Ilia Mirkin
2014-Sep-24 03:56 UTC
[Nouveau] [PATCH 1/2] allow path to envyas binary to be specified
Signed-off-by: Ilia Mirkin <imirkin at alum.mit.edu> --- src/shader/Makefile | 13 +++++++------ 1 file changed, 7 insertions(+), 6 deletions(-) diff --git a/src/shader/Makefile b/src/shader/Makefile index 46658e9..2d789be 100644 --- a/src/shader/Makefile +++ b/src/shader/Makefile @@ -24,20 +24,21 @@ NVF0_SHADERS = xfrm2nvf0.vpc \ videonvf0.fpc SHADERS = $(NVC0_SHADERS) $(NVE0_SHADERS) $(NVF0_SHADERS) +ENVYAS ?= envyas all: $(SHADERS) $(filter %nvc0.vpc,$(SHADERS)): %.vpc: %.vp - cpp -DENVYAS $< | sed -e '/^#/d' | envyas -w -m nvc0 -o $@ + cpp -DENVYAS $< | sed -e '/^#/d' | $(ENVYAS) -w -m nvc0 -o $@ $(filter %nvc0.fpc,$(SHADERS)): %.fpc: %.fp - cpp -DENVYAS $< | sed -e '/^#/d' | envyas -w -m nvc0 -o $@ + cpp -DENVYAS $< | sed -e '/^#/d' | $(ENVYAS) -w -m nvc0 -o $@ $(filter %nve0.vpc,$(SHADERS)): %.vpc: %.vp - cpp -DENVYAS $< | sed -e '/^#/d' | envyas -w -m nvc0 -V nve4 -o $@ + cpp -DENVYAS $< | sed -e '/^#/d' | $(ENVYAS) -w -m nvc0 -V nve4 -o $@ $(filter %nve0.fpc,$(SHADERS)): %.fpc: %.fp - cpp -DENVYAS $< | sed -e '/^#/d' | envyas -w -m nvc0 -V nve4 -o $@ + cpp -DENVYAS $< | sed -e '/^#/d' | $(ENVYAS) -w -m nvc0 -V nve4 -o $@ $(filter %nvf0.vpc,$(SHADERS)): %.vpc: %.vp - cpp -DENVYAS $< | sed -e '/^#/d' | envyas -w -m gk110 -o $@ + cpp -DENVYAS $< | sed -e '/^#/d' | $(ENVYAS) -w -m gk110 -o $@ $(filter %nvf0.fpc,$(SHADERS)): %.fpc: %.fp - cpp -DENVYAS $< | sed -e '/^#/d' | envyas -w -m gk110 -o $@ + cpp -DENVYAS $< | sed -e '/^#/d' | $(ENVYAS) -w -m gk110 -o $@ -- 1.8.5.5
Ilia Mirkin
2014-Sep-24 03:56 UTC
[Nouveau] [PATCH 2/2] kepler: remove unnecessary texbars, add live-only tex for nvf0
Signed-off-by: Ilia Mirkin <imirkin at alum.mit.edu> --- Noticed the texbars when looking at maxwell stuff, and nvf0 wouldn't even compile without the new flags, which I made to match the nve0 versions. Untested. src/shader/exac8nvf0.fp | 4 ++-- src/shader/exac8nvf0.fpc | 4 ++-- src/shader/exacanve0.fp | 1 - src/shader/exacanve0.fpc | 2 -- src/shader/exacanvf0.fp | 5 ++--- src/shader/exacanvf0.fpc | 6 ++---- src/shader/exacmnve0.fp | 1 - src/shader/exacmnve0.fpc | 2 -- src/shader/exacmnvf0.fp | 5 ++--- src/shader/exacmnvf0.fpc | 6 ++---- src/shader/exas8nvf0.fp | 2 +- src/shader/exas8nvf0.fpc | 2 +- src/shader/exasanve0.fp | 1 - src/shader/exasanve0.fpc | 2 -- src/shader/exasanvf0.fp | 5 ++--- src/shader/exasanvf0.fpc | 6 ++---- src/shader/exascnvf0.fp | 2 +- src/shader/exascnvf0.fpc | 2 +- src/shader/videonvf0.fp | 4 ++-- src/shader/videonvf0.fpc | 4 ++-- 20 files changed, 24 insertions(+), 42 deletions(-) diff --git a/src/shader/exac8nvf0.fp b/src/shader/exac8nvf0.fp index e4a7b04..f1c7fed 100644 --- a/src/shader/exac8nvf0.fp +++ b/src/shader/exac8nvf0.fp @@ -29,10 +29,10 @@ interp pass f32 $r0 a[0x7c] 0x0 0x0 0x0 rcp f32 $r0 $r0 interp mul f32 $r3 a[0x94] $r0 0x0 0x0 interp mul f32 $r2 a[0x90] $r0 0x0 0x0 -tex t lauto #:#:#:$r1 t2d c[0x4] xy__ $r2:$r3 0x0 +tex t lauto live dfp #:#:#:$r1 t2d c[0x4] xy__ $r2:$r3 0x0 interp mul f32 $r3 a[0x84] $r0 0x0 0x0 interp mul f32 $r2 a[0x80] $r0 0x0 0x0 -tex t lauto #:#:#:$r0 t2d c[0x0] xy__ $r2:$r3 0x0 +tex t lauto live dfp #:#:#:$r0 t2d c[0x0] xy__ $r2:$r3 0x0 texbar 0x0 mul ftz rn f32 $r3 $r0 $r1 mov b32 $r2 $r3 diff --git a/src/shader/exac8nvf0.fpc b/src/shader/exac8nvf0.fpc index 465cabf..7cfecb5 100644 --- a/src/shader/exac8nvf0.fpc +++ b/src/shader/exac8nvf0.fpc @@ -6,13 +6,13 @@ 0x74a3fc4a, 0x001ffc0a, 0x74a3fc48, -0x7f9c0805, +0xff9c0805, 0x600080a1, 0x001ffc0e, 0x74a3fc42, 0x001ffc0a, 0x74a3fc40, -0x7f9c0801, +0xff9c0801, 0x600000a1, 0x001c0002, 0x77000000, diff --git a/src/shader/exacanve0.fp b/src/shader/exacanve0.fp index edeb717..3928b6d 100644 --- a/src/shader/exacanve0.fp +++ b/src/shader/exacanve0.fp @@ -30,7 +30,6 @@ rcp f32 $r0 $r0 interp mul f32 $r3 a[0x94] $r0 0x0 interp mul f32 $r2 a[0x90] $r0 0x0 tex t lauto live dfp $r4:$r5:$r6:$r7 t2d $t1 $s0 $r2:$r3 () -texbar 0x0 interp mul f32 $r1 a[0x84] $r0 0x0 interp mul f32 $r0 a[0x80] $r0 0x0 tex t lauto live dfp $r0:$r1:$r2:$r3 t2d $t0 $s0 $r0:$r1 () diff --git a/src/shader/exacanve0.fpc b/src/shader/exacanve0.fpc index a8320f0..fa96dae 100644 --- a/src/shader/exacanve0.fpc +++ b/src/shader/exacanve0.fpc @@ -8,8 +8,6 @@ 0xc07e0090, 0x00211e86, 0x8013c001, -0x00001de6, -0xf0000000, 0x03f05c40, 0xc07e0084, 0x03f01c40, diff --git a/src/shader/exacanvf0.fp b/src/shader/exacanvf0.fp index 338a1e1..dddc22e 100644 --- a/src/shader/exacanvf0.fp +++ b/src/shader/exacanvf0.fp @@ -29,11 +29,10 @@ interp pass f32 $r0 a[0x7c] 0x0 0x0 0x0 rcp f32 $r0 $r0 interp mul f32 $r3 a[0x94] $r0 0x0 0x0 interp mul f32 $r2 a[0x90] $r0 0x0 0x0 -tex t lauto $r4:$r5:$r6:$r7 t2d c[0x4] xy__ $r2:$r3 0x0 -texbar 0x0 +tex t lauto live dfp $r4:$r5:$r6:$r7 t2d c[0x4] xy__ $r2:$r3 0x0 interp mul f32 $r1 a[0x84] $r0 0x0 0x0 interp mul f32 $r0 a[0x80] $r0 0x0 0x0 -tex t lauto $r0:$r1:$r2:$r3 t2d c[0x0] xy__ $r0:$r1 0x0 +tex t lauto live dfp $r0:$r1:$r2:$r3 t2d c[0x0] xy__ $r0:$r1 0x0 texbar 0x0 mul ftz rn f32 $r3 $r3 $r7 mul ftz rn f32 $r2 $r2 $r6 diff --git a/src/shader/exacanvf0.fpc b/src/shader/exacanvf0.fpc index 70dd4b1..793f15c 100644 --- a/src/shader/exacanvf0.fpc +++ b/src/shader/exacanvf0.fpc @@ -6,15 +6,13 @@ 0x74a3fc4a, 0x001ffc0a, 0x74a3fc48, -0x7f9c0811, +0xff9c0811, 0x600080bd, -0x001c0002, -0x77000000, 0x001ffc06, 0x74a3fc42, 0x001ffc02, 0x74a3fc40, -0x7f9c0001, +0xff9c0001, 0x600000bd, 0x001c0002, 0x77000000, diff --git a/src/shader/exacmnve0.fp b/src/shader/exacmnve0.fp index 09d22c1..71895f4 100644 --- a/src/shader/exacmnve0.fp +++ b/src/shader/exacmnve0.fp @@ -30,7 +30,6 @@ rcp f32 $r0 $r0 interp mul f32 $r3 a[0x94] $r0 0x0 interp mul f32 $r2 a[0x90] $r0 0x0 tex t lauto live dfp #:#:#:$r4 t2d $t1 $s0 $r2:$r3 () -texbar 0x0 interp mul f32 $r1 a[0x84] $r0 0x0 interp mul f32 $r0 a[0x80] $r0 0x0 tex t lauto live dfp $r0:$r1:$r2:$r3 t2d $t0 $s0 $r0:$r1 () diff --git a/src/shader/exacmnve0.fpc b/src/shader/exacmnve0.fpc index 5c2d4bf..2c256b1 100644 --- a/src/shader/exacmnve0.fpc +++ b/src/shader/exacmnve0.fpc @@ -8,8 +8,6 @@ 0xc07e0090, 0x00211e86, 0x80120001, -0x00001de6, -0xf0000000, 0x03f05c40, 0xc07e0084, 0x03f01c40, diff --git a/src/shader/exacmnvf0.fp b/src/shader/exacmnvf0.fp index 787b4f5..e52b7bd 100644 --- a/src/shader/exacmnvf0.fp +++ b/src/shader/exacmnvf0.fp @@ -29,11 +29,10 @@ interp pass f32 $r0 a[0x7c] 0x0 0x0 0x0 rcp f32 $r0 $r0 interp mul f32 $r3 a[0x94] $r0 0x0 0x0 interp mul f32 $r2 a[0x90] $r0 0x0 0x0 -tex t lauto #:#:#:$r4 t2d c[0x4] xy__ $r2:$r3 0x0 -texbar 0x0 +tex t lauto live dfp #:#:#:$r4 t2d c[0x4] xy__ $r2:$r3 0x0 interp mul f32 $r1 a[0x84] $r0 0x0 0x0 interp mul f32 $r0 a[0x80] $r0 0x0 0x0 -tex t lauto $r0:$r1:$r2:$r3 t2d c[0x0] xy__ $r0:$r1 0x0 +tex t lauto live dfp $r0:$r1:$r2:$r3 t2d c[0x0] xy__ $r0:$r1 0x0 texbar 0x0 mul ftz rn f32 $r3 $r3 $r4 mul ftz rn f32 $r2 $r2 $r4 diff --git a/src/shader/exacmnvf0.fpc b/src/shader/exacmnvf0.fpc index b2acf6f..4ec8a33 100644 --- a/src/shader/exacmnvf0.fpc +++ b/src/shader/exacmnvf0.fpc @@ -6,15 +6,13 @@ 0x74a3fc4a, 0x001ffc0a, 0x74a3fc48, -0x7f9c0811, +0xff9c0811, 0x600080a1, -0x001c0002, -0x77000000, 0x001ffc06, 0x74a3fc42, 0x001ffc02, 0x74a3fc40, -0x7f9c0001, +0xff9c0001, 0x600000bd, 0x001c0002, 0x77000000, diff --git a/src/shader/exas8nvf0.fp b/src/shader/exas8nvf0.fp index 3804b27..245262c 100644 --- a/src/shader/exas8nvf0.fp +++ b/src/shader/exas8nvf0.fp @@ -29,7 +29,7 @@ interp pass f32 $r0 a[0x7c] 0x0 0x0 0x0 rcp f32 $r0 $r0 interp mul f32 $r1 a[0x84] $r0 0x0 0x0 interp mul f32 $r0 a[0x80] $r0 0x0 0x0 -tex t lauto #:#:#:$r0 t2d c[0x0] xy__ $r0:$r1 0x0 +tex t lauto live dfp #:#:#:$r0 t2d c[0x0] xy__ $r0:$r1 0x0 texbar 0x0 mov b32 $r3 $r0 mov b32 $r2 $r0 diff --git a/src/shader/exas8nvf0.fpc b/src/shader/exas8nvf0.fpc index 4ec3bb7..a59ffe6 100644 --- a/src/shader/exas8nvf0.fpc +++ b/src/shader/exas8nvf0.fpc @@ -6,7 +6,7 @@ 0x74a3fc42, 0x001ffc02, 0x74a3fc40, -0x7f9c0001, +0xff9c0001, 0x600000a1, 0x001c0002, 0x77000000, diff --git a/src/shader/exasanve0.fp b/src/shader/exasanve0.fp index dea8eab..8ddcc4a 100644 --- a/src/shader/exasanve0.fp +++ b/src/shader/exasanve0.fp @@ -30,7 +30,6 @@ rcp f32 $r0 $r0 interp mul f32 $r3 a[0x84] $r0 0x0 interp mul f32 $r2 a[0x80] $r0 0x0 tex t lauto live dfp #:#:#:$r4 t2d $t0 $s0 $r2:$r3 () -texbar 0x0 interp mul f32 $r1 a[0x94] $r0 0x0 interp mul f32 $r0 a[0x90] $r0 0x0 tex t lauto live dfp $r0:$r1:$r2:$r3 t2d $t1 $s0 $r0:$r1 () diff --git a/src/shader/exasanve0.fpc b/src/shader/exasanve0.fpc index efc701e..170c5df 100644 --- a/src/shader/exasanve0.fpc +++ b/src/shader/exasanve0.fpc @@ -8,8 +8,6 @@ 0xc07e0080, 0x00211e86, 0x80120000, -0x00001de6, -0xf0000000, 0x03f05c40, 0xc07e0094, 0x03f01c40, diff --git a/src/shader/exasanvf0.fp b/src/shader/exasanvf0.fp index 8175f9b..c5c60a3 100644 --- a/src/shader/exasanvf0.fp +++ b/src/shader/exasanvf0.fp @@ -29,11 +29,10 @@ interp pass f32 $r0 a[0x7c] 0x0 0x0 0x0 rcp f32 $r0 $r0 interp mul f32 $r3 a[0x84] $r0 0x0 0x0 interp mul f32 $r2 a[0x80] $r0 0x0 0x0 -tex t lauto #:#:#:$r4 t2d c[0x0] xy__ $r2:$r3 0x0 -texbar 0x0 +tex t lauto live dfp #:#:#:$r4 t2d c[0x0] xy__ $r2:$r3 0x0 interp mul f32 $r1 a[0x94] $r0 0x0 0x0 interp mul f32 $r0 a[0x90] $r0 0x0 0x0 -tex t lauto $r0:$r1:$r2:$r3 t2d c[0x4] xy__ $r0:$r1 0x0 +tex t lauto live dfp $r0:$r1:$r2:$r3 t2d c[0x4] xy__ $r0:$r1 0x0 texbar 0x0 mul ftz rn f32 $r3 $r3 $r4 mul ftz rn f32 $r2 $r2 $r4 diff --git a/src/shader/exasanvf0.fpc b/src/shader/exasanvf0.fpc index 6e68d98..afddc84 100644 --- a/src/shader/exasanvf0.fpc +++ b/src/shader/exasanvf0.fpc @@ -6,15 +6,13 @@ 0x74a3fc42, 0x001ffc0a, 0x74a3fc40, -0x7f9c0811, +0xff9c0811, 0x600000a1, -0x001c0002, -0x77000000, 0x001ffc06, 0x74a3fc4a, 0x001ffc02, 0x74a3fc48, -0x7f9c0001, +0xff9c0001, 0x600080bd, 0x001c0002, 0x77000000, diff --git a/src/shader/exascnvf0.fp b/src/shader/exascnvf0.fp index e56c27f..447c67d 100644 --- a/src/shader/exascnvf0.fp +++ b/src/shader/exascnvf0.fp @@ -29,7 +29,7 @@ interp pass f32 $r0 a[0x7c] 0x0 0x0 0x0 rcp f32 $r0 $r0 interp mul f32 $r1 a[0x84] $r0 0x0 0x0 interp mul f32 $r0 a[0x80] $r0 0x0 0x0 -tex t lauto $r0:$r1:$r2:$r3 t2d c[0x0] xy__ $r0:$r1 0x0 +tex t lauto live dfp $r0:$r1:$r2:$r3 t2d c[0x0] xy__ $r0:$r1 0x0 texbar 0x0 exit #endif diff --git a/src/shader/exascnvf0.fpc b/src/shader/exascnvf0.fpc index 53af859..5d2dce6 100644 --- a/src/shader/exascnvf0.fpc +++ b/src/shader/exascnvf0.fpc @@ -6,7 +6,7 @@ 0x74a3fc42, 0x001ffc02, 0x74a3fc40, -0x7f9c0001, +0xff9c0001, 0x600000bd, 0x001c0002, 0x77000000, diff --git a/src/shader/videonvf0.fp b/src/shader/videonvf0.fp index a684203..3612dcd 100644 --- a/src/shader/videonvf0.fp +++ b/src/shader/videonvf0.fp @@ -29,8 +29,8 @@ interp pass f32 $r2 a[0x7c] 0x0 0x0 0x0 rcp f32 $r2 $r2 interp mul f32 $r0 a[0x80] $r2 0x0 0x0 interp mul f32 $r1 a[0x84] $r2 0x0 0x0 -tex t lauto #:#:#:$r4 t2d c[0x0] xy__ $r0:$r1 0x0 -tex p lauto #:#:$r0:$r1 t2d c[0x4] xy__ $r0:$r1 0x0 +tex t lauto live dfp #:#:#:$r4 t2d c[0x0] xy__ $r0:$r1 0x0 +tex p lauto live dfp #:#:$r0:$r1 t2d c[0x4] xy__ $r0:$r1 0x0 texbar 0x1 mul ftz rn f32 $r5 $r4 c0[0x0] add ftz rn f32 $r3 $r5 c0[0x4] diff --git a/src/shader/videonvf0.fpc b/src/shader/videonvf0.fpc index c545967..a7e5e98 100644 --- a/src/shader/videonvf0.fpc +++ b/src/shader/videonvf0.fpc @@ -6,9 +6,9 @@ 0x74a3fc40, 0x011ffc06, 0x74a3fc42, -0x7f9c0011, +0xff9c0011, 0x600000a1, -0x7f9c0001, +0xff9c0001, 0x600080b2, 0x009c0002, 0x77000000, -- 1.8.5.5
Possibly Parallel Threads
- [PATCH] exa: add GM10x acceleration support
- [PATCH v2 0/7] Add Maxwell support
- [LLVMdev] Modeling GPU vector registers, again (with my implementation)
- [LLVMdev] Determining the register type of a MachineOperand
- [LLVMdev] Determining the register type of a MachineOperand