maxwell,pascal: add scheduling data to shaders
PATCH 1/1 maxwell,pascal: add scheduling data to shaders
Generated with envysched. Tested by running rendercheck from piglit, running mplayer -vo xv, and staring at gnome-shell.
Signed-off-by Rhys Perry <[email protected]>
--- src/shader/exac8nv110.fp | 11 ++++---- src/shader/exac8nv110.fpc | 22 ++++++++-------- src/shader/exacanv110.fp | 11 ++++---- src/shader/exacanv110.fpc | 22 ++++++++-------- src/shader/exacmnv110.fp | 10 ++++---- src/shader/exacmnv110.fpc | 20 +++++++-------- src/shader/exas8nv110.fp | 10 +++++--- src/shader/exas8nv110.fpc | 20 +++++++++------ src/shader/exasanv110.fp | 11 ++++---- src/shader/exasanv110.fpc | 22 ++++++++-------- src/shader/exascnv110.fp | 8 +++--- src/shader/exascnv110.fpc | 16 +++++++----- src/shader/videonv110.fp | 16 +++++++----- src/shader/videonv110.fpc | 32 +++++++++++++---------- src/shader/xfrm2nv110.vp | 27 ++++++++++---------- src/shader/xfrm2nv110.vpc | 54 ++++++++++++++++++++------------------- 16 files changed, 171 insertions(+), 141 deletions(-)
src/shader/exac8nv110.fp +6 -5
@@ -25,23 +25,24 @@ NV110FP_Composite_A8[] = { }; #else -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0xf wr 0x0 wt 0x3f) (st 0xd wr 0x0 wt 0x1) (st 0x1 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 0x2 wr 0x1 rd 0x0 wt 0x3) (st 0x1 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 0x2) (st 0x1 wr 0x0 wt 0x5) (st 0xe) 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 wt 0x3f) (st 0x1) mov $r0 $r3 0xf exit +nop 0x0 #endif
src/shader/exac8nv110.fpc +12 -10
@@ -1,38 +1,40 @@ -0xfc0007e0, -0x001f8000, +0xe1a1ff0f, +0x003c0401, 0xcff7ff00, 0xe003ff87, 0x00470000, 0x50800000, 0x4007ff03, 0xe043ff89, -0xfc0007e0, -0x001f8000, +0x0440072f, +0x003c0403, 0x0007ff02, 0xe043ff89, 0x2ff70201, 0xc03a0014, 0x4007ff03, 0xe043ff88, -0xfc0007e0, -0x001f8000, +0xe020074f, +0x001fb805, 0x0007ff02, 0xe043ff88, 0x2ff70200, 0xc03a0004, 0x34070000, 0xf0f00000, -0xfc0007e0, -0x001f8000, +0xfc201fe6, +0x001f8400, 0x00170003, 0x5c681000, 0x00370002, 0x5c980780, 0x00370001, 0x5c980780, -0xfc0007e0, -0x001f8000, +0xfde007e1, +0x001f843f, 0x00370000, 0x5c980780, 0x0007000f, 0xe3000000, +0x00070f00, +0x50b00000,
src/shader/exacanv110.fp +6 -5
@@ -25,23 +25,24 @@ NV110FP_CAComposite[] = { }; #else -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0xf wr 0x0 wt 0x3f) (st 0xd wr 0x0 wt 0x1) (st 0x1 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 0x1 wr 0x1 rd 0x0 wt 0x3) (st 0x2 wr 0x3 rd 0x2) 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 0x2 wt 0x4) (st 0x1 wr 0x0 wt 0xd) (st 0xe) 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 wt 0x3f) (st 0x1) fmul ftz $r0 $r0 $r4 exit +nop 0x0 #endif
src/shader/exacanv110.fpc +12 -10
@@ -1,38 +1,40 @@ -0xfc0007e0, -0x001f8000, +0xe1a1ff0f, +0x003c0401, 0xcff7ff00, 0xe003ff87, 0x00470000, 0x50800000, 0x4007ff03, 0xe043ff89, -0xfc0007e0, -0x001f8000, +0x0420072f, +0x00098803, 0x0007ff02, 0xe043ff89, 0xaff70204, 0xc03a0017, 0x4007ff01, 0xe043ff88, -0xfc0007e0, -0x001f8000, +0xe020274f, +0x001fb80d, 0x0007ff00, 0xe043ff88, 0xaff70000, 0xc03a0007, 0x34070000, 0xf0f00000, -0xfc0007e0, -0x001f8000, +0xfc201fe1, +0x001f8400, 0x00770303, 0x5c681000, 0x00670202, 0x5c681000, 0x00570101, 0x5c681000, -0xfc0007e0, -0x001f8000, +0xfde007e1, +0x001f843f, 0x00470000, 0x5c681000, 0x0007000f, 0xe3000000, +0x00070f00, +0x50b00000,
src/shader/exacmnv110.fp +5 -5
@@ -25,23 +25,23 @@ NV110FP_Composite[] = { }; #else -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0xf wr 0x0 wt 0x3f) (st 0xd wr 0x0 wt 0x1) (st 0x1 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 0x1 wr 0x1 rd 0x0 wt 0x3) (st 0x2 wr 0x3 rd 0x2) 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 0x2 wt 0x4) (st 0x1 wr 0x0 wt 0xd) (st 0xe) 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 wt 0x3f) (st 0x1) fmul ftz $r0 $r0 $r4 exit #endif
src/shader/exacmnv110.fpc +10 -10
@@ -1,37 +1,37 @@ -0xfc0007e0, -0x001f8000, +0xe1a1ff0f, +0x003c0401, 0xcff7ff00, 0xe003ff87, 0x00470000, 0x50800000, 0x4007ff03, 0xe043ff89, -0xfc0007e0, -0x001f8000, +0x0420072f, +0x00098803, 0x0007ff02, 0xe043ff89, 0x2ff70204, 0xc03a0014, 0x4007ff01, 0xe043ff88, -0xfc0007e0, -0x001f8000, +0xe020274f, +0x001fb80d, 0x0007ff00, 0xe043ff88, 0xaff70000, 0xc03a0007, 0x34070000, 0xf0f00000, -0xfc0007e0, -0x001f8000, +0xfc201fe1, +0x001f8400, 0x00470303, 0x5c681000, 0x00470202, 0x5c681000, 0x00470101, 0x5c681000, -0xfc0007e0, -0x001f8000, +0xfde007e1, +0x001f843f, 0x00470000, 0x5c681000, 0x0007000f,
src/shader/exas8nv110.fp +6 -4
@@ -25,18 +25,20 @@ NV110FP_Source_A8[] = { }; #else -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0xf wr 0x0 wt 0x3f) (st 0xd wr 0x0 wt 0x1) (st 0x2 wr 0x1 rd 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 0x0 wt 0x1) (st 0x1 wr 0x0 wt 0x3) (st 0xe) 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 -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0xf wt 0x3f) (st 0x1) (st 0x1) exit +nop 0x0 +nop 0x0 #endif
src/shader/exas8nv110.fpc +12 -8
@@ -1,28 +1,32 @@ -0xfc0007e0, -0x001f8000, +0xe1a1ff0f, +0x00208801, 0xcff7ff00, 0xe003ff87, 0x00470000, 0x50800000, 0x4007ff01, 0xe043ff88, -0xfc0007e0, -0x001f8000, +0xe0200f0f, +0x001fb803, 0x0007ff00, 0xe043ff88, 0x2ff70000, 0xc03a0004, 0x34070000, 0xf0f00000, -0xfc0007e0, -0x001f8000, +0xfc200fe1, +0x001f8400, 0x00070003, 0x5c980780, 0x00070002, 0x5c980780, 0x00070001, 0x5c980780, -0xfc0007e0, -0x001f8000, +0xfc21ffef, +0x001f8400, 0x0007000f, 0xe3000000, +0x00070f00, +0x50b00000, +0x00070f00, +0x50b00000,
src/shader/exasanv110.fp +6 -5
@@ -25,23 +25,24 @@ NV110FP_CACompositeSrcAlpha[] = { }; #else -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0xf wr 0x0 wt 0x3f) (st 0xd wr 0x0 wt 0x1) (st 0x1 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 0x1 wr 0x1 rd 0x0 wt 0x3) (st 0x2 wr 0x3 rd 0x2) 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 0x2 wt 0x4) (st 0x1 wr 0x0 wt 0xd) (st 0xe) 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 wt 0x3f) (st 0x1) fmul ftz $r0 $r0 $r4 exit +nop 0x0 #endif
src/shader/exasanv110.fpc +12 -10
@@ -1,38 +1,40 @@ -0xfc0007e0, -0x001f8000, +0xe1a1ff0f, +0x003c0401, 0xcff7ff00, 0xe003ff87, 0x00470000, 0x50800000, 0x4007ff03, 0xe043ff88, -0xfc0007e0, -0x001f8000, +0x0420072f, +0x00098803, 0x0007ff02, 0xe043ff88, 0x2ff70204, 0xc03a0004, 0x4007ff01, 0xe043ff89, -0xfc0007e0, -0x001f8000, +0xe020274f, +0x001fb80d, 0x0007ff00, 0xe043ff89, 0xaff70000, 0xc03a0017, 0x34070000, 0xf0f00000, -0xfc0007e0, -0x001f8000, +0xfc201fe1, +0x001f8400, 0x00470303, 0x5c681000, 0x00470202, 0x5c681000, 0x00470101, 0x5c681000, -0xfc0007e0, -0x001f8000, +0xfde007e1, +0x001f843f, 0x00470000, 0x5c681000, 0x0007000f, 0xe3000000, +0x00070f00, +0x50b00000,
src/shader/exascnv110.fp +5 -3
@@ -25,14 +25,16 @@ NV110FP_Source[] = { }; #else -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0xf wr 0x0 wt 0x3f) (st 0xd wr 0x0 wt 0x1) (st 0x2 wr 0x1 rd 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 0x0 wt 0x1) (st 0x1 wt 0x3) (st 0x1) 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 wt 0x3f) (st 0x1) (st 0x1) exit +nop 0x0 +nop 0x0 #endif
src/shader/exascnv110.fpc +10 -6
@@ -1,20 +1,24 @@ -0xfc0007e0, -0x001f8000, +0xe1a1ff0f, +0x00208801, 0xcff7ff00, 0xe003ff87, 0x00470000, 0x50800000, 0x4007ff01, 0xe043ff88, -0xfc0007e0, -0x001f8000, +0xfc200f0f, +0x001f8403, 0x0007ff00, 0xe043ff88, 0xaff70000, 0xc03a0007, 0x34070000, 0xf0f00000, -0xfc0007e0, -0x001f8000, +0xfc21ffef, +0x001f8400, 0x0007000f, 0xe3000000, +0x00070f00, +0x50b00000, +0x00070f00, +0x50b00000,
src/shader/videonv110.fp +9 -7
@@ -25,30 +25,32 @@ NV110FP_NV12[] = { }; #else -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0xf wr 0x0 wt 0x3f) (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 0x0 wt 0x1) (st 0x2 wr 0x1 rd 0x0 wt 0x1) (st 0x1 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 0xd) (st 0x6 wt 0x2) (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 0x1) (st 0x1) (st 0x3) 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 0x1 wt 0x1) (st 0x1) (st 0x4) 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 0x2) (st 0x1) (st 0x1) 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 wt 0x3f) (st 0x1) (st 0x1) exit +nop 0x0 +nop 0x0 #endif
src/shader/videonv110.fpc +18 -14
@@ -1,52 +1,56 @@ -0xfc0007e0, -0x001f8000, +0xe1a1ff0f, +0x003c3c01, 0xcff7ff02, 0xe003ff87, 0x00470202, 0x50800000, 0x0027ff00, 0xe043ff88, -0xfc0007e0, -0x001f8000, +0x04400f0f, +0x003c0401, 0x4027ff01, 0xe043ff88, 0x2ff70004, 0xc03a0004, 0x2ff70000, 0xc03a0016, -0xfc0007e0, -0x001f8000, +0xfcc007ed, +0x001f8402, 0x34170001, 0xf0f00000, 0x00070405, 0x4c681000, 0x00170503, 0x4c581000, -0xfc0007e0, -0x001f8000, +0xfc2007e1, +0x001f8c00, 0x00270504, 0x4c581000, 0x00370505, 0x4c581000, 0x34070000, 0xf0f00000, -0xfc0007e0, -0x001f8000, +0xfc200fe1, +0x001f9000, 0x00470003, 0x49a00180, 0x00570004, 0x49a00200, 0x00670005, 0x49a00280, -0xfc0007e0, -0x001f8000, +0xfc2007e2, +0x001f8400, 0x00770100, 0x49a00180, 0x00970102, 0x49a00280, 0x00870101, 0x49a00200, -0xfc0007e0, -0x001f8000, +0xfc21ffef, +0x001f8400, 0x0007000f, 0xe3000000, +0x00070f00, +0x50b00000, +0x00070f00, +0x50b00000,
src/shader/xfrm2nv110.vp +14 -13
@@ -25,58 +25,59 @@ NV110VP_Transform2[] = { }; #else -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0xf wr 0x0 wt 0x3f) (st 0x6 wt 0x1) (st 0x1 wr 0x0) ld b32 $r5 a[0x2fc] 0x0 shl $r5 $r5 0x5 ld b64 $r0 c0[$r5+0x80] -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0xf wr 0x1) (st 0x2 rd 0x0 wt 0x3) (st 0xf wr 0x0 wt 0x1) ld b64 $r2 c0[$r5+0x88] st b128 a[0x70] $r0 0x0 ld b64 $r0 c0[$r5+0x90] -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0x1 wt 0x1) (st 0x1) (st 0x4) fmul ftz $r2 $r0 c0[0x0] fmul ftz $r3 $r0 c0[0xc] fmul ftz $r4 $r0 c0[0x18] -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0x1) (st 0x1) (st 0x4) ffma ftz $r2 $r1 c0[0x4] $r2 ffma ftz $r3 $r1 c0[0x10] $r3 ffma ftz $r4 $r1 c0[0x1c] $r4 -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0x1) (st 0x1) (st 0x6) fadd ftz $r2 $r2 c0[0x8] fadd ftz $r3 $r3 c0[0x14] fadd ftz $r4 $r4 c0[0x20] -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0xd wr 0x0) (st 0x1 wt 0x1) (st 0x5) mufu rcp $r4 $r4 fmul ftz $r2 $r2 $r4 fmul ftz $r3 $r3 $r4 -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0x1) (st 0x6) (st 0x2 rd 0x0) fmul ftz $r0 $r2 c0[0x24] fmul ftz $r1 $r3 c0[0x28] st b64 a[0x80] $r0 0x0 -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0xf wr 0x0 wt 0x1) (st 0x1 wt 0x1) (st 0x1) ld b64 $r0 c0[$r5+0x98] fmul ftz $r2 $r0 c0[0x2c] fmul ftz $r3 $r0 c0[0x38] -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0x4) (st 0x1) (st 0x1) fmul ftz $r4 $r0 c0[0x44] ffma ftz $r2 $r1 c0[0x30] $r2 ffma ftz $r3 $r1 c0[0x3c] $r3 -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0x4) (st 0x1) (st 0x1) ffma ftz $r4 $r1 c0[0x48] $r4 fadd ftz $r2 $r2 c0[0x34] fadd ftz $r3 $r3 c0[0x40] -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0x6) (st 0xd wr 0x0) (st 0x1 wt 0x1) fadd ftz $r4 $r4 c0[0x4c] mufu rcp $r4 $r4 fmul ftz $r2 $r2 $r4 -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0x5) (st 0x1) (st 0x6) fmul ftz $r3 $r3 $r4 fmul ftz $r0 $r2 c0[0x50] fmul ftz $r1 $r3 c0[0x54] -sched (st 0x0) (st 0x0) (st 0x0) +sched (st 0x1) (st 0xf wt 0x3f) (st 0x1) st b64 a[0x90] $r0 0x0 exit +nop 0x0 #endif
src/shader/xfrm2nv110.vpc +28 -26
130 lines not on this page · raw message
Signature · 6 lines
2.17.1 _______________________________________________ Nouveau mailing list [email protected] https://lists.freedesktop.org/mailman/listinfo/nouveau