exa: add GM10x acceleration support

rendercheck -f a8r8g8b8 passes as much as on a GK208, and xv appears to
work. Very lightly tested.

Instead of sticking coordinates into pushbufs, the vertex shader is
modified to read them from a constbuf, indexed by vertex id. This
approach could be used for all nvc0 generations, but I didn't want to
rock the boat.

Signed-off-by: Ilia Mirkin <imirkin@alum.mit.edu>
Reviewed-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>

26 files changed, 918 insertions, 19 deletions

diff --git a/src/Makefile.am b/src/Makefile.am
index 1e04ddf..6ba8d87 100644
--- a/src/Makefile.am
+++ b/src/Makefile.am
@@ -77,48 +77,64 @@ EXTRA_DIST = hwdefs/nv_3ddefs.xml.h \
 	     shader/exac8nve0.fpc \
 	     shader/exac8nvf0.fp \
 	     shader/exac8nvf0.fpc \
+	     shader/exac8nv110.fp \
+	     shader/exac8nv110.fpc \
 	     shader/exacanvc0.fp \
 	     shader/exacanvc0.fpc \
 	     shader/exacanve0.fp \
 	     shader/exacanve0.fpc \
 	     shader/exacanvf0.fp \
 	     shader/exacanvf0.fpc \
+	     shader/exacanv110.fp \
+	     shader/exacanv110.fpc \
 	     shader/exacmnvc0.fp \
 	     shader/exacmnvc0.fpc \
 	     shader/exacmnve0.fp \
 	     shader/exacmnve0.fpc \
 	     shader/exacmnvf0.fp \
 	     shader/exacmnvf0.fpc \
+	     shader/exacmnv110.fp \
+	     shader/exacmnv110.fpc \
 	     shader/exas8nvc0.fp \
 	     shader/exas8nvc0.fpc \
 	     shader/exas8nve0.fp \
 	     shader/exas8nve0.fpc \
 	     shader/exas8nvf0.fp \
 	     shader/exas8nvf0.fpc \
+	     shader/exas8nv110.fp \
+	     shader/exas8nv110.fpc \
 	     shader/exasanvc0.fp \
 	     shader/exasanvc0.fpc \
 	     shader/exasanve0.fp \
 	     shader/exasanve0.fpc \
 	     shader/exasanvf0.fp \
 	     shader/exasanvf0.fpc \
+	     shader/exasanv110.fp \
+	     shader/exasanv110.fpc \
 	     shader/exascnvc0.fp \
 	     shader/exascnvc0.fpc \
 	     shader/exascnve0.fp \
 	     shader/exascnve0.fpc \
 	     shader/exascnvf0.fp \
 	     shader/exascnvf0.fpc \
+	     shader/exascnv110.fp \
+	     shader/exascnv110.fpc \
 	     shader/videonvc0.fp \
 	     shader/videonvc0.fpc \
 	     shader/videonve0.fp \
 	     shader/videonve0.fpc \
 	     shader/videonvf0.fp \
 	     shader/videonvf0.fpc \
+	     shader/videonv110.fp \
+	     shader/videonv110.fpc \
 	     shader/xfrm2nvc0.vp \
 	     shader/xfrm2nvc0.vpc \
 	     shader/xfrm2nve0.vp \
 	     shader/xfrm2nve0.vpc \
 	     shader/xfrm2nvf0.vp \
 	     shader/xfrm2nvf0.vpc \
+	     shader/xfrm2nv110.vp \
+	     shader/xfrm2nv110.vpc \
 	     shader/Makefile \
 	     nouveau_local.h \
 	     nouveau_copy.h \
diff --git a/src/nouveau_copy.c b/src/nouveau_copy.c
index e152a53..c139de6 100644
--- a/src/nouveau_copy.c
+++ b/src/nouveau_copy.c
@@ -81,6 +81,7 @@ nouveau_copy_init(ScreenPtr pScreen)
 					 &pNv->ce_channel);
 		break;
 	case NV_KEPLER:
+	case NV_MAXWELL:
 		ret = nouveau_object_new(&pNv->dev->object, 0,
 					 NOUVEAU_FIFO_CHANNEL_CLASS,
 					 &(struct nve0_fifo) {
diff --git a/src/nouveau_exa.c b/src/nouveau_exa.c
index def66ac..0f02b99 100644
--- a/src/nouveau_exa.c
+++ b/src/nouveau_exa.c
@@ -514,12 +514,12 @@ nouveau_exa_init(ScreenPtr pScreen)
 		break;
 	case NV_FERMI:
 	case NV_KEPLER:
+	case NV_MAXWELL:
 		exa->CheckComposite   = NVC0EXACheckComposite;
 		exa->PrepareComposite = NVC0EXAPrepareComposite;
 		exa->Composite        = NVC0EXAComposite;
 		exa->DoneComposite    = NVC0EXADoneComposite;
 		break;
-	case NV_MAXWELL:
 	default:
 		break;
 	}
diff --git a/src/nouveau_xv.c b/src/nouveau_xv.c
index d514dbf..716b18d 100644
--- a/src/nouveau_xv.c
+++ b/src/nouveau_xv.c
@@ -2142,7 +2142,7 @@ NVSetupTexturedVideo (ScreenPtr pScreen, XF86VideoAdaptorPtr *textureAdaptor)
 		textureAdaptor[0] = NV40SetupTexturedVideo(pScreen, FALSE);
 		textureAdaptor[1] = NV40SetupTexturedVideo(pScreen, TRUE);
 	} else
-	if (pNv->Architecture >= NV_TESLA && pNv->Architecture < NV_MAXWELL) {
+	if (pNv->Architecture >= NV_TESLA) {
 		textureAdaptor[0] = NV50SetupTexturedVideo(pScreen);
 	}
 }
diff --git a/src/nv_accel_common.c b/src/nv_accel_common.c
index 9361ce8..5d12dd8 100644
--- a/src/nv_accel_common.c
+++ b/src/nv_accel_common.c
@@ -722,6 +722,7 @@ NVAccelCommonInit(ScrnInfoPtr pScrn)
 	switch (pNv->Architecture) {
 	case NV_FERMI:
 	case NV_KEPLER:
+	case NV_MAXWELL:
 		INIT_CONTEXT_OBJECT(3D_NVC0);
 		break;
 	case NV_TESLA:
diff --git a/src/nv_driver.c b/src/nv_driver.c
index 4dde8e0..fff83f8 100644
--- a/src/nv_driver.c
+++ b/src/nv_driver.c
@@ -389,6 +389,7 @@ NVHasKMS(struct pci_device *pci_dev, struct xf86_platform_device *platform_dev)
 	case 0xe0:
 	case 0xf0:
 	case 0x100:
+	case 0x110:
 		break;
 	default:
 		xf86DrvMsg(-1, X_ERROR, "Unknown chipset: NV%02X\n", chipset);
diff --git a/src/nvc0_accel.c b/src/nvc0_accel.c
index d2a3b93..52a17db 100644
--- a/src/nvc0_accel.c
+++ b/src/nvc0_accel.c
@@ -53,6 +53,16 @@
 #include "shader/exas8nvf0.fp"
 #include "shader/exac8nvf0.fp"
 
+#include "shader/xfrm2nv110.vp"
+#include "shader/videonv110.fp"
+
+#include "shader/exascnv110.fp"
+#include "shader/exacmnv110.fp"
+#include "shader/exacanv110.fp"
+#include "shader/exasanv110.fp"
+#include "shader/exas8nv110.fp"
+#include "shader/exac8nv110.fp"
+
 #define NVC0PushProgram(pNv,addr,code) do {                                    \
 	const unsigned size = sizeof(code) / sizeof(code[0]);                  \
 	PUSH_DATAu((pNv)->pushbuf, (pNv)->scratch, (addr), size);              \
@@ -223,9 +233,12 @@ NVAccelInit3D_NVC0(ScrnInfoPtr pScrn)
 	} else if (pNv->dev->chipset < 0xf0) {
 		class  = 0xa097;
 		handle = 0x0000906e;
-	} else {
+	} else if (pNv->dev->chipset < 0x110) {
 		class  = 0xa197;
 		handle = 0x0000906e;
+	} else {
+		class  = 0xb097;
+		handle = 0x0000906e;
 	}
 
 	ret = nouveau_object_new(pNv->channel, class, class,
@@ -304,10 +317,12 @@ NVAccelInit3D_NVC0(ScrnInfoPtr pScrn)
 		PUSH_DATA (push, 1);
 	}
 
-	BEGIN_NVC0(push, NVC0_3D(VERTEX_QUARANTINE_ADDRESS_HIGH), 3);
-	PUSH_DATA (push, (bo->offset + MISC_OFFSET) >> 32);
-	PUSH_DATA (push, (bo->offset + MISC_OFFSET));
-	PUSH_DATA (push, 1);
+	if (pNv->Architecture < NV_MAXWELL) {
+		BEGIN_NVC0(push, NVC0_3D(VERTEX_QUARANTINE_ADDRESS_HIGH), 3);
+		PUSH_DATA (push, (bo->offset + MISC_OFFSET) >> 32);
+		PUSH_DATA (push, (bo->offset + MISC_OFFSET));
+		PUSH_DATA (push, 1);
+	}
 
 	BEGIN_NVC0(push, NVC0_3D(CODE_ADDRESS_HIGH), 2);
 	PUSH_DATA (push, (bo->offset + CODE_OFFSET) >> 32);
@@ -334,7 +349,8 @@ NVAccelInit3D_NVC0(ScrnInfoPtr pScrn)
 		NVC0PushProgram(pNv, PFP_S_A8, NVE0FP_Source_A8);
 		NVC0PushProgram(pNv, PFP_C_A8, NVE0FP_Composite_A8);
 		NVC0PushProgram(pNv, PFP_NV12, NVE0FP_NV12);
-	} else {
+	} else
+	if (pNv->dev->chipset < 0x110) {
 		NVC0PushProgram(pNv, PVP_PASS, NVF0VP_Transform2);
 		NVC0PushProgram(pNv, PFP_S, NVF0FP_Source);
 		NVC0PushProgram(pNv, PFP_C, NVF0FP_Composite);
@@ -343,6 +359,15 @@ NVAccelInit3D_NVC0(ScrnInfoPtr pScrn)
 		NVC0PushProgram(pNv, PFP_S_A8, NVF0FP_Source_A8);
 		NVC0PushProgram(pNv, PFP_C_A8, NVF0FP_Composite_A8);
 		NVC0PushProgram(pNv, PFP_NV12, NVF0FP_NV12);
+	} else {
+		NVC0PushProgram(pNv, PVP_PASS, NV110VP_Transform2);
+		NVC0PushProgram(pNv, PFP_S, NV110FP_Source);
+		NVC0PushProgram(pNv, PFP_C, NV110FP_Composite);
+		NVC0PushProgram(pNv, PFP_CCA, NV110FP_CAComposite);
+		NVC0PushProgram(pNv, PFP_CCASA, NV110FP_CACompositeSrcAlpha);
+		NVC0PushProgram(pNv, PFP_S_A8, NV110FP_Source_A8);
+		NVC0PushProgram(pNv, PFP_C_A8, NV110FP_Composite_A8);
+		NVC0PushProgram(pNv, PFP_NV12, NV110FP_NV12);
 	}
 
 	BEGIN_NVC0(push, NVC0_3D(SP_SELECT(1)), 4);
diff --git a/src/nvc0_exa.c b/src/nvc0_exa.c
index 6add60b..d3fd316 100644
--- a/src/nvc0_exa.c
+++ b/src/nvc0_exa.c
@@ -914,14 +914,56 @@ NVC0EXAComposite(PixmapPtr pdpix,
 	if (!PUSH_SPACE(push, 64))
 		return;
 
+	if (pNv->dev->chipset >= 0x110) {
+		BEGIN_NVC0(push, NVC0_3D(CB_SIZE), 3);
+		PUSH_DATA (push, 256);
+		PUSH_DATA (push, (pNv->scratch->offset + PVP_DATA) >> 32);
+		PUSH_DATA (push, (pNv->scratch->offset + PVP_DATA));
+		BEGIN_1IC0(push, NVC0_3D(CB_POS), 24 + 1);
+		PUSH_DATA (push, 0x80);
+
+		PUSH_DATAf(push, dx);
+		PUSH_DATAf(push, dy + (h * 2));
+		PUSH_DATAf(push, 0);
+		PUSH_DATAf(push, 1);
+		PUSH_DATAf(push, sx);
+		PUSH_DATAf(push, sy + (h * 2));
+		PUSH_DATAf(push, mx);
+		PUSH_DATAf(push, my + (h * 2));
+
+		PUSH_DATAf(push, dx);
+		PUSH_DATAf(push, dy);
+		PUSH_DATAf(push, 0);
+		PUSH_DATAf(push, 1);
+		PUSH_DATAf(push, sx);
+		PUSH_DATAf(push, sy);
+		PUSH_DATAf(push, mx);
+		PUSH_DATAf(push, my);
+
+		PUSH_DATAf(push, dx + (w * 2));
+		PUSH_DATAf(push, dy);
+		PUSH_DATAf(push, 0);
+		PUSH_DATAf(push, 1);
+		PUSH_DATAf(push, sx + (w * 2));
+		PUSH_DATAf(push, sy);
+		PUSH_DATAf(push, mx + (w * 2));
+		PUSH_DATAf(push, my);
+	}
+
 	BEGIN_NVC0(push, NVC0_3D(SCISSOR_HORIZ(0)), 2);
 	PUSH_DATA (push, ((dx + w) << 16) | dx);
 	PUSH_DATA (push, ((dy + h) << 16) | dy);
 	BEGIN_NVC0(push, NVC0_3D(VERTEX_BEGIN_GL), 1);
 	PUSH_DATA (push, NVC0_3D_VERTEX_BEGIN_GL_PRIMITIVE_TRIANGLES);
-	PUSH_VTX2s(push, sx, sy + (h * 2), mx, my + (h * 2), dx, dy + (h * 2));
-	PUSH_VTX2s(push, sx, sy, mx, my, dx, dy);
-	PUSH_VTX2s(push, sx + (w * 2), sy, mx + (w * 2), my, dx + (w * 2), dy);
+	if (pNv->dev->chipset < 0x110) {
+		PUSH_VTX2s(push, sx, sy + (h * 2), mx, my + (h * 2), dx, dy + (h * 2));
+		PUSH_VTX2s(push, sx, sy, mx, my, dx, dy);
+		PUSH_VTX2s(push, sx + (w * 2), sy, mx + (w * 2), my, dx + (w * 2), dy);
+	} else {
+		BEGIN_NVC0(push, NVC0_3D(VERTEX_BUFFER_FIRST), 2);
+		PUSH_DATA (push, 0);
+		PUSH_DATA (push, 3);
+	}
 	BEGIN_NVC0(push, NVC0_3D(VERTEX_END_GL), 1);
 	PUSH_DATA (push, 0);
 }
diff --git a/src/nvc0_xv.c b/src/nvc0_xv.c
index d1d8f18..2d66fa8 100644
--- a/src/nvc0_xv.c
+++ b/src/nvc0_xv.c
@@ -247,15 +247,57 @@ nvc0_xv_image_put(ScrnInfoPtr pScrn,
 		    nouveau_pushbuf_refn (push, refs, 3))
 			return BadImplementation;
 
+		if (pNv->dev->chipset >= 0x110) {
+			BEGIN_NVC0(push, NVC0_3D(CB_SIZE), 3);
+			PUSH_DATA (push, 256);
+			PUSH_DATA (push, (pNv->scratch->offset + PVP_DATA) >> 32);
+			PUSH_DATA (push, (pNv->scratch->offset + PVP_DATA));
+			BEGIN_1IC0(push, NVC0_3D(CB_POS), 24 + 1);
+			PUSH_DATA (push, 0x80);
+
+			PUSH_DATAf(push, sx1);
+			PUSH_DATAf(push, sy1);
+			PUSH_DATAf(push, 0);
+			PUSH_DATAf(push, 1);
+			PUSH_DATAf(push, tx1);
+			PUSH_DATAf(push, ty1);
+			PUSH_DATAf(push, 0);
+			PUSH_DATAf(push, 0);
+
+			PUSH_DATAf(push, sx2+(sx2-sx1));
+			PUSH_DATAf(push, sy1);
+			PUSH_DATAf(push, 0);
+			PUSH_DATAf(push, 1);
+			PUSH_DATAf(push, tx2+(tx2-tx1));
+			PUSH_DATAf(push, ty1);
+			PUSH_DATAf(push, 0);
+			PUSH_DATAf(push, 0);
+
+			PUSH_DATAf(push, sx1);
+			PUSH_DATAf(push, sy2+(sy2-sy1));
+			PUSH_DATAf(push, 0);
+			PUSH_DATAf(push, 1);
+			PUSH_DATAf(push, tx1);
+			PUSH_DATAf(push, ty2+(ty2-ty1));
+			PUSH_DATAf(push, 0);
+			PUSH_DATAf(push, 0);
+		}
+
 		BEGIN_NVC0(push, NVC0_3D(SCISSOR_HORIZ(0)), 2);
 		PUSH_DATA (push, sx2 << NVC0_3D_SCISSOR_HORIZ_MAX__SHIFT | sx1);
 		PUSH_DATA (push, sy2 << NVC0_3D_SCISSOR_VERT_MAX__SHIFT | sy1 );
 
 		BEGIN_NVC0(push, NVC0_3D(VERTEX_BEGIN_GL), 1);
 		PUSH_DATA (push, NVC0_3D_VERTEX_BEGIN_GL_PRIMITIVE_TRIANGLES);
-		PUSH_VTX1s(push, tx1, ty1, sx1, sy1);
-		PUSH_VTX1s(push, tx2+(tx2-tx1), ty1, sx2+(sx2-sx1), sy1);
-		PUSH_VTX1s(push, tx1, ty2+(ty2-ty1), sx1, sy2+(sy2-sy1));
+		if (pNv->dev->chipset < 0x110) {
+			PUSH_VTX1s(push, tx1, ty1, sx1, sy1);
+			PUSH_VTX1s(push, tx2+(tx2-tx1), ty1, sx2+(sx2-sx1), sy1);
+			PUSH_VTX1s(push, tx1, ty2+(ty2-ty1), sx1, sy2+(sy2-sy1));
+		} else {
+			BEGIN_NVC0(push, NVC0_3D(VERTEX_BUFFER_FIRST), 2);
+			PUSH_DATA (push, 0);
+			PUSH_DATA (push, 3);
+		}
 		BEGIN_NVC0(push, NVC0_3D(VERTEX_END_GL), 1);
 		PUSH_DATA (push, 0);
 
diff --git a/src/shader/Makefile b/src/shader/Makefile
index 2d789be..12bf455 100644
--- a/src/shader/Makefile
+++ b/src/shader/Makefile
@@ -22,23 +22,36 @@ NVF0_SHADERS = xfrm2nvf0.vpc \
 	       exas8nvf0.fpc \
 	       exac8nvf0.fpc \
 	       videonvf0.fpc
+NV110_SHADERS = xfrm2nv110.vpc \
+	       exascnv110.fpc \
+	       exacmnv110.fpc \
+	       exacanv110.fpc \
+	       exasanv110.fpc \
+	       exas8nv110.fpc \
+	       exac8nv110.fpc \
+	       videonv110.fpc
 
-SHADERS = $(NVC0_SHADERS) $(NVE0_SHADERS) $(NVF0_SHADERS)
+SHADERS = $(NVC0_SHADERS) $(NVE0_SHADERS) $(NVF0_SHADERS) $(NV110_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 gf100 -V gf100 -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 gf100 -V gf100 -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 gf100 -V gk104 -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 gf100 -V gk104 -o $@
 
 $(filter %nvf0.vpc,$(SHADERS)): %.vpc: %.vp
 	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 $@
+
+$(filter %nv110.vpc,$(SHADERS)): %.vpc: %.vp
+	cpp -DENVYAS $< | sed -e '/^#/d' | $(ENVYAS) -w -m gm107 -o $@
+$(filter %nv110.fpc,$(SHADERS)): %.fpc: %.fp
+	cpp -DENVYAS $< | sed -e '/^#/d' | $(ENVYAS) -w -m gm107 -o $@
diff --git a/src/shader/exac8nv110.fp b/src/shader/exac8nv110.fp
new file mode 100644
index 0000000..ce78036
--- /dev/null
+++ b/src/shader/exac8nv110.fp
@@ -0,0 +1,47 @@
+#ifndef ENVYAS
+static uint32_t
+NV110FP_Composite_A8[] = {
+	0x00001462,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x80000000,
+	0x00000a0a,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x0000000f,
+	0x00000000,
+#include "exac8nv110.fpc"
+};
+#else
+
+sched (st 0x0) (st 0x0) (st 0x0)
+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)
+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)
+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)
+fmul ftz $r3 $r0 $r1
+mov $r2 $r3 0xf
+mov $r1 $r3 0xf
+sched (st 0x0) (st 0x0) (st 0x0)
+mov $r0 $r3 0xf
+exit
+#endif
diff --git a/src/shader/exac8nv110.fpc b/src/shader/exac8nv110.fpc
new file mode 100644
index 0000000..4aa1368
--- /dev/null
+++ b/src/shader/exac8nv110.fpc
@@ -0,0 +1,38 @@
+0xfc0007e0,
+0x001f8000,
+0xcff7ff00,
+0xe003ff87,
+0x00470000,
+0x50800000,
+0x4007ff03,
+0xe043ff89,
+0xfc0007e0,
+0x001f8000,
+0x0007ff02,
+0xe043ff89,
+0x2ff70201,
+0xc03a0014,
+0x4007ff03,
+0xe043ff88,
+0xfc0007e0,
+0x001f8000,
+0x0007ff02,
+0xe043ff88,
+0x2ff70200,
+0xc03a0004,
+0x34070000,
+0xf0f00000,
+0xfc0007e0,
+0x001f8000,
+0x00170003,
+0x5c681000,
+0x00370002,
+0x5c980780,
+0x00370001,
+0x5c980780,
+0xfc0007e0,
+0x001f8000,
+0x00370000,
+0x5c980780,
+0x0007000f,
+0xe3000000,
diff --git a/src/shader/exacanv110.fp b/src/shader/exacanv110.fp
new file mode 100644
index 0000000..a70d5c5
--- /dev/null
+++ b/src/shader/exacanv110.fp
@@ -0,0 +1,47 @@
+#ifndef ENVYAS
+static uint32_t
+NV110FP_CAComposite[] = {
+	0x00001462, /* 0x0000c000 = USES_KIL, MULTI_COLORS */
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x80000000, /* FRAG_COORD_UMASK = 0x8 */
+	0x00000a0a, /* FP_INTERP[0x080], 0022 0022 */
+	0x00000000, /* FP_INTERP[0x0c0], 0 = OFF */
+	0x00000000, /* FP_INTERP[0x100], 1 = FLAT */
+	0x00000000, /* FP_INTERP[0x140], 2 = PERSPECTIVE */
+	0x00000000, /* FP_INTERP[0x180], 3 = LINEAR */
+	0x00000000, /* FP_INTERP[0x1c0] */
+	0x00000000, /* FP_INTERP[0x200] */
+	0x00000000, /* FP_INTERP[0x240] */
+	0x00000000, /* FP_INTERP[0x280] */
+	0x00000000, /* FP_INTERP[0x2c0] */
+	0x00000000, /* FP_INTERP[0x300] */
+	0x00000000,
+	0x0000000f, /* FP_RESULT_MASK (0x8000 Face ?) */
+	0x00000000, /* 0x2 = FragDepth, 0x1 = SampleMask */
+#include "exacanv110.fpc"
+};
+#else
+
+sched (st 0x0) (st 0x0) (st 0x0)
+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)
+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)
+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)
+fmul ftz $r3 $r3 $r7
+fmul ftz $r2 $r2 $r6
+fmul ftz $r1 $r1 $r5
+sched (st 0x0) (st 0x0) (st 0x0)
+fmul ftz $r0 $r0 $r4
+exit
+#endif
diff --git a/src/shader/exacanv110.fpc b/src/shader/exacanv110.fpc
new file mode 100644
index 0000000..7c0ca5e
--- /dev/null
+++ b/src/shader/exacanv110.fpc
@@ -0,0 +1,38 @@
+0xfc0007e0,
+0x001f8000,
+0xcff7ff00,
+0xe003ff87,
+0x00470000,
+0x50800000,
+0x4007ff03,
+0xe043ff89,
+0xfc0007e0,
+0x001f8000,
+0x0007ff02,
+0xe043ff89,
+0xaff70204,
+0xc03a0017,
+0x4007ff01,
+0xe043ff88,
+0xfc0007e0,
+0x001f8000,
+0x0007ff00,
+0xe043ff88,
+0xaff70000,
+0xc03a0007,
+0x34070000,
+0xf0f00000,
+0xfc0007e0,
+0x001f8000,
+0x00770303,
+0x5c681000,
+0x00670202,
+0x5c681000,
+0x00570101,
+0x5c681000,
+0xfc0007e0,
+0x001f8000,
+0x00470000,
+0x5c681000,
+0x0007000f,
+0xe3000000,
diff --git a/src/shader/exacmnv110.fp b/src/shader/exacmnv110.fp
new file mode 100644
index 0000000..fe5c294
--- /dev/null
+++ b/src/shader/exacmnv110.fp
@@ -0,0 +1,47 @@
+#ifndef ENVYAS
+static uint32_t
+NV110FP_Composite[] = {
+	0x00001462,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x80000000,
+	0x00000a0a,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x0000000f,
+	0x00000000,
+#include "exacmnv110.fpc"
+};
+#else
+
+sched (st 0x0) (st 0x0) (st 0x0)
+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)
+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)
+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)
+fmul ftz $r3 $r3 $r4
+fmul ftz $r2 $r2 $r4
+fmul ftz $r1 $r1 $r4
+sched (st 0x0) (st 0x0) (st 0x0)
+fmul ftz $r0 $r0 $r4
+exit
+#endif
diff --git a/src/shader/exacmnv110.fpc b/src/shader/exacmnv110.fpc
new file mode 100644
index 0000000..9d62c1a
--- /dev/null
+++ b/src/shader/exacmnv110.fpc
@@ -0,0 +1,38 @@
+0xfc0007e0,
+0x001f8000,
+0xcff7ff00,
+0xe003ff87,
+0x00470000,
+0x50800000,
+0x4007ff03,
+0xe043ff89,
+0xfc0007e0,
+0x001f8000,
+0x0007ff02,
+0xe043ff89,
+0x2ff70204,
+0xc03a0014,
+0x4007ff01,
+0xe043ff88,
+0xfc0007e0,
+0x001f8000,
+0x0007ff00,
+0xe043ff88,
+0xaff70000,
+0xc03a0007,
+0x34070000,
+0xf0f00000,
+0xfc0007e0,
+0x001f8000,
+0x00470303,
+0x5c681000,
+0x00470202,
+0x5c681000,
+0x00470101,
+0x5c681000,
+0xfc0007e0,
+0x001f8000,
+0x00470000,
+0x5c681000,
+0x0007000f,
+0xe3000000,
diff --git a/src/shader/exas8nv110.fp b/src/shader/exas8nv110.fp
new file mode 100644
index 0000000..4fe2e19
--- /dev/null
+++ b/src/shader/exas8nv110.fp
@@ -0,0 +1,42 @@
+#ifndef ENVYAS
+static uint32_t
+NV110FP_Source_A8[] = {
+	0x00001462,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x80000000,
+	0x0000000a,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x0000000f,
+	0x00000000,
+#include "exas8nv110.fpc"
+};
+#else
+
+sched (st 0x0) (st 0x0) (st 0x0)
+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)
+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)
+mov $r3 $r0 0xf
+mov $r2 $r0 0xf
+mov $r1 $r0 0xf
+sched (st 0x0) (st 0x0) (st 0x0)
+exit
+#endif
diff --git a/src/shader/exas8nv110.fpc b/src/shader/exas8nv110.fpc
new file mode 100644
index 0000000..1181c41
--- /dev/null
+++ b/src/shader/exas8nv110.fpc
@@ -0,0 +1,28 @@
+0xfc0007e0,
+0x001f8000,
+0xcff7ff00,
+0xe003ff87,
+0x00470000,
+0x50800000,
+0x4007ff01,
+0xe043ff88,
+0xfc0007e0,
+0x001f8000,
+0x0007ff00,
+0xe043ff88,
+0x2ff70000,
+0xc03a0004,
+0x34070000,
+0xf0f00000,
+0xfc0007e0,
+0x001f8000,
+0x00070003,
+0x5c980780,
+0x00070002,
+0x5c980780,
+0x00070001,
+0x5c980780,
+0xfc0007e0,
+0x001f8000,
+0x0007000f,
+0xe3000000,
diff --git a/src/shader/exasanv110.fp b/src/shader/exasanv110.fp
new file mode 100644
index 0000000..61374a6
--- /dev/null
+++ b/src/shader/exasanv110.fp
@@ -0,0 +1,47 @@
+#ifndef ENVYAS
+static uint32_t
+NV110FP_CACompositeSrcAlpha[] = {
+	0x00001462,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x80000000,
+	0x00000a0a,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x0000000f,
+	0x00000000,
+#include "exasanv110.fpc"
+};
+#else
+
+sched (st 0x0) (st 0x0) (st 0x0)
+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)
+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)
+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)
+fmul ftz $r3 $r3 $r4
+fmul ftz $r2 $r2 $r4
+fmul ftz $r1 $r1 $r4
+sched (st 0x0) (st 0x0) (st 0x0)
+fmul ftz $r0 $r0 $r4
+exit
+#endif
diff --git a/src/shader/exasanv110.fpc b/src/shader/exasanv110.fpc
new file mode 100644
index 0000000..5516a03
--- /dev/null
+++ b/src/shader/exasanv110.fpc
@@ -0,0 +1,38 @@
+0xfc0007e0,
+0x001f8000,
+0xcff7ff00,
+0xe003ff87,
+0x00470000,
+0x50800000,
+0x4007ff03,
+0xe043ff88,
+0xfc0007e0,
+0x001f8000,
+0x0007ff02,
+0xe043ff88,
+0x2ff70204,
+0xc03a0004,
+0x4007ff01,
+0xe043ff89,
+0xfc0007e0,
+0x001f8000,
+0x0007ff00,
+0xe043ff89,
+0xaff70000,
+0xc03a0017,
+0x34070000,
+0xf0f00000,
+0xfc0007e0,
+0x001f8000,
+0x00470303,
+0x5c681000,
+0x00470202,
+0x5c681000,
+0x00470101,
+0x5c681000,
+0xfc0007e0,
+0x001f8000,
+0x00470000,
+0x5c681000,
+0x0007000f,
+0xe3000000,
diff --git a/src/shader/exascnv110.fp b/src/shader/exascnv110.fp
new file mode 100644
index 0000000..90bbb55
--- /dev/null
+++ b/src/shader/exascnv110.fp
@@ -0,0 +1,38 @@
+#ifndef ENVYAS
+static uint32_t
+NV110FP_Source[] = {
+	0x00001462,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x80000000,
+	0x0000000a,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x0000000f,
+	0x00000000,
+#include "exascnv110.fpc"
+};
+#else
+
+sched (st 0x0) (st 0x0) (st 0x0)
+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)
+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)
+exit
+#endif
diff --git a/src/shader/exascnv110.fpc b/src/shader/exascnv110.fpc
new file mode 100644
index 0000000..2dba15d
--- /dev/null
+++ b/src/shader/exascnv110.fpc
@@ -0,0 +1,20 @@
+0xfc0007e0,
+0x001f8000,
+0xcff7ff00,
+0xe003ff87,
+0x00470000,
+0x50800000,
+0x4007ff01,
+0xe043ff88,
+0xfc0007e0,
+0x001f8000,
+0x0007ff00,
+0xe043ff88,
+0xaff70000,
+0xc03a0007,
+0x34070000,
+0xf0f00000,
+0xfc0007e0,
+0x001f8000,
+0x0007000f,
+0xe3000000,
diff --git a/src/shader/videonv110.fp b/src/shader/videonv110.fp
new file mode 100644
index 0000000..2728311
--- /dev/null
+++ b/src/shader/videonv110.fp
@@ -0,0 +1,54 @@
+#ifndef ENVYAS
+static uint32_t
+NV110FP_NV12[] = {
+	0x00001462,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x80000000,
+	0x0000000a,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x0000000f,
+	0x00000000,
+#include "videonv110.fpc"
+};
+#else
+
+sched (st 0x0) (st 0x0) (st 0x0)
+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)
+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)
+depbar le 0x5 0x1 0x1
+fmul ftz $r5 $r4 c0[0x0]
+fadd ftz $r3 $r5 c0[0x4]
+sched (st 0x0) (st 0x0) (st 0x0)
+fadd ftz $r4 $r5 c0[0x8]
+fadd ftz $r5 $r5 c0[0xc]
+depbar le 0x5 0x0 0x0
+sched (st 0x0) (st 0x0) (st 0x0)
+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)
+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)
+exit
+#endif
diff --git a/src/shader/videonv110.fpc b/src/shader/videonv110.fpc
new file mode 100644
index 0000000..31d745a
--- /dev/null
+++ b/src/shader/videonv110.fpc
@@ -0,0 +1,52 @@
+0xfc0007e0,
+0x001f8000,
+0xcff7ff02,
+0xe003ff87,
+0x00470202,
+0x50800000,
+0x0027ff00,
+0xe043ff88,
+0xfc0007e0,
+0x001f8000,
+0x4027ff01,
+0xe043ff88,
+0x2ff70004,
+0xc03a0004,
+0x2ff70000,
+0xc03a0016,
+0xfc0007e0,
+0x001f8000,
+0x34170001,
+0xf0f00000,
+0x00070405,
+0x4c681000,
+0x00170503,
+0x4c581000,
+0xfc0007e0,
+0x001f8000,
+0x00270504,
+0x4c581000,
+0x00370505,
+0x4c581000,
+0x34070000,
+0xf0f00000,
+0xfc0007e0,
+0x001f8000,
+0x00470003,
+0x49a00180,
+0x00570004,
+0x49a00200,
+0x00670005,
+0x49a00280,
+0xfc0007e0,
+0x001f8000,
+0x00770100,
+0x49a00180,
+0x00970102,
+0x49a00280,
+0x00870101,
+0x49a00200,
+0xfc0007e0,
+0x001f8000,
+0x0007000f,
+0xe3000000,
diff --git a/src/shader/xfrm2nv110.vp b/src/shader/xfrm2nv110.vp
new file mode 100644
index 0000000..bbfc527
--- /dev/null
+++ b/src/shader/xfrm2nv110.vp
@@ -0,0 +1,82 @@
+#ifndef ENVYAS
+static uint32_t
+NV110VP_Transform2[] = {
+	0x02000461,
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x000ff000,
+	0x00000000, /* VP_ATTR_EN[0x000] */
+	0x00000000, /* VP_ATTR_EN[0x080] */
+	0x00000000, /* VP_ATTR_EN[0x100] */
+	0x00000000,
+	0x00000000, /* VP_ATTR_EN[0x200] */
+	0x80000000, /* VERTEXID */
+	0x00000000, /* VP_ATTR_EN[0x300] */
+	0x00000000,
+	0x0033f000, /* VP_EXPORT_EN[0x040] */
+	0x00000000, /* VP_EXPORT_EN[0x0c0] */
+	0x00000000,
+	0x00000000,
+	0x00000000,
+	0x00000000, /* VP_EXPORT_EN[0x2c0] */
+	0x00000000,
+#include "xfrm2nv110.vpc"
+};
+#else
+
+sched (st 0x0) (st 0x0) (st 0x0)
+ld b32 $r5 a[0x2fc] 0x0
+shl $r5 $r5 0x5
+ld b64 $r0 c0[$r5+0x80]
+sched (st 0x0) (st 0x0) (st 0x0)
+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)
+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)
+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)
+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)
+mufu rcp $r4 $r4
+fmul ftz $r2 $r2 $r4
+fmul ftz $r3 $r3 $r4
+sched (st 0x0) (st 0x0) (st 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)
+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)
+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)
+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)
+fadd ftz $r4 $r4 c0[0x4c]
+mufu rcp $r4 $r4
+fmul ftz $r2 $r2 $r4
+sched (st 0x0) (st 0x0) (st 0x0)
+fmul ftz $r3 $r3 $r4
+fmul ftz $r0 $r2 c0[0x50]
+fmul ftz $r1 $r3 c0[0x54]
+sched (st 0x0) (st 0x0) (st 0x0)
+st b64 a[0x90] $r0 0x0
+
+exit
+#endif
diff --git a/src/shader/xfrm2nv110.vpc b/src/shader/xfrm2nv110.vpc
new file mode 100644
index 0000000..0d9ebfd
--- /dev/null
+++ b/src/shader/xfrm2nv110.vpc
@@ -0,0 +1,102 @@
+0xfc0007e0,
+0x001f8000,
+0x2fc7ff05,
+0xefd87f80,
+0x00570505,
+0x38480000,
+0x08070500,
+0xef950000,
+0xfc0007e0,
+0x001f8000,
+0x08870502,
+0xef950000,
+0x0707ff00,
+0xeff1ff80,
+0x09070500,
+0xef950000,
+0xfc0007e0,
+0x001f8000,
+0x00070002,
+0x4c681000,
+0x00370003,
+0x4c681000,
+0x00670004,
+0x4c681000,
+0xfc0007e0,
+0x001f8000,
+0x00170102,
+0x49a00100,
+0x00470103,
+0x49a00180,
+0x00770104,
+0x49a00200,
+0xfc0007e0,
+0x001f8000,
+0x00270202,
+0x4c581000,
+0x00570303,
+0x4c581000,
+0x00870404,
+0x4c581000,
+0xfc0007e0,
+0x001f8000,
+0x00470404,
+0x50800000,
+0x00470202,
+0x5c681000,
+0x00470303,
+0x5c681000,
+0xfc0007e0,
+0x001f8000,
+0x00970200,
+0x4c681000,
+0x00a70301,
+0x4c681000,
+0x0807ff00,
+0xeff0ff80,
+0xfc0007e0,
+0x001f8000,
+0x09870500,
+0xef950000,
+0x00b70002,
+0x4c681000,
+0x00e70003,
+0x4c681000,
+0xfc0007e0,
+0x001f8000,
+0x01170004,
+0x4c681000,
+0x00c70102,
+0x49a00100,
+0x00f70103,
+0x49a00180,
+0xfc0007e0,
+0x001f8000,
+0x01270104,
+0x49a00200,
+0x00d70202,
+0x4c581000,
+0x01070303,
+0x4c581000,
+0xfc0007e0,
+0x001f8000,
+0x01370404,
+0x4c581000,
+0x00470404,
+0x50800000,
+0x00470202,
+0x5c681000,
+0xfc0007e0,
+0x001f8000,
+0x00470303,
+0x5c681000,
+0x01470200,
+0x4c681000,
+0x01570301,
+0x4c681000,
+0xfc0007e0,
+0x001f8000,
+0x0907ff00,
+0xeff0ff80,
+0x0007000f,
+0xe3000000,