Fix make dist.

9 files changed, 471 insertions, 237 deletions

diff --git a/configure.ac b/configure.ac
index 18b9ad3..fbff021 100644
--- a/configure.ac
+++ b/configure.ac
@@ -82,6 +82,7 @@ AC_OUTPUT([
     src/Makefile
     src/shaders/Makefile
     src/shaders/h264/Makefile
+    src/shaders/h264/ildb/Makefile
     src/shaders/h264/mc/Makefile
     src/shaders/mpeg2/Makefile
     src/shaders/mpeg2/vld/Makefile
diff --git a/src/shaders/Makefile.am b/src/shaders/Makefile.am
index 6669923..998065c 100644
--- a/src/shaders/Makefile.am
+++ b/src/shaders/Makefile.am
@@ -1,4 +1,6 @@
 SUBDIRS = h264 mpeg2 render post_processing vme
 
+EXTRA_DIST = gpp.py
+
 # Extra clean files so that maintainer-clean removes *everything*
 MAINTAINERCLEANFILES = Makefile.in
diff --git a/src/shaders/h264/Makefile.am b/src/shaders/h264/Makefile.am
index 68a9b59..51e0a6f 100644
--- a/src/shaders/h264/Makefile.am
+++ b/src/shaders/h264/Makefile.am
@@ -1,4 +1,4 @@
-SUBDIRS = mc
+SUBDIRS = ildb mc
 
 # Extra clean files so that maintainer-clean removes *everything*
 MAINTAINERCLEANFILES = Makefile.in
diff --git a/src/shaders/h264/ildb/Makefile.am b/src/shaders/h264/ildb/Makefile.am
index e69de29..8cc5622 100644
--- a/src/shaders/h264/ildb/Makefile.am
+++ b/src/shaders/h264/ildb/Makefile.am
@@ -0,0 +1,98 @@
+INTEL_ILDB_INC = \
+	AVC_ILDB.inc				\
+	Child_Undefs.inc			\
+	ILDB_header.inc				\
+	Root_Undefs.inc				\
+	$(NULL)
+
+INTEL_ILDB_ASM = \
+	AVC_ILDB_Child_Field_UV.asm		\
+	AVC_ILDB_Child_Field_Y.asm		\
+	AVC_ILDB_Child_Mbaff_UV.asm		\
+	AVC_ILDB_Child_Mbaff_Y.asm		\
+	AVC_ILDB_Child_UV.asm			\
+	AVC_ILDB_Child_Y.asm			\
+	AVC_ILDB_Chroma_Core.asm		\
+	AVC_ILDB_Chroma_Core_Mbaff.asm		\
+	AVC_ILDB_CloseGateway.asm		\
+	AVC_ILDB_Dep_Check.asm			\
+	AVC_ILDB_Filter_Mbaff_UV_h.asm		\
+	AVC_ILDB_Filter_Mbaff_UV_v.asm		\
+	AVC_ILDB_Filter_Mbaff_Y_h.asm		\
+	AVC_ILDB_Filter_Mbaff_Y_v.asm		\
+	AVC_ILDB_Filter_UV_h.asm		\
+	AVC_ILDB_Filter_UV_v.asm		\
+	AVC_ILDB_Filter_Y_h.asm			\
+	AVC_ILDB_Filter_Y_v.asm			\
+	AVC_ILDB_ForwardMsg.asm			\
+	AVC_ILDB_LumaThrdLimit.asm		\
+	AVC_ILDB_Luma_Core.asm			\
+	AVC_ILDB_Luma_Core_Mbaff.asm		\
+	AVC_ILDB_OpenGateway.asm		\
+	AVC_ILDB_Root_Field_UV.asm		\
+	AVC_ILDB_Root_Field_Y.asm		\
+	AVC_ILDB_Root_Mbaff_UV.asm		\
+	AVC_ILDB_Root_Mbaff_Y.asm		\
+	AVC_ILDB_Root_UV.asm			\
+	AVC_ILDB_Root_Y.asm			\
+	AVC_ILDB_Spawn.asm			\
+	AVC_ILDB_SpawnChild.asm			\
+	AVC_ILDB_SpawnChromaRoot.asm		\
+	Load_ILDB_Cntrl_Data.asm		\
+	Load_ILDB_Cntrl_Data_16DW.asm		\
+	Load_ILDB_Cntrl_Data_22DW.asm		\
+	Load_ILDB_Cntrl_Data_64DW.asm		\
+	SetupVPKernel.asm			\
+	TransposeNV12_16x16.asm			\
+	TransposeNV12_4x16.asm			\
+	Transpose_Cur_UV_2x8.asm		\
+	Transpose_Cur_UV_8x8.asm		\
+	Transpose_Cur_UV_Right_Most_2x8.asm	\
+	Transpose_Cur_Y_16x16.asm		\
+	Transpose_Cur_Y_4x16.asm		\
+	Transpose_Cur_Y_Right_Most_4x16.asm	\
+	Transpose_Left_UV_2x8.asm		\
+	Transpose_Left_Y_4x16.asm		\
+	loadNV12_16x16T.asm			\
+	loadNV12_16x4.asm			\
+	load_Cur_UV_8x8T.asm			\
+	load_Cur_UV_8x8T_Mbaff.asm		\
+	load_Cur_UV_Right_Most_2x8.asm		\
+	load_Cur_Y_16x16T.asm			\
+	load_Cur_Y_16x16T_Mbaff.asm		\
+	load_Cur_Y_Right_Most_4x16.asm		\
+	load_Left_UV_2x8T.asm			\
+	load_Left_UV_2x8T_Mbaff.asm		\
+	load_Left_Y_4x16T.asm			\
+	load_Left_Y_4x16T_Mbaff.asm		\
+	load_Top_UV_8x2.asm			\
+	load_Top_UV_8x2_Mbaff.asm		\
+	load_Top_Y_16x4.asm			\
+	load_Top_Y_16x4_Mbaff.asm		\
+	saveNV12_16x16.asm			\
+	saveNV12_16x4.asm			\
+	saveNV12_16x4T.asm			\
+	save_Cur_UV_8x8.asm			\
+	save_Cur_UV_8x8_Mbaff.asm		\
+	save_Cur_Y_16x16.asm			\
+	save_Cur_Y_16x16_Mbaff.asm		\
+	save_Left_UV_8x2T.asm			\
+	save_Left_UV_8x2T_Mbaff.asm		\
+	save_Left_Y_16x4T.asm			\
+	save_Left_Y_16x4T_Mbaff.asm		\
+	save_Top_UV_8x2.asm			\
+	save_Top_UV_8x2_Mbaff.asm		\
+	save_Top_Y_16x4.asm			\
+	save_Top_Y_16x4_Mbaff.asm		\
+	writeURB.asm				\
+	writeURB_UV_Child.asm			\
+	writeURB_Y_Child.asm			\
+	$(NULL)
+
+EXTRA_DIST = \
+	$(INTEL_ILDB_ASM)			\
+	$(INTEL_ILDB_INC)			\
+	$(NULL)
+
+# Extra clean files so that maintainer-clean removes *everything*
+MAINTAINERCLEANFILES = Makefile.in
diff --git a/src/shaders/h264/mc/Makefile.am b/src/shaders/h264/mc/Makefile.am
index f3be1ed..6608e4d 100644
--- a/src/shaders/h264/mc/Makefile.am
+++ b/src/shaders/h264/mc/Makefile.am
@@ -7,8 +7,10 @@ INTEL_G4B = null.g4b
 
 INTEL_G4B_GEN5 = null.g4b.gen5
 
-INTEL_MC_G4B_GEN5 = avc_mc.g4b.gen5
-INTEL_MC_EXPORT_GEN5 = export.inc.gen5
+INTEL_MC_G4B		= avc_mc.g4b
+INTEL_MC_G4B_GEN5	= avc_mc.g4b.gen5
+INTEL_MC_EXPORT		= export.inc
+INTEL_MC_EXPORT_GEN5	= export.inc.gen5
 
 INTEL_MC_ASM =	\
 	add_Error_16x16_Y.asm	\
@@ -69,6 +71,18 @@ INTEL_MC_ASM =	\
 	writeRecon_Y_16x8.asm	\
 	writeRecon_YC.asm
 
+INTEL_MC_INC = \
+	AllAVC_Build.inc			\
+	AllAVC_Export.inc			\
+	export.inc				\
+	header.inc				\
+	HwmcOnlyHeader.inc			\
+	inter_Header.inc			\
+	intra_Header.inc			\
+	Scoreboard_header.inc			\
+	SetHWScoreboard_header.inc		\
+	$(NULL)
+
 INTEL_ILDB_ASM = \
 	../ildb/AVC_ILDB_Child_Field_UV.asm	\
 	../ildb/AVC_ILDB_Child_Field_Y.asm	\
@@ -152,36 +166,50 @@ INTEL_ILDB_ASM = \
 	../ildb/writeURB_UV_Child.asm	\
 	../ildb/writeURB_Y_Child.asm
 
-EXTRA_DIST = $(INTEL_G4I)	\
-	     $(INTEL_G4A)       \
-	     $(INTEL_G4B)    	\
-	     $(INTEL_G4B_GEN5)
+INTEL_MC_GEN5_ASM = avc_mc.gen5.asm
 
+TARGETS  =
 if HAVE_GEN4ASM
+TARGETS += $(INTEL_MC_G4B_GEN5)
+endif
+
+all-local: $(TARGETS)
+
+SUFFIXES = .g4a .g4b .gen5.asm
 
-SUFFIXES = .g4a .g4b
 .g4a.g4b:
-	m4 $*.g4a > $*.g4m && intel-gen4asm -o $@ $*.g4m && intel-gen4asm -g 5 -o $@.gen5 $*.g4m && rm $*.g4m
-
-$(INTEL_MC_G4B_GEN5): $(INTEL_MC_ASM) $(INTEL_ILDB_ASM)
-	@cpp -D DEV_ILK -I ../ildb/ AllAVC.asm > a.asm; \
-	../../gpp.py a.asm avc_mc.asm; \
-	intel-gen4asm -l list -a -e _export.inc -o $@ -g 5 avc_mc.asm; \
-	cpp -D DEV_ILK -I ../ildb/ AllAVC.asm > a.asm; \
-	../../gpp.py a.asm avc_mc.asm; \
-	intel-gen4asm -l list -a -e _export.inc -o $@ -g 5 avc_mc.asm; \
-	cat _export.inc | sed "s/_IP/_IP_GEN5/g" > $(INTEL_MC_EXPORT_GEN5); \
-	rm a.asm avc_mc.asm _export.inc
+	m4 $*.g4a > $*.g4m			&& \
+	intel-gen4asm -o $@ $*.g4m		&& \
+	intel-gen4asm -g 5 -o $@.gen5 $*.g4m	&& \
+	rm $*.g4m
+
+$(INTEL_MC_GEN5_ASM): $(INTEL_MC_ASM) $(INTEL_MC_INC) $(INTEL_ILDB_ASM)
+	cpp -D DEV_ILK -I ../ildb/ AllAVC.asm > _mc.$@; \
+	../../gpp.py _mc.$@ $@ ; \
+	rm _mc.$@
+
+$(INTEL_MC_G4B_GEN5): $(INTEL_MC_GEN5_ASM)
+	intel-gen4asm -l list -a -e _export.inc.gen5 -o $@ -g 5 $<; \
+	cat _export.inc.gen5 | sed "s/_IP/_IP_GEN5/g" > $(INTEL_MC_EXPORT_GEN5); \
+	rm _export.inc.gen5
 
 $(INTEL_G4B): $(INTEL_G4I)
 
-BUILT_SOURCES= $(INTEL_G4B) $(INTEL_MC_G4B) $(INTEL_MC_G4B_GEN5)
+CLEANFILES = $(INTEL_MC_GEN5_ASM)
 
-clean-local:
-	-rm -f $(INTEL_G4B)
-	-rm -f $(INTEL_G4B_GEN5)
-	-rm -f $(INTEL_MC_G4B_GEN5) $(INTEL_MC_EXPORT_GEN5)
-endif    
+EXTRA_DIST = \
+	$(INTEL_G4A)		\
+	$(INTEL_G4B)    	\
+	$(INTEL_G4B_GEN5)	\
+	$(INTEL_G4I)		\
+	$(INTEL_MC_ASM)		\
+	$(INTEL_MC_EXPORT)	\
+	$(INTEL_MC_EXPORT_GEN5)	\
+	$(INTEL_MC_G4B)		\
+	$(INTEL_MC_G4B_GEN5)	\
+	$(INTEL_MC_INC)		\
+	list			\
+	$(NULL)
 
 # Extra clean files so that maintainer-clean removes *everything*
 MAINTAINERCLEANFILES = Makefile.in
diff --git a/src/shaders/mpeg2/vld/Makefile.am b/src/shaders/mpeg2/vld/Makefile.am
index 0413054..ed5f997 100644
--- a/src/shaders/mpeg2/vld/Makefile.am
+++ b/src/shaders/mpeg2/vld/Makefile.am
@@ -1,23 +1,42 @@
-INTEL_G4I = addidct.g4i               \
-	    do_iq_intra.g4i           \
-	    do_iq_non_intra.g4i       \
-	    idct.g4i                  \
-	    iq_intra.g4i              \
-	    iq_non_intra.g4i          \
-	    motion_field_uv.g4i       \
-	    motion_field_y.g4i        \
-	    motion_frame_uv.g4i       \
-	    motion_frame_y.g4i        \
-	    read_field_x0y0_uv.g4i    \
-	    read_field_x0y0_y.g4i     \
-	    read_field_x0y1_y.g4i     \
-	    read_field_x1y0_y.g4i     \
-	    read_field_x1y1_y.g4i     \
-	    read_frame_x0y0_uv.g4i    \
-	    read_frame_x0y0_y.g4i     \
-	    read_frame_x0y1_y.g4i     \
-	    read_frame_x1y0_y.g4i     \
-	    read_frame_x1y1_y.g4i
+INTEL_G4I =					\
+	addidct.g4i				\
+	do_iq_intra.g4i				\
+	do_iq_non_intra.g4i			\
+	field_addidct.g4i			\
+	field_motion_uv.g4i			\
+	field_motion_y.g4i			\
+	field_read_x0y0_uv.g4i			\
+	field_read_x0y0_y.g4i			\
+	field_read_x0y1_uv.g4i			\
+	field_read_x0y1_y.g4i			\
+	field_read_x1y0_uv.g4i			\
+	field_read_x1y0_y.g4i			\
+	field_read_x1y1_uv.g4i			\
+	field_read_x1y1_y.g4i			\
+	idct.g4i				\
+	iq_intra.g4i				\
+	iq_non_intra.g4i			\
+	motion_field_uv.g4i			\
+	motion_field_y.g4i			\
+	motion_frame_uv.g4i			\
+	motion_frame_y.g4i			\
+	read_field_x0y0_uv.g4i			\
+	read_field_x0y0_y.g4i			\
+	read_field_x0y1_uv.g4i			\
+	read_field_x0y1_y.g4i			\
+	read_field_x1y0_uv.g4i			\
+	read_field_x1y0_y.g4i			\
+	read_field_x1y1_uv.g4i			\
+	read_field_x1y1_y.g4i			\
+	read_frame_x0y0_uv.g4i			\
+	read_frame_x0y0_y.g4i			\
+	read_frame_x0y1_uv.g4i			\
+	read_frame_x0y1_y.g4i			\
+	read_frame_x1y0_uv.g4i			\
+	read_frame_x1y0_y.g4i			\
+	read_frame_x1y1_uv.g4i			\
+	read_frame_x1y1_y.g4i			\
+	$(NULL)
 
 INTEL_G4A = frame_intra.g4a 			\
 	    frame_frame_pred_forward.g4a	\
@@ -36,6 +55,8 @@ INTEL_G4A = frame_intra.g4a 			\
 	    field_bidirect_16x8.g4a		\
 	    null.g4a
 
+INTEL_G4S = $(INTEL_G4A:%.g4a=%.g4s)
+
 INTEL_G4B = frame_intra.g4b 			\
 	    frame_frame_pred_forward.g4b	\
 	    frame_frame_pred_backward.g4b	\
@@ -68,25 +89,32 @@ INTEL_G4B_GEN5 = frame_intra.g4b.gen5 		\
 	    field_bidirect.g4b.gen5		\
 	    field_bidirect_16x8.g4b.gen5
 
-EXTRA_DIST = $(INTEL_G4I)	\
-	     $(INTEL_G4A)       \
-	     $(INTEL_G4B)    	\
-	     $(INTEL_G4B_GEN5)
-
+TARGETS  =
 if HAVE_GEN4ASM
+TARGETS += $(INTEL_G4B)
+TARGETS += $(INTEL_G4B_GEN5)
+endif
+
+all-local: $(TARGETS)
 
-SUFFIXES = .g4a .g4b
-.g4a.g4b:
-	m4 $*.g4a > $*.g4m && intel-gen4asm -o $@ $*.g4m && intel-gen4asm -g 5 -o $@.gen5 $*.g4m && rm $*.g4m
+SUFFIXES = .g4a .g4s .g4b .g4b.gen5
 
-$(INTEL_G4B): $(INTEL_G4I)
+$(INTEL_G4S): $(INTEL_G4A) $(INTEL_G4I)
+.g4a.g4s:
+	m4 $< > $@
+.g4s.g4b:
+	intel-gen4asm -o $@ $<
+.g4s.g4b.gen5:
+	intel-gen4asm -g 5 -o $@ $<
 
-BUILT_SOURCES= $(INTEL_G4B)
+CLEANFILES = $(INTEL_G4S)
 
-clean-local:
-	-rm -f $(INTEL_G4B)
-	-rm -f $(INTEL_G4B_GEN5)
-endif    
+EXTRA_DIST = \
+	$(INTEL_G4A)		\
+	$(INTEL_G4B)		\
+	$(INTEL_G4B_GEN5)	\
+	$(INTEL_G4I)		\
+	$(NULL)
 
 # Extra clean files so that maintainer-clean removes *everything*
 MAINTAINERCLEANFILES = Makefile.in
diff --git a/src/shaders/post_processing/Makefile.am b/src/shaders/post_processing/Makefile.am
index 762c3ce..a6fc525 100644
--- a/src/shaders/post_processing/Makefile.am
+++ b/src/shaders/post_processing/Makefile.am
@@ -1,145 +1,189 @@
 
 INTEL_G4I = 
 
-INTEL_G4A = null.g4a
-
-INTEL_G4B = null.g4b
-
-INTEL_G4B_GEN5 = null.g4b.gen5
-
-INTEL_G6A = null.g6a
-
-INTEL_G6B = null.g6b
-
-INTEL_PP_G4B_GEN5 = 		\
-	nv12_avs_nv12.g4b.gen5	\
-	nv12_dndi_nv12.g4b.gen5	\
-	nv12_load_save_nv12.g4b.gen5	\
-	nv12_scaling_nv12.g4b.gen5
-
-INTEL_PP_G6B =	 		\
-	nv12_avs_nv12.g6b	\
-	nv12_dndi_nv12.g6b	\
-	nv12_load_save_nv12.g6b	\
-	nv12_scaling_nv12.g6b
-
-INTEL_PP_ASM =				\
-	Common/AYUV_Load_16x8.asm	\
-	Common/IMC3_Load_8x4.asm	\
-	Common/IMC3_Load_8x5.asm	\
-	Common/IMC3_Load_9x5.asm	\
-	Common/Init_All_Regs.asm	\
-	Common/Multiple_Loop.asm	\
-	Common/Multiple_Loop_Head.asm	\
-	Common/NV11_Load_4x8.asm	\
-	Common/NV11_Load_5x8.asm	\
-	Common/NV12_Load_8x4.asm	\
-	Common/NV12_Load_8x5.asm	\
-	Common/NV12_Load_9x5.asm	\
-	Common/P208_Load_8x8.asm	\
-	Common/P208_Load_9x8.asm	\
-	Common/PA_Load_8x8.asm	\
-	Common/PA_Load_9x8.asm	\
-	Common/PL16x8_PL8x4.asm	\
-	Common/PL16x8_PL8x8.asm	\
-	Common/PL4x8_Save_NV11.asm	\
-	Common/PL5x8_PL16x8.asm	\
-	Common/PL5x8_PL8x8.asm	\
-	Common/PL8x4_Save_IMC3.asm	\
-	Common/PL8x4_Save_NV12.asm	\
-	Common/PL8x5_PL8x8.asm	\
-	Common/PL8x8_PL8x4.asm	\
-	Common/PL8x8_Save_P208.asm	\
-	Common/PL8x8_Save_PA.asm	\
-	Common/PL9x5_PL16x8.asm	\
-	Common/PL9x8_PL16x8.asm	\
-	Common/readSampler16x1.asm	\
-	Common/RGB16x8_Save_RGB16.asm	\
-	Common/RGB16x8_Save_RGB.asm	\
-	Common/RGB16x8_Save_Y416.asm	\
-	Common/RGB_Pack.asm	\
-	Common/SetupVPKernel.asm	\
-	Core_Kernels/AVS_SetupFirstBlock.asm	\
-	Core_Kernels/AVS_SetupSecondBlock.asm	\
-	Core_Kernels/DI_Hist_Save.asm	\
-	Core_Kernels/DI_SAVE_PA.asm	\
-	Core_Kernels/DNDI_COMMAND.asm	\
-	Core_Kernels/DNDI_Hist_Save.asm	\
-	Core_Kernels/PA_AVS_IEF_16x8.asm	\
-	Core_Kernels/PA_AVS_IEF_8x4.asm	\
-	Core_Kernels/PA_AVS_IEF_8x8.asm	\
-	Core_Kernels/PA_AVS_IEF_Sample.asm	\
-	Core_Kernels/PA_AVS_IEF_Unpack_16x8.asm	\
-	Core_Kernels/PA_AVS_IEF_Unpack_8x4.asm	\
-	Core_Kernels/PA_AVS_IEF_Unpack_8x8.asm	\
-	Core_Kernels/PA_DN_ALG.asm	\
-	Core_Kernels/PA_DNDI_ALG.asm	\
-	Core_Kernels/PA_Scaling.asm	\
-	Core_Kernels/PL2_AVS_IEF_16x8.asm	\
-	Core_Kernels/PL2_AVS_IEF_8x4.asm	\
-	Core_Kernels/PL2_AVS_IEF_8x8.asm	\
+INTEL_G4A	= null.g4a
+INTEL_G4B	= null.g4b
+INTEL_G4B_GEN5	= null.g4b.gen5
+INTEL_G6A	= null.g6a
+INTEL_G6B	= null.g6b
+
+INTEL_PP_G4B_GEN5 = \
+	nv12_avs_nv12.g4b.gen5			\
+	nv12_dndi_nv12.g4b.gen5			\
+	nv12_load_save_nv12.g4b.gen5		\
+	nv12_scaling_nv12.g4b.gen5		\
+	$(NULL)
+
+INTEL_PP_G6B = \
+	nv12_avs_nv12.g6b			\
+	nv12_dndi_nv12.g6b			\
+	nv12_load_save_nv12.g6b			\
+	nv12_scaling_nv12.g6b			\
+	$(NULL)
+
+INTEL_PP_ASM = \
+	nv12_avs_nv12.asm			\
+	nv12_dndi_nv12.asm			\
+	nv12_load_save_nv12.asm			\
+	nv12_scaling_nv12.asm			\
+	$(NULL)
+
+INTEL_PP_ASM += \
+	Common/AYUV_Load_16x8.asm			\
+	Common/IMC3_Load_8x4.asm			\
+	Common/IMC3_Load_8x5.asm			\
+	Common/IMC3_Load_9x5.asm			\
+	Common/Init_All_Regs.asm			\
+	Common/Multiple_Loop.asm			\
+	Common/Multiple_Loop_Head.asm			\
+	Common/NV11_Load_4x8.asm			\
+	Common/NV11_Load_5x8.asm			\
+	Common/NV12_Load_8x4.asm			\
+	Common/NV12_Load_8x5.asm			\
+	Common/NV12_Load_9x5.asm			\
+	Common/P208_Load_8x8.asm			\
+	Common/P208_Load_9x8.asm			\
+	Common/PA_Load_8x8.asm				\
+	Common/PA_Load_9x8.asm				\
+	Common/PL16x8_PL8x4.asm				\
+	Common/PL16x8_PL8x8.asm				\
+	Common/PL4x8_Save_NV11.asm			\
+	Common/PL5x8_PL16x8.asm				\
+	Common/PL5x8_PL8x8.asm				\
+	Common/PL8x4_Save_IMC3.asm			\
+	Common/PL8x4_Save_NV12.asm			\
+	Common/PL8x5_PL8x8.asm				\
+	Common/PL8x8_PL8x4.asm				\
+	Common/PL8x8_Save_P208.asm			\
+	Common/PL8x8_Save_PA.asm			\
+	Common/PL9x5_PL16x8.asm				\
+	Common/PL9x8_PL16x8.asm				\
+	Common/RGB16x8_Save_RGB.asm			\
+	Common/RGB16x8_Save_RGB16.asm			\
+	Common/RGB16x8_Save_Y416.asm			\
+	Common/RGB_Pack.asm				\
+	Common/SetupVPKernel.asm			\
+	Common/readSampler16x1.asm			\
+	Core_Kernels/AVS_SetupFirstBlock.asm		\
+	Core_Kernels/AVS_SetupSecondBlock.asm		\
+	Core_Kernels/DI_Hist_Save.asm			\
+	Core_Kernels/DI_SAVE_PA.asm			\
+	Core_Kernels/DNDI_COMMAND.asm			\
+	Core_Kernels/DNDI_Hist_Save.asm			\
+	Core_Kernels/PA_AVS_IEF_16x8.asm		\
+	Core_Kernels/PA_AVS_IEF_8x4.asm			\
+	Core_Kernels/PA_AVS_IEF_8x8.asm			\
+	Core_Kernels/PA_AVS_IEF_Sample.asm		\
+	Core_Kernels/PA_AVS_IEF_Unpack_16x8.asm		\
+	Core_Kernels/PA_AVS_IEF_Unpack_8x4.asm		\
+	Core_Kernels/PA_AVS_IEF_Unpack_8x8.asm		\
+	Core_Kernels/PA_DNDI_ALG.asm			\
+	Core_Kernels/PA_DN_ALG.asm			\
+	Core_Kernels/PA_Scaling.asm			\
+	Core_Kernels/PL2_AVS_IEF_16x8.asm		\
+	Core_Kernels/PL2_AVS_IEF_8x4.asm		\
+	Core_Kernels/PL2_AVS_IEF_8x8.asm		\
 	Core_Kernels/PL2_AVS_IEF_Unpack_16x8.asm	\
-	Core_Kernels/PL2_AVS_IEF_Unpack_8x4.asm	\
-	Core_Kernels/PL2_AVS_IEF_Unpack_8x8.asm	\
-	Core_Kernels/PL2_Scaling.asm	\
-	Core_Kernels/PL3_AVS_IEF_16x8.asm	\
-	Core_Kernels/PL3_AVS_IEF_8x4.asm	\
-	Core_Kernels/PL3_AVS_IEF_8x8.asm	\
+	Core_Kernels/PL2_AVS_IEF_Unpack_8x4.asm		\
+	Core_Kernels/PL2_AVS_IEF_Unpack_8x8.asm		\
+	Core_Kernels/PL2_Scaling.asm			\
+	Core_Kernels/PL3_AVS_IEF_16x8.asm		\
+	Core_Kernels/PL3_AVS_IEF_8x4.asm		\
+	Core_Kernels/PL3_AVS_IEF_8x8.asm		\
 	Core_Kernels/PL3_AVS_IEF_Unpack_16x8.asm	\
-	Core_Kernels/PL3_AVS_IEF_Unpack_8x4.asm	\
-	Core_Kernels/PL3_AVS_IEF_Unpack_8x8.asm	\
-	Core_Kernels/PL3_Scaling.asm	\
-	Core_Kernels/PL_DN_ALG.asm	\
-	Core_Kernels/PL_DNDI_ALG.asm	\
+	Core_Kernels/PL3_AVS_IEF_Unpack_8x4.asm		\
+	Core_Kernels/PL3_AVS_IEF_Unpack_8x8.asm		\
+	Core_Kernels/PL3_Scaling.asm			\
+	Core_Kernels/PL_DNDI_ALG.asm			\
 	Core_Kernels/PL_DNDI_ALG_UVCopy_NV11.asm	\
 	Core_Kernels/PL_DNDI_ALG_UVCopy_NV12.asm	\
 	Core_Kernels/PL_DNDI_ALG_UVCopy_P208.asm	\
-	Core_Kernels/PL_DNDI_ALG_UVCopy_PL3.asm	\
-	Core_Kernels/RGB_AVS_IEF_16x8.asm	\
+	Core_Kernels/PL_DNDI_ALG_UVCopy_PL3.asm		\
+	Core_Kernels/PL_DN_ALG.asm			\
+	Core_Kernels/RGB_AVS_IEF_16x8.asm		\
 	Core_Kernels/RGB_AVS_IEF_Unpack_16x8.asm	\
 	Core_Kernels/RGB_AVS_IEF_Unscramble_16x8.asm	\
-	Core_Kernels/RGB_Scaling.asm
+	Core_Kernels/RGB_Scaling.asm			\
+	$(NULL)
+
+INTEL_PP_INC = \
+	Common/AYUV_Load_16x8.inc		\
+	Common/Expansion.inc			\
+	Common/PA_Load.inc			\
+	Common/PL2_Load.inc			\
+	Common/PL3_Load.inc			\
+	Common/PL4x8_Save_NV11.inc		\
+	Common/PL8x4_Save_IMC3.inc		\
+	Common/PL8x4_Save_NV12.inc		\
+	Common/PL8x8_PL8x4.inc			\
+	Common/PL8x8_Save_P208.inc		\
+	Common/PL8x8_Save_PA.inc		\
+	Common/RGB16x8_Save_RGB.inc		\
+	Common/RGB16x8_Save_RGB16.inc		\
+	Common/RGB16x8_Save_Y416.inc		\
+	Common/common.inc			\
+	Common/undefall.inc			\
+	Core_Kernels/AVS_IEF.inc		\
+	Core_Kernels/DI.inc			\
+	Core_Kernels/DNDI.inc			\
+	Core_Kernels/Scaling.inc
+	$(NULL)
+
+INTEL_PP_GEN5_ASM = $(INTEL_PP_G4B_GEN5:%.g4b.gen5=%.g5s)
+INTEL_PP_GEN6_ASM = $(INTEL_PP_G6B:%.g6b=%.g6s)
+
+TARGETS  =
+if HAVE_GEN4ASM
+TARGETS += $(INTEL_PP_G4B_GEN5)
+TARGETS += $(INTEL_PP_G6B)
+endif
 
-EXTRA_DIST = $(INTEL_G4I)	\
-	     $(INTEL_G4A)       \
-	     $(INTEL_G4B)    	\
-	     $(INTEL_G4B_GEN5)
+all-local: $(TARGETS)
 
-if HAVE_GEN4ASM
+SUFFIXES = .g4a .g4b .g6a .g6b .g5s .g6s .asm
 
-SUFFIXES = .g4a .g4b .g6a .g6b
 .g4a.g4b:
-	m4 $*.g4a > $*.g4m && intel-gen4asm -o $@ $*.g4m && intel-gen4asm -g 5 -o $@.gen5 $*.g4m && rm $*.g4m
+	m4 $*.g4a > $*.g4m			&& \
+	intel-gen4asm -o $@ $*.g4m		&& \
+	intel-gen4asm -g 5 -o $@.gen5 $*.g4m	&& \
+	rm $*.g4m
 
 .g6a.g6b:
-	m4 $< > $*.g6m && intel-gen4asm -g 6 -o $@ $*.g6m && rm $*.g6m
+	m4 $< > $*.g6m				&& \
+	intel-gen4asm -g 6 -o $@ $*.g6m		&& \
+	rm $*.g6m
 
 $(INTEL_G4B): $(INTEL_G4I)
 
-$(INTEL_PP_G4B_GEN5): $(INTEL_PP_ASM)
-	@_PP_TARGET=$@; \
-	cpp -D DEV_ILK -I Common/ -I Core_Kernels $${_PP_TARGET/.g4b.gen5/.asm} > _pp0.asm; \
-	../gpp.py _pp0.asm _pp1.asm;	\
-	intel-gen4asm -a -o $@ -g 5 _pp1.asm; \
-	rm _pp0.asm _pp1.asm
-
-$(INTEL_PP_G6B): $(INTEL_PP_ASM)
-	@_PP_TARGET=$@; \
-	cpp -D GT -I Common/ -I Core_Kernels $${_PP_TARGET/.g6b/.asm} > _pp0.asm; \
-	../gpp.py _pp0.asm _pp1.asm;	\
-	intel-gen4asm -a -o $@ -g 6 _pp1.asm; \
-	rm _pp0.asm _pp1.asm
-
-BUILT_SOURCES= $(INTEL_G4B) $(INTEL_G6B) $(INTEL_PP_G4B_GEN5) $(INTEL_PP_G6B)
-
-clean-local:
-	-rm -f $(INTEL_G4B)
-	-rm -f $(INTEL_G4B_GEN5)
-	-rm -f $(INTEL_PP_G4B_GEN5)
-	-rm -f $(INTEL_G6B)
-	-rm -f $(INTEL_PP_G6B)
-
-endif    
+$(INTEL_PP_GEN5_ASM): $(INTEL_PP_ASM)
+.asm.g5s:
+	cpp -D DEV_ILK -I Common/ -I Core_Kernels $< > _pp0.$@; \
+	../gpp.py _pp0.$@ $@; \
+	rm _pp0.$@
+.g5s.g4b.gen5:
+	intel-gen4asm -a -o $@ -g 5 $<
+
+$(INTEL_PP_GEN6_ASM): $(INTEL_PP_ASM)
+.asm.g6s:
+	cpp -D GT -I Common/ -I Core_Kernels $< > _pp0.$@; \
+	../gpp.py _pp0.$@ $@; \
+	rm _pp0.$@
+.g6s.g6b:
+	intel-gen4asm -a -o $@ -g 6 $<
+
+CLEANFILES = $(INTEL_PP_GEN5_ASM) $(INTEL_PP_GEN6_ASM)
+
+EXTRA_DIST = \
+	$(INTEL_G4A)		\
+	$(INTEL_G4B)		\
+	$(INTEL_G4B_GEN5)	\
+	$(INTEL_G4I)		\
+	$(INTEL_G6B)		\
+	$(INTEL_PP_ASM)		\
+	$(INTEL_PP_G4B_GEN5)	\
+	$(INTEL_PP_G6B)		\
+	$(INTEL_PP_INC)		\
+	$(NULL)
 
 # Extra clean files so that maintainer-clean removes *everything*
 MAINTAINERCLEANFILES = Makefile.in
diff --git a/src/shaders/render/Makefile.am b/src/shaders/render/Makefile.am
index b3a8c23..7b228f9 100644
--- a/src/shaders/render/Makefile.am
+++ b/src/shaders/render/Makefile.am
@@ -12,6 +12,8 @@ INTEL_G4A =				\
 	exa_wm_yuv_rgb.g4a		\
 	exa_wm_write.g4a
 
+INTEL_G4S = $(INTEL_G4A:%.g4a=%.g4s)
+
 INTEL_G4B =				\
 	exa_sf.g4b			\
 	exa_wm_xy.g4b			\
@@ -30,11 +32,6 @@ INTEL_G4B_GEN5 =				\
 	exa_wm_yuv_rgb.g4b.gen5			\
 	exa_wm_write.g4b.gen5
 
-EXTRA_DIST = $(INTEL_G4I)	\
-	     $(INTEL_G4A)       \
-	     $(INTEL_G4B)    	\
-	     $(INTEL_G4B_GEN5)
-
 INTEL_G6A =				\
 	exa_wm_src_affine.g6a 		\
 	exa_wm_src_sample_argb.g6a 	\
@@ -42,6 +39,8 @@ INTEL_G6A =				\
 	exa_wm_write.g6a 		\
 	exa_wm_yuv_rgb.g6a
 
+INTEL_G6S = $(INTEL_G6A:%.g6a=%.g6s)
+
 INTEL_G6B =				\
 	exa_wm_src_affine.g6b 		\
 	exa_wm_src_sample_argb.g6b 	\
@@ -56,6 +55,8 @@ INTEL_G7A =				\
 	exa_wm_write.g7a 		\
 	exa_wm_yuv_rgb.g7a
 
+INTEL_G7S = $(INTEL_G7A:%.g7a=%.g7s)
+
 INTEL_G7B =				\
 	exa_wm_src_affine.g7b 		\
 	exa_wm_src_sample_argb.g7b 	\
@@ -63,30 +64,54 @@ INTEL_G7B =				\
 	exa_wm_write.g7b 		\
 	exa_wm_yuv_rgb.g7b
 
+TARGETS  =
 if HAVE_GEN4ASM
-
-SUFFIXES = .g4a .g4b .g6a .g6b .g7a .g7b
-.g4a.g4b:
-	m4 $*.g4a > $*.g4m && intel-gen4asm -o $@ $*.g4m && intel-gen4asm -g 5 -o $@.gen5 $*.g4m && rm $*.g4m
-
-.g6a.g6b:
-	m4 -I$(srcdir) -s $< > $*.g6m && intel-gen4asm -g 6 -o $@ $*.g6m && rm $*.g6m
-
-.g7a.g7b:
-	m4 -I$(srcdir) -s $< > $*.g7m && intel-gen4asm -g 7 -o $@ $*.g7m && rm $*.g7m
-
-$(INTEL_G4B): $(INTEL_G4I)
-$(INTEL_G6B): $(INTEL_G4I)
-$(INTEL_G7B): $(INTEL_G4I)
-
-BUILT_SOURCES= $(INTEL_G4B) $(INTEL_G6B) $(INTEL_G7B)
-
-clean-local:
-	-rm -f $(INTEL_G4B)
-	-rm -f $(INTEL_G4B_GEN5)
-	-rm -f $(INTEL_G6B)
-	-rm -f $(INTEL_G7B)
-endif    
+TARGETS += $(INTEL_G4B)
+TARGETS += $(INTEL_G4B_GEN5)
+TARGETS += $(INTEL_G6B)
+TARGETS += $(INTEL_G7B)
+endif
+
+all-local: $(TARGETS)
+
+SUFFIXES = .g4a .g4s .g4b .g6a .g6s .g6b .g7a .g7s .g7b
+
+$(INTEL_G4S): $(INTEL_G4A) $(INTEL_G4I)
+.g4a.g4s:
+	m4 $< > $@
+.g4s.g4b:
+	intel-gen4asm -o $@ $<
+.g4s.g4b.gen5:
+	intel-gen4asm -g 5 -o $@ $<
+
+$(INTEL_G6S): $(INTEL_G6A) $(INTEL_G6I)
+.g6a.g6s:
+	m4 $< > $@
+.g6s.g6b:
+	intel-gen4asm -g 6 -o $@ $<
+
+$(INTEL_G7S): $(INTEL_G7A) $(INTEL_G7I)
+.g7a.g7s:
+	m4 $< > $@
+.g7s.g7b:
+	intel-gen4asm -g 7 -o $@ $<
+
+CLEANFILES = \
+	$(INTEL_G4S)		\
+	$(INTEL_G6S)		\
+	$(INTEL_G7S)		\
+	$(NULL)
+
+EXTRA_DIST = \
+	$(INTEL_G4A)		\
+	$(INTEL_G4B)		\
+	$(INTEL_G4B_GEN5)	\
+	$(INTEL_G4I)		\
+	$(INTEL_G6A)		\
+	$(INTEL_G6B)		\
+	$(INTEL_G7A)		\
+	$(INTEL_G7B)		\
+	$(NULL)
 
 # Extra clean files so that maintainer-clean removes *everything*
 MAINTAINERCLEANFILES = Makefile.in
diff --git a/src/shaders/vme/Makefile.am b/src/shaders/vme/Makefile.am
index 5252ff9..ac7f1b4 100644
--- a/src/shaders/vme/Makefile.am
+++ b/src/shaders/vme/Makefile.am
@@ -1,40 +1,48 @@
-VME_CORE  = intra_frame.asm inter_frame.asm
+VME_CORE	= intra_frame.asm inter_frame.asm
 
-INTEL_G6B = intra_frame.g6b inter_frame.g6b
-INTEL_G6A = intra_frame.g6a inter_frame.g6a
-INTEL_INC = gen6_vme_header.inc
+INTEL_G6B	= intra_frame.g6b inter_frame.g6b
+INTEL_G6A	= intra_frame.g6a inter_frame.g6a
+INTEL_GEN6_INC	= gen6_vme_header.inc
+INTEL_GEN6_ASM	= $(INTEL_G6A:%.g6a=%.gen6.asm)
 
-INTEL_G7B = intra_frame.g7b inter_frame.g7b
-INTEL_G7A = intra_frame.g7a inter_frame.g7a
-INTEL_INC_GEN7 = gen7_vme_header.inc
-
-EXTRA_DIST = $(INTEL_G6B)	\
-	$(INTEL_G6A)		\
-	$(INTEL_INC)		\
-	$(INTEL_G7B)		\
-	$(INTEL_G7A)		\
-	$(INTEL_INC_GEN7)
+INTEL_G7B	= intra_frame.g7b inter_frame.g7b
+INTEL_G7A	= intra_frame.g7a inter_frame.g7a
+INTEL_GEN7_INC	= gen7_vme_header.inc
+INTEL_GEN7_ASM	= $(INTEL_G7A:%.g7a=%.gen7.asm)
 
+TARGETS  =
 if HAVE_GEN4ASM
+TARGETS += $(INTEL_G6B)
+TARGETS += $(INTEL_G7B)
+endif
 
-SUFFIXES = .g6a .g6b .g7a .g7b
-.g6a.g6b:
-	m4 $*.g6a > $*.g6m && intel-gen4asm -g 6 -o $@ $*.g6m && rm $*.g6m
+all-local: $(TARGETS)
 
-.g7a.g7b:
-	m4 $*.g7a > $*.g7m && intel-gen4asm -g 7 -o $@ $*.g7m && rm $*.g7m
+SUFFIXES = .g6a .g6b .g7a .g7b .gen6.asm .gen7.asm
 
-$(INTEL_G6B): $(INTEL_INC) $(VME_CORE)
+$(INTEL_GEN6_ASM): $(VME_CORE) $(INTEL_GEN6_INC)
+.g6a.gen6.asm:
+	m4 $< > $@
+.gen6.asm.g6b:
+	intel-gen4asm -g 6 -o $@ $<
 
-$(INTEL_G7B): $(INTEL_INC_GEN7) $(VME_CORE)
+$(INTEL_GEN7_ASM): $(VME_CORE) $(INTEL_GEN7_INC)
+.g7a.gen7.asm:
+	m4 $< > $@
+.gen7.asm.g7b:
+	intel-gen4asm -g 7 -o $@ $<
 
-BUILT_SOURCES= $(INTEL_G6B) $(INTEL_G7B)
+CLEANFILES = $(INTEL_GEN6_ASM) $(INTEL_GEN7_ASM)
 
-clean-local:
-	-rm -f $(INTEL_G6B)
-	-rm -f $(INTEL_G7B)
-
-endif    
+EXTRA_DIST = \
+	$(INTEL_G6A)		\
+	$(INTEL_G6B)		\
+	$(INTEL_G7A)		\
+	$(INTEL_G7B)		\
+	$(INTEL_GEN6_INC)	\
+	$(INTEL_GEN7_INC)	\
+	$(VME_CORE)		\
+	$(NULL)
 
 # Extra clean files so that maintainer-clean removes *everything*
 MAINTAINERCLEANFILES = Makefile.in