From mboxrd@z Thu Jan 1 00:00:00 1970 From: bugzilla-daemon@freedesktop.org Subject: [Bug 101484] [bisected, SI] Steam fails to render content Date: Sat, 17 Jun 2017 16:02:16 +0000 Message-ID: Mime-Version: 1.0 Content-Type: multipart/mixed; boundary="===============0437537194==" Return-path: Received: from culpepper.freedesktop.org (culpepper.freedesktop.org [IPv6:2610:10:20:722:a800:ff:fe98:4b55]) by gabe.freedesktop.org (Postfix) with ESMTP id 095756E076 for ; Sat, 17 Jun 2017 16:02:16 +0000 (UTC) List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dri-devel-bounces@lists.freedesktop.org Sender: "dri-devel" To: dri-devel@lists.freedesktop.org List-Id: dri-devel@lists.freedesktop.org --===============0437537194== Content-Type: multipart/alternative; boundary="14977153350.AD3b28.18984"; charset="UTF-8" --14977153350.AD3b28.18984 Date: Sat, 17 Jun 2017 16:02:15 +0000 MIME-Version: 1.0 Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable X-Bugzilla-URL: http://bugs.freedesktop.org/ Auto-Submitted: auto-generated https://bugs.freedesktop.org/show_bug.cgi?id=3D101484 Bug ID: 101484 Summary: [bisected, SI] Steam fails to render content Product: Mesa Version: git Hardware: x86-64 (AMD64) OS: Linux (All) Status: NEW Severity: major Priority: medium Component: Drivers/Gallium/radeonsi Assignee: dri-devel@lists.freedesktop.org Reporter: gr.muench@gmail.com QA Contact: dri-devel@lists.freedesktop.org Created attachment 132023 --> https://bugs.freedesktop.org/attachment.cgi?id=3D132023&action=3Dedit Steam main window Steam is no longer usable with mesa git. I suspect this is SI (Radeon HD 79= 70) specific though. Confirmed bad commit by reverting it.=20 2b8b9a56efc24cc0f27469bf1532c288cdca2076 is the first bad commit commit 2b8b9a56efc24cc0f27469bf1532c288cdca2076 Author: Marek Ol=C5=A1=C3=A1k Date: Mon May 29 00:40:39 2017 +0200 radeonsi: move PSIZE and CLIPDIST unique IO indices after GENERIC Heaven LDS usage for LS+HS is below. The masks are "outputs_written" for LS and HS. Note that 32K is the maximum size. Before: heaven_x64: ls=3D1f1 tcs=3D1f1, lds=3D32K heaven_x64: ls=3D31 tcs=3D31, lds=3D24K heaven_x64: ls=3D71 tcs=3D71, lds=3D28K After: heaven_x64: ls=3D3f tcs=3D3f, lds=3D24K heaven_x64: ls=3D7 tcs=3D7, lds=3D13K heaven_x64: ls=3Df tcs=3Df, lds=3D17K All other apps have a similar decrease in LDS usage, because the "outputs_written" masks are similar. Also, most apps don't write POSITION in these shader stages, so there is room for improvement. (tight per-component input/output packing might help even more) It's unknown whether this improves performance. Tested-by: Edmondo Tommasina Tested-by: Dieter N=C3=BCtzel Reviewed-by: Nicolai H=C3=A4hnle :040000 040000 53bea508d363add63bb60fe4d7d776a16ef260c7 b654c367d8856228ec2059a2c3f42c5db2e36119 M src git bisect log git bisect start # bad: [1f958c1337290b4062a77f79fc101bb9f4bdf515] radeonsi: include ac_bina= ry.h for struct ac_shader_binary git bisect bad 1f958c1337290b4062a77f79fc101bb9f4bdf515 # good: [bec1c13be2154dfb20baa4fbb33b1560a4ef1910] Android: Drop linking li= bgcc git bisect good bec1c13be2154dfb20baa4fbb33b1560a4ef1910 # good: [fe14a9a50140d7b2e25052823efa671bf8d63d71] i965: Drop duplicate sha= dow variable. git bisect good fe14a9a50140d7b2e25052823efa671bf8d63d71 # bad: [978e6876f1cd8ccc8850a5665e9619a3e29b731e] etnaviv: flush resource w= hen binding as sampler view git bisect bad 978e6876f1cd8ccc8850a5665e9619a3e29b731e # good: [ee38dfe9a5525375012d1c6681e7c39c15ac3049] mesa: make _mesa_scissor_bounding_box() static git bisect good ee38dfe9a5525375012d1c6681e7c39c15ac3049 # good: [9d3f177e4b1ecd5e6ac4673e1ac8c72df9e159eb] dri: Optionally turn off= a couple of GLX extensions based on driconf options git bisect good 9d3f177e4b1ecd5e6ac4673e1ac8c72df9e159eb # bad: [97f6f411db9b16ebc7c4bebaf26513c185c8f550] i965/surface_state: Images can't handle CCS at all git bisect bad 97f6f411db9b16ebc7c4bebaf26513c185c8f550 # bad: [9cb42ae997054f52be2e99764199e00eb28056eb] util: Port nir_array functionality to u_dynarray git bisect bad 9cb42ae997054f52be2e99764199e00eb28056eb # bad: [e9409c86e7b076801626474dfa5a9151da078a73] radeonsi: remove 8 bytes = from si_shader_key git bisect bad e9409c86e7b076801626474dfa5a9151da078a73 # good: [1887faf73b379f28eb6c73bdb790dbcc97213b3a] svga: Allow format differences in 16-bit RGBA surface sharing git bisect good 1887faf73b379f28eb6c73bdb790dbcc97213b3a # good: [df4d6003dc75395f8ded57fdf59046f0d008eea3] svga: Fix imported surfa= ce view creation git bisect good df4d6003dc75395f8ded57fdf59046f0d008eea3 # bad: [2b8b9a56efc24cc0f27469bf1532c288cdca2076] radeonsi: move PSIZE and CLIPDIST unique IO indices after GENERIC git bisect bad 2b8b9a56efc24cc0f27469bf1532c288cdca2076 # good: [2c4ec3f93fcab3fddcbe132200b210e7def1facc] svga: Always set the alp= ha value to 1 when sampling using an XRGB view git bisect good 2c4ec3f93fcab3fddcbe132200b210e7def1facc # first bad commit: [2b8b9a56efc24cc0f27469bf1532c288cdca2076] radeonsi: mo= ve PSIZE and CLIPDIST unique IO indices after GENERIC --=20 You are receiving this mail because: You are the assignee for the bug.= --14977153350.AD3b28.18984 Date: Sat, 17 Jun 2017 16:02:15 +0000 MIME-Version: 1.0 Content-Type: text/html; charset="UTF-8" Content-Transfer-Encoding: quoted-printable X-Bugzilla-URL: http://bugs.freedesktop.org/ Auto-Submitted: auto-generated
Bug ID 101484
Summary [bisected, SI] Steam fails to render content
Product Mesa
Version git
Hardware x86-64 (AMD64)
OS Linux (All)
Status NEW
Severity major
Priority medium
Component Drivers/Gallium/radeonsi
Assignee dri-devel@lists.freedesktop.org
Reporter gr.muench@gmail.com
QA Contact dri-devel@lists.freedesktop.org

Created attachment 132023 =
[details]
Steam main window

Steam is no longer usable with mesa git. I suspect this is SI (Radeon HD 79=
70)
specific though. Confirmed bad commit by reverting it.=20

2b8b9a56efc24cc0f27469bf1532c288cdca2076 is the first bad commit
commit 2b8b9a56efc24cc0f27469bf1532c288cdca2076
Author: Marek Ol=C5=A1=C3=A1k <marek.olsak@amd.com>
Date:   Mon May 29 00:40:39 2017 +0200

    radeonsi: move PSIZE and CLIPDIST unique IO indices after GENERIC

    Heaven LDS usage for LS+HS is below. The masks are "outputs_writte=
n"
    for LS and HS. Note that 32K is the maximum size.

    Before:
      heaven_x64: ls=3D1f1 tcs=3D1f1, lds=3D32K
      heaven_x64: ls=3D31 tcs=3D31, lds=3D24K
      heaven_x64: ls=3D71 tcs=3D71, lds=3D28K

    After:
      heaven_x64: ls=3D3f tcs=3D3f, lds=3D24K
      heaven_x64: ls=3D7 tcs=3D7, lds=3D13K
      heaven_x64: ls=3Df tcs=3Df, lds=3D17K

    All other apps have a similar decrease in LDS usage, because
    the "outputs_written" masks are similar. Also, most apps don'=
t write
    POSITION in these shader stages, so there is room for improvement.
    (tight per-component input/output packing might help even more)

    It's unknown whether this improves performance.

    Tested-by: Edmondo Tommasina <edmondo.tommasina@gmail.com>
    Tested-by: Dieter N=C3=BCtzel <Dieter@nuetzel-hh.de>
    Reviewed-by: Nicolai H=C3=A4hnle <nicolai.haehnle@amd.com>

:040000 040000 53bea508d363add63bb60fe4d7d776a16ef260c7
b654c367d8856228ec2059a2c3f42c5db2e36119 M      src

git bisect log
git bisect start
# bad: [1f958c1337290b4062a77f79fc101bb9f4bdf515] radeonsi: include ac_bina=
ry.h
for struct ac_shader_binary
git bisect bad 1f958c1337290b4062a77f79fc101bb9f4bdf515
# good: [bec1c13be2154dfb20baa4fbb33b1560a4ef1910] Android: Drop linking li=
bgcc
git bisect good bec1c13be2154dfb20baa4fbb33b1560a4ef1910
# good: [fe14a9a50140d7b2e25052823efa671bf8d63d71] i965: Drop duplicate sha=
dow
variable.
git bisect good fe14a9a50140d7b2e25052823efa671bf8d63d71
# bad: [978e6876f1cd8ccc8850a5665e9619a3e29b731e] etnaviv: flush resource w=
hen
binding as sampler view
git bisect bad 978e6876f1cd8ccc8850a5665e9619a3e29b731e
# good: [ee38dfe9a5525375012d1c6681e7c39c15ac3049] mesa: make
_mesa_scissor_bounding_box() static
git bisect good ee38dfe9a5525375012d1c6681e7c39c15ac3049
# good: [9d3f177e4b1ecd5e6ac4673e1ac8c72df9e159eb] dri: Optionally turn off=
 a
couple of GLX extensions based on driconf options
git bisect good 9d3f177e4b1ecd5e6ac4673e1ac8c72df9e159eb
# bad: [97f6f411db9b16ebc7c4bebaf26513c185c8f550] i965/surface_state: Images
can't handle CCS at all
git bisect bad 97f6f411db9b16ebc7c4bebaf26513c185c8f550
# bad: [9cb42ae997054f52be2e99764199e00eb28056eb] util: Port nir_array
functionality to u_dynarray
git bisect bad 9cb42ae997054f52be2e99764199e00eb28056eb
# bad: [e9409c86e7b076801626474dfa5a9151da078a73] radeonsi: remove 8 bytes =
from
si_shader_key
git bisect bad e9409c86e7b076801626474dfa5a9151da078a73
# good: [1887faf73b379f28eb6c73bdb790dbcc97213b3a] svga: Allow format
differences in 16-bit RGBA surface sharing
git bisect good 1887faf73b379f28eb6c73bdb790dbcc97213b3a
# good: [df4d6003dc75395f8ded57fdf59046f0d008eea3] svga: Fix imported surfa=
ce
view creation
git bisect good df4d6003dc75395f8ded57fdf59046f0d008eea3
# bad: [2b8b9a56efc24cc0f27469bf1532c288cdca2076] radeonsi: move PSIZE and
CLIPDIST unique IO indices after GENERIC
git bisect bad 2b8b9a56efc24cc0f27469bf1532c288cdca2076
# good: [2c4ec3f93fcab3fddcbe132200b210e7def1facc] svga: Always set the alp=
ha
value to 1 when sampling using an XRGB view
git bisect good 2c4ec3f93fcab3fddcbe132200b210e7def1facc
# first bad commit: [2b8b9a56efc24cc0f27469bf1532c288cdca2076] radeonsi: mo=
ve
PSIZE and CLIPDIST unique IO indices after GENERIC


You are receiving this mail because:
  • You are the assignee for the bug.
= --14977153350.AD3b28.18984-- --===============0437537194== Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: base64 Content-Disposition: inline X19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX19fX18KZHJpLWRldmVs IG1haWxpbmcgbGlzdApkcmktZGV2ZWxAbGlzdHMuZnJlZWRlc2t0b3Aub3JnCmh0dHBzOi8vbGlz dHMuZnJlZWRlc2t0b3Aub3JnL21haWxtYW4vbGlzdGluZm8vZHJpLWRldmVsCg== --===============0437537194==--