<div dir="ltr">Hi,<div> </div><div>Any updates on the review of this patch?</div><div> </div><div>Cheers,</div><div>Aaryaman</div></div><div class="gmail_extra"> <div class="gmail_quote">On Sun, Jul 2, 2017 at 12:37 AM, Aaryaman Vasishta <<a href="mailto:jem456.vasishta@gmail.com" target="_blank">jem456.vasishta@gmail.com</a>> wrote: <blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">v5: Rebased on depbar removal patch; removed a redundant read dep-bar. This patch adds proper delays to maxwell exa shaders. rendercheck tests seem consistent with/without this patch. I haven't extensively tested them though. 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">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 | 4 ++-- src/shader/exascnv110.fpc | 8 ++++---- src/shader/videonv110.fp | 12 ++++++------ src/shader/videonv110.fpc | 22 +++++++++++----------- 14 files changed, 88 insertions(+), 88 deletions(-) diff --git a/src/shader/exac8nv110.fp b/src/shader/exac8nv110.fp index 220d7e5..7797ef4 100644 --- a/src/shader/exac8nv110.fp +++ b/src/shader/exac8nv110.fp @@ -25,22 +25,22 @@ 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 wt 0x3) (st 0xf wr 0x0 wt 0x1) 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 0x1) (st 0xf wr 0x0 wt 0x3) (st 0x6 wt 0x1) ipa $r2 a[0x80] $r0 0x0 0x1 tex nodep $r0 $r2 0x0 0x0 t2d 0x8 fmul ftz $r3 $r0 $r1 -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0x1) (st 0x1) (st 0x1) mov $r2 $r3 0xf mov $r1 $r3 0xf mov $r0 $r3 0xf -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0xf) (st 0x0) (st 0x0) exit #endif diff --git a/src/shader/exac8nv110.fpc b/src/shader/exac8nv110.fpc index d8d5517..7eb9c02 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, +0xe1e0072f, +0x003c3c03, 0x0007ff02, 0xe043ff89, 0x2ff70201, 0xc03a0014, 0x4007ff03, 0xe043ff88, -0xfc0007e0, -0x001f8000, +0xe1e0072f, +0x003f9803, 0x0007ff02, 0xe043ff88, 0x2ff70200, 0xc03a0004, 0x00170003, 0x5c681000, -0xfc0007e0, -0x001f8000, +0xfc2007e1, +0x001f8400, 0x00370002, 0x5c980780, 0x00370001, 0x5c980780, 0x00370000, 0x5c980780, -0xfc0007e0, +0xfc0007ef, 0x001f8000, 0x0007000f, 0xe3000000, diff --git a/src/shader/exacanv110.fp b/src/shader/exacanv110.fp index bad34c9..912f630 100644 --- a/src/shader/exacanv110.fp +++ b/src/shader/exacanv110.fp @@ -25,22 +25,22 @@ 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 0x1 wt 0x3) ipa $r0 a[0x80] $r0 0x0 0x1 tex nodep $r0 $r0 0x0 0x0 t2d 0xf fmul ftz $r3 $r3 $r7 -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0x1) (st 0x1) (st 0x1) fmul ftz $r2 $r2 $r6 fmul ftz $r1 $r1 $r5 fmul ftz $r0 $r0 $r4 -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0xf) (st 0x0) (st 0x0) exit #endif diff --git a/src/shader/exacanv110.fpc b/src/shader/exacanv110.fpc index 1a151a2..4c35845 100644 <div><div class="h5">--- 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, </div></div>+0x007f8402, 0x0007ff00, 0xe043ff88, 0xaff70000, 0xc03a0007, 0x00770303, 0x5c681000, -0xfc0007e0, -0x001f8000, +0xfc2007e1, +0x001f8400, 0x00670202, 0x5c681000, 0x00570101, 0x5c681000, 0x00470000, 0x5c681000, -0xfc0007e0, +0xfc0007ef, 0x001f8000, 0x0007000f, 0xe3000000, diff --git a/src/shader/exacmnv110.fp b/src/shader/exacmnv110.fp index c1eb38e..02a0835 100644 --- a/src/shader/exacmnv110.fp +++ b/src/shader/exacmnv110.fp @@ -25,22 +25,22 @@ 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 0x1 wt 0x3) ipa $r0 a[0x80] $r0 0x0 0x1 tex nodep $r0 $r0 0x0 0x0 t2d 0xf fmul ftz $r3 $r3 $r4 -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0x1) (st 0x1) (st 0x1) fmul ftz $r2 $r2 $r4 fmul ftz $r1 $r1 $r4 fmul ftz $r0 $r0 $r4 -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0xf) (st 0x0) (st 0x0) exit #endif diff --git a/src/shader/exacmnv110.fpc b/src/shader/exacmnv110.fpc index 0b21a0a..56e4e18 100644 <div><div class="h5">--- 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, </div></div>+0x007f8402, 0x0007ff00, 0xe043ff88, 0xaff70000, 0xc03a0007, 0x00470303, 0x5c681000, -0xfc0007e0, -0x001f8000, +0xfc2007e1, +0x001f8400, 0x00470202, 0x5c681000, 0x00470101, 0x5c681000, 0x00470000, 0x5c681000, -0xfc0007e0, +0xfc0007ef, 0x001f8000, 0x0007000f, 0xe3000000, diff --git a/src/shader/exas8nv110.fp b/src/shader/exas8nv110.fp index c5349d9..847cc6a 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 0x1 wt 0x1) ipa $r0 a[0x80] $r0 0x0 0x1 tex nodep $r0 $r0 0x0 0x0 t2d 0x8 mov $r3 $r0 0xf -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0x1) (st 0x1) (st 0xf) mov $r2 $r0 0xf mov $r1 $r0 0xf exit diff --git a/src/shader/exas8nv110.fpc b/src/shader/exas8nv110.fpc index fabf980..5671a12 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, +0x003f8403, 0x0007ff00, 0xe043ff88, 0x2ff70000, 0xc03a0004, 0x00070003, 0x5c980780, -0xfc0007e0, -0x001f8000, +0xfc2007e1, +0x001fbc00, 0x00070002, 0x5c980780, 0x00070001, diff --git a/src/shader/exasanv110.fp b/src/shader/exasanv110.fp index 4392c1f..a3d372e 100644 --- a/src/shader/exasanv110.fp +++ b/src/shader/exasanv110.fp @@ -25,22 +25,22 @@ 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 0x1 wt 0x3) ipa $r0 a[0x90] $r0 0x0 0x1 tex nodep $r0 $r0 0x0 0x1 t2d 0xf fmul ftz $r3 $r3 $r4 -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0x1) (st 0x1) (st 0x1) fmul ftz $r2 $r2 $r4 fmul ftz $r1 $r1 $r4 fmul ftz $r0 $r0 $r4 -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0xf) (st 0x0) (st 0x0) exit #endif diff --git a/src/shader/exasanv110.fpc b/src/shader/exasanv110.fpc index 80a2731..b61e396 100644 <div><div class="h5">--- 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, </div></div>+0x007f8402, 0x0007ff00, 0xe043ff89, 0xaff70000, 0xc03a0017, 0x00470303, 0x5c681000, -0xfc0007e0, -0x001f8000, +0xfc2007e1, +0x001f8400, 0x00470202, 0x5c681000, 0x00470101, 0x5c681000, 0x00470000, 0x5c681000, -0xfc0007e0, +0xfc0007ef, 0x001f8000, 0x0007000f, 0xe3000000, diff --git a/src/shader/exascnv110.fp b/src/shader/exascnv110.fp index 83a089a..91702d2 100644 --- a/src/shader/exascnv110.fp +++ b/src/shader/exascnv110.fp @@ -25,11 +25,11 @@ 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 exit diff --git a/src/shader/exascnv110.fpc b/src/shader/exascnv110.fpc index 3dd3f89..790a797 100644 --- a/src/shader/exascnv110.fpc +++ b/src/shader/exascnv110.fpc @@ -1,13 +1,13 @@ -0xfc0007e0, -0x001f8000, +0xe1a0070f, +0x003c3c01, 0xcff7ff00, 0xe003ff87, 0x00470000, 0x50800000, 0x4007ff01, 0xe043ff88, -0xfc0007e0, -0x001f8000, +0xfde0072f, +0x001fbc03, 0x0007ff00, 0xe043ff88, 0xaff70000, diff --git a/src/shader/videonv110.fp b/src/shader/videonv110.fp index b171e51..ce6769d 100644 --- a/src/shader/videonv110.fp +++ b/src/shader/videonv110.fp @@ -25,27 +25,27 @@ 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 0x6) (st 0x1) (st 0x6) fmul ftz $r5 $r4 c0[0x0] fadd ftz $r3 $r5 c0[0x4] fadd ftz $r4 $r5 c0[0x8] -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0x6) (st 0x6 wt 0x1) (st 0x1) fadd ftz $r5 $r5 c0[0xc] ffma ftz $r3 $r0 c0[0x10] $r3 ffma ftz $r4 $r0 c0[0x14] $r4 -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0x1) (st 0x1) (st 0x1) ffma ftz $r5 $r0 c0[0x18] $r5 ffma ftz $r0 $r1 c0[0x1c] $r3 ffma ftz $r2 $r1 c0[0x24] $r5 -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0x6) (st 0xf) (st 0x0) ffma ftz $r1 $r1 c0[0x20] $r4 exit #endif diff --git a/src/shader/videonv110.fpc b/src/shader/videonv110.fpc index 850163a..7560311 100644 --- a/src/shader/videonv110.fpc +++ b/src/shader/videonv110.fpc @@ -1,44 +1,44 @@ -0xfc0007e0, -0x001f8000, +0xe1a0070f, +0x003c3c01, 0xcff7ff02, 0xe003ff87, 0x00470202, 0x50800000, 0x0027ff00, 0xe043ff88, -0xfc0007e0, -0x001f8000, +0xe1e0072f, +0x003c3c03, 0x4027ff01, 0xe043ff88, 0x2ff70004, 0xc03a0004, 0x2ff70000, 0xc03a0016, -0xfc0007e0, -0x001f8000, +0xfc2007e6, +0x001f9800, 0x00070405, 0x4c681000, 0x00170503, 0x4c581000, 0x00270504, 0x4c581000, -0xfc0007e0, -0x001f8000, +0xfcc007e6, +0x001f8401, 0x00370505, 0x4c581000, 0x00470003, 0x49a00180, 0x00570004, 0x49a00200, -0xfc0007e0, -0x001f8000, +0xfc2007e1, +0x001f8400, 0x00670005, 0x49a00280, 0x00770100, 0x49a00180, 0x00970102, 0x49a00280, -0xfc0007e0, +0xfde007e6, 0x001f8000, 0x00870101, 0x49a00200, -- 2.11.0 </blockquote></div> </div>