1.04%)
fills in affected programs: 44 -> 34 (-22.73%)
helped: 1
HURT: 0
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/15090 >
2022-02-22 15:21:09 +00:00
e0e63c2a8e
pan/bi: Specialize IDVS in NIR
...
It's a bit more code, but it's needed to chew through control flow since we
don't have a backend version of dead_cf. Results are really good, meaning I
really screwed this up the first time around (hence the cc mesa-stable).
total instructions in shared programs: 1963576 -> 1939513 (-1.23%)
instructions in affected programs: 671053 -> 646990 (-3.59%)
helped: 4436
HURT: 729
helped stats (abs) min: 1.0 max: 43.0 x̄: 5.75 x̃: 6
helped stats (rel) min: 0.21% max: 100.00% x̄: 6.47% x̃: 5.17%
HURT stats (abs) min: 1.0 max: 22.0 x̄: 2.01 x̃: 1
HURT stats (rel) min: 0.50% max: 50.00% x̄: 10.45% x̃: 9.09%
95% mean confidence interval for instructions value: -4.77 -4.55
95% mean confidence interval for instructions %-change: -4.36% -3.80%
Instructions are helped.
total tuples in shared programs: 1533335 -> 1523194 (-0.66%)
tuples in affected programs: 483167 -> 473026 (-2.10%)
helped: 3414
HURT: 1288
helped stats (abs) min: 1.0 max: 20.0 x̄: 3.73 x̃: 2
helped stats (rel) min: 0.27% max: 100.00% x̄: 4.87% x̃: 3.03%
HURT stats (abs) min: 1.0 max: 19.0 x̄: 2.02 x̃: 1
HURT stats (rel) min: 0.24% max: 38.10% x̄: 8.10% x̃: 5.88%
95% mean confidence interval for tuples value: -2.28 -2.03
95% mean confidence interval for tuples %-change: -1.62% -1.02%
Tuples are helped.
total clauses in shared programs: 351432 -> 329158 (-6.34%)
clauses in affected programs: 142237 -> 119963 (-15.66%)
helped: 5328
HURT: 3
helped stats (abs) min: 1.0 max: 43.0 x̄: 4.18 x̃: 4
helped stats (rel) min: 0.74% max: 100.00% x̄: 19.44% x̃: 17.24%
HURT stats (abs) min: 1.0 max: 1.0 x̄: 1.00 x̃: 1
HURT stats (rel) min: 9.09% max: 12.50% x̄: 10.90% x̃: 11.11%
95% mean confidence interval for clauses value: -4.25 -4.11
95% mean confidence interval for clauses %-change: -19.72% -19.12%
Clauses are helped.
total cycles in shared programs: 202830.92 -> 172084.50 (-15.16%)
cycles in affected programs: 117078.42 -> 86332 (-26.26%)
helped: 5450
HURT: 1
helped stats (abs) min: 0.083333 max: 49.0 x̄: 5.64 x̃: 5
helped stats (rel) min: 1.42% max: 100.00% x̄: 27.94% x̃: 25.64%
HURT stats (abs) min: 0.25 max: 0.25 x̄: 0.25 x̃: 0
HURT stats (rel) min: 2.46% max: 2.46% x̄: 2.46% x̃: 2.46%
95% mean confidence interval for cycles value: -5.74 -5.54
95% mean confidence interval for cycles %-change: -28.30% -27.58%
Cycles are helped.
total arith in shared programs: 57274.29 -> 57145.04 (-0.23%)
arith in affected programs: 16418.33 -> 16289.08 (-0.79%)
helped: 2442
HURT: 1784
helped stats (abs) min: 0.041665999999999315 max: 0.75 x̄: 0.14 x̃: 0
helped stats (rel) min: 0.23% max: 100.00% x̄: 5.51% x̃: 2.87%
HURT stats (abs) min: 0.041665999999999315 max: 0.9166670000000003 x̄: 0.12 x̃: 0
HURT stats (rel) min: 0.00% max: 100.00% x̄: 25.13% x̃: 9.09%
95% mean confidence interval for arith value: -0.04 -0.03
95% mean confidence interval for arith %-change: 6.61% 8.24%
Inconclusive result (value mean confidence interval and %-change mean confidence interval disagree).
total texture in shared programs: 12857 -> 12857 (0.00%)
texture in affected programs: 0 -> 0
helped: 0
HURT: 0
total vary in shared programs: 11157.75 -> 11157.75 (0.00%)
vary in affected programs: 0 -> 0
helped: 0
HURT: 0
total ldst in shared programs: 177208 -> 146420 (-17.37%)
ldst in affected programs: 117098 -> 86310 (-26.29%)
helped: 5447
HURT: 0
helped stats (abs) min: 1.0 max: 49.0 x̄: 5.65 x̃: 5
helped stats (rel) min: 1.92% max: 100.00% x̄: 27.91% x̃: 25.64%
95% mean confidence interval for ldst value: -5.75 -5.55
95% mean confidence interval for ldst %-change: -28.27% -27.56%
Ldst are helped.
total quadwords in shared programs: 1436507 -> 1398329 (-2.66%)
quadwords in affected programs: 515101 -> 476923 (-7.41%)
helped: 5150
HURT: 111
helped stats (abs) min: 1.0 max: 39.0 x̄: 7.46 x̃: 6
helped stats (rel) min: 0.17% max: 100.00% x̄: 10.02% x̃: 8.24%
HURT stats (abs) min: 1.0 max: 9.0 x̄: 2.01 x̃: 1
HURT stats (rel) min: 0.43% max: 21.62% x̄: 3.57% x̃: 1.94%
95% mean confidence interval for quadwords value: -7.41 -7.11
95% mean confidence interval for quadwords %-change: -9.98% -9.49%
Quadwords are helped.
total threads in shared programs: 35025 -> 35228 (0.58%)
threads in affected programs: 218 -> 421 (93.12%)
helped: 208
HURT: 5
helped stats (abs) min: 1.0 max: 1.0 x̄: 1.00 x̃: 1
helped stats (rel) min: 100.00% max: 100.00% x̄: 100.00% x̃: 100.00%
HURT stats (abs) min: 1.0 max: 1.0 x̄: 1.00 x̃: 1
HURT stats (rel) min: 50.00% max: 50.00% x̄: 50.00% x̃: 50.00%
95% mean confidence interval for threads value: 0.91 0.99
95% mean confidence interval for threads %-change: 93.40% 99.55%
Threads are helped.
total loops in shared programs: 128 -> 125 (-2.34%)
loops in affected programs: 3 -> 0
helped: 3
HURT: 0
helped stats (abs) min: 1.0 max: 1.0 x̄: 1.00 x̃: 1
helped stats (rel) min: 100.00% max: 100.00% x̄: 100.00% x̃: 100.00%
total spills in shared programs: 158 -> 149 (-5.70%)
spills in affected programs: 15 -> 6 (-60.00%)
helped: 9
HURT: 0
total fills in shared programs: 1133 -> 966 (-14.74%)
fills in affected programs: 197 -> 30 (-84.77%)
helped: 9
HURT: 0
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Cc: mesa-stable
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/15090 >
2022-02-22 15:21:09 +00:00
a8418abd74
pan/bi: Revert "Fix load_const of 1-bit booleans"
...
This reverts commit 29d319c767https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/14576 >
2022-02-19 03:02:10 +00:00
21bdee7bcc
pan/bi: Switch to lower_bool_to_bitsize
...
Instead of ingesting 1-bit booleans and trying to force everything to be
16-bit, except when it isn't, and creating a mess in the backend... just
use the NIR pass designed to select bitsize for booleans. Yes, this
means we need to handle more NIR instructions, but the handling is
easier and the conversion is more obvious (except for some edge cases
like 16-bit vectorized b32csel). This generates noticeably better code,
and the generated code will be easier to optimize.
total instructions in shared programs: 90257 -> 88941 (-1.46%)
instructions in affected programs: 49145 -> 47829 (-2.68%)
helped: 201
HURT: 2
helped stats (abs) min: 1.0 max: 40.0 x̄: 6.57 x̃: 3
helped stats (rel) min: 0.29% max: 13.89% x̄: 2.57% x̃: 1.90%
HURT stats (abs) min: 2.0 max: 2.0 x̄: 2.00 x̃: 2
HURT stats (rel) min: 2.15% max: 2.74% x̄: 2.45% x̃: 2.45%
95% mean confidence interval for instructions value: -7.71 -5.26
95% mean confidence interval for instructions %-change: -2.84% -2.20%
Instructions are helped.
total tuples in shared programs: 73740 -> 72922 (-1.11%)
tuples in affected programs: 36564 -> 35746 (-2.24%)
helped: 184
HURT: 7
helped stats (abs) min: 1.0 max: 74.0 x̄: 4.49 x̃: 2
helped stats (rel) min: 0.30% max: 16.67% x̄: 2.86% x̃: 1.89%
HURT stats (abs) min: 1.0 max: 2.0 x̄: 1.29 x̃: 1
HURT stats (rel) min: 0.12% max: 12.50% x̄: 4.26% x̃: 3.33%
95% mean confidence interval for tuples value: -5.29 -3.28
95% mean confidence interval for tuples %-change: -3.06% -2.13%
Tuples are helped.
total clauses in shared programs: 15993 -> 15928 (-0.41%)
clauses in affected programs: 2464 -> 2399 (-2.64%)
helped: 35
HURT: 16
helped stats (abs) min: 1.0 max: 27.0 x̄: 2.31 x̃: 1
helped stats (rel) min: 0.49% max: 18.88% x̄: 7.63% x̃: 5.88%
HURT stats (abs) min: 1.0 max: 1.0 x̄: 1.00 x̃: 1
HURT stats (rel) min: 0.79% max: 6.25% x̄: 1.91% x̃: 1.01%
95% mean confidence interval for clauses value: -2.46 -0.09
95% mean confidence interval for clauses %-change: -6.38% -2.90%
Clauses are helped.
total cycles in shared programs: 7622.13 -> 7594.75 (-0.36%)
cycles in affected programs: 1078.67 -> 1051.29 (-2.54%)
helped: 103
HURT: 4
helped stats (abs) min: 0.041665999999999315 max: 3.0833319999999986 x̄: 0.27 x̃: 0
helped stats (rel) min: 0.32% max: 21.05% x̄: 3.62% x̃: 2.44%
HURT stats (abs) min: 0.0416669999999999 max: 0.0833330000000001 x̄: 0.05 x̃: 0
HURT stats (rel) min: 0.13% max: 7.14% x̄: 2.94% x̃: 2.25%
95% mean confidence interval for cycles value: -0.33 -0.19
95% mean confidence interval for cycles %-change: -4.14% -2.61%
Cycles are helped.
total arith in shared programs: 2762.46 -> 2728.08 (-1.24%)
arith in affected programs: 1550.12 -> 1515.75 (-2.22%)
helped: 197
HURT: 6
helped stats (abs) min: 0.041665999999999315 max: 3.0833319999999986 x̄: 0.18 x̃: 0
helped stats (rel) min: 0.32% max: 21.05% x̄: 2.93% x̃: 1.61%
HURT stats (abs) min: 0.0416669999999999 max: 0.0833330000000001 x̄: 0.06 x̃: 0
HURT stats (rel) min: 0.13% max: 20.00% x̄: 5.78% x̃: 3.37%
95% mean confidence interval for arith value: -0.21 -0.13
95% mean confidence interval for arith %-change: -3.20% -2.15%
Arith are helped.
total quadwords in shared programs: 68155 -> 67555 (-0.88%)
quadwords in affected programs: 27944 -> 27344 (-2.15%)
helped: 151
HURT: 9
helped stats (abs) min: 1.0 max: 52.0 x̄: 4.09 x̃: 3
helped stats (rel) min: 0.23% max: 12.35% x̄: 2.87% x̃: 2.17%
HURT stats (abs) min: 1.0 max: 5.0 x̄: 1.89 x̃: 1
HURT stats (rel) min: 0.20% max: 6.76% x̄: 1.91% x̃: 1.13%
95% mean confidence interval for quadwords value: -4.67 -2.83
95% mean confidence interval for quadwords %-change: -2.99% -2.21%
Quadwords are helped.
total threads in shared programs: 2232 -> 2233 (0.04%)
threads in affected programs: 1 -> 2 (100.00%)
helped: 1
HURT: 0
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/14576 >
2022-02-19 03:02:10 +00:00
a64534754d
pan/bi: Handle vectorized u2f16/i2f16
...
Will be useful when we enable int16, I guess...
No shader-db changes.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/14576 >
2022-02-19 03:02:10 +00:00
6a05852f5b
pan/bi: Handle trivial i2i32
...
lower_bool_to_bitsize can generate i2i32 from a 32-bit source, which is
trivial but needs to be handled explicitly to avoid going down the 8-bit
conversion path.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/14576 >
2022-02-19 03:02:10 +00:00
9168dcbbc1
pan/bi: Disambiguate IDVS variants in shader-db
...
Label IDVS variants as being MESA_SHADER_{POSITION, VARYING} stages;
reserve the MESA_SHADER_VERTEX label for non-IDVS shaders. This reduces
confusion where a single shader compiles to two MESA_SHADER_VERTEX
shaders with different stats.
While we're at it, de-vendor the blend shader stage name; these stats
are internal anyway.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/15086 >
2022-02-19 00:01:07 +00:00
29d319c767
pan/bi: Fix load_const of 1-bit booleans
...
For historical reasons, we ingest 1-bit booleans in NIR but expand them
to 16/32-bit booleans in the backend IR. We need to handle this case
when loading boolean constants, extending from 1-bit to 16/32-bit as
required. This issue is masked by effective constant folding for
booleans, but is visible in a shader from Firefox WebRender.
Fixes: 646e03c451Closes : #5797
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/14371 >
2022-01-02 20:26:15 +00:00
795638767d
pan/bi: Use fused dual source blending
...
Instead of emitting a pile of moves to fixed registers at codegen time
and hoping everything works out, add a second staging source to the
BLEND instruction in the intermediate representation containing the dual
source colour, and modify register allocation appropriately. This better
models the operation of blending render target #0 with two sources.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13714 >
2022-01-02 01:12:05 +00:00
c4da1b84d3
panfrost: Remove pan_nir_reorder_writeout
...
Now that dual source stores are fused, there's no ordering hazard so we
can remove this tricky code.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13714 >
2022-01-02 01:12:05 +00:00
d3fb341b4a
panfrost: Combine dual source blends
...
Reuse the store_combined_output_pan infrastructure for dual source
blending as well. This simplifies ordering.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13714 >
2022-01-02 01:12:05 +00:00
996645e479
pan/bi: Don't read base for combined stores
...
`base` is meaningless for combined stores, so don't read it. This allows
us to remove the base index from the intrinsic and simplify the lowering
code generating the combined store intrinsic.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13714 >
2022-01-02 01:12:05 +00:00
944c8907ba
pan/bi: Don't call useless NIR passes
...
Cargo culted from the Midgard compiler.
nir_move_vec_src_uses_to_dest is intended for vec4 backends, which does
not apply to Bifrost. nir_lower_locals_to_regs runs much earlier in the
compiler and is a no-op here.
total instructions in shared programs: 107252 -> 107242 (<.01%)
instructions in affected programs: 2403 -> 2393 (-0.42%)
helped: 10
HURT: 0
helped stats (abs) min: 1.0 max: 1.0 x̄: 1.00 x̃: 1
helped stats (rel) min: 0.33% max: 0.57% x̄: 0.43% x̃: 0.42%
95% mean confidence interval for instructions value: -1.00 -1.00
95% mean confidence interval for instructions %-change: -0.49% -0.37%
Instructions are helped.
total tuples in shared programs: 89664 -> 89664 (0.00%)
tuples in affected programs: 333 -> 333 (0.00%)
helped: 1
HURT: 1
helped stats (abs) min: 1.0 max: 1.0 x̄: 1.00 x̃: 1
helped stats (rel) min: 0.52% max: 0.52% x̄: 0.52% x̃: 0.52%
HURT stats (abs) min: 1.0 max: 1.0 x̄: 1.00 x̃: 1
HURT stats (rel) min: 0.70% max: 0.70% x̄: 0.70% x̃: 0.70%
total cycles in shared programs: 8103.88 -> 8103.79 (<.01%)
cycles in affected programs: 29.42 -> 29.33 (-0.28%)
helped: 3
HURT: 1
helped stats (abs) min: 0.041665999999999315 max: 0.04166700000000034 x̄:
0.04 x̃: 0
helped stats (rel) min: 0.49% max: 0.55% x̄: 0.53% x̃: 0.54%
HURT stats (abs) min: 0.04166700000000034 max: 0.04166700000000034 x̄:
0.04 x̃: 0
HURT stats (rel) min: 0.74% max: 0.74% x̄: 0.74% x̃: 0.74%
95% mean confidence interval for cycles value: -0.09 0.05
95% mean confidence interval for cycles %-change: -1.22% 0.80%
Inconclusive result (value mean confidence interval includes 0).
total arith in shared programs: 3376.42 -> 3376.33 (<.01%)
arith in affected programs: 29.42 -> 29.33 (-0.28%)
helped: 3
HURT: 1
helped stats (abs) min: 0.041665999999999315 max: 0.04166700000000034 x̄:
0.04 x̃: 0
helped stats (rel) min: 0.49% max: 0.55% x̄: 0.53% x̃: 0.54%
HURT stats (abs) min: 0.04166700000000034 max: 0.04166700000000034 x̄:
0.04 x̃: 0
HURT stats (rel) min: 0.74% max: 0.74% x̄: 0.74% x̃: 0.74%
95% mean confidence interval for arith value: -0.09 0.05
95% mean confidence interval for arith %-change: -1.22% 0.80%
Inconclusive result (value mean confidence interval includes 0).
total quadwords in shared programs: 79681 -> 79681 (0.00%)
quadwords in affected programs: 283 -> 283 (0.00%)
helped: 1
HURT: 1
helped stats (abs) min: 1.0 max: 1.0 x̄: 1.00 x̃: 1
helped stats (rel) min: 0.62% max: 0.62% x̄: 0.62% x̃: 0.62%
HURT stats (abs) min: 1.0 max: 1.0 x̄: 1.00 x̃: 1
HURT stats (rel) min: 0.82% max: 0.82% x̄: 0.82% x̃: 0.82%
total threads in shared programs: 2226 -> 2227 (0.04%)
threads in affected programs: 1 -> 2 (100.00%)
helped: 1
HURT: 0
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/14293 >
2021-12-23 14:01:48 +00:00
1d21de788d
pan/bi: Specialize shaders for IDVS
...
We need to compile multiple variants and report them together in a
common shader info. To do so, we split off per-variant shader infos and
combine at the end.
glmark2 is very happy: https://people.collabora.com/~alyssa/idvs-g52.txt
Highlights include -bshading up 41% fps and -bbump:bump-render=high-poly
up 62% faster
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/14154 >
2021-12-20 18:21:41 +00:00
c59977c3bf
pan/bi: Add helper to decide if IDVS should be used
...
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/14154 >
2021-12-20 18:21:41 +00:00
a211d2b4e4
pan/bi: Use position shader ST_CVT path
...
We need to use a preload instead of the LEA_ATTR. Not sure why.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/14154 >
2021-12-20 18:21:41 +00:00
fe8ec31114
pan/bi: Split out varying store paths
...
This means we don't need to special case IDVS quite so hard.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/14154 >
2021-12-20 18:21:41 +00:00
e0771d5832
pan/bi: Remove the "wrong" stores in IDVS variants
...
Position shaders should only write gl_Position (and gl_PointSize on
Valhall), varying shaders should only write varyings.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/14154 >
2021-12-20 18:21:41 +00:00
e2f7871bcf
pan/bi: Extract bi_finalize_nir
...
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/14154 >
2021-12-20 18:21:41 +00:00
52fe998aa6
panfrost: Track preloaded registers
...
We already collect this information. We may as well make use of it.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/14154 >
2021-12-20 18:21:40 +00:00
d051854cca
treewide: drop mtypes/macros includes from main
...
These aren't required in lots of places, so remove them.
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/14127 >
2021-12-08 22:14:45 +00:00
a4d3a29647
pan/bi: Enable dual texture fusing pass
...
Everything is in place for it now -- ship it! Our Bifrost cycle model is
coarse, so take the shader-db results with a massive spoonful of salt:
total instructions in shared programs: 107504 -> 107252 (-0.23%)
instructions in affected programs: 39692 -> 39440 (-0.63%)
helped: 191
HURT: 1
helped stats (abs) min: 1.0 max: 20.0 x̄: 1.32 x̃: 1
helped stats (rel) min: 0.11% max: 9.52% x̄: 1.21% x̃: 0.98%
HURT stats (abs) min: 1.0 max: 1.0 x̄: 1.00 x̃: 1
HURT stats (rel) min: 2.04% max: 2.04% x̄: 2.04% x̃: 2.04%
95% mean confidence interval for instructions value: -1.60 -1.02
95% mean confidence interval for instructions %-change: -1.37% -1.01%
Instructions are helped.
total tuples in shared programs: 89864 -> 89664 (-0.22%)
tuples in affected programs: 27787 -> 27587 (-0.72%)
helped: 146
HURT: 6
helped stats (abs) min: 1.0 max: 17.0 x̄: 1.54 x̃: 1
helped stats (rel) min: 0.14% max: 15.38% x̄: 1.83% x̃: 1.25%
HURT stats (abs) min: 1.0 max: 11.0 x̄: 4.17 x̃: 2
HURT stats (rel) min: 0.54% max: 3.55% x̄: 1.29% x̃: 0.87%
95% mean confidence interval for tuples value: -1.64 -0.99
95% mean confidence interval for tuples %-change: -2.06% -1.36%
Tuples are helped.
total clauses in shared programs: 18253 -> 18044 (-1.15%)
clauses in affected programs: 5127 -> 4918 (-4.08%)
helped: 164
HURT: 1
helped stats (abs) min: 1.0 max: 19.0 x̄: 1.28 x̃: 1
helped stats (rel) min: 0.78% max: 28.57% x̄: 6.73% x̃: 5.88%
HURT stats (abs) min: 1.0 max: 1.0 x̄: 1.00 x̃: 1
HURT stats (rel) min: 2.94% max: 2.94% x̄: 2.94% x̃: 2.94%
95% mean confidence interval for clauses value: -1.50 -1.04
95% mean confidence interval for clauses %-change: -7.42% -5.91%
Clauses are helped.
total cycles in shared programs: 8118.54 -> 8103.88 (-0.18%)
cycles in affected programs: 414.96 -> 400.29 (-3.53%)
helped: 43
HURT: 27
helped stats (abs) min: 0.041665999999999315 max: 4.375 x̄: 0.41 x̃: 0
helped stats (rel) min: 0.24% max: 50.00% x̄: 11.49% x̃: 5.26%
HURT stats (abs) min: 0.041665999999999315 max: 1.1666639999999973 x̄:
0.10 x̃: 0
HURT stats (rel) min: 0.43% max: 4.71% x̄: 1.42% x̃: 1.28%
95% mean confidence interval for cycles value: -0.35 -0.07
95% mean confidence interval for cycles %-change: -9.50% -3.53%
Cycles are helped.
total arith in shared programs: 3375.67 -> 3376.42 (0.02%)
arith in affected programs: 345.29 -> 346.04 (0.22%)
helped: 24
HURT: 32
helped stats (abs) min: 0.041665999999999315 max: 0.5833329999999997 x̄:
0.09 x̃: 0
helped stats (rel) min: 0.24% max: 14.29% x̄: 2.82% x̃: 1.50%
HURT stats (abs) min: 0.041665999999999315 max: 1.1666639999999973 x̄:
0.09 x̃: 0
HURT stats (rel) min: 0.43% max: 4.71% x̄: 1.42% x̃: 1.28%
95% mean confidence interval for arith value: -0.04 0.07
95% mean confidence interval for arith %-change: -1.19% 0.39%
Inconclusive result (value mean confidence interval includes 0).
total texture in shared programs: 1275 -> 1157 (-9.25%)
texture in affected programs: 725.50 -> 607.50 (-16.26%)
helped: 192
HURT: 0
helped stats (abs) min: 0.5 max: 10.0 x̄: 0.61 x̃: 0
helped stats (rel) min: 2.86% max: 50.00% x̄: 25.20% x̃: 25.00%
95% mean confidence interval for texture value: -0.72 -0.51
95% mean confidence interval for texture %-change: -27.12% -23.27%
Texture are helped.
total vary in shared programs: 537.88 -> 536.12 (-0.33%)
vary in affected programs: 2.75 -> 1 (-63.64%)
helped: 1
HURT: 0
total quadwords in shared programs: 79762 -> 79681 (-0.10%)
quadwords in affected programs: 10261 -> 10180 (-0.79%)
helped: 59
HURT: 18
helped stats (abs) min: 1.0 max: 14.0 x̄: 1.88 x̃: 1
helped stats (rel) min: 0.38% max: 8.20% x̄: 1.95% x̃: 1.43%
HURT stats (abs) min: 1.0 max: 4.0 x̄: 1.67 x̃: 1
HURT stats (rel) min: 0.46% max: 8.89% x̄: 2.22% x̃: 1.21%
95% mean confidence interval for quadwords value: -1.57 -0.53
95% mean confidence interval for quadwords %-change: -1.59% -0.37%
Quadwords are helped.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13723 >
2021-11-12 16:30:02 +00:00
98c1b3e7e1
pan/bi: Use BIFROST_TEXTURE_OPERATION_SINGLE enum
...
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13723 >
2021-11-12 16:30:02 +00:00
7dc90b68d9
pan/bi: Add second destination to TEXC
...
Used to model dual texturing, which writes to separate sets of staging
registers.
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13723 >
2021-11-12 16:30:02 +00:00
c00e7b729f
pan/bi: Optimize abs(derivative)
...
We implement fine derivatives as:
broadcast(x, (lane & ~1) + 1) - broadcast(x, lane & ~1)
Most of the complexity is to get the right sign. If we can ignore the
sign, we can generate the simpler code:
broadcast(x, lane ^ 1) - lane
This is a particular win on v7+ where the broadcast instruction (CLPER)
can do `lane ^ value` for free. However, even on v6 where we lower to an
explicit XOR instruction, it's still a win.
The limiting case is fwidth. The fragment shader
gl_FragColor = fwidth(vec4_varying);
has the following results on v6, v7, and v9:
G72 (-26% instructions, -43% cycles):
38 inst, 30 tuples, 5 clauses, 1.166667 cycles, 1.166667 arith, 28 quadwords
28 inst, 19 tuples, 4 clauses, 0.666667 cycles, 0.666667 arith, 19 quadwords
G76 (-37% instructions, -54% cycles):
38 inst, 30 tuples, 5 clauses, 1.166667 cycles, 1.166667 arith, 28 quadwords
24 inst, 16 tuples, 4 clauses, 0.541667 cycles, 0.541667 arith, 18 quadwords
G78 (-40% instructions, -56% cycles):
40 inst, 1.125000 cycles, 0.250000 fma, 0.109375 cvt, 1.125000 sfu, 20 quadwords
24 inst, 0.500000 cycles, 0.250000 fma, 0.015625 cvt, 0.500000 sfu, 12 quadwords
shader-db tells a similar story -- most shaders are unaffected, but a
shader that uses fwidth has a 20% reduction in cycle count:
instructions helped: shaders/tesseract/488.shader_test MESA_SHADER_FRAGMENT: 264 -> 262 (-0.76%)
instructions helped: shaders/chromeos/109-1.shader_test MESA_SHADER_FRAGMENT: 36 -> 28 (-22.22%)
tuples helped: shaders/chromeos/109-1.shader_test MESA_SHADER_FRAGMENT: 27 -> 22 (-18.52%)
tuples HURT: shaders/tesseract/488.shader_test MESA_SHADER_FRAGMENT: 211 -> 212 (0.47%)
clauses HURT: shaders/tesseract/488.shader_test MESA_SHADER_FRAGMENT: 32 -> 33 (3.12%)
cycles helped: shaders/chromeos/109-1.shader_test MESA_SHADER_FRAGMENT: 1 -> 0.79 (-20.83%)
arith helped: shaders/chromeos/109-1.shader_test MESA_SHADER_FRAGMENT: 1 -> 0.79 (-20.83%)
quadwords helped: shaders/chromeos/109-1.shader_test MESA_SHADER_FRAGMENT: 31 -> 28 (-9.68%)
quadwords HURT: shaders/tesseract/488.shader_test MESA_SHADER_FRAGMENT: 176 -> 178 (1.14%)
total instructions in shared programs: 148370 -> 148360 (<.01%)
instructions in affected programs: 300 -> 290 (-3.33%)
helped: 2
HURT: 0
total tuples in shared programs: 124188 -> 124184 (<.01%)
tuples in affected programs: 238 -> 234 (-1.68%)
helped: 1
HURT: 1
helped stats (abs) min: 5.0 max: 5.0 x̄: 5.00 x̃: 5
helped stats (rel) min: 18.52% max: 18.52% x̄: 18.52% x̃: 18.52%
HURT stats (abs) min: 1.0 max: 1.0 x̄: 1.00 x̃: 1
HURT stats (rel) min: 0.47% max: 0.47% x̄: 0.47% x̃: 0.47%
total clauses in shared programs: 25692 -> 25693 (<.01%)
clauses in affected programs: 32 -> 33 (3.12%)
helped: 0
HURT: 1
total cycles in shared programs: 12132.04 -> 12131.83 (<.01%)
cycles in affected programs: 1 -> 0.79 (-20.83%)
helped: 1
HURT: 0
total arith in shared programs: 4623.75 -> 4623.54 (<.01%)
arith in affected programs: 1 -> 0.79 (-20.83%)
helped: 1
HURT: 0
total quadwords in shared programs: 110386 -> 110385 (<.01%)
quadwords in affected programs: 207 -> 206 (-0.48%)
helped: 1
HURT: 1
helped stats (abs) min: 3.0 max: 3.0 x̄: 3.00 x̃: 3
helped stats (rel) min: 9.68% max: 9.68% x̄: 9.68% x̃: 9.68%
HURT stats (abs) min: 2.0 max: 2.0 x̄: 2.00 x̃: 2
HURT stats (rel) min: 1.14% max: 1.14% x̄: 1.14% x̃: 1.14%
Signed-off-by: Alyssa Rosenzweig <alyssa@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/12332 >
2021-10-06 00:40:57 +00:00
2f68c58767
pan/blend: Allow passing blend constants through a sysval
...
This is needed to allow lowering blend operations in fragment shaders
when the blend operation uses dynamic blend constants.
Signed-off-by: Boris Brezillon <boris.brezillon@collabora.com>
Reviewed-by: Alyssa Rosenzweig <alyssa.rosenzweig@collabora.com>
Part-of: <https://gitlab.freedesktop.org/mesa/mesa/-/merge_requests/13060 >
2021-09-30 16:54:42 +02:00
Alyssa Rosenzweig
Jason Ekstrand
Icecream95
Dave Airlie
Boris Brezillon