Merge git://proxy01.pd.intel.com:9419/git/mesa/mesa into crestline

6 files changed, 179 insertions, 187 deletions

diff --git a/src/mesa/drivers/dri/r300/r300_cmdbuf.c b/src/mesa/drivers/dri/r300/r300_cmdbuf.c
index ace9b667240..2c7b5aa011f 100644
--- a/src/mesa/drivers/dri/r300/r300_cmdbuf.c
+++ b/src/mesa/drivers/dri/r300/r300_cmdbuf.c
@@ -292,13 +292,13 @@ void r300InitCmdBuf(r300ContextPtr r300)
 	ALLOC_STATE( vpt, always, R300_VPT_CMDSIZE, "vpt", 0 );
 		r300->hw.vpt.cmd[R300_VPT_CMD_0] = cmdpacket0(R300_SE_VPORT_XSCALE, 6);
 	ALLOC_STATE( unk2080, always, 2, "unk2080", 0 );
-		r300->hw.unk2080.cmd[0] = cmdpacket0(0x2080, 1);
+		r300->hw.unk2080.cmd[0] = cmdpacket0(R300_VAP_CNTL, 1);
 	ALLOC_STATE( vte, always, 3, "vte", 0 );
 		r300->hw.vte.cmd[0] = cmdpacket0(R300_SE_VTE_CNTL, 2);
 	ALLOC_STATE( unk2134, always, 3, "unk2134", 0 );
 		r300->hw.unk2134.cmd[0] = cmdpacket0(0x2134, 2);
 	ALLOC_STATE( unk2140, always, 2, "unk2140", 0 );
-		r300->hw.unk2140.cmd[0] = cmdpacket0(0x2140, 1);
+		r300->hw.unk2140.cmd[0] = cmdpacket0(R300_VAP_CNTL_STATUS, 1);
 	ALLOC_STATE( vir[0], variable, R300_VIR_CMDSIZE, "vir/0", 0 );
 		r300->hw.vir[0].cmd[R300_VIR_CMD_0] = cmdpacket0(R300_VAP_INPUT_ROUTE_0_0, 1);
 	ALLOC_STATE( vir[1], variable, R300_VIR_CMDSIZE, "vir/1", 1 );
@@ -308,11 +308,11 @@ void r300InitCmdBuf(r300ContextPtr r300)
 	ALLOC_STATE( unk21DC, always, 2, "unk21DC", 0 );
 		r300->hw.unk21DC.cmd[0] = cmdpacket0(0x21DC, 1);
 	ALLOC_STATE( unk221C, always, 2, "unk221C", 0 );
-		r300->hw.unk221C.cmd[0] = cmdpacket0(0x221C, 1);
+		r300->hw.unk221C.cmd[0] = cmdpacket0(R300_VAP_UNKNOWN_221C, 1);
 	ALLOC_STATE( unk2220, always, 5, "unk2220", 0 );
 		r300->hw.unk2220.cmd[0] = cmdpacket0(0x2220, 4);
 	ALLOC_STATE( unk2288, always, 2, "unk2288", 0 );
-		r300->hw.unk2288.cmd[0] = cmdpacket0(0x2288, 1);
+		r300->hw.unk2288.cmd[0] = cmdpacket0(R300_VAP_UNKNOWN_2288, 1);
 	ALLOC_STATE( vof, always, R300_VOF_CMDSIZE, "vof", 0 );
 		r300->hw.vof.cmd[R300_VOF_CMD_0] = cmdpacket0(R300_VAP_OUTPUT_VTX_FMT_0, 2);
 	ALLOC_STATE( pvs, always, R300_PVS_CMDSIZE, "pvs", 0 );
@@ -336,9 +336,9 @@ void r300InitCmdBuf(r300ContextPtr r300)
 	ALLOC_STATE( unk4260, always, 4, "unk4260", 0 );
 		r300->hw.unk4260.cmd[0] = cmdpacket0(0x4260, 3);
 	ALLOC_STATE( unk4274, always, 5, "unk4274", 0 );
-		r300->hw.unk4274.cmd[0] = cmdpacket0(0x4274, 4);
+		r300->hw.unk4274.cmd[0] = cmdpacket0(R300_RE_SHADE, 4);
 	ALLOC_STATE( unk4288, always, 4, "unk4288", 0 );
-		r300->hw.unk4288.cmd[0] = cmdpacket0(0x4288, 3);
+		r300->hw.unk4288.cmd[0] = cmdpacket0(R300_RE_POLYGON_MODE, 3);
 	ALLOC_STATE( fogp, always, 3, "fogp", 0 );
 		r300->hw.fogp.cmd[0] = cmdpacket0(R300_RE_FOG_SCALE, 2);
 	ALLOC_STATE( unk42A0, always, 2, "unk42A0", 0 );
@@ -346,7 +346,7 @@ void r300InitCmdBuf(r300ContextPtr r300)
 	ALLOC_STATE( zbs, always, R300_ZBS_CMDSIZE, "zbs", 0 );
 		r300->hw.zbs.cmd[R300_ZBS_CMD_0] = cmdpacket0(R300_RE_ZBIAS_T_FACTOR, 4);
 	ALLOC_STATE( unk42B4, always, 2, "unk42B4", 0 );
-		r300->hw.unk42B4.cmd[0] = cmdpacket0(0x42B4, 1);
+		r300->hw.unk42B4.cmd[0] = cmdpacket0(R300_RE_OCCLUSION_CNTL, 1);
 	ALLOC_STATE( cul, always, R300_CUL_CMDSIZE, "cul", 0 );
 		r300->hw.cul.cmd[R300_CUL_CMD_0] = cmdpacket0(R300_RE_CULL_CNTL, 1);
 	ALLOC_STATE( unk42C0, always, 3, "unk42C0", 0 );
@@ -393,7 +393,7 @@ void r300InitCmdBuf(r300ContextPtr r300)
 	ALLOC_STATE( cmk, always, R300_CMK_CMDSIZE, "cmk", 0 );
 		r300->hw.cmk.cmd[R300_CMK_CMD_0] = cmdpacket0(R300_RB3D_COLORMASK, 1);
 	ALLOC_STATE( unk4E10, always, 4, "unk4E10", 0 );
-		r300->hw.unk4E10.cmd[0] = cmdpacket0(0x4E10, 3);
+		r300->hw.unk4E10.cmd[0] = cmdpacket0(R300_RB3D_BLEND_COLOR, 3);
 	ALLOC_STATE( cb, always, R300_CB_CMDSIZE, "cb", 0 );
 		r300->hw.cb.cmd[R300_CB_CMD_0] = cmdpacket0(R300_RB3D_COLOROFFSET0, 1);
 		r300->hw.cb.cmd[R300_CB_CMD_1] = cmdpacket0(R300_RB3D_COLORPITCH0, 1);
@@ -406,7 +406,7 @@ void r300InitCmdBuf(r300ContextPtr r300)
 	ALLOC_STATE( zs, always, R300_ZS_CMDSIZE, "zstencil", 0 );
 		r300->hw.zs.cmd[R300_ZS_CMD_0] = cmdpacket0(R300_RB3D_ZSTENCIL_CNTL_0, 3);
 	ALLOC_STATE( unk4F10, always, 5, "unk4F10", 0 );
-		r300->hw.unk4F10.cmd[0] = cmdpacket0(0x4F10, 4);
+		r300->hw.unk4F10.cmd[0] = cmdpacket0(R300_RB3D_ZSTENCIL_FORMAT, 4);
 	ALLOC_STATE( zb, always, R300_ZB_CMDSIZE, "zb", 0 );
 		r300->hw.zb.cmd[R300_ZB_CMD_0] = cmdpacket0(R300_RB3D_DEPTHOFFSET, 2);
 	ALLOC_STATE( unk4F28, always, 2, "unk4F28", 0 );
diff --git a/src/mesa/drivers/dri/r300/r300_fragprog.c b/src/mesa/drivers/dri/r300/r300_fragprog.c
index 8e45bd54030..a1c634a54d0 100644
--- a/src/mesa/drivers/dri/r300/r300_fragprog.c
+++ b/src/mesa/drivers/dri/r300/r300_fragprog.c
@@ -1214,8 +1214,8 @@ static void make_sin_const(struct r300_fragment_program *rp)
 	    cnstv[3] = 0.2225;      // weight
 	    rp->const_sin[0] = emit_const4fv(rp, cnstv);
 
-	    cnstv[0] = 0.5;
-	    cnstv[1] = -1.5;
+	    cnstv[0] = 0.75;
+	    cnstv[1] = 0.0;
 	    cnstv[2] = 0.159154943; // 1/(2*PI)
 	    cnstv[3] = 6.283185307; // 2*PI
 	    rp->const_sin[1] = emit_const4fv(rp, cnstv);
@@ -1227,7 +1227,7 @@ static GLboolean parse_program(struct r300_fragment_program *rp)
 	struct gl_fragment_program *mp = &rp->mesa_program;
 	const struct prog_instruction *inst = mp->Base.Instructions;
 	struct prog_instruction *fpi;
-	GLuint src[3], dest, temp;
+	GLuint src[3], dest, temp[2];
 	GLuint cnst;
 	int flags, mask = 0;
 	GLfloat cnstv[4] = {0.0, 0.0, 0.0, 0.0};
@@ -1277,70 +1277,63 @@ static GLboolean parse_program(struct r300_fragment_program *rp)
 			/*
 			 * cos using a parabola (see SIN):
 			 * cos(x):
-			 *   x += PI/2
-			 *   x = (x/(2*PI))+0.5
+			 *   x = (x/(2*PI))+0.75
 			 *   x = frac(x)
 			 *   x = (x*2*PI)-PI
 			 *   result = sin(x)
 			 */
-			temp = get_temp_reg(rp);
+			temp[0] = get_temp_reg(rp);
 			make_sin_const(rp);
 			src[0] = t_scalar_src(rp, fpi->SrcReg[0]);
 
 			/* add 0.5*PI and do range reduction */
 
-			emit_arith(rp, PFS_OP_MAD, temp, WRITEMASK_X,
-				   swizzle(rp->const_sin[0], Z, Z, Z, Z), //PI
-				   pfs_half,
-				   swizzle(keep(src[0]), X, X, X, X),
-				   0);
-
-			emit_arith(rp, PFS_OP_MAD, temp, WRITEMASK_X,
-				   swizzle(temp, X, X, X, X),
+			emit_arith(rp, PFS_OP_MAD, temp[0], WRITEMASK_X,
+				   swizzle(src[0], X, X, X, X),
 				   swizzle(rp->const_sin[1], Z, Z, Z, Z),
-				   pfs_half,
+				   swizzle(rp->const_sin[1], X, X, X, X),
 				   0);
 
-			emit_arith(rp, PFS_OP_FRC, temp, WRITEMASK_X,
-				   swizzle(temp, X, X, X, X),
+			emit_arith(rp, PFS_OP_FRC, temp[0], WRITEMASK_X,
+				   swizzle(temp[0], X, X, X, X),
 				   undef,
 				   undef,
 				   0);
 
-			emit_arith(rp, PFS_OP_MAD, temp, WRITEMASK_Z,
-				   swizzle(temp, X, X, X, X),
+			emit_arith(rp, PFS_OP_MAD, temp[0], WRITEMASK_Z,
+				   swizzle(temp[0], X, X, X, X),
 				   swizzle(rp->const_sin[1], W, W, W, W), //2*PI
 				   negate(swizzle(rp->const_sin[0], Z, Z, Z, Z)), //-PI
 				   0);
 
 			/* SIN */
 
-			emit_arith(rp, PFS_OP_MAD, temp, WRITEMASK_X | WRITEMASK_Y,
-				   swizzle(temp, Z, Z, Z, Z),
+			emit_arith(rp, PFS_OP_MAD, temp[0], WRITEMASK_X | WRITEMASK_Y,
+				   swizzle(temp[0], Z, Z, Z, Z),
 				   rp->const_sin[0],
 				   pfs_zero,
 				   0);
 
-			emit_arith(rp, PFS_OP_MAD, temp, WRITEMASK_X,
-				   swizzle(temp, Y, Y, Y, Y),
-				   absolute(swizzle(temp, Z, Z, Z, Z)),
-				   swizzle(temp, X, X, X, X),
+			emit_arith(rp, PFS_OP_MAD, temp[0], WRITEMASK_X,
+				   swizzle(temp[0], Y, Y, Y, Y),
+				   absolute(swizzle(temp[0], Z, Z, Z, Z)),
+				   swizzle(temp[0], X, X, X, X),
 				   0);
 			
-			emit_arith(rp, PFS_OP_MAD, temp, WRITEMASK_Y,
-				   swizzle(temp, X, X, X, X),
-				   absolute(swizzle(temp, X, X, X, X)),
-				   negate(swizzle(temp, X, X, X, X)),
+			emit_arith(rp, PFS_OP_MAD, temp[0], WRITEMASK_Y,
+				   swizzle(temp[0], X, X, X, X),
+				   absolute(swizzle(temp[0], X, X, X, X)),
+				   negate(swizzle(temp[0], X, X, X, X)),
 				   0);
 
 
 	    		emit_arith(rp, PFS_OP_MAD, dest, mask,
-				   swizzle(temp, Y, Y, Y, Y),
+				   swizzle(temp[0], Y, Y, Y, Y),
 				   swizzle(rp->const_sin[0], W, W, W, W),
-				   swizzle(temp, X, X, X, X),
+				   swizzle(temp[0], X, X, X, X),
 				   flags);
 
-			free_temp(rp, temp);
+			free_temp(rp, temp[0]);
 			break;
 		case OPCODE_DP3:
 			src[0] = t_src(rp, fpi->SrcReg[0]);
@@ -1363,15 +1356,15 @@ static GLboolean parse_program(struct r300_fragment_program *rp)
 			 * DP4 dest, temp, src1
 			 */
 #if 0
-			temp = get_temp_reg(rp);
+			temp[0] = get_temp_reg(rp);
 			src[0].s_swz = SWIZZLE_ONE;
-			emit_arith(rp, PFS_OP_MAD, temp, mask,
+			emit_arith(rp, PFS_OP_MAD, temp[0], mask,
 				   src[0], pfs_one, pfs_zero,
 				   0);
 			emit_arith(rp, PFS_OP_DP4, dest, mask,
-				   temp, src[1], undef,
+				   temp[0], src[1], undef,
 				   flags);	
-			free_temp(rp, temp);
+			free_temp(rp, temp[0]);
 #else
 			emit_arith(rp, PFS_OP_DP4, dest, mask,
 				   swizzle(src[0], X, Y, Z, ONE), src[1],
@@ -1408,17 +1401,17 @@ static GLboolean parse_program(struct r300_fragment_program *rp)
 			break;
 		case OPCODE_FLR:		
 			src[0] = t_src(rp, fpi->SrcReg[0]);
-			temp = get_temp_reg(rp);
+			temp[0] = get_temp_reg(rp);
 			/* FRC temp, src0
 			 * MAD dest, src0, 1.0, -temp
 			 */
-			emit_arith(rp, PFS_OP_FRC, temp, mask,
+			emit_arith(rp, PFS_OP_FRC, temp[0], mask,
 				   keep(src[0]), undef, undef,
 				   0);
 			emit_arith(rp, PFS_OP_MAD, dest, mask,
-				   src[0], pfs_one, negate(temp),
+				   src[0], pfs_one, negate(temp[0]),
 				   flags);
-			free_temp(rp, temp);
+			free_temp(rp, temp[0]);
 			break;
 		case OPCODE_FRC:
 			src[0] = t_src(rp, fpi->SrcReg[0]);
@@ -1450,44 +1443,44 @@ static GLboolean parse_program(struct r300_fragment_program *rp)
 			 */
 			cnstv[0] = cnstv[1] = cnstv[2] = cnstv[3] = 0.50001;
 			src[0] = t_src(rp, fpi->SrcReg[0]);
-			temp = get_temp_reg(rp);
+			temp[0] = get_temp_reg(rp);
 			cnst = emit_const4fv(rp, cnstv);
-			emit_arith(rp, PFS_OP_CMP, temp,
+			emit_arith(rp, PFS_OP_CMP, temp[0],
 				   WRITEMASK_X | WRITEMASK_Y,
 				   src[0], pfs_zero, src[0], flags);
-			emit_arith(rp, PFS_OP_MIN, temp, WRITEMASK_Z,
+			emit_arith(rp, PFS_OP_MIN, temp[0], WRITEMASK_Z,
 				   swizzle(keep(src[0]), W, W, W, W),
 				   cnst, undef, flags);
-			emit_arith(rp, PFS_OP_LG2, temp, WRITEMASK_W,
-				   swizzle(temp, Y, Y, Y, Y),
+			emit_arith(rp, PFS_OP_LG2, temp[0], WRITEMASK_W,
+				   swizzle(temp[0], Y, Y, Y, Y),
 				   undef, undef, flags);
-			emit_arith(rp, PFS_OP_MAX, temp, WRITEMASK_Z,
-				   temp, negate(cnst), undef, flags);
-			emit_arith(rp, PFS_OP_MAD, temp, WRITEMASK_W,
-				   temp, swizzle(temp, Z, Z, Z, Z),
+			emit_arith(rp, PFS_OP_MAX, temp[0], WRITEMASK_Z,
+				   temp[0], negate(cnst), undef, flags);
+			emit_arith(rp, PFS_OP_MAD, temp[0], WRITEMASK_W,
+				   temp[0], swizzle(temp[0], Z, Z, Z, Z),
 				   pfs_zero, flags);
-			emit_arith(rp, PFS_OP_EX2, temp, WRITEMASK_W,
-				   temp, undef, undef, flags);
+			emit_arith(rp, PFS_OP_EX2, temp[0], WRITEMASK_W,
+				   temp[0], undef, undef, flags);
 			emit_arith(rp, PFS_OP_MAD, dest, WRITEMASK_Y,
-				   swizzle(keep(temp), X, X, X, X),
+				   swizzle(keep(temp[0]), X, X, X, X),
 				   pfs_one, pfs_zero, flags);
 #if 0
-			emit_arith(rp, PFS_OP_MAD, temp, WRITEMASK_X,
-				   temp, pfs_one, pfs_half, flags);
-			emit_arith(rp, PFS_OP_CMPH, temp, WRITEMASK_Z,
-				   swizzle(keep(temp), W, W, W, W),
-				   pfs_zero, swizzle(keep(temp), X, X, X, X),
+			emit_arith(rp, PFS_OP_MAD, temp[0], WRITEMASK_X,
+				   temp[0], pfs_one, pfs_half, flags);
+			emit_arith(rp, PFS_OP_CMPH, temp[0], WRITEMASK_Z,
+				   swizzle(keep(temp[0]), W, W, W, W),
+				   pfs_zero, swizzle(keep(temp[0]), X, X, X, X),
 				   flags);
 #else
-			emit_arith(rp, PFS_OP_CMP, temp, WRITEMASK_Z,
+			emit_arith(rp, PFS_OP_CMP, temp[0], WRITEMASK_Z,
 				   pfs_zero,
-				   swizzle(keep(temp), W, W, W, W),
-				   negate(swizzle(keep(temp), X, X, X, X)),
+				   swizzle(keep(temp[0]), W, W, W, W),
+				   negate(swizzle(keep(temp[0]), X, X, X, X)),
 				   flags);
 #endif
 			emit_arith(rp, PFS_OP_CMP, dest, WRITEMASK_Z,
-				   pfs_zero, temp,
-				   negate(swizzle(keep(temp), Y, Y, Y, Y)),
+				   pfs_zero, temp[0],
+				   negate(swizzle(keep(temp[0]), Y, Y, Y, Y)),
 				   flags);
 			emit_arith(rp, PFS_OP_MAD, dest,
 				   WRITEMASK_X | WRITEMASK_W,
@@ -1495,7 +1488,7 @@ static GLboolean parse_program(struct r300_fragment_program *rp)
 				   pfs_one,
 				   pfs_zero,
 				   flags);
-			free_temp(rp, temp);
+			free_temp(rp, temp[0]);
 			break;
 		case OPCODE_LRP:
 			src[0] = t_src(rp, fpi->SrcReg[0]);
@@ -1506,14 +1499,14 @@ static GLboolean parse_program(struct r300_fragment_program *rp)
 			 *     MAD temp, -tmp0, tmp2, tmp2
 			 *     MAD result, tmp0, tmp1, temp
 			 */
-			temp = get_temp_reg(rp);
-			emit_arith(rp, PFS_OP_MAD, temp, mask,
+			temp[0] = get_temp_reg(rp);
+			emit_arith(rp, PFS_OP_MAD, temp[0], mask,
 				   negate(keep(src[0])), keep(src[2]), src[2],
 				   0);
 			emit_arith(rp, PFS_OP_MAD, dest, mask,
-				   src[0], src[1], temp,
+				   src[0], src[1], temp[0],
 				   flags);
-			free_temp(rp, temp);
+			free_temp(rp, temp[0]);
 			break;			
 		case OPCODE_MAD:
 			src[0] = t_src(rp, fpi->SrcReg[0]);
@@ -1554,17 +1547,17 @@ static GLboolean parse_program(struct r300_fragment_program *rp)
 		case OPCODE_POW:
 			src[0] = t_scalar_src(rp, fpi->SrcReg[0]);
 			src[1] = t_scalar_src(rp, fpi->SrcReg[1]);
-			temp = get_temp_reg(rp);	
-			emit_arith(rp, PFS_OP_LG2, temp, WRITEMASK_W,
+			temp[0] = get_temp_reg(rp);	
+			emit_arith(rp, PFS_OP_LG2, temp[0], WRITEMASK_W,
 				   src[0], undef, undef,
 				   0);
-			emit_arith(rp, PFS_OP_MAD, temp, WRITEMASK_W,
-				   temp, src[1], pfs_zero,
+			emit_arith(rp, PFS_OP_MAD, temp[0], WRITEMASK_W,
+				   temp[0], src[1], pfs_zero,
 				   0);
 			emit_arith(rp, PFS_OP_EX2, dest, fpi->DstReg.WriteMask,
-				   temp, undef, undef,
+				   temp[0], undef, undef,
 				   0);
-			free_temp(rp, temp);
+			free_temp(rp, temp[0]);
 			break;
 		case OPCODE_RCP:
 			src[0] = t_scalar_src(rp, fpi->SrcReg[0]);
@@ -1580,107 +1573,91 @@ static GLboolean parse_program(struct r300_fragment_program *rp)
 			break;
 		case OPCODE_SCS:
 			/*
-			 * cos using a parabola (see SIN):
-			 * cos(x):
-			 *   x += PI/2
-			 *   x = (x/(2*PI))+0.5
-			 *   x = frac(x)
-			 *   x = (x*2*PI)-PI
-			 *   result = sin(x)
+			 * scs using a parabola :
+			 * scs(x):
+			 *   result.x = sin(-abs(x)+0.5*PI)  (cos)
+			 *   result.y = sin(x)               (sin)
+			 *
 			 */
-			temp = get_temp_reg(rp);
+			temp[0] = get_temp_reg(rp);
+			temp[1] = get_temp_reg(rp);
 			make_sin_const(rp);
 			src[0] = t_scalar_src(rp, fpi->SrcReg[0]);
 
-			/* add 0.5*PI and do range reduction */
+			/* x = -abs(x)+0.5*PI */
+			emit_arith(rp, PFS_OP_MAD, temp[0], WRITEMASK_Z,
+				   swizzle(rp->const_sin[0], Z, Z, Z, Z), //PI
+				   pfs_half,
+				   negate(abs(swizzle(keep(src[0]), X, X, X, X))),
+				   0);
 
-			emit_arith(rp, PFS_OP_MAD, temp, WRITEMASK_X|WRITEMASK_Y,
-				   swizzle(rp->const_sin[0], Z, Z, Z, Z),
-				   rp->const_sin[1],
+			/* C*x (sin) */
+			emit_arith(rp, PFS_OP_MAD, temp[0], WRITEMASK_W,
+				   swizzle(rp->const_sin[0], Y, Y, Y, Y),
 				   swizzle(keep(src[0]), X, X, X, X),
+				   pfs_zero,
 				   0);
 
-			emit_arith(rp, PFS_OP_CMP, temp, WRITEMASK_W,
-				   swizzle(rp->const_sin[0], Z, Z, Z, Z),
-				   negate(pfs_half),
-				   swizzle(keep(src[0]), X, X, X, X),
+			/* B*x, C*x (cos) */
+			emit_arith(rp, PFS_OP_MAD, temp[0], WRITEMASK_X | WRITEMASK_Y,
+			           swizzle(temp[0], Z, Z, Z, Z),
+				   rp->const_sin[0],
+			           pfs_zero,
 				   0);
 
-			emit_arith(rp, PFS_OP_CMP, temp, WRITEMASK_Z,
-				   swizzle(temp, X, X, X, X),
-				   swizzle(temp, Y, Y, Y, Y),
-				   swizzle(temp, W, W, W, W),
+			/* B*x (sin) */
+			emit_arith(rp, PFS_OP_MAD, temp[1], WRITEMASK_W,
+				   swizzle(rp->const_sin[0], X, X, X, X),
+				   keep(src[0]),
+				   pfs_zero,
 				   0);
 
-			emit_arith(rp, PFS_OP_MAD, temp, WRITEMASK_X | WRITEMASK_Y,
-			           swizzle(temp, Z, Z, Z, Z),
-				   rp->const_sin[0],
-			           pfs_zero,
+			/* y = B*x + C*x*abs(x) (sin)*/
+		    	emit_arith(rp, PFS_OP_MAD, temp[1], WRITEMASK_Z,
+				   absolute(src[0]),
+				   swizzle(temp[0], W, W, W, W),
+				   swizzle(temp[1], W, W, W, W),
 				   0);
 
-			emit_arith(rp, PFS_OP_MAD, temp, WRITEMASK_W,
-				   swizzle(temp, Y, Y, Y, Y),
-				   absolute(swizzle(temp, Z, Z, Z, Z)),
-				   swizzle(temp, X, X, X, X),
+			/* y = B*x + C*x*abs(x) (cos)*/
+			emit_arith(rp, PFS_OP_MAD, temp[1], WRITEMASK_W,
+				   swizzle(temp[0], Y, Y, Y, Y),
+				   absolute(swizzle(temp[0], Z, Z, Z, Z)),
+				   swizzle(temp[0], X, X, X, X),
 				   0);
 
-			if(mask & WRITEMASK_Y)
-			{
-			    emit_arith(rp, PFS_OP_MAD, temp, WRITEMASK_X | WRITEMASK_Y,
-				       swizzle(keep(src[0]), X, X, X, X),
-				       rp->const_sin[0],
-				       pfs_zero,
-				       0);
-
-			    emit_arith(rp, PFS_OP_MAD, temp, WRITEMASK_X,
-				       swizzle(temp, Y, Y, Y, Y),
-				       absolute(swizzle(keep(src[0]), X, X, X, X)),
-				       swizzle(temp, X, X, X, X),
-				       0);
-			}
+			/* y*abs(y) - y (cos), y*abs(y) - y (sin) */
+			emit_arith(rp, PFS_OP_MAD, temp[0], WRITEMASK_X | WRITEMASK_Y,
+			           swizzle(temp[1], W, Z, Y, X),
+				   absolute(swizzle(temp[1], W, Z, Y, X)),
+				   negate(swizzle(temp[1], W, Z, Y, X)),
 
-			emit_arith(rp, PFS_OP_MAD, temp, WRITEMASK_Z,
-				   swizzle(temp, W, W, W, W),
-				   absolute(swizzle(temp, W, W, W, W)),
-				   negate(swizzle(temp, W, W, W, W)),
 				   0);
 
-			emit_arith(rp, PFS_OP_MAD, dest, WRITEMASK_X,
-				   swizzle(temp, Z, Z, Z, Z),
+			/* dest.xy = mad(temp.xy, P, temp2.wz) */
+			emit_arith(rp, PFS_OP_MAD, dest, mask & (WRITEMASK_X | WRITEMASK_Y),
+				   temp[0],
 				   swizzle(rp->const_sin[0], W, W, W, W),
-				   swizzle(temp, W, W, W, W),
+				   swizzle(temp[1], W, Z, Y, X),
 				   flags);
 
-			if(mask & WRITEMASK_Y)
-			{
-			    emit_arith(rp, PFS_OP_MAD, temp, WRITEMASK_W,
-				       swizzle(temp, X, X, X, X),
-				       absolute(swizzle(temp, X, X, X, X)),
-				       negate(swizzle(temp, X, X, X, X)),
-				       0);
-
-	    		    emit_arith(rp, PFS_OP_MAD, dest, WRITEMASK_Y,
-				       swizzle(temp, W, W, W, W),
-				       swizzle(rp->const_sin[0], W, W, W, W),
-				       swizzle(temp, X, X, X, X),
-				       flags);
-			}
-			free_temp(rp, temp);
+			free_temp(rp, temp[0]);
+			free_temp(rp, temp[1]);
 			break;
 		case OPCODE_SGE:
 			src[0] = t_src(rp, fpi->SrcReg[0]);
 			src[1] = t_src(rp, fpi->SrcReg[1]);
-			temp = get_temp_reg(rp);
+			temp[0] = get_temp_reg(rp);
 			/* temp = src0 - src1
 			 * dest.c = (temp.c < 0.0) ? 0 : 1
 			 */
-			emit_arith(rp, PFS_OP_MAD, temp, mask,
+			emit_arith(rp, PFS_OP_MAD, temp[0], mask,
 				   src[0], pfs_one, negate(src[1]),
 				   0);
 			emit_arith(rp, PFS_OP_CMP, dest, mask,
-				   pfs_one, pfs_zero, temp,
+				   pfs_one, pfs_zero, temp[0],
 				   0);
-			free_temp(rp, temp);
+			free_temp(rp, temp[0]);
 			break;
 		case OPCODE_SIN:
 			/*
@@ -1690,73 +1667,74 @@ static GLboolean parse_program(struct r300_fragment_program *rp)
 			 * itself squared.
 			 */
 
-			temp = get_temp_reg(rp);
+			temp[0] = get_temp_reg(rp);
 			make_sin_const(rp);
 			src[0] = t_scalar_src(rp, fpi->SrcReg[0]);
 
+
 			/* do range reduction */
 
-			emit_arith(rp, PFS_OP_MAD, temp, WRITEMASK_X,
+			emit_arith(rp, PFS_OP_MAD, temp[0], WRITEMASK_X,
 				   swizzle(keep(src[0]), X, X, X, X),
 				   swizzle(rp->const_sin[1], Z, Z, Z, Z),
 				   pfs_half,
 				   0);
 
-			emit_arith(rp, PFS_OP_FRC, temp, WRITEMASK_X,
-				   swizzle(temp, X, X, X, X),
+			emit_arith(rp, PFS_OP_FRC, temp[0], WRITEMASK_X,
+				   swizzle(temp[0], X, X, X, X),
 				   undef,
 				   undef,
 				   0);
 
-			emit_arith(rp, PFS_OP_MAD, temp, WRITEMASK_Z,
-				   swizzle(temp, X, X, X, X),
+			emit_arith(rp, PFS_OP_MAD, temp[0], WRITEMASK_Z,
+				   swizzle(temp[0], X, X, X, X),
 				   swizzle(rp->const_sin[1], W, W, W, W), //2*PI
 				   negate(swizzle(rp->const_sin[0], Z, Z, Z, Z)), //PI
 				   0);
 
 			/* SIN */
 
-			emit_arith(rp, PFS_OP_MAD, temp, WRITEMASK_X | WRITEMASK_Y,
-				   swizzle(temp, Z, Z, Z, Z),
+			emit_arith(rp, PFS_OP_MAD, temp[0], WRITEMASK_X | WRITEMASK_Y,
+				   swizzle(temp[0], Z, Z, Z, Z),
 				   rp->const_sin[0],
 				   pfs_zero,
 				   0);
 
-			emit_arith(rp, PFS_OP_MAD, temp, WRITEMASK_X,
-				   swizzle(temp, Y, Y, Y, Y),
-				   absolute(swizzle(temp, Z, Z, Z, Z)),
-				   swizzle(temp, X, X, X, X),
+			emit_arith(rp, PFS_OP_MAD, temp[0], WRITEMASK_X,
+				   swizzle(temp[0], Y, Y, Y, Y),
+				   absolute(swizzle(temp[0], Z, Z, Z, Z)),
+				   swizzle(temp[0], X, X, X, X),
 				   0);
 			
-			emit_arith(rp, PFS_OP_MAD, temp, WRITEMASK_Y,
-				   swizzle(temp, X, X, X, X),
-				   absolute(swizzle(temp, X, X, X, X)),
-				   negate(swizzle(temp, X, X, X, X)),
+			emit_arith(rp, PFS_OP_MAD, temp[0], WRITEMASK_Y,
+				   swizzle(temp[0], X, X, X, X),
+				   absolute(swizzle(temp[0], X, X, X, X)),
+				   negate(swizzle(temp[0], X, X, X, X)),
 				   0);
 
 
 	    		emit_arith(rp, PFS_OP_MAD, dest, mask,
-				   swizzle(temp, Y, Y, Y, Y),
+				   swizzle(temp[0], Y, Y, Y, Y),
 				   swizzle(rp->const_sin[0], W, W, W, W),
-				   swizzle(temp, X, X, X, X),
+				   swizzle(temp[0], X, X, X, X),
 				   flags);
 
-			free_temp(rp, temp);
+			free_temp(rp, temp[0]);
 			break;
 		case OPCODE_SLT:
 			src[0] = t_src(rp, fpi->SrcReg[0]);
 			src[1] = t_src(rp, fpi->SrcReg[1]);
-			temp = get_temp_reg(rp);
+			temp[0] = get_temp_reg(rp);
 			/* temp = src0 - src1
 			 * dest.c = (temp.c < 0.0) ? 1 : 0
 			 */
-			emit_arith(rp, PFS_OP_MAD, temp, mask,
+			emit_arith(rp, PFS_OP_MAD, temp[0], mask,
 				   src[0], pfs_one, negate(src[1]),
 				   0);
 			emit_arith(rp, PFS_OP_CMP, dest, mask,
-				   pfs_zero, pfs_one, temp,
+				   pfs_zero, pfs_one, temp[0],
 				   0);
-			free_temp(rp, temp);
+			free_temp(rp, temp[0]);
 			break;
 		case OPCODE_SUB:
 			src[0] = t_src(rp, fpi->SrcReg[0]);
@@ -1777,9 +1755,9 @@ static GLboolean parse_program(struct r300_fragment_program *rp)
 		case OPCODE_XPD: {
 			src[0] = t_src(rp, fpi->SrcReg[0]);
 			src[1] = t_src(rp, fpi->SrcReg[1]);
-			temp = get_temp_reg(rp);
+			temp[0] = get_temp_reg(rp);
 			/* temp = src0.zxy * src1.yzx */
-			emit_arith(rp, PFS_OP_MAD, temp, WRITEMASK_XYZ,
+			emit_arith(rp, PFS_OP_MAD, temp[0], WRITEMASK_XYZ,
 				   swizzle(keep(src[0]), Z, X, Y, W),
 				   swizzle(keep(src[1]), Y, Z, X, W),
 				   pfs_zero,
@@ -1790,10 +1768,10 @@ static GLboolean parse_program(struct r300_fragment_program *rp)
 			emit_arith(rp, PFS_OP_MAD, dest, mask & WRITEMASK_XYZ,
 				   swizzle(src[0], Y, Z, X, W),
 				   swizzle(src[1], Z, X, Y, W),
-				   negate(temp),
+				   negate(temp[0]),
 				   flags);
 			/* cleanup */
-			free_temp(rp, temp);
+			free_temp(rp, temp[0]);
 			break;
 		}
 		default:
diff --git a/src/mesa/drivers/dri/r300/r300_ioctl.c b/src/mesa/drivers/dri/r300/r300_ioctl.c
index c5ad0260457..6fa34ee482a 100644
--- a/src/mesa/drivers/dri/r300/r300_ioctl.c
+++ b/src/mesa/drivers/dri/r300/r300_ioctl.c
@@ -228,7 +228,7 @@ static void r300EmitClearState(GLcontext * ctx)
 	e32(0);
 	
 	R300_STATECHANGE(r300, unk221C);
-	reg_start(0x221C, 0);
+	reg_start(R300_VAP_UNKNOWN_221C, 0);
 	e32(R300_221C_CLEAR);
 	
 	R300_STATECHANGE(r300, ps);
diff --git a/src/mesa/drivers/dri/r300/r300_reg.h b/src/mesa/drivers/dri/r300/r300_reg.h
index 9f636ec1d2e..69bc994cf66 100644
--- a/src/mesa/drivers/dri/r300/r300_reg.h
+++ b/src/mesa/drivers/dri/r300/r300_reg.h
@@ -63,6 +63,12 @@ USE OR OTHER DEALINGS IN THE SOFTWARE.
 #define R300_SE_VPORT_ZOFFSET               0x1DAC
 
 
+/*
+ * Vertex Array Processing (VAP) Control
+ * Stolen from r200 code from Christoph Brill (It's a guess!)
+ */
+#define R300_VAP_CNTL	0x2080
+
 /* This register is written directly and also starts data section
  * in many 3d CP_PACKET3's
  */
@@ -135,7 +141,7 @@ USE OR OTHER DEALINGS IN THE SOFTWARE.
 
 /* gap */
 
-#define R300_VAP_CNTL                     0x2140
+#define R300_VAP_CNTL_STATUS              0x2140
 #	define R300_VC_NO_SWAP                  (0 << 0)
 #	define R300_VC_16BIT_SWAP               (1 << 0)
 #	define R300_VC_32BIT_SWAP               (2 << 0)
@@ -538,6 +544,9 @@ USE OR OTHER DEALINGS IN THE SOFTWARE.
 /* Some sort of scale or clamp value for texcoordless textures. */
 #define R300_RE_UNK4238                       0x4238
 
+/* Something shade related */
+#define R300_RE_SHADE                         0x4274
+
 #define R300_RE_SHADE_MODEL                   0x4278
 #	define R300_RE_SHADE_MODEL_SMOOTH     0x3aaaa
 #	define R300_RE_SHADE_MODEL_FLAT       0x39595
@@ -1273,6 +1282,7 @@ USE OR OTHER DEALINGS IN THE SOFTWARE.
 #       define R300_BLEND_MASK                       (63)
 #       define R300_SRC_BLEND_SHIFT                  (16)
 #       define R300_DST_BLEND_SHIFT                  (24)
+#define R300_RB3D_BLEND_COLOR               0x4E10
 #define R300_RB3D_COLORMASK                 0x4E0C
 #       define R300_COLORMASK0_B                 (1<<0)
 #       define R300_COLORMASK0_G                 (1<<1)
@@ -1378,6 +1388,10 @@ USE OR OTHER DEALINGS IN THE SOFTWARE.
 	/* 16 bit format or some aditional bit ? */
 #	define R300_DEPTH_FORMAT_UNK32          (32 << 0)
 
+#define R300_RB3D_EARLY_Z                           0x4F14
+#	define R300_EARLY_Z_DISABLE              (0 << 0)
+#	define R300_EARLY_Z_ENABLE               (1 << 0)
+
 /* gap */
 
 #define R300_RB3D_DEPTHOFFSET               0x4F20
diff --git a/src/mesa/drivers/dri/r300/r300_state.c b/src/mesa/drivers/dri/r300/r300_state.c
index b30ece160a0..0e33e51ef3b 100644
--- a/src/mesa/drivers/dri/r300/r300_state.c
+++ b/src/mesa/drivers/dri/r300/r300_state.c
@@ -328,24 +328,24 @@ static void r300UpdateCulling(GLcontext* ctx)
 
 static void update_early_z(GLcontext *ctx)
 {
-	/* updates register 0x4f14 
-	   if depth test is not enabled it should be 0x00000000
-	   if depth is enabled and alpha not it should be 0x00000001
-	   if depth and alpha is enabled it should be 0x00000000
+	/* updates register R300_RB3D_EARLY_Z (0x4F14)
+	   if depth test is not enabled it should be R300_EARLY_Z_DISABLE
+	   if depth is enabled and alpha not it should be R300_EARLY_Z_ENABLE
+	   if depth and alpha is enabled it should be R300_EARLY_Z_DISABLE
 	*/
 	r300ContextPtr r300 = R300_CONTEXT(ctx);
 
 	R300_STATECHANGE(r300, unk4F10);
 	if (ctx->Color.AlphaEnabled && ctx->Color.AlphaFunc != GL_ALWAYS)
 		/* disable early Z */
-		r300->hw.unk4F10.cmd[2] = 0x00000000;
+		r300->hw.unk4F10.cmd[2] = R300_EARLY_Z_DISABLE;
 	else {
 		if (ctx->Depth.Test && ctx->Depth.Func != GL_NEVER)
 			/* enable early Z */
-			r300->hw.unk4F10.cmd[2] = 0x00000001;
+			r300->hw.unk4F10.cmd[2] = R300_EARLY_Z_ENABLE;
 		else
 			/* disable early Z */
-			r300->hw.unk4F10.cmd[2] = 0x00000000;
+			r300->hw.unk4F10.cmd[2] = R300_EARLY_Z_DISABLE;
 	}
 }
 
diff --git a/src/mesa/drivers/dri/r300/radeon_mm.c b/src/mesa/drivers/dri/r300/radeon_mm.c
index f86a1b4e72e..32ed1f43939 100644
--- a/src/mesa/drivers/dri/r300/radeon_mm.c
+++ b/src/mesa/drivers/dri/r300/radeon_mm.c
@@ -283,7 +283,7 @@ static void emit_lin_cp(r300ContextPtr rmesa, unsigned long dst, unsigned long s
 		size -= cp_size;
 	}
 	
-	reg_start(0x4e4c,0);
+	reg_start(R300_RB3D_DSTCACHE_CTLSTAT,0);
 	e32(0x0000000a);
 	
 	reg_start(0x342c,0);