Lionel Landwerlin [Sat, 28 Jul 2018 18:11:56 +0000 (19:11 +0100)]
intel: common: add missing stdint include
Reviewed-by: Eric Engestrom <eric.engestrom@intel.com>
Lionel Landwerlin [Mon, 30 Jul 2018 01:55:54 +0000 (02:55 +0100)]
intel: decoder: remove unused variable
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Eric Engestrom <eric.engestrom@intel.com>
Lionel Landwerlin [Tue, 31 Jul 2018 09:48:37 +0000 (10:48 +0100)]
intel: tools: aubwrite: reuse canonical address helper
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Eric Engestrom <eric.engestrom@intel.com>
Lionel Landwerlin [Tue, 31 Jul 2018 06:12:56 +0000 (07:12 +0100)]
intel: aubinator: fix read the context/ring
Up to now we've been lucky that the buffer returned was always exactly
at the address we requested.
Fixes: 144b40db5411 ("intel: aubinator: drop the 1Tb GTT mapping")
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Rafael Antognolli <rafael.antognolli@intel.com>
Ian Romanick [Thu, 2 Aug 2018 02:34:02 +0000 (19:34 -0700)]
nir: Transform expressions of b2f(a) and b2f(b) to a == b
All Gen7+ platforms had similar results. (Skylake shown)
total instructions in shared programs:
14276886 ->
14276838 (<.01%)
instructions in affected programs: 312 -> 264 (-15.38%)
helped: 2
HURT: 0
total cycles in shared programs:
532578395 ->
532570985 (<.01%)
cycles in affected programs: 682562 -> 675152 (-1.09%)
helped: 374
HURT: 4
helped stats (abs) min: 2 max: 200 x̄: 20.39 x̃: 18
helped stats (rel) min: 0.07% max: 11.64% x̄: 1.25% x̃: 1.28%
HURT stats (abs) min: 2 max: 114 x̄: 53.50 x̃: 49
HURT stats (rel) min: 0.06% max: 11.70% x̄: 5.02% x̃: 4.15%
95% mean confidence interval for cycles value: -21.30 -17.91
95% mean confidence interval for cycles %-change: -1.30% -1.06%
Cycles are helped.
Sandy Bridge
total instructions in shared programs:
10488123 ->
10488075 (<.01%)
instructions in affected programs: 336 -> 288 (-14.29%)
helped: 2
HURT: 0
total cycles in shared programs:
150260379 ->
150260439 (<.01%)
cycles in affected programs: 4726 -> 4786 (1.27%)
helped: 0
HURT: 2
No changes on Iron Lake or GM45.
Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Thomas Helland <thomashelland90@gmail.com>
Ian Romanick [Thu, 2 Aug 2018 02:33:24 +0000 (19:33 -0700)]
nir: Transform expressions of b2f(a) and b2f(b) to a ^^ b
All Gen platforms had pretty similar results. (Skylake shown)
total instructions in shared programs:
14276892 ->
14276886 (<.01%)
instructions in affected programs: 484 -> 478 (-1.24%)
helped: 2
HURT: 0
total cycles in shared programs:
532578397 ->
532578395 (<.01%)
cycles in affected programs: 3522 -> 3520 (-0.06%)
helped: 1
HURT: 0
Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Thomas Helland <thomashelland90@gmail.com>
Ian Romanick [Thu, 2 Aug 2018 02:32:18 +0000 (19:32 -0700)]
nir: Transform expressions of b2f(a) and b2f(b) to !(a && b)
All Gen platforms had pretty similar results. (Skylake shown)
total cycles in shared programs:
532578400 ->
532578397 (<.01%)
cycles in affected programs: 2784 -> 2781 (-0.11%)
helped: 1
HURT: 1
helped stats (abs) min: 4 max: 4 x̄: 4.00 x̃: 4
helped stats (rel) min: 0.26% max: 0.26% x̄: 0.26% x̃: 0.26%
HURT stats (abs) min: 1 max: 1 x̄: 1.00 x̃: 1
HURT stats (rel) min: 0.08% max: 0.08% x̄: 0.08% x̃: 0.08%
v2: s/fmax/fmin/. Noticed by Thomas Helland.
Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Thomas Helland <thomashelland90@gmail.com>
Ian Romanick [Thu, 2 Aug 2018 02:31:22 +0000 (19:31 -0700)]
nir: Transform expressions of b2f(a) and b2f(b) to a && b
No changes on any Gen platform.
v2: s/fmax/fmin/. Noticed by Thomas Helland.
Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Thomas Helland <thomashelland90@gmail.com>
Ian Romanick [Thu, 2 Aug 2018 02:27:01 +0000 (19:27 -0700)]
nir: Transform expressions of b2f(a) and b2f(b) to !(a || b)
All Gen6+ platforms had similar results. (Skylake shown)
total instructions in shared programs:
14276961 ->
14276892 (<.01%)
instructions in affected programs: 3215 -> 3146 (-2.15%)
helped: 28
HURT: 0
helped stats (abs) min: 1 max: 6 x̄: 2.46 x̃: 2
helped stats (rel) min: 0.47% max: 9.52% x̄: 4.34% x̃: 1.92%
95% mean confidence interval for instructions value: -2.87 -2.06
95% mean confidence interval for instructions %-change: -5.73% -2.95%
Instructions are helped.
total cycles in shared programs:
532577068 ->
532578400 (<.01%)
cycles in affected programs: 121864 -> 123196 (1.09%)
helped: 35
HURT: 30
helped stats (abs) min: 2 max: 268 x̄: 42.34 x̃: 22
helped stats (rel) min: 0.12% max: 12.14% x̄: 3.22% x̃: 1.86%
HURT stats (abs) min: 2 max: 246 x̄: 93.80 x̃: 36
HURT stats (rel) min: 0.09% max: 13.63% x̄: 4.47% x̃: 2.58%
95% mean confidence interval for cycles value: -5.02 46.01
95% mean confidence interval for cycles %-change: -0.99% 1.65%
Inconclusive result (value mean confidence interval includes 0).
Iron Lake and GM45 had similar results. (Iron Lake shown)
total instructions in shared programs:
7781299 ->
7781342 (<.01%)
instructions in affected programs: 22300 -> 22343 (0.19%)
helped: 13
HURT: 40
helped stats (abs) min: 2 max: 3 x̄: 2.85 x̃: 3
helped stats (rel) min: 1.15% max: 7.69% x̄: 3.72% x̃: 3.33%
HURT stats (abs) min: 2 max: 2 x̄: 2.00 x̃: 2
HURT stats (rel) min: 0.26% max: 1.30% x̄: 0.47% x̃: 0.43%
95% mean confidence interval for instructions value: 0.23 1.39
95% mean confidence interval for instructions %-change: -1.18% 0.07%
Inconclusive result (%-change mean confidence interval includes 0).
total cycles in shared programs:
177878928 ->
177879332 (<.01%)
cycles in affected programs: 383298 -> 383702 (0.11%)
helped: 7
HURT: 43
helped stats (abs) min: 2 max: 18 x̄: 10.00 x̃: 10
helped stats (rel) min: 0.17% max: 4.81% x̄: 2.62% x̃: 3.40%
HURT stats (abs) min: 2 max: 38 x̄: 11.02 x̃: 12
HURT stats (rel) min: 0.08% max: 1.54% x̄: 0.25% x̃: 0.09%
95% mean confidence interval for cycles value: 5.21 10.95
95% mean confidence interval for cycles %-change: -0.51% 0.21%
Inconclusive result (%-change mean confidence interval includes 0).
v2: s/fmin/fmax/. Noticed by Thomas Helland.
Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Thomas Helland <thomashelland90@gmail.com>
Ian Romanick [Thu, 2 Aug 2018 02:46:26 +0000 (19:46 -0700)]
nir: Transform -fabs(a) >= 0 to a == 0
All Gen platforms had pretty similar results. (Skylake shown)
total instructions in shared programs:
14276964 ->
14276961 (<.01%)
instructions in affected programs: 411 -> 408 (-0.73%)
helped: 3
HURT: 0
helped stats (abs) min: 1 max: 1 x̄: 1.00 x̃: 1
helped stats (rel) min: 0.47% max: 1.96% x̄: 1.04% x̃: 0.68%
total cycles in shared programs:
532577062 ->
532577068 (<.01%)
cycles in affected programs: 1093 -> 1099 (0.55%)
helped: 1
HURT: 1
helped stats (abs) min: 16 max: 16 x̄: 16.00 x̃: 16
helped stats (rel) min: 7.77% max: 7.77% x̄: 7.77% x̃: 7.77%
HURT stats (abs) min: 22 max: 22 x̄: 22.00 x̃: 22
HURT stats (rel) min: 2.48% max: 2.48% x̄: 2.48% x̃: 2.48%
Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Thomas Helland <thomashelland90@gmail.com>
Ian Romanick [Thu, 2 Aug 2018 00:18:07 +0000 (17:18 -0700)]
nir: Transform expressions of b2f(a) and b2f(b) to a || b
All Gen6+ platforms had pretty similar results. (Skylake shown)
total instructions in shared programs:
14277184 ->
14276964 (<.01%)
instructions in affected programs: 10082 -> 9862 (-2.18%)
helped: 37
HURT: 1
helped stats (abs) min: 1 max: 30 x̄: 5.97 x̃: 4
helped stats (rel) min: 0.14% max: 16.00% x̄: 5.23% x̃: 2.04%
HURT stats (abs) min: 1 max: 1 x̄: 1.00 x̃: 1
HURT stats (rel) min: 0.70% max: 0.70% x̄: 0.70% x̃: 0.70%
95% mean confidence interval for instructions value: -7.87 -3.71
95% mean confidence interval for instructions %-change: -6.98% -3.16%
Instructions are helped.
total cycles in shared programs:
532577990 ->
532577062 (<.01%)
cycles in affected programs: 170959 -> 170031 (-0.54%)
helped: 33
HURT: 9
helped stats (abs) min: 2 max: 120 x̄: 30.91 x̃: 30
helped stats (rel) min: 0.02% max: 7.65% x̄: 2.66% x̃: 1.13%
HURT stats (abs) min: 2 max: 24 x̄: 10.22 x̃: 8
HURT stats (rel) min: 0.09% max: 1.79% x̄: 0.61% x̃: 0.22%
95% mean confidence interval for cycles value: -31.23 -12.96
95% mean confidence interval for cycles %-change: -2.90% -1.02%
Cycles are helped.
Iron Lake and GM45 had similar results. (Iron Lake shown)
total instructions in shared programs:
7781539 ->
7781301 (<.01%)
instructions in affected programs: 10169 -> 9931 (-2.34%)
helped: 32
HURT: 0
helped stats (abs) min: 2 max: 20 x̄: 7.44 x̃: 6
helped stats (rel) min: 0.47% max: 17.02% x̄: 4.03% x̃: 1.88%
95% mean confidence interval for instructions value: -9.53 -5.34
95% mean confidence interval for instructions %-change: -5.94% -2.12%
Instructions are helped.
total cycles in shared programs:
177878590 ->
177878932 (<.01%)
cycles in affected programs: 78706 -> 79048 (0.43%)
helped: 7
HURT: 21
helped stats (abs) min: 6 max: 34 x̄: 24.57 x̃: 28
helped stats (rel) min: 0.15% max: 8.33% x̄: 4.66% x̃: 6.37%
HURT stats (abs) min: 2 max: 86 x̄: 24.48 x̃: 22
HURT stats (rel) min: 0.01% max: 4.28% x̄: 1.21% x̃: 0.70%
95% mean confidence interval for cycles value: 0.30 24.13
95% mean confidence interval for cycles %-change: -1.52% 1.01%
Inconclusive result (%-change mean confidence interval includes 0).
v2: s/fmin/fmax/. Noticed by Thomas Helland.
Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Thomas Helland <thomashelland90@gmail.com>
Ian Romanick [Fri, 27 Jul 2018 01:26:18 +0000 (18:26 -0700)]
nir: Transform -fabs(a) < 0 to a != 0
Unlike the much older -abs(a) >= 0.0 transformation, this is not
precise. The behavior changes if a is NaN.
All Gen platforms had pretty similar results. (Skylake shown)
total instructions in shared programs:
14277216 ->
14277184 (<.01%)
instructions in affected programs: 2300 -> 2268 (-1.39%)
helped: 8
HURT: 0
helped stats (abs) min: 1 max: 8 x̄: 4.00 x̃: 3
helped stats (rel) min: 0.48% max: 15.15% x̄: 4.41% x̃: 1.01%
95% mean confidence interval for instructions value: -6.45 -1.55
95% mean confidence interval for instructions %-change: -9.96% 1.13%
Inconclusive result (%-change mean confidence interval includes 0).
total cycles in shared programs:
532577848 ->
532577990 (<.01%)
cycles in affected programs: 17486 -> 17628 (0.81%)
helped: 2
HURT: 5
helped stats (abs) min: 2 max: 6 x̄: 4.00 x̃: 4
helped stats (rel) min: 0.06% max: 1.81% x̄: 0.93% x̃: 0.93%
HURT stats (abs) min: 6 max: 50 x̄: 30.00 x̃: 26
HURT stats (rel) min: 0.55% max: 2.17% x̄: 1.19% x̃: 1.02%
95% mean confidence interval for cycles value: -1.06 41.63
95% mean confidence interval for cycles %-change: -0.58% 1.74%
Inconclusive result (value mean confidence interval includes 0).
Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Thomas Helland <thomashelland90@gmail.com>
Ian Romanick [Wed, 1 Aug 2018 23:51:35 +0000 (16:51 -0700)]
nir: Rearrange bcsel with two bcsel sources
All Gen platforms had pretty similar results. (Skylake shown)
total instructions in shared programs:
14277220 ->
14277216 (<.01%)
instructions in affected programs: 422 -> 418 (-0.95%)
helped: 2
HURT: 0
total cycles in shared programs:
532577908 ->
532577848 (<.01%)
cycles in affected programs: 2800 -> 2740 (-2.14%)
helped: 2
HURT: 0
Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Thomas Helland <thomashelland90@gmail.com>
Ian Romanick [Wed, 1 Aug 2018 16:58:19 +0000 (09:58 -0700)]
nir: Collapse more repeated bcsels on the same argument
All Gen platforms had pretty similar results. (Skylake shown)
total instructions in shared programs:
14277230 ->
14277220 (<.01%)
instructions in affected programs: 751 -> 741 (-1.33%)
helped: 4
HURT: 0
helped stats (abs) min: 2 max: 3 x̄: 2.50 x̃: 2
helped stats (rel) min: 1.23% max: 1.40% x̄: 1.32% x̃: 1.32%
95% mean confidence interval for instructions value: -3.42 -1.58
95% mean confidence interval for instructions %-change: -1.47% -1.17%
Instructions are helped.
total cycles in shared programs:
532577947 ->
532577908 (<.01%)
cycles in affected programs: 10641 -> 10602 (-0.37%)
helped: 4
HURT: 3
helped stats (abs) min: 1 max: 40 x̄: 13.75 x̃: 7
helped stats (rel) min: 0.11% max: 3.08% x̄: 1.10% x̃: 0.60%
HURT stats (abs) min: 2 max: 8 x̄: 5.33 x̃: 6
HURT stats (rel) min: 0.13% max: 0.55% x̄: 0.30% x̃: 0.23%
95% mean confidence interval for cycles value: -20.69 9.55
95% mean confidence interval for cycles %-change: -1.63% 0.63%
Inconclusive result (value mean confidence interval includes 0).
Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Thomas Helland <thomashelland90@gmail.com>
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Ian Romanick [Tue, 3 Jul 2018 19:39:54 +0000 (12:39 -0700)]
nir: Don't compare i2f or u2i with zero
Broadwell and Skylake had similar results. (Skylake shown)
total instructions in shared programs:
14277620 ->
14277230 (<.01%)
instructions in affected programs: 36905 -> 36515 (-1.06%)
helped: 101
HURT: 6
helped stats (abs) min: 1 max: 6 x̄: 4.46 x̃: 6
helped stats (rel) min: 0.32% max: 7.69% x̄: 1.80% x̃: 1.51%
HURT stats (abs) min: 1 max: 28 x̄: 10.00 x̃: 1
HURT stats (rel) min: 0.33% max: 1.74% x̄: 0.68% x̃: 0.47%
95% mean confidence interval for instructions value: -4.59 -2.70
95% mean confidence interval for instructions %-change: -1.90% -1.41%
Instructions are helped.
total cycles in shared programs:
532580716 ->
532577947 (<.01%)
cycles in affected programs: 940575 -> 937806 (-0.29%)
helped: 92
HURT: 12
helped stats (abs) min: 2 max: 158 x̄: 51.04 x̃: 62
helped stats (rel) min: 0.24% max: 3.99% x̄: 2.14% x̃: 2.41%
HURT stats (abs) min: 10 max: 1112 x̄: 160.58 x̃: 63
HURT stats (rel) min: 0.06% max: 21.90% x̄: 4.22% x̃: 0.20%
95% mean confidence interval for cycles value: -50.66 -2.59
95% mean confidence interval for cycles %-change: -2.09% -0.73%
Cycles are helped.
total spills in shared programs: 8116 -> 8124 (0.10%)
spills in affected programs: 200 -> 208 (4.00%)
helped: 0
HURT: 2
total fills in shared programs: 11086 -> 11094 (0.07%)
fills in affected programs: 436 -> 444 (1.83%)
helped: 0
HURT: 2
Ivy Bridge and Haswell had similar results. (Haswell shown)
total instructions in shared programs:
12979054 ->
12978067 (<.01%)
instructions in affected programs: 33633 -> 32646 (-2.93%)
helped: 120
HURT: 2
helped stats (abs) min: 1 max: 13 x̄: 8.53 x̃: 13
helped stats (rel) min: 0.30% max: 16.67% x̄: 4.55% x̃: 3.17%
HURT stats (abs) min: 18 max: 18 x̄: 18.00 x̃: 18
HURT stats (rel) min: 1.15% max: 2.84% x̄: 2.00% x̃: 2.00%
95% mean confidence interval for instructions value: -9.19 -6.99
95% mean confidence interval for instructions %-change: -5.27% -3.62%
Instructions are helped.
total cycles in shared programs:
411212880 ->
411199636 (<.01%)
cycles in affected programs: 696441 -> 683197 (-1.90%)
helped: 107
HURT: 5
helped stats (abs) min: 2 max: 864 x̄: 124.90 x̃: 146
helped stats (rel) min: 0.03% max: 29.20% x̄: 8.58% x̃: 5.88%
HURT stats (abs) min: 2 max: 50 x̄: 24.00 x̃: 22
HURT stats (rel) min: 0.01% max: 5.35% x̄: 1.29% x̃: 0.25%
95% mean confidence interval for cycles value: -136.96 -99.54
95% mean confidence interval for cycles %-change: -9.75% -6.53%
Cycles are helped.
total spills in shared programs: 78623 -> 78631 (0.01%)
spills in affected programs: 66 -> 74 (12.12%)
helped: 0
HURT: 2
total fills in shared programs: 80104 -> 80108 (<.01%)
fills in affected programs: 133 -> 137 (3.01%)
helped: 0
HURT: 2
No changes on Sandy Bridge, Iron Lake, or GM45.
Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Thomas Helland <thomashelland90@gmail.com>
Ian Romanick [Tue, 3 Jul 2018 20:57:06 +0000 (13:57 -0700)]
nir: Remove f2i(i2f(x)) conversions
Broadwell and Skylake had similar results. (Skylake shown)
total instructions in shared programs:
14277978 ->
14277620 (<.01%)
instructions in affected programs: 36957 -> 36599 (-0.97%)
helped: 76
HURT: 1
helped stats (abs) min: 2 max: 90 x̄: 4.89 x̃: 4
helped stats (rel) min: 0.44% max: 5.88% x̄: 1.04% x̃: 0.87%
HURT stats (abs) min: 14 max: 14 x̄: 14.00 x̃: 14
HURT stats (rel) min: 0.36% max: 0.36% x̄: 0.36% x̃: 0.36%
95% mean confidence interval for instructions value: -7.06 -2.24
95% mean confidence interval for instructions %-change: -1.28% -0.77%
Instructions are helped.
total cycles in shared programs:
532584581 ->
532580716 (<.01%)
cycles in affected programs: 973591 -> 969726 (-0.40%)
helped: 76
HURT: 1
helped stats (abs) min: 2 max: 9940 x̄: 159.80 x̃: 32
helped stats (rel) min: <.01% max: 8.70% x̄: 1.15% x̃: 1.19%
HURT stats (abs) min: 8280 max: 8280 x̄: 8280.00 x̃: 8280
HURT stats (rel) min: 2.10% max: 2.10% x̄: 2.10% x̃: 2.10%
95% mean confidence interval for cycles value: -386.98 286.59
95% mean confidence interval for cycles %-change: -1.41% -0.81%
Inconclusive result (value mean confidence interval includes 0).
total spills in shared programs: 8127 -> 8116 (-0.14%)
spills in affected programs: 108 -> 97 (-10.19%)
helped: 1
HURT: 0
total fills in shared programs: 11090 -> 11086 (-0.04%)
fills in affected programs: 440 -> 436 (-0.91%)
helped: 1
HURT: 1
Haswell
total instructions in shared programs:
12979174 ->
12979054 (<.01%)
instructions in affected programs: 9040 -> 8920 (-1.33%)
helped: 14
HURT: 1
helped stats (abs) min: 2 max: 34 x̄: 8.79 x̃: 6
helped stats (rel) min: 0.41% max: 7.04% x̄: 2.66% x̃: 1.14%
HURT stats (abs) min: 3 max: 3 x̄: 3.00 x̃: 3
HURT stats (rel) min: 0.19% max: 0.19% x̄: 0.19% x̃: 0.19%
95% mean confidence interval for instructions value: -13.58 -2.42
95% mean confidence interval for instructions %-change: -3.94% -1.01%
Instructions are helped.
total cycles in shared programs:
411227148 ->
411212880 (<.01%)
cycles in affected programs: 630506 -> 616238 (-2.26%)
helped: 15
HURT: 0
helped stats (abs) min: 2 max: 11192 x̄: 951.20 x̃: 38
helped stats (rel) min: <.01% max: 16.01% x̄: 3.92% x̃: 0.17%
95% mean confidence interval for cycles value: -2544.28 641.88
95% mean confidence interval for cycles %-change: -6.89% -0.94%
Inconclusive result (value mean confidence interval includes 0).
total spills in shared programs: 78626 -> 78623 (<.01%)
spills in affected programs: 42 -> 39 (-7.14%)
helped: 1
HURT: 0
total fills in shared programs: 80111 -> 80104 (<.01%)
fills in affected programs: 140 -> 133 (-5.00%)
helped: 1
HURT: 1
Ivy Bridge
total instructions in shared programs:
11684101 ->
11684030 (<.01%)
instructions in affected programs: 3080 -> 3009 (-2.31%)
helped: 4
HURT: 1
helped stats (abs) min: 5 max: 59 x̄: 18.50 x̃: 5
helped stats (rel) min: 6.47% max: 7.04% x̄: 6.87% x̃: 6.99%
HURT stats (abs) min: 3 max: 3 x̄: 3.00 x̃: 3
HURT stats (rel) min: 0.15% max: 0.15% x̄: 0.15% x̃: 0.15%
95% mean confidence interval for instructions value: -45.59 17.19
95% mean confidence interval for instructions %-change: -9.38% -1.56%
Inconclusive result (value mean confidence interval includes 0).
total cycles in shared programs:
258407697 ->
258389653 (<.01%)
cycles in affected programs: 328323 -> 310279 (-5.50%)
helped: 5
HURT: 0
helped stats (abs) min: 32 max: 14908 x̄: 3608.80 x̃: 32
helped stats (rel) min: 1.26% max: 17.22% x̄: 9.30% x̃: 10.60%
95% mean confidence interval for cycles value: -11616.71 4399.11
95% mean confidence interval for cycles %-change: -16.56% -2.03%
Inconclusive result (value mean confidence interval includes 0).
total spills in shared programs: 4537 -> 4528 (-0.20%)
spills in affected programs: 64 -> 55 (-14.06%)
helped: 1
HURT: 0
total fills in shared programs: 4823 -> 4815 (-0.17%)
fills in affected programs: 189 -> 181 (-4.23%)
helped: 1
HURT: 1
Sandy Bridge
total instructions in shared programs:
10488464 ->
10488449 (<.01%)
instructions in affected programs: 272 -> 257 (-5.51%)
helped: 3
HURT: 0
helped stats (abs) min: 5 max: 5 x̄: 5.00 x̃: 5
helped stats (rel) min: 5.49% max: 5.56% x̄: 5.51% x̃: 5.49%
total cycles in shared programs:
150263359 ->
150263263 (<.01%)
cycles in affected programs: 7978 -> 7882 (-1.20%)
helped: 3
HURT: 0
helped stats (abs) min: 32 max: 32 x̄: 32.00 x̃: 32
helped stats (rel) min: 1.15% max: 1.23% x̄: 1.20% x̃: 1.23%
No changes on Iron Lake or GM45.
Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Thomas Helland <thomashelland90@gmail.com>
Ian Romanick [Wed, 1 Aug 2018 17:13:55 +0000 (10:13 -0700)]
nir: Mark the 0.0 < abs(a) transformation as imprecise
Unlike the much older -abs(a) >= 0.0 transformation, this is not
precise. The behavior changes if the source is NaN.
No shader-db changes on any platform.
Signed-off-by: Ian Romanick <ian.d.romanick@intel.com>
Reviewed-by: Thomas Helland <thomashelland90@gmail.com>
Marek Olšák [Thu, 2 Aug 2018 20:39:41 +0000 (16:39 -0400)]
radeonsi: cosmetic changes
Marek Olšák [Mon, 11 Jun 2018 22:54:26 +0000 (18:54 -0400)]
st/mesa: expose & set limits for AMD_framebuffer_multisample_advanced
Reviewed-by: Brian Paul <brianp@vmware.com>
Marek Olšák [Mon, 11 Jun 2018 22:48:58 +0000 (18:48 -0400)]
st/mesa: add renderbuffer support for AMD_framebuffer_multisample_advanced
Reviewed-by: Brian Paul <brianp@vmware.com>
Marek Olšák [Mon, 11 Jun 2018 19:04:11 +0000 (15:04 -0400)]
st/mesa: pass storage_sample_count parameter into st_choose_format
Reviewed-by: Brian Paul <brianp@vmware.com>
Marek Olšák [Mon, 11 Jun 2018 22:30:34 +0000 (18:30 -0400)]
mesa: add functional FBO changes for AMD_framebuffer_multisample_advanced
- relax FBO completeness rules
- validate sample counts
Reviewed-by: Brian Paul <brianp@vmware.com>
Marek Olšák [Mon, 11 Jun 2018 21:24:16 +0000 (17:24 -0400)]
mesa: add gl_renderbuffer::NumStorageSamples
Reviewed-by: Brian Paul <brianp@vmware.com>
Marek Olšák [Mon, 11 Jun 2018 19:10:50 +0000 (15:10 -0400)]
mesa: implement glGet for AMD_framebuffer_multisample_advanced
Reviewed-by: Brian Paul <brianp@vmware.com>
Marek Olšák [Thu, 28 Jun 2018 06:05:12 +0000 (02:05 -0400)]
glapi: define AMD_framebuffer_multisample_advanced and add its functions
Reviewed-by: Brian Paul <brianp@vmware.com>
Marek Olšák [Mon, 11 Jun 2018 19:26:41 +0000 (15:26 -0400)]
mesa: add storageSamples parameter to renderbuffer functions
It's just passed to other functions but otherwise unused.
It will be used in following commits.
Reviewed-by: Brian Paul <brianp@vmware.com>
Marek Olšák [Wed, 18 Jul 2018 22:06:37 +0000 (18:06 -0400)]
include: update GL & GLES headers (v2)
v2: use correct files
Acked-by: Ian Romanick <ian.d.romanick@intel.com>
Marek Olšák [Sun, 1 Jul 2018 19:50:51 +0000 (15:50 -0400)]
amd: remove support for LLVM 5.0
Users are encouraged to switch to LLVM 6.0 released in March 2018.
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Marek Olšák [Thu, 12 Jul 2018 04:50:52 +0000 (00:50 -0400)]
winsys/amdgpu: pass the BO list via the CS ioctl on DRM >= 3.27.0
Marek Olšák [Tue, 17 Jul 2018 05:52:25 +0000 (01:52 -0400)]
gallium/u_vbuf: handle indirect multidraws correctly and efficiently (v3)
v2: need to do MAX{start+count} instead of MAX{count}
added piglit tests
v3: use malloc
Cc: 18.2 <mesa-stable@lists.freedesktop.org>
Reviewed-by: Eric Anholt <eric@anholt.net>
Mauro Rossi [Thu, 2 Aug 2018 19:07:31 +0000 (21:07 +0200)]
android: radv: build vulkan.radv conditionally to radeonsi
A problem was reported with arm,arm64 targets build due to missing
libLLVM shared library dependency with AOSP; to avoid this issue vulkan.radv
is built conditionally only when radeonsi is in BOARD_GPU_DRIVERS
Fixes: 0ca153f869 ("android: radv: enable build of vulkan.radv HAL module")
Reported-by: John Stultz <john.stultz@linaro.org>
Signed-off-by: Mauro Rossi <issor.oruam@gmail.com>
Reviewed-by: Emil Velikov <emil.velikov@collabora.com>
Cc: "18.2" <mesa-stable@lists.freedesktop.org>
Roland Scheidegger [Fri, 3 Aug 2018 03:34:07 +0000 (05:34 +0200)]
util: return 0 for NaNs in float_to_ubyte
d3d10 requires NaNs to get converted to 0 for float->unorm conversions
(and float->int etc.). GL spec probably doesn't care in general, but it
would make sense to have reasonable behavior in any case imho - the
old code was converting negative NaNs to 0, and positive NaNs to 255.
(Note that using float comparison isn't actually all that much more
effort in any case, at least with sse2 it's just float comparison
(ucommiss) instead of int one - I converted the second comparison
to float too simply because it saves the probably somewhat expensive
transfer of the float from simd to int domain (with sse2 via stack),
so the generated code actually has 2 less instructions, although float
comparisons are more expensive than int ones.)
Reviewed-by: Brian Paul <brianp@vmware.com>
Jason Ekstrand [Wed, 11 Jul 2018 07:03:27 +0000 (00:03 -0700)]
anv/pipeline: Disable FS dispatch for pointless fragment shaders
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Timothy Arceri [Thu, 2 Aug 2018 00:04:51 +0000 (10:04 +1000)]
nir: add fall through comment to nir_gather_info
This stops Coverity reporting a defect and helps make the code less
error-prone.
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Dan Willemsen [Wed, 1 Aug 2018 23:20:38 +0000 (16:20 -0700)]
CleanSpec.mk: Remove HOST_OUT_release
This is a forward port of a patch from the AOSP/master tree:
https://android.googlesource.com/platform/external/mesa3d/+/
bd633f11de0c6ac1ed333a28344c74fd9898df9e%5E%21/
Which replaces HOST_OUT_release with HOST_OUT
As per Dan's explanation, the current code was incorrect to use
$(HOST_OUT_release) as $(HOST_OUT) will be set properly for
whether the current build that's being cleaned during
incrementals is using host debug or release builds.
Additionally Dan noted it was incredibly uncommon to use a debug
host build, as there was never a shortcut and one had to set an
environment variable manually. Thus it was rarely if ever tested.
Change-Id: I7972c0a50fa3520dcfa962d6dd7e602bfe22368d
Cc: Rob Herring <rob.herring@linaro.org>
Cc: Alistair Strachan <astrachan@google.com>
Cc: Marissa Wall <marissaw@google.com>
Cc: Sumit Semwal <sumit.semwal@linaro.org>
Cc: Emil Velikov <emil.l.velikov@gmail.com>
Cc: Rob Clark <robdclark@gmail.com>
Reviewed-by: Emil Velikov <emil.velikov@collabora.com>
Signed-off-by: John Stultz <john.stultz@linaro.org>
Signed-off-by: Rob Herring <robh@kernel.org>
Sumit Semwal [Wed, 1 Aug 2018 23:20:37 +0000 (16:20 -0700)]
Android.common.mk: define HAVE_TIMESPEC_GET
This is a forward port of a patch from the AOSP/master tree:
https://android.googlesource.com/platform/external/mesa3d/+/
bd30b663f55f8af73a0be4446349c5a2d4c641b0%5E%21/
Since https://android-review.googlesource.com/c/718518 added
timespec_get() to bionic, mesa3d doesn't build due to redefinition
of timespec_get().
Avoid redefinition by defining HAVE_TIMESPEC_GET flag.
Test: build and boot tested db820c to UI.
Change-Id: I3dcc8034b48785e45cd3fa50e4d9cf2c684694a0
Cc: Rob Herring <rob.herring@linaro.org>
Cc: Alistair Strachan <astrachan@google.com>
Cc: Marissa Wall <marissaw@google.com>
Cc: Sumit Semwal <sumit.semwal@linaro.org>
Cc: Emil Velikov <emil.l.velikov@gmail.com>
Cc: Rob Clark <robdclark@gmail.com>
Reviewed-by: Emil Velikov <emil.velikov@collabora.com>
Signed-off-by: Sumit Semwal <sumit.semwal@linaro.org>
Signed-off-by: John Stultz <john.stultz@linaro.org>
Signed-off-by: Rob Herring <robh@kernel.org>
Dan Willemsen [Wed, 1 Aug 2018 23:20:36 +0000 (16:20 -0700)]
util: Android.mk: Convert implicit rules to static pattern rules
This is a partial cherry-pick from AOSP's mesa3d tree:
https://android.googlesource.com/platform/external/mesa3d/+/
a88dcf769eb00a4ffc7183a0396d881a28b5a29b%5E%21/
"We're deprecating make implicit rules, preferring static pattern
rules, or just regular rules."
Without this patch, the freedesktop/master branch won't build in
the AOSP environment, and this patch corrects that, as tested
on the Dragonboard 820c.
The i965 portion of the patch this is based on collided badly,
and I'm not sure how to best forward port it. However, so far
we don't see build issues without that portion.
Comments or feedback would be appreciated!
Change-Id: Id6dfd0d018cbd665fa19d80c14abd5f75fa10b8a
Cc: Rob Herring <rob.herring@linaro.org>
Cc: Alistair Strachan <astrachan@google.com>
Cc: Marissa Wall <marissaw@google.com>
Cc: Sumit Semwal <sumit.semwal@linaro.org>
Cc: Emil Velikov <emil.l.velikov@gmail.com>
Cc: Rob Clark <robdclark@gmail.com>
Reviewed-by: Emil Velikov <emil.velikov@collabora.com>
Signed-off-by: John Stultz <john.stultz@linaro.org>
Signed-off-by: Rob Herring <robh@kernel.org>
Darren Powell [Wed, 13 Jun 2018 22:54:24 +0000 (18:54 -0400)]
radeonsi: add new R600_DEBUG test "testclearbufperf"
Signed-off-by: Darren Powell <darren.powell@amd.com>
Signed-off-by: Marek Olšák <marek.olsak@amd.com>
Brian Paul [Thu, 2 Aug 2018 15:32:58 +0000 (09:32 -0600)]
mesa: add switch case for GL 2.0 in _mesa_compute_version()
Previously, I added a switch case for GL 2.1 (
ed7a0770b881791dd697f3).
I don't know of any driver which only supports GL 2.0, but adding
this switch case avoids a failure if the app queries
GL_SHADING_LANGUAGE_VERSION.
Reviewed-by: Eric Anholt <eric@anholt.net>
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Andres Gomez [Thu, 2 Aug 2018 16:39:06 +0000 (19:39 +0300)]
intel/tools: add error2aub creation into autotools
Tarball distribution is done through "make distcheck". We include the
meson targets also into autotools so they won't fail when building
from the tarball.
Fixes: 6a60beba408 ("intel/tools: Add an error state to aub translator")
Cc: Jason Ekstrand <jason.ekstrand@intel.com>
Cc: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Cc: Dylan Baker <dylan.c.baker@intel.com>
Signed-off-by: Andres Gomez <agomez@igalia.com>
Reviewed-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Dylan Baker <dylan@pnwbakers.com>
Jason Ekstrand [Sat, 28 Oct 2017 00:07:52 +0000 (17:07 -0700)]
anv/pipeline: Do cross-stage linking optimizations
This appears to help the Aztec Ruins benchmark by about 2% on my Kaby
Lake gt2 laptop.
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Jason Ekstrand [Fri, 27 Oct 2017 23:54:32 +0000 (16:54 -0700)]
anv/pipeline: Pull most of the anv_pipeline_compile_* into common code
This leaves us with a series of little anv_pipeline_compile_* functions
which each take a compiler object, a mem_ctx, the stage to compile, and
the previous stage for VUE linking purposes. Some of them do
interesting things but most are little more than wrappers around
brw_compile_*.
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Jason Ekstrand [Fri, 27 Oct 2017 23:03:58 +0000 (16:03 -0700)]
anv/pipeline: Add a separate "link" stage
This breaks compilation up a bit into "link" and "compile". In the
"link" stage, new anv_pipeline_link_* helpers are called which are
responsible for setting up the binding table and doing anything needed
to properly link with the next stage in the pipeline if one exists.
They are called in reverse order starting with the fragment shader so
you can assume linking in later stages is already done.
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Jason Ekstrand [Fri, 27 Oct 2017 22:47:11 +0000 (15:47 -0700)]
anv/pipeline: Compile to NIR in compile_graphics
This pulls the SPIR-V to NIR step out into common code.
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Jason Ekstrand [Fri, 27 Oct 2017 22:05:02 +0000 (15:05 -0700)]
anv/pipeline: Recompile all shaders if any are missing from the cache
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Jason Ekstrand [Fri, 27 Oct 2017 21:47:38 +0000 (14:47 -0700)]
anv/pipeline: Drop anv_pipeline_add_compiled_stage
We can set active_stages much more directly and then it's just candy
around setting pipeline->stages[stage].
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Jason Ekstrand [Fri, 27 Oct 2017 17:18:31 +0000 (10:18 -0700)]
anv/pipeline: Pull shader compilation out into a helper.
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Jason Ekstrand [Fri, 27 Oct 2017 17:13:38 +0000 (10:13 -0700)]
anv/pipeline: Call anv_pipeline_compile_* in a loop
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Jason Ekstrand [Fri, 27 Oct 2017 02:24:28 +0000 (19:24 -0700)]
anv/pipeline: Hash the entire pipeline in one go
Instead of hashing each stage separately (and TES and TCS together), we
hash the entire pipeline. This means we'll get fewer cache hits if
they, for instance, re-use the same VS over and over again but it also
means we can now safely do cross-stage optimizations.
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Jason Ekstrand [Fri, 27 Oct 2017 01:59:33 +0000 (18:59 -0700)]
anv/pipeline: Populate keys up-front
Instead of having each anv_pipeline_compile_* function populate the
shader key, make it part of the anv_pipeline_stage struct and fill it
out up-front.
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Jason Ekstrand [Fri, 27 Oct 2017 01:42:35 +0000 (18:42 -0700)]
anv/pipline: Add a helper struct for per-stage info
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Jon Turney [Thu, 2 Aug 2018 13:50:27 +0000 (14:50 +0100)]
meson: use correct keyword to fix a meson warning
With a sufficently recent meson, the following warning is produced:
WARNING: Passed invalid keyword argument "extra_args".
WARNING: This will become a hard error in the future.
It seems that compiler.links(args:) is meant here.
Signed-off-by: Jon Turney <jon.turney@dronecode.org.uk>
Reviewed-and-Tested-by: Eric Engestrom <eric.engestrom@intel.com>
Reviewed-by: Dylan Baker <dylan@pnwbakers.com>
Andres Gomez [Thu, 2 Aug 2018 15:15:33 +0000 (18:15 +0300)]
docs: add 18.3.0-devel release notes template
Signed-off-by: Andres Gomez <agomez@igalia.com>
Andres Gomez [Thu, 2 Aug 2018 15:00:01 +0000 (18:00 +0300)]
mesa: bump version to 18.3.0-devel
Signed-off-by: Andres Gomez <agomez@igalia.com>
Eric Engestrom [Thu, 2 Aug 2018 10:56:13 +0000 (11:56 +0100)]
egl/main: fix indentation
Signed-off-by: Eric Engestrom <eric.engestrom@intel.com>
Reviewed-by: Frank Binns <frank.binns@imgtec.com>
Eric Engestrom [Thu, 2 Aug 2018 10:49:40 +0000 (11:49 +0100)]
loader: fix indentation
Signed-off-by: Eric Engestrom <eric.engestrom@intel.com>
Reviewed-by: Frank Binns <frank.binns@imgtec.com>
Vlad Golovkin [Wed, 1 Aug 2018 17:56:23 +0000 (20:56 +0300)]
swr: Remove unnecessary memset call
Zeroing memory after calloc is not necessary. This also allows to avoid
possible crash when allocation fails, because memset is called before
checking screen for NULL.
Fixes: a29d63ecf71546c4798c6 "swr: refactor swr_create_screen to allow
for proper cleanup on error"
Reviewed-by: Eric Engestrom <eric.engestrom@intel.com>
Andres Gomez [Wed, 1 Aug 2018 14:16:24 +0000 (17:16 +0300)]
mesa: replace binary constants with hexadecimal constants
The binary constant notation "0b" is a GCC extension. Instead, we use
hexadecimal notation to fix the MSVC 2013 build:
Compiling src\mesa\main\texcompress_astc.cpp ...
texcompress_astc.cpp
src\mesa\main\texcompress_astc.cpp(111) : error C2059: syntax error : 'bad suffix on number'
...
src\mesa\main\texcompress_astc.cpp(1007) : fatal error C1003: error count exceeds 100; stopping compilation
scons: *** [build\windows-x86-debug\mesa\main\texcompress_astc.obj] Error 2
scons: building terminated because of errors.
v2: Fix wrong conversion (Ilia).
Fixes: 38ab39f6501 ("mesa: add ASTC 2D LDR decoder")
Cc: Marek Olšák <marek.olsak@amd.com>
Cc: Brian Paul <brianp@vmware.com>
Cc: Roland Scheidegger <sroland@vmware.com>
Cc: Mike Lothian <mike@fireburn.co.uk>
Cc: Gert Wollny <gert.wollny@collabora.com>
Cc: Dieter Nützel <Dieter@nuetzel-hh.de>
Cc: Ilia Mirkin <imirkin@alum.mit.edu>
Signed-off-by: Andres Gomez <agomez@igalia.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Andres Gomez [Wed, 1 Aug 2018 13:26:48 +0000 (16:26 +0300)]
ddebug: use util_snprintf() in dd_get_debug_filename_and_mkdir
Instead of plain snprintf(). To fix the MSVC 2013 build:
Compiling src\gallium\auxiliary\driver_ddebug\dd_draw.c ...
dd_draw.c
c:\projects\mesa\src\gallium\auxiliary\driver_ddebug\dd_util.h(60) : warning C4013: 'snprintf' undefined; assuming extern returning int
...
gallium.lib(dd_draw.obj) : error LNK2001: unresolved external symbol _snprintf
build\windows-x86-debug\gallium\targets\graw-gdi\graw.dll : fatal error LNK1120: 1 unresolved externals
scons: *** [build\windows-x86-debug\gallium\targets\graw-gdi\graw.dll] Error 1120
scons: building terminated because of errors.
Fixes: 6ff0c6f4ebc ("gallium: move ddebug, noop, rbug, trace to auxiliary to improve build times")
Cc: Marek Olšák <marek.olsak@amd.com>
Cc: Brian Paul <brianp@vmware.com>
Cc: Roland Scheidegger <sroland@vmware.com>
Cc: Nicolai Hähnle <nicolai.haehnle@amd.com>
Signed-off-by: Andres Gomez <agomez@igalia.com>
Reviewed-by: Brian Paul <brianp@vmware.com>
Reviewed-by: Nicolai Hähnle <nicolai.haehnle@amd.com>
Andres Gomez [Wed, 1 Aug 2018 12:55:51 +0000 (15:55 +0300)]
kutil/queue: use util_snprintf() in util_queue_init
Instead of plain snprintf(). To fix the MSVC 2013 build:
Compiling src\util\u_queue.c ...
u_queue.c
src\util\u_queue.c(325) : warning C4013: 'snprintf' undefined; assuming extern returning int
...
mesautil.lib(u_queue.obj) : error LNK2001: unresolved external symbol _snprintf
scons: building terminated because of errors.
Fixes: b238e33bc9d ("kutil/queue: add a process name into a thread name")
Cc: Marek Olšák <marek.olsak@amd.com>
Cc: Brian Paul <brianp@vmware.com>
Cc: Roland Scheidegger <sroland@vmware.com>
Cc: Timothy Arceri <tarceri@itsqueeze.com>
Cc: Eric Engestrom <eric.engestrom@intel.com>
Signed-off-by: Andres Gomez <agomez@igalia.com>
Reviewed-by: Brian Paul <brianp@vmware.com>
Andres Gomez [Wed, 1 Aug 2018 12:47:13 +0000 (15:47 +0300)]
gallium/aux/util: use util_snprintf() in test_texture_barrier
Instead of plain snprintf(). To fix the MSVC 2013 build:
Compiling src\gallium\auxiliary\util\u_tests.c ...
u_tests.c
src\gallium\auxiliary\util\u_tests.c(624) : warning C4013: 'snprintf' undefined; assuming extern returning int
...
gallium.lib(u_tests.obj) : error LNK2019: unresolved external symbol _snprintf referenced in function _test_texture_barrier
build\windows-x86-debug\gallium\targets\graw-gdi\graw.dll : fatal error LNK1120: 1 unresolved externals
scons: *** [build\windows-x86-debug\gallium\targets\graw-gdi\graw.dll] Error 1120
scons: building terminated because of errors.
Fixes: 56342c97ee7 ("gallium/u_tests: test FBFETCH and shader-based blending with MSAA")
Cc: Marek Olšák <marek.olsak@amd.com>
Cc: Brian Paul <brianp@vmware.com>
Cc: Roland Scheidegger <sroland@vmware.com>
Cc: Dieter Nützel <Dieter@nuetzel-hh.de>
Signed-off-by: Andres Gomez <agomez@igalia.com>
Reviewed-by: Brian Paul <brianp@vmware.com>
Andres Gomez [Wed, 1 Aug 2018 10:22:00 +0000 (13:22 +0300)]
glsl: use util_snprintf()
Instead of plain snprintf(). To fix the MSVC 2013 build.
Fixes: 6ff0c6f4ebc ("gallium: move ddebug, noop, rbug, trace to auxiliary to improve build times")
Cc: Marek Olšák <marek.olsak@amd.com>
Cc: Brian Paul <brianp@vmware.com>
Cc: Roland Scheidegger <sroland@vmware.com>
Signed-off-by: Andres Gomez <agomez@igalia.com>
Reviewed-by: Brian Paul <brianp@vmware.com>
Jordan Justen [Wed, 25 Jul 2018 21:31:05 +0000 (14:31 -0700)]
intel/compiler: Add brw_get_compiler_config_value for disk cache
During code review, Jason pointed out that:
2b3064c0731 "i965, anv: Use INTEL_DEBUG for disk_cache driver flags"
Didn't account for INTEL_SCALER_* environment variables.
To fix this, let the compiler return the disk_cache driver flags.
Another possible fix would be to pull the INTEL_SCALER_* into
INTEL_DEBUG bits, but as we are currently using 41 of 64 bits, I
didn't think it was a good use of 4 more of these bits. (5 since
INTEL_PRECISE_TRIG needs to be accounted for as well.)
Cc: Jason Ekstrand <jason@jlekstrand.net>
Signed-off-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Jordan Justen [Wed, 25 Jul 2018 00:13:52 +0000 (17:13 -0700)]
i965: Disable shader cache with INTEL_DEBUG=shader_time
Shader time hard codes an index of the shader time buffer within the
gen program.
In order to support shader time in the disk shader cache, we'd need to
add the shader time index into the program key. This should work, but
probably is not worth it for this particular debug feature.
Therefore, let's just disable the disk shader cache if the shader time
debug feature is used.
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=106382
Fixes: 96fe36f7acc "i965: Enable disk shader cache by default"
Cc: Eero Tamminen <eero.t.tamminen@intel.com>
Cc: Kenneth Graunke <kenneth@whitecape.org>
Signed-off-by: Jordan Justen <jordan.l.justen@intel.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Timothy Arceri [Sat, 21 Jul 2018 05:22:24 +0000 (15:22 +1000)]
glsl: make a copy of array indices that are used to deref a function out param
Fixes new piglit test:
tests/spec/glsl-1.20/execution/qualifiers/vs-out-conversion-int-to-float-vec4-index.shader_test
Reviewed-by: Ian Romanick <ian.d.romanick@intel.com>
Jason Ekstrand [Fri, 27 Oct 2017 01:11:25 +0000 (18:11 -0700)]
anv/pipeline: Add populate_tcs/tes_key helpers
They don't really do anything interesting, but it's more consistent this
way.
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Jason Ekstrand [Fri, 27 Oct 2017 00:56:07 +0000 (17:56 -0700)]
anv/pipeline: Rework the parameters to populate_wm_prog_key
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Jason Ekstrand [Wed, 11 Jul 2018 06:31:47 +0000 (23:31 -0700)]
anv/pipeline: More aggressively optimize away color attachments
Instead of just looking at the number of color attachments, look at
which ones are actually used by the subpass. This lets us potentially
throw away chunks of the fragment shader. In DXVK, for example, all
subpasses have 8 attachments and most are VK_ATTACHMENT_UNUSED so this
is very helpful in that case.
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Jason Ekstrand [Thu, 28 Jun 2018 01:30:09 +0000 (18:30 -0700)]
anv: Restrict the number of color regions to those actually written
The back-end compiler emits the number of color writes specified by
wm_prog_key::nr_color_regions regardless of what nir_store_outputs we
have. Once we've gone through and figured out which render targets
actually exist and are written by the shader, we should restrict the key
to avoid extra RT write messages.
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Jason Ekstrand [Thu, 28 Jun 2018 01:25:17 +0000 (18:25 -0700)]
anv/pipeline: Fix up deref modes if we delete a FS output
With the new deref instructions, we have to keep the modes consistent
between the derefs and the variables they reference. Since we remove
outputs by changing them to local variables, we need to run the fixup
pass to fix the modes.
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Jason Ekstrand [Sat, 28 Oct 2017 16:05:01 +0000 (09:05 -0700)]
nir/lower_indirect: Bail early if modes == 0
There's no point in walking the program if we're never going to actually
lower anything.
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Jason Ekstrand [Tue, 31 Jul 2018 13:16:34 +0000 (06:16 -0700)]
intel/nir: Call nir_lower_io_to_scalar_early
Shader-db results on Kaby Lake:
total instructions in shared programs:
15166953 ->
15073611 (-0.62%)
instructions in affected programs:
2390284 ->
2296942 (-3.91%)
helped: 16469
HURT: 505
total loops in shared programs: 4954 -> 4951 (-0.06%)
loops in affected programs: 3 -> 0
helped: 3
HURT: 0
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Jason Ekstrand [Thu, 26 Jul 2018 05:52:39 +0000 (22:52 -0700)]
intel/nir: Split IO arrays into elements
The NIR nir_lower_io_arrays_to_elements pass attempts to split I/O
variables which are arrays or matrices into a sequence of separate
variables. This can help link-time optimization by allowing us to
remove varyings at a more granular level.
Shader-db results on Kaby Lake:
total instructions in shared programs:
15177645 ->
15168494 (-0.06%)
instructions in affected programs: 79857 -> 70706 (-11.46%)
helped: 392
HURT: 0
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Jason Ekstrand [Tue, 31 Jul 2018 12:31:47 +0000 (05:31 -0700)]
i965/fs: Flag all slots of a flat input as flat
Otherwise, only the first vec4 of a matrix or other complex type will
get marked as flat and we'll interpolate the others. This was caught by
a dEQP test which started failing because it did a SSO vs. non-SSO
comparison. Previously, we did the interpolation wrong consistently in
both versions. However, with one of Tim Arceri's NIR linkingpatches, we
started splitting the matrix input into vectors at link time in the
non-SSO version and it started getting correctly interpolated which
didn't match the broken SSO version. As of this commit, they both get
correctly interpolated.
Fixes: e61cc87c757f8bc "i965/fs: Add a flat_inputs field to prog_data"
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Jason Ekstrand [Tue, 31 Jul 2018 18:31:22 +0000 (11:31 -0700)]
intel/nir: Use the correct scalar stage for consumers when linking
Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
Reviewed-by: Timothy Arceri <tarceri@itsqueeze.com>
Dave Airlie [Wed, 1 Aug 2018 22:43:56 +0000 (08:43 +1000)]
docs: update 18.2.0 release notes for virgl
Dylan Baker [Tue, 22 May 2018 22:34:38 +0000 (15:34 -0700)]
nir/meson: fix c vs cpp args for nir test
Fixes: d1992255bb29054fa51763376d125183a9f602f3
("meson: Add build Intel "anv" vulkan driver")
Signed-off-by: Dylan Baker <dylan.c.baker@intel.com>
Reviewed-by: Eric Engestrom <eric.engestrom@intel.com>
Dylan Baker [Wed, 18 Apr 2018 17:21:14 +0000 (10:21 -0700)]
gallium: fix ddebug on windows
By including the proper headers for getpid and for mkdir.
Fixes: 6ff0c6f4ebcb87ea6c6fe5a4ba90b548f666067d
("gallium: move ddebug, noop, rbug, trace to auxiliary to improve build times")
Signed-off-by: Dylan Baker <dylan.c.baker@intel.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Dylan Baker [Tue, 10 Jul 2018 22:00:13 +0000 (15:00 -0700)]
util: move process.[ch] to u_process.[ch]
On windows process.h is a system provided header, and it's required in
include/c11/threads_win32.h. This header interferes with searching for
that header, and results in windows build warnings with scons, but
errors in meson which doesn't allow implicit function declarations. Just
rename process to u_process, which follows the style of utils anyway.
Fixes: 2e1e6511f76370870b5cde10caa9ca3b6d0dc65f
("util: extract get_process_name from xmlconfig.c")
Signed-off-by: Dylan Baker <dylan.c.baker@intel.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Marek Olšák [Fri, 20 Jul 2018 02:55:49 +0000 (22:55 -0400)]
ac,radeonsi: reduce optimizations for complex compute shaders on older APUs (v2)
To make dEQP-GLES31.functional.ssbo.layout.random.all_shared_buffer.23
finish sooner on the older CPUs. (otherwise it gets killed and we fail
the test)
Acked-by: Dave Airlie <airlied@gmail.com>
Eric Anholt [Wed, 1 Aug 2018 18:25:58 +0000 (11:25 -0700)]
v3d: Actually put the "%s" in the snprintf.
I missed an important part when porting the change over, fixing my
compiler warning but breaking -Werror=format-security.
Fixes: e6ff5ac4468e ("v3d: use snprintf(..., "%s", ...) instead of strncpy")
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=107443
Juan A. Suarez Romero [Tue, 31 Jul 2018 12:17:23 +0000 (14:17 +0200)]
vc4: Fix automake linking error.
CXXLD gallium_dri.la
../../../../src/gallium/drivers/vc4/.libs/libvc4.a(vc4_cl_dump.o): In function `vc4_dump_cl':
src/gallium/drivers/vc4/vc4_cl_dump.c:45: undefined reference to `clif_dump_init'
src/gallium/drivers/vc4/vc4_cl_dump.c:82: undefined reference to `clif_dump_destroy'
../../../../src/broadcom/cle/.libs/libbroadcom_cle.a(cle_libbroadcom_cle_la-v3d_decoder.o): In function `v3d_field_iterator_next':
src/broadcom/cle/v3d_decoder.c:902: undefined reference to `clif_lookup_bo'
Fixes: e92959c4e0 ("v3d: Pass the whole clif_dump structure to v3d_print_group().")
Bugzilla: https://bugs.freedesktop.org/show_bug.cgi?id=107423
CC: Eric Anholt <eric@anholt.net>
Acked-by: Eric Anholt <eric@anholt.net>
Reviewed-by: Andres Gomez <agomez@igalia.com>
Juan A. Suarez Romero [Wed, 1 Aug 2018 15:48:11 +0000 (17:48 +0200)]
scons: require scons 2.4 or greater
There is a bug with scons 2.3, used in Travis, where it fails to detect
some C functions.
Reviewed-by: Andres Gomez <agomez@igalia.com>
Juan A. Suarez Romero [Wed, 1 Aug 2018 15:14:56 +0000 (17:14 +0200)]
travis: install scons from pip
The ubuntu version provided by Travis is a bit old, and does not detect
correctly some C functions.
Use a more modern version through scons.
Reviewed-by: Andres Gomez <agomez@igalia.com>
Marek Olšák [Wed, 1 Aug 2018 15:36:18 +0000 (11:36 -0400)]
docs: mark ARB_ES3_2_compatibility as done for radeonsi
Lionel Landwerlin [Sat, 28 Jul 2018 12:52:44 +0000 (13:52 +0100)]
intel: tools: aubwrite: split gen[89] from gen10+
Gen10+ has an additional bit in MI_BATCH_BUFFER_END to signal the end
of the context image.
We select the largest size for the context image regardless of the
generation.
Signed-off-by: Lionel Landwerlin <lionel.g.landwerlin@intel.com>
Reviewed-by: Rafael Antognolli <rafael.antognolli@intel.com>
Mathieu Bridon [Thu, 7 Jun 2018 10:26:20 +0000 (12:26 +0200)]
python: Use the unicode_escape codec
Python 2 had string_escape and unicode_escape codecs. Python 3 only has
the latter. These work the same as far as we're concerned, so let's use
the future-proof one.
However, the reste of the code expects unicode strings, so we need to
decode them again.
Signed-off-by: Mathieu Bridon <bochecha@daitauha.fr>
Reviewed-by: Dylan Baker <dylan@pnwbakers.com>
Mathieu Bridon [Mon, 25 Jun 2018 16:31:01 +0000 (18:31 +0200)]
python: Explicitly add the 'L' suffix on Python 3
Python 2 had two integer types: int and long. Python 3 dropped the
latter, as it made the int type automatically support bigger numbers.
As a result, Python 3 lost the 'L' suffix on integer litterals.
This probably doesn't make much difference when compiling the generated
C code, but adding it explicitly means that both Python 2 and 3 generate
the exact same C code anyway, which makes it easier to compare and check
for discrepencies when moving to Python 3.
Signed-off-by: Mathieu Bridon <bochecha@daitauha.fr>
Reviewed-by: Dylan Baker <dylan@pnwbakers.com>
Mathieu Bridon [Sun, 17 Jun 2018 12:40:31 +0000 (14:40 +0200)]
python: Explicitly use byte strings
In both Python 2 and 3, zlib.Compress.compress() takes a byte string,
and returns a byte string as well.
In Python 2, the script was working because:
1. string literalls were byte strings;
2. opening a file in unicode mode, reading from it, then passing the
unicode string to compress() would automatically encode to a byte
string;
On Python 3, the above two points are not valid any more, so:
1. zlib.Compress.compress() refuses the passed unicode string;
2. compressed_data, defined as an empty unicode string literal, can't be
concatenated with the byte string returned by compress();
This commit fixes this by explicitly using byte strings where
appropriate, so that the script works on both Python 2 and 3.
Signed-off-by: Mathieu Bridon <bochecha@daitauha.fr>
Reviewed-by: Eric Engestrom <eric.engestrom@intel.com>
Mathieu Bridon [Fri, 1 Jun 2018 13:02:21 +0000 (15:02 +0200)]
python: Use open(), not file()
The latter is a constructor for file objects, but when actually opening
a file, using the former is more idiomatic.
In addition, file() is not a builtin any more in Python 3, so this makes
the script compatible with both Python 2 and Python 3.
Signed-off-by: Mathieu Bridon <bochecha@daitauha.fr>
Reviewed-by: Eric Engestrom <eric.engestrom@intel.com>
Reviewed-by: Dylan Baker <dylan@pnwbakers.com>
Mathieu Bridon [Tue, 26 Jun 2018 06:52:08 +0000 (08:52 +0200)]
python: Open file in binary mode
The XML parser wants byte strings, not unicode strings.
In both Python 2 and 3, opening a file without specifying the mode will
open it for reading in text mode ('r').
On Python 2, the read() method of the file object will return byte
strings, while on Python 3 it will return unicode strings.
Explicitly specifying the binary mode ('rb') makes the behaviour
identical in both Python 2 and 3, returning what the XML parser
expects.
Signed-off-by: Mathieu Bridon <bochecha@daitauha.fr>
Reviewed-by: Eric Engestrom <eric.engestrom@intel.com>
Reviewed-by: Dylan Baker <dylan@pnwbakers.com>
Mathieu Bridon [Sun, 17 Jun 2018 15:53:16 +0000 (17:53 +0200)]
python: Don't abuse hex()
The hex() builtin returns a string containing the hexa-decimal
representation of an integer.
When the argument is not an integer, then the function calls that
object's __hex__() method, if one is defined. That method is supposed to
return a string.
While that's not explicitly documented, that string is supposed to be a
valid hexa-decimal representation for a number. Python 2 doesn't enforce
this though, which is why we got away with returning things like
'NIR_TRUE' which are not numbers.
In Python 3, the hex() builtin instead calls an object's __index__()
method, which itself must return an integer. That integer is then
automatically converted to a string with its hexa-decimal representation
by the rest of the hex() function.
As a result, we really can't make this compatible with Python 3 as it
is.
The solution is to stop using the hex() builtin, and instead use a hex()
object method, which can return whatever we want, in Python 2 and 3.
Signed-off-by: Mathieu Bridon <bochecha@daitauha.fr>
Reviewed-by: Eric Engestrom <eric.engestrom@intel.com>
Reviewed-by: Dylan Baker <dylan@pnwbakers.com>
Mathieu Bridon [Sun, 17 Jun 2018 12:44:46 +0000 (14:44 +0200)]
python: Better get character ordinals
In Python 2, iterating over a byte-string yields single-byte strings,
and we can pass them to ord() to get the corresponding integer.
In Python 3, iterating over a byte-string directly yields those
integers.
Transforming the byte string into a bytearray gives us a list of the
integers corresponding to each byte in the string, removing the need to
call ord().
This makes the script compatible with both Python 2 and 3.
Signed-off-by: Mathieu Bridon <bochecha@daitauha.fr>
Reviewed-by: Eric Engestrom <eric.engestrom@intel.com>
Mario Kleiner [Thu, 14 Jun 2018 04:04:24 +0000 (06:04 +0200)]
loader_dri3: Handle mismatched depth 30 formats for Prime renderoffload.
Detect if the display (X-Server) gpu and Prime renderoffload gpu prefer
different channel ordering for color depth 30 formats ([X/A]BGR2101010
vs. [X/A]RGB2101010) and perform format conversion during the blitImage()
detiling op from tiled backbuffer -> linear buffer.
For this we need to find the visual (= red channel mask) for the
X-Drawable used to display on the server gpu. We use the same proven
logic for finding that visual as in commit "egl/x11: Handle both depth
30 formats for eglCreateImage()".
This is mostly to allow "NVidia Optimus" at depth 30, as Intel/AMD
gpu's prefer xRGB2101010 ordering, whereas NVidia gpu's prefer
xBGR2101010 ordering, so we can offload to nouveau without getting
funky colors.
Tested on Intel single gpu, NVidia single gpu, Intel + NVidia prime
offload with DRI3/Present.
Note: An unintended but pleasant surprise of this patch is that it also
seems to make the modesetting-ddx of server 1.20.0 work at depth 30
on nouveau, at least with unredirected "classic" X rendering, and
with redirected desktop compositing under XRender accel, and with OpenGL
compositing under GLX. Only X11 compositing via OpenGL + EGL still gives
funky colors. modesetting-ddx + glamor are not yet ready to deal with
nouveau's ABGR2101010 format, and treat it as ARGB2101010, also exposing
X-visuals with ARGB2101010 style channel masks. Seems somehow this triggers
the logic in this patch on modesetting-ddx + depth 30 + DRI3 buffer sharing
and does the "wrong" channel swizzling that then cancels out the "wrong"
swizzling of glamor and we end up with the proper pixel formatting in
the scanout buffer :). This so far tested on a NVA5 Tesla card under KDE5
Plasma as shipping with Ubuntu 16.04.4 LTS.
Signed-off-by: Mario Kleiner <mario.kleiner.de@gmail.com>
Cc: Ilia Mirkin <imirkin@alum.mit.edu>
Reviewed-by: Eric Engestrom <eric.engestrom@intel.com>
Mario Kleiner [Wed, 13 Jun 2018 04:04:13 +0000 (06:04 +0200)]
egl/x11: Handle both depth 30 formats for eglCreateImage(). (v4)
We need to distinguish if the backing storage of a pixmap
is XRGB2101010 or XBGR2101010, as different gpu hw supports
different formats. NVidia hw prefers XBGR, whereas AMD and
Intel are happy with XRGB.
Use the red channel mask of the first depth 30 visual of
the x-screen to distinguish which hw format to choose.
This fixes desktop composition of color depth 30 windows
when the X11 compositor uses EGL.
v2: Switch from using the visual of the root window to simply
using the first depth 30 visual for the x-screen, as testing
shows that each driver only exports either xrgb ordering or
xbgr ordering for the channel masks of its depth 30 visuals,
so this should be unambiguous and avoid trouble if X ever
supports depth 30 pixmaps on screens with a non-depth 30 root
window visual. This per Michels suggestion.
v3: No change to v2, but spent some time testing this more on
AMD hw, with my software hacked up to intentionally choose
pixel formats/visual with the non-preferred xBGR2101010
ordering on the ati-ddx, also with a standard non-OpenGL
X-Window with depth 30 visual, to make sure that things show
up properly with the right colors on the screen when going
through EGL+OpenGL based compositing on KDE-5. Iow. to confirm
that my explanation to the v2 patch on the mailing list of why
it should work and the actual practice agree (or possibly that
i am good at fooling myself during testing ;).
v4: Drop the local `red_mask` and just `return visual->red_mask`/
`return 0`, as suggested by Eric Engestrom.
Rebased onto current master, to take the cleanup via the new
function dri2_format_for_depth() into account.
Signed-off-by: Mario Kleiner <mario.kleiner.de@gmail.com>
Reviewed-by: Eric Engestrom <eric.engestrom@intel.com>
Daniel Stone [Wed, 13 Jun 2018 04:04:12 +0000 (06:04 +0200)]
gbm: Add support for 10bpp BGR formats
Add support for XBGR2101010 and ABGR2101010 formats.
Signed-off-by: Daniel Stone <daniels@collabora.com>
Reviewed-by: Mario Kleiner <mario.kleiner.de@gmail.com>
Tested-by: Mario Kleiner <mario.kleiner.de@gmail.com>
Tested-by: Ilia Mirkin <imirkin@alum.mit.edu>
Reviewed-by: Eric Engestrom <eric.engestrom@intel.com>
Daniel Stone [Wed, 13 Jun 2018 04:04:11 +0000 (06:04 +0200)]
egl/wayland: Add 10bpc BGR configs
Add support for XBGR2101010 and ABGR2101010.
Signed-off-by: Daniel Stone <daniels@collabora.com>
Reviewed-by: Eric Engestrom <eric.engestrom@imgtec.com>
Reviewed-by: Mario Kleiner <mario.kleiner.de@gmail.com>
Tested-by: Mario Kleiner <mario.kleiner.de@gmail.com>
Tested-by: Ilia Mirkin <imirkin@alum.mit.edu>
Iago Toral Quiroga [Fri, 27 Jul 2018 11:38:39 +0000 (13:38 +0200)]
intel/compiler: implement 8-bit constant load
Fixes VK-GL-CTS CL#2567
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Iago Toral Quiroga [Fri, 27 Jul 2018 11:38:38 +0000 (13:38 +0200)]
intel/compiler: add setup_imm_(u)b helpers
The hardware doesn't support byte immediates, so similar to setup_imm_df()
for doubles, these helpers work by loading the constant value into a
VGRF.
Reviewed-by: Jason Ekstrand <jason@jlekstrand.net>
Rhys Perry [Wed, 6 Jun 2018 19:55:08 +0000 (20:55 +0100)]
glsl: fix function inlining with opaque parameters
Signed-off-by: Rhys Perry <pendingchaos02@gmail.com>
Reviewed-by: Marek Olšák <marek.olsak@amd.com>
Signed-off-by: Marek Olšák <marek.olsak@amd.com>