<div dir="ltr">Hi, <div class="gmail_extra"> <div class="gmail_quote">On Fri, Jun 30, 2017 at 6:26 AM, Samuel Pitoiset <<a href="mailto:samuel.pitoiset@gmail.com" target="_blank">samuel.pitoiset@gmail.com</a>> wrote: <blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex">Do you still have some glitches or does it work correctly now?</blockquote><div>No visible glitches on my machine so far (Pascal 1080, Debain stretch GNOME desktop)</div><div>I used "rendercheck -f a8r8g8b8" to make sure there's no differences between the test results after the patch. They've helped me in my debugging to an extent.</div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"> Did you also remove the spurious wait dep bars between v3 and v4?</blockquote><div>There's a redundant read dep-bar on "sched (st 0xf wr 0x1) (st 0xf wr 0x0 rd 0x1 wt 0x3) (st 0xf wr 0x1 wt 0x2)" which I've removed in v5 of this patch. I'll be sending them to the ML now.</div><div> </div><div>Cheers,</div><div>Aaryaman</div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><div class="gmail-m_-7663460522227076715gmail-HOEnZb"><div class="gmail-m_-7663460522227076715gmail-h5"> On 06/27/2017 05:16 PM, Aaryaman Vasishta wrote: <blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"> v4: Updated the wait dependancy bars based on tex component masks. This patch adds proper delays to maxwell exa shaders. Tested with rendercheck -f a8r8g8b8. I am still wondering whether the rd's are required. We could still wait on the write bars instead. eg. see "sched (st 0xf wr 0x1 wt 0x2) (st 0xf wr 0x1 wt 0x2) (st 0xf)" in exacmnv110.fp Trello: <a href="https://trello.com/c/6LPB2EIS/174-update-maxwell-shaders-with-proper-delays" rel="noreferrer" target="_blank">https://trello.com/c/6LPB2EIS/174-update-maxwell-shaders-with-proper-delays</a> Signed-off-by: Aaryaman Vasishta <<a href="mailto:jem456.vasishta@gmail.com" target="_blank">jem456.vasishta@gmail.com</a>> --- src/shader/exac8nv110.fp | 10 +++++----- src/shader/exac8nv110.fpc | 18 +++++++++--------- src/shader/exacanv110.fp | 10 +++++----- src/shader/exacanv110.fpc | 18 +++++++++--------- src/shader/exacmnv110.fp | 10 +++++----- src/shader/exacmnv110.fpc | 18 +++++++++--------- src/shader/exas8nv110.fp | 6 +++--- src/shader/exas8nv110.fpc | 12 ++++++------ src/shader/exasanv110.fp | 10 +++++----- src/shader/exasanv110.fpc | 18 +++++++++--------- src/shader/exascnv110.fp | 6 +++--- src/shader/exascnv110.fpc | 10 +++++----- src/shader/videonv110.fp | 14 +++++++------- src/shader/videonv110.fpc | 26 +++++++++++++------------- 14 files changed, 93 insertions(+), 93 deletions(-) diff --git a/src/shader/exac8nv110.fp b/src/shader/exac8nv110.fp index ce78036..101b67f 100644 --- a/src/shader/exac8nv110.fp +++ b/src/shader/exac8nv110.fp @@ -25,23 +25,23 @@ NV110FP_Composite_A8[] = { }; #else -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0xf wr 0x0) (st 0xd wr 0x0 wt 0x1) (st 0xf wr 0x0 wt 0x1) ipa pass $r0 a[0x7c] 0x0 0x0 0x1 mufu rcp $r0 $r0 ipa $r3 a[0x94] $r0 0x0 0x1 -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0xf wr 0x1) (st 0xf wr 0x0 rd 0x1 wt 0x3) (st 0xf wr 0x1 wt 0x2) ipa $r2 a[0x90] $r0 0x0 0x1 tex nodep $r1 $r2 0x0 0x1 t2d 0x8 ipa $r3 a[0x84] $r0 0x0 0x1 -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0xf wr 0x2) (st 0xf wr 0x1 wt 0x6) (st 0xf) ipa $r2 a[0x80] $r0 0x0 0x1 tex nodep $r0 $r2 0x0 0x0 t2d 0x8 depbar le 0x5 0x0 0x0 -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0x6 wt 0x3) (st 0x1) (st 0x1) fmul ftz $r3 $r0 $r1 mov $r2 $r3 0xf mov $r1 $r3 0xf -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0x1) (st 0xf) (st 0x0) mov $r0 $r3 0xf exit #endif diff --git a/src/shader/exac8nv110.fpc b/src/shader/exac8nv110.fpc index 4aa1368..1f7d649 100644 --- a/src/shader/exac8nv110.fpc +++ b/src/shader/exac8nv110.fpc @@ -1,36 +1,36 @@ -0xfc0007e0, -0x001f8000, +0xe1a0070f, +0x003c3c01, 0xcff7ff00, 0xe003ff87, 0x00470000, 0x50800000, 0x4007ff03, 0xe043ff89, -0xfc0007e0, -0x001f8000, +0x21e0072f, +0x005cbc03, 0x0007ff02, 0xe043ff89, 0x2ff70201, 0xc03a0014, 0x4007ff03, 0xe043ff88, -0xfc0007e0, -0x001f8000, +0xe5e0074f, +0x001fbc06, 0x0007ff02, 0xe043ff88, 0x2ff70200, 0xc03a0004, 0x34070000, 0xf0f00000, -0xfc0007e0, -0x001f8000, +0xfc201fe6, +0x001f8400, 0x00170003, 0x5c681000, 0x00370002, 0x5c980780, 0x00370001, 0x5c980780, -0xfc0007e0, +0xfde007e1, 0x001f8000, 0x00370000, 0x5c980780, diff --git a/src/shader/exacanv110.fp b/src/shader/exacanv110.fp index a70d5c5..fe55fcd 100644 --- a/src/shader/exacanv110.fp +++ b/src/shader/exacanv110.fp @@ -25,23 +25,23 @@ NV110FP_CAComposite[] = { }; #else -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0xf wr 0x0) (st 0xd wr 0x0 wt 0x1) (st 0xf wr 0x0 wt 0x1) ipa pass $r0 a[0x7c] 0x0 0x0 0x1 mufu rcp $r0 $r0 ipa $r3 a[0x94] $r0 0x0 0x1 -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0xf wr 0x1) (st 0xf wr 0x0 wt 0x3) (st 0xf wr 0x1) ipa $r2 a[0x90] $r0 0x0 0x1 tex nodep $r4 $r2 0x0 0x1 t2d 0xf ipa $r1 a[0x84] $r0 0x0 0x1 -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0xf wr 0x1 wt 0x2) (st 0xf wr 0x1 wt 0x2) (st 0xf) ipa $r0 a[0x80] $r0 0x0 0x1 tex nodep $r0 $r0 0x0 0x0 t2d 0xf depbar le 0x5 0x0 0x0 -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0x1 wt 0x3) (st 0x1) (st 0x1) fmul ftz $r3 $r3 $r7 fmul ftz $r2 $r2 $r6 fmul ftz $r1 $r1 $r5 -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0x1) (st 0xf) (st 0x0) fmul ftz $r0 $r0 $r4 exit #endif diff --git a/src/shader/exacanv110.fpc b/src/shader/exacanv110.fpc index 7c0ca5e..7c8ebbd 100644 --- a/src/shader/exacanv110.fpc +++ b/src/shader/exacanv110.fpc @@ -1,36 +1,36 @@ -0xfc0007e0, -0x001f8000, +0xe1a0070f, +0x003c3c01, 0xcff7ff00, 0xe003ff87, 0x00470000, 0x50800000, 0x4007ff03, 0xe043ff89, -0xfc0007e0, -0x001f8000, +0xe1e0072f, +0x001cbc03, 0x0007ff02, 0xe043ff89, 0xaff70204, 0xc03a0017, 0x4007ff01, 0xe043ff88, -0xfc0007e0, -0x001f8000, +0xe5e0172f, +0x001fbc02, 0x0007ff00, 0xe043ff88, 0xaff70000, 0xc03a0007, 0x34070000, 0xf0f00000, -0xfc0007e0, -0x001f8000, +0xfc201fe1, +0x001f8400, 0x00770303, 0x5c681000, 0x00670202, 0x5c681000, 0x00570101, 0x5c681000, -0xfc0007e0, +0xfde007e1, 0x001f8000, 0x00470000, 0x5c681000, diff --git a/src/shader/exacmnv110.fp b/src/shader/exacmnv110.fp index fe5c294..7113ab3 100644 --- a/src/shader/exacmnv110.fp +++ b/src/shader/exacmnv110.fp @@ -25,23 +25,23 @@ NV110FP_Composite[] = { }; #else -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0xf wr 0x0) (st 0xd wr 0x0 wt 0x1) (st 0xf wr 0x0 wt 0x1) ipa pass $r0 a[0x7c] 0x0 0x0 0x1 mufu rcp $r0 $r0 ipa $r3 a[0x94] $r0 0x0 0x1 -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0xf wr 0x1) (st 0xf wr 0x0 wt 0x3) (st 0xf wr 0x1) ipa $r2 a[0x90] $r0 0x0 0x1 tex nodep $r4 $r2 0x0 0x1 t2d 0x8 ipa $r1 a[0x84] $r0 0x0 0x1 -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0xf wr 0x1 wt 0x2) (st 0xf wr 0x1 wt 0x2) (st 0xf) ipa $r0 a[0x80] $r0 0x0 0x1 tex nodep $r0 $r0 0x0 0x0 t2d 0xf depbar le 0x5 0x0 0x0 -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0x1 wt 0x3) (st 0x1) (st 0x1) fmul ftz $r3 $r3 $r4 fmul ftz $r2 $r2 $r4 fmul ftz $r1 $r1 $r4 -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0x1) (st 0xf) (st 0x0) fmul ftz $r0 $r0 $r4 exit #endif diff --git a/src/shader/exacmnv110.fpc b/src/shader/exacmnv110.fpc index 9d62c1a..60352a8 100644 --- a/src/shader/exacmnv110.fpc +++ b/src/shader/exacmnv110.fpc @@ -1,36 +1,36 @@ -0xfc0007e0, -0x001f8000, +0xe1a0070f, +0x003c3c01, 0xcff7ff00, 0xe003ff87, 0x00470000, 0x50800000, 0x4007ff03, 0xe043ff89, -0xfc0007e0, -0x001f8000, +0xe1e0072f, +0x001cbc03, 0x0007ff02, 0xe043ff89, 0x2ff70204, 0xc03a0014, 0x4007ff01, 0xe043ff88, -0xfc0007e0, -0x001f8000, +0xe5e0172f, +0x001fbc02, 0x0007ff00, 0xe043ff88, 0xaff70000, 0xc03a0007, 0x34070000, 0xf0f00000, -0xfc0007e0, -0x001f8000, +0xfc201fe1, +0x001f8400, 0x00470303, 0x5c681000, 0x00470202, 0x5c681000, 0x00470101, 0x5c681000, -0xfc0007e0, +0xfde007e1, 0x001f8000, 0x00470000, 0x5c681000, diff --git a/src/shader/exas8nv110.fp b/src/shader/exas8nv110.fp index 4fe2e19..a555beb 100644 --- a/src/shader/exas8nv110.fp +++ b/src/shader/exas8nv110.fp @@ -25,15 +25,15 @@ NV110FP_Source_A8[] = { }; #else -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0xf wr 0x0) (st 0xd wr 0x0 wt 0x1) (st 0xf wr 0x0 wt 0x1) ipa pass $r0 a[0x7c] 0x0 0x0 0x1 mufu rcp $r0 $r0 ipa $r1 a[0x84] $r0 0x0 0x1 -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0xf wr 0x1) (st 0xf wr 0x0 wt 0x3) (st 0xf) ipa $r0 a[0x80] $r0 0x0 0x1 tex nodep $r0 $r0 0x0 0x0 t2d 0x8 depbar le 0x5 0x0 0x0 -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0x1 wt 0x1) (st 0x1) (st 0x1) mov $r3 $r0 0xf mov $r2 $r0 0xf mov $r1 $r0 0xf diff --git a/src/shader/exas8nv110.fpc b/src/shader/exas8nv110.fpc index 1181c41..e58d168 100644 --- a/src/shader/exas8nv110.fpc +++ b/src/shader/exas8nv110.fpc @@ -1,21 +1,21 @@ -0xfc0007e0, -0x001f8000, +0xe1a0070f, +0x003c3c01, 0xcff7ff00, 0xe003ff87, 0x00470000, 0x50800000, 0x4007ff01, 0xe043ff88, -0xfc0007e0, -0x001f8000, +0xe1e0072f, +0x001fbc03, 0x0007ff00, 0xe043ff88, 0x2ff70000, 0xc03a0004, 0x34070000, 0xf0f00000, -0xfc0007e0, -0x001f8000, +0xfc200fe1, +0x001f8400, 0x00070003, 0x5c980780, 0x00070002, diff --git a/src/shader/exasanv110.fp b/src/shader/exasanv110.fp index 61374a6..ee818cd 100644 --- a/src/shader/exasanv110.fp +++ b/src/shader/exasanv110.fp @@ -25,23 +25,23 @@ NV110FP_CACompositeSrcAlpha[] = { }; #else -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0xf wr 0x0) (st 0xd wr 0x0 wt 0x1) (st 0xf wr 0x0 wt 0x1) ipa pass $r0 a[0x7c] 0x0 0x0 0x1 mufu rcp $r0 $r0 ipa $r3 a[0x84] $r0 0x0 0x1 -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0xf wr 0x1) (st 0xf wr 0x0 wt 0x3) (st 0xf wr 0x1) ipa $r2 a[0x80] $r0 0x0 0x1 tex nodep $r4 $r2 0x0 0x0 t2d 0x8 ipa $r1 a[0x94] $r0 0x0 0x1 -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0xf wr 0x1 wt 0x2) (st 0xf wr 0x1 wt 0x2) (st 0xf) ipa $r0 a[0x90] $r0 0x0 0x1 tex nodep $r0 $r0 0x0 0x1 t2d 0xf depbar le 0x5 0x0 0x0 -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0x1 wt 0x3) (st 0x1) (st 0x1) fmul ftz $r3 $r3 $r4 fmul ftz $r2 $r2 $r4 fmul ftz $r1 $r1 $r4 -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0x1) (st 0xf) (st 0x0) fmul ftz $r0 $r0 $r4 exit #endif diff --git a/src/shader/exasanv110.fpc b/src/shader/exasanv110.fpc index 5516a03..604bf9a 100644 --- a/src/shader/exasanv110.fpc +++ b/src/shader/exasanv110.fpc @@ -1,36 +1,36 @@ -0xfc0007e0, -0x001f8000, +0xe1a0070f, +0x003c3c01, 0xcff7ff00, 0xe003ff87, 0x00470000, 0x50800000, 0x4007ff03, 0xe043ff88, -0xfc0007e0, -0x001f8000, +0xe1e0072f, +0x001cbc03, 0x0007ff02, 0xe043ff88, 0x2ff70204, 0xc03a0004, 0x4007ff01, 0xe043ff89, -0xfc0007e0, -0x001f8000, +0xe5e0172f, +0x001fbc02, 0x0007ff00, 0xe043ff89, 0xaff70000, 0xc03a0017, 0x34070000, 0xf0f00000, -0xfc0007e0, -0x001f8000, +0xfc201fe1, +0x001f8400, 0x00470303, 0x5c681000, 0x00470202, 0x5c681000, 0x00470101, 0x5c681000, -0xfc0007e0, +0xfde007e1, 0x001f8000, 0x00470000, 0x5c681000, diff --git a/src/shader/exascnv110.fp b/src/shader/exascnv110.fp index 90bbb55..86e14e8 100644 --- a/src/shader/exascnv110.fp +++ b/src/shader/exascnv110.fp @@ -25,14 +25,14 @@ NV110FP_Source[] = { }; #else -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0xf wr 0x0) (st 0xd wr 0x0 wt 0x1) (st 0xf wr 0x0 wt 0x1) ipa pass $r0 a[0x7c] 0x0 0x0 0x1 mufu rcp $r0 $r0 ipa $r1 a[0x84] $r0 0x0 0x1 -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0xf wr 0x1) (st 0xf wt 0x3) (st 0xf) ipa $r0 a[0x80] $r0 0x0 0x1 tex nodep $r0 $r0 0x0 0x0 t2d 0xf depbar le 0x5 0x0 0x0 -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0xf) (st 0x0) (st 0x0) exit #endif diff --git a/src/shader/exascnv110.fpc b/src/shader/exascnv110.fpc index 2dba15d..1fef5d2 100644 --- a/src/shader/exascnv110.fpc +++ b/src/shader/exascnv110.fpc @@ -1,20 +1,20 @@ -0xfc0007e0, -0x001f8000, +0xe1a0070f, +0x003c3c01, 0xcff7ff00, 0xe003ff87, 0x00470000, 0x50800000, 0x4007ff01, 0xe043ff88, -0xfc0007e0, -0x001f8000, +0xfde0072f, +0x001fbc03, 0x0007ff00, 0xe043ff88, 0xaff70000, 0xc03a0007, 0x34070000, 0xf0f00000, -0xfc0007e0, +0xfc0007ef, 0x001f8000, 0x0007000f, 0xe3000000, diff --git a/src/shader/videonv110.fp b/src/shader/videonv110.fp index 2728311..773aad5 100644 --- a/src/shader/videonv110.fp +++ b/src/shader/videonv110.fp @@ -25,30 +25,30 @@ NV110FP_NV12[] = { }; #else -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0xf wr 0x0) (st 0xd wr 0x0 wt 0x1) (st 0xf wr 0x0 wt 0x1) ipa pass $r2 a[0x7c] 0x0 0x0 0x1 mufu rcp $r2 $r2 ipa $r0 a[0x80] $r2 0x0 0x1 -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0xf wr 0x1) (st 0xf wr 0x0 wt 0x3) (st 0xf wr 0x0 wt 0x1) ipa $r1 a[0x84] $r2 0x0 0x1 tex nodep $r4 $r0 0x0 0x0 t2d 0x8 tex nodep $r0 $r0 0x0 0x1 t2d 0xc -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0xf) (st 0x6) (st 0x1) depbar le 0x5 0x1 0x1 fmul ftz $r5 $r4 c0[0x0] fadd ftz $r3 $r5 c0[0x4] -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0x6) (st 0x6) (st 0xf) fadd ftz $r4 $r5 c0[0x8] fadd ftz $r5 $r5 c0[0xc] depbar le 0x5 0x0 0x0 -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0x6 wt 0x1) (st 0x1) (st 0x1) ffma ftz $r3 $r0 c0[0x10] $r3 ffma ftz $r4 $r0 c0[0x14] $r4 ffma ftz $r5 $r0 c0[0x18] $r5 -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0x1) (st 0x1) (st 0x6) ffma ftz $r0 $r1 c0[0x1c] $r3 ffma ftz $r2 $r1 c0[0x24] $r5 ffma ftz $r1 $r1 c0[0x20] $r4 -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0xf) (st 0x0) (st 0x0) exit #endif diff --git a/src/shader/videonv110.fpc b/src/shader/videonv110.fpc index 31d745a..8e7bedf 100644 --- a/src/shader/videonv110.fpc +++ b/src/shader/videonv110.fpc @@ -1,52 +1,52 @@ -0xfc0007e0, -0x001f8000, +0xe1a0070f, +0x003c3c01, 0xcff7ff02, 0xe003ff87, 0x00470202, 0x50800000, 0x0027ff00, 0xe043ff88, -0xfc0007e0, -0x001f8000, +0xe1e0072f, +0x003c3c03, 0x4027ff01, 0xe043ff88, 0x2ff70004, 0xc03a0004, 0x2ff70000, 0xc03a0016, -0xfc0007e0, -0x001f8000, +0xfcc007ef, +0x001f8400, 0x34170001, 0xf0f00000, 0x00070405, 0x4c681000, 0x00170503, 0x4c581000, -0xfc0007e0, -0x001f8000, +0xfcc007e6, +0x001fbc00, 0x00270504, 0x4c581000, 0x00370505, 0x4c581000, 0x34070000, 0xf0f00000, -0xfc0007e0, -0x001f8000, +0xfc200fe6, +0x001f8400, 0x00470003, 0x49a00180, 0x00570004, 0x49a00200, 0x00670005, 0x49a00280, -0xfc0007e0, -0x001f8000, +0xfc2007e1, +0x001f9800, 0x00770100, 0x49a00180, 0x00970102, 0x49a00280, 0x00870101, 0x49a00200, -0xfc0007e0, +0xfc0007ef, 0x001f8000, 0x0007000f, 0xe3000000, </blockquote> </div></div></blockquote></div> </div></div>