From f59987301c15657016a5a3838d41e1bdea4316e1 Mon Sep 17 00:00:00 2001
From: Lectem <lectem@gmail.com>
Date: Sat, 27 Dec 2014 15:53:21 +0100
Subject: [PATCH 01/16] 1st attempt to install dkA and build

---
 .travis.yml | 11 +++++++++++
 1 file changed, 11 insertions(+)
 create mode 100644 .travis.yml

diff --git a/.travis.yml b/.travis.yml
new file mode 100644
index 0000000..e19974f
--- /dev/null
+++ b/.travis.yml
@@ -0,0 +1,11 @@
+language: cpp
+
+before_install:
+  - wget http://sourceforge.net/projects/devkitpro/files/Automated%20Installer/devkitARMupdate.pl/download
+
+install:
+  - perl devkitARMupdate.pl
+
+script:
+  - cd libctru
+  - make
\ No newline at end of file

From 943fb0f8a786f73f9a7016e27bcf91afb687ec3b Mon Sep 17 00:00:00 2001
From: Lectem <lectem@gmail.com>
Date: Sat, 27 Dec 2014 15:56:13 +0100
Subject: [PATCH 02/16] sudo might help

---
 .travis.yml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/.travis.yml b/.travis.yml
index e19974f..ae07b30 100644
--- a/.travis.yml
+++ b/.travis.yml
@@ -4,7 +4,7 @@ before_install:
   - wget http://sourceforge.net/projects/devkitpro/files/Automated%20Installer/devkitARMupdate.pl/download
 
 install:
-  - perl devkitARMupdate.pl
+  - sudo perl devkitARMupdate.pl
 
 script:
   - cd libctru

From 8b12d3d82777d1e9382d7c640826c53965cc9157 Mon Sep 17 00:00:00 2001
From: Lectem <lectem@gmail.com>
Date: Sat, 27 Dec 2014 15:59:26 +0100
Subject: [PATCH 03/16] language changed to c

---
 .travis.yml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/.travis.yml b/.travis.yml
index ae07b30..71635eb 100644
--- a/.travis.yml
+++ b/.travis.yml
@@ -1,4 +1,4 @@
-language: cpp
+language: c
 
 before_install:
   - wget http://sourceforge.net/projects/devkitpro/files/Automated%20Installer/devkitARMupdate.pl/download

From 374bb2207611a1bcfcab9b9e0e9ddefc98277ea3 Mon Sep 17 00:00:00 2001
From: Lectem <lectem@gmail.com>
Date: Sat, 27 Dec 2014 16:02:09 +0100
Subject: [PATCH 04/16] fixed wget name download issue

---
 .travis.yml | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/.travis.yml b/.travis.yml
index 71635eb..bb6c332 100644
--- a/.travis.yml
+++ b/.travis.yml
@@ -1,7 +1,7 @@
 language: c
 
 before_install:
-  - wget http://sourceforge.net/projects/devkitpro/files/Automated%20Installer/devkitARMupdate.pl/download
+  - wget http://sourceforge.net/projects/devkitpro/files/Automated%20Installer/devkitARMupdate.pl
 
 install:
   - sudo perl devkitARMupdate.pl

From aada32fdf21fc68a5e923d8a81392e02b3c1f6fd Mon Sep 17 00:00:00 2001
From: Lectem <lectem@gmail.com>
Date: Sat, 27 Dec 2014 16:05:01 +0100
Subject: [PATCH 05/16] added env vars

---
 .travis.yml | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/.travis.yml b/.travis.yml
index bb6c332..c2e5193 100644
--- a/.travis.yml
+++ b/.travis.yml
@@ -2,6 +2,8 @@ language: c
 
 before_install:
   - wget http://sourceforge.net/projects/devkitpro/files/Automated%20Installer/devkitARMupdate.pl
+  - export DEVKITPRO=/home/travis/devkitPro
+  - export DEVKITARM=${DEVKITPRO}/devkitARM
 
 install:
   - sudo perl devkitARMupdate.pl

From a4a4f7b4a0578392984481b2f003e8aebebd4368 Mon Sep 17 00:00:00 2001
From: Lectem <lectem@gmail.com>
Date: Sat, 27 Dec 2014 16:08:48 +0100
Subject: [PATCH 06/16] Added the build status (pre replaced with a future
 smealum travis)

---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index 59d8261..f628817 100644
--- a/README.md
+++ b/README.md
@@ -1,4 +1,4 @@
-ctrulib
+ctrulib[![Build Status](https://travis-ci.org/smealum/ctrulib.svg?branch=master)](https://travis-ci.org/smealum/ctrulib)
 =======
 
 CTR User Library

From d8ddd15287e4890ab64835190f4319be66638175 Mon Sep 17 00:00:00 2001
From: Lectem <lectem@gmail.com>
Date: Sat, 21 Mar 2015 14:32:56 +0100
Subject: [PATCH 07/16] test doc generation

---
 .gitignore   |  1 +
 .travis.yml  | 19 ++++++++++++++++++-
 exportdoc.sh | 12 ++++++++++++
 3 files changed, 31 insertions(+), 1 deletion(-)
 create mode 100644 exportdoc.sh

diff --git a/.gitignore b/.gitignore
index 0a8db49..f9bfa40 100644
--- a/.gitignore
+++ b/.gitignore
@@ -5,3 +5,4 @@
 Thumbs.db
 build/
 lib/
+docs/
\ No newline at end of file
diff --git a/.travis.yml b/.travis.yml
index c2e5193..c2fb70b 100644
--- a/.travis.yml
+++ b/.travis.yml
@@ -4,10 +4,27 @@ before_install:
   - wget http://sourceforge.net/projects/devkitpro/files/Automated%20Installer/devkitARMupdate.pl
   - export DEVKITPRO=/home/travis/devkitPro
   - export DEVKITARM=${DEVKITPRO}/devkitARM
+  - sudo add-apt-repository --yes ppa:libreoffice/ppa
+  - sudo apt-get update -qq
 
 install:
   - sudo perl devkitARMupdate.pl
 
+  
+env:
+  global:
+    - secure: "O+zG6TSo9y2XQOUn8n+LcOIKg40ONpLgdZDYPnGjKM+OYp5dffLUjIWQj7PCknhL7HO+fObLGroLvDI7lWOvD81FhsTl5axGxt8NrtslfAnv6SIBom4dww1acqHTo0C1le1+mdhbB1anm7gYCAdDn3TApWBWbGkAOCkS5JzwqC4="
+
+  
 script:
   - cd libctru
-  - make
\ No newline at end of file
+  - make
+  - cd ..
+  
+  
+after_success:
+  - #Build the doxygen files and upload to GH pages
+  - git config --global user.email "travis@travis-ci.org"
+  - git config --global user.name "TravisCI-DocBuilder"
+  - #export doc only once, in gcc job
+  - sh exportdoc.sh
\ No newline at end of file
diff --git a/exportdoc.sh b/exportdoc.sh
new file mode 100644
index 0000000..182ea03
--- /dev/null
+++ b/exportdoc.sh
@@ -0,0 +1,12 @@
+#!/bin/sh
+if [ "$CC" = "clang" ] && [ "$TRAVIS_REPO_SLUG" = "Lectem/ctrulib" ] && [ "$TRAVIS_PULL_REQUEST" = "false" ] && [ "$TRAVIS_BRANCH" = "master" ]; then
+sudo apt-get install -qq doxygen
+git clone --branch=gh-pages --single-branch --depth 1 https://${GH_TOKEN}@github.com/Lectem/ctrulib docs
+doxygen Doxyfile
+cd docs
+git rm -rf ./*
+git add --all
+git commit -m"Doc generated from Travis build #$TRAVIS_BUILD_NUMBER"
+git push -f origin gh-pages
+
+fi
\ No newline at end of file

From 222bc24165576899786f6dff5d54ce09c1882c4c Mon Sep 17 00:00:00 2001
From: Lectem <lectem@gmail.com>
Date: Sat, 21 Mar 2015 15:23:17 +0100
Subject: [PATCH 08/16] forgot to remove a condition

---
 exportdoc.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/exportdoc.sh b/exportdoc.sh
index 182ea03..6793efb 100644
--- a/exportdoc.sh
+++ b/exportdoc.sh
@@ -1,5 +1,5 @@
 #!/bin/sh
-if [ "$CC" = "clang" ] && [ "$TRAVIS_REPO_SLUG" = "Lectem/ctrulib" ] && [ "$TRAVIS_PULL_REQUEST" = "false" ] && [ "$TRAVIS_BRANCH" = "master" ]; then
+if [ "$TRAVIS_REPO_SLUG" = "Lectem/ctrulib" ] && [ "$TRAVIS_PULL_REQUEST" = "false" ] && [ "$TRAVIS_BRANCH" = "master" ]; then
 sudo apt-get install -qq doxygen
 git clone --branch=gh-pages --single-branch --depth 1 https://${GH_TOKEN}@github.com/Lectem/ctrulib docs
 doxygen Doxyfile

From 53f307836a8c35b2ec8e8cd6636581178d07bb24 Mon Sep 17 00:00:00 2001
From: Lectem <lectem@gmail.com>
Date: Sat, 21 Mar 2015 15:28:25 +0100
Subject: [PATCH 09/16] fix doxyfile path

---
 exportdoc.sh | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/exportdoc.sh b/exportdoc.sh
index 6793efb..7d4942a 100644
--- a/exportdoc.sh
+++ b/exportdoc.sh
@@ -2,7 +2,7 @@
 if [ "$TRAVIS_REPO_SLUG" = "Lectem/ctrulib" ] && [ "$TRAVIS_PULL_REQUEST" = "false" ] && [ "$TRAVIS_BRANCH" = "master" ]; then
 sudo apt-get install -qq doxygen
 git clone --branch=gh-pages --single-branch --depth 1 https://${GH_TOKEN}@github.com/Lectem/ctrulib docs
-doxygen Doxyfile
+doxygen libctru/Doxyfile
 cd docs
 git rm -rf ./*
 git add --all

From 30e407a013a5db6ed185adafbd63d90f25fa25a9 Mon Sep 17 00:00:00 2001
From: Lectem <lectem@gmail.com>
Date: Sat, 21 Mar 2015 15:41:04 +0100
Subject: [PATCH 10/16] new secure token

---
 .travis.yml | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/.travis.yml b/.travis.yml
index c2fb70b..8e04ad5 100644
--- a/.travis.yml
+++ b/.travis.yml
@@ -13,8 +13,7 @@ install:
   
 env:
   global:
-    - secure: "O+zG6TSo9y2XQOUn8n+LcOIKg40ONpLgdZDYPnGjKM+OYp5dffLUjIWQj7PCknhL7HO+fObLGroLvDI7lWOvD81FhsTl5axGxt8NrtslfAnv6SIBom4dww1acqHTo0C1le1+mdhbB1anm7gYCAdDn3TApWBWbGkAOCkS5JzwqC4="
-
+    - secure: "Hayg1mC1ejZWoTC3vl4sv8TNCLGMYC4kxjzectUBQLPve0abgekTUm7wAkYoBo9CecbVnDqMH4sUazR46uZmtji/xeXVc1++9m/r1A7kubsJJsEMi1e5VYaKkpDc+/FycClaSyojwiv69EjtAaHhAld7qmu+zN/pJZNTbmX071Y="
   
 script:
   - cd libctru

From 51deccd4d0f15d81695dfa2f8aacfcee3bcce985 Mon Sep 17 00:00:00 2001
From: Lectem <lectem@gmail.com>
Date: Sat, 21 Mar 2015 15:47:06 +0100
Subject: [PATCH 11/16] fixed docs clean order

---
 exportdoc.sh | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/exportdoc.sh b/exportdoc.sh
index 7d4942a..0880dd1 100644
--- a/exportdoc.sh
+++ b/exportdoc.sh
@@ -2,9 +2,12 @@
 if [ "$TRAVIS_REPO_SLUG" = "Lectem/ctrulib" ] && [ "$TRAVIS_PULL_REQUEST" = "false" ] && [ "$TRAVIS_BRANCH" = "master" ]; then
 sudo apt-get install -qq doxygen
 git clone --branch=gh-pages --single-branch --depth 1 https://${GH_TOKEN}@github.com/Lectem/ctrulib docs
-doxygen libctru/Doxyfile
 cd docs
 git rm -rf ./*
+cd ..
+doxygen libctru/Doxyfile
+cd docs
+mv ./html/* .
 git add --all
 git commit -m"Doc generated from Travis build #$TRAVIS_BUILD_NUMBER"
 git push -f origin gh-pages

From 31502c21fe8502783ac6df8654bc052a5d99da09 Mon Sep 17 00:00:00 2001
From: Lectem <lectem@gmail.com>
Date: Sat, 21 Mar 2015 15:55:40 +0100
Subject: [PATCH 12/16] reverted readme to use my travis build

---
 README.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/README.md b/README.md
index f628817..1f25744 100644
--- a/README.md
+++ b/README.md
@@ -1,4 +1,4 @@
-ctrulib[![Build Status](https://travis-ci.org/smealum/ctrulib.svg?branch=master)](https://travis-ci.org/smealum/ctrulib)
+ctrulib[![Build Status](https://travis-ci.org/Lectem/ctrulib.svg?branch=master)](https://travis-ci.org/Lectem/ctrulib)
 =======
 
 CTR User Library

From d2e9db6c8404b76a338ec83e9413cd0b87384a67 Mon Sep 17 00:00:00 2001
From: Lectem <lectem@gmail.com>
Date: Sun, 22 Mar 2015 15:48:25 +0100
Subject: [PATCH 13/16] hello triangle picasso

---
 examples/graphics/hello_triangle/Makefile     | 170 ++++++++++++
 examples/graphics/hello_triangle/README.md    |   4 +
 .../graphics/hello_triangle/data/shader.vsh   |  32 +++
 .../graphics/hello_triangle/source/3dutils.c  |  31 +++
 .../graphics/hello_triangle/source/3dutils.h  |  10 +
 .../graphics/hello_triangle/source/main.c     | 246 ++++++++++++++++++
 .../graphics/hello_triangle/source/mmath.c    | 203 +++++++++++++++
 .../graphics/hello_triangle/source/mmath.h    | 152 +++++++++++
 8 files changed, 848 insertions(+)
 create mode 100644 examples/graphics/hello_triangle/Makefile
 create mode 100644 examples/graphics/hello_triangle/README.md
 create mode 100644 examples/graphics/hello_triangle/data/shader.vsh
 create mode 100644 examples/graphics/hello_triangle/source/3dutils.c
 create mode 100644 examples/graphics/hello_triangle/source/3dutils.h
 create mode 100644 examples/graphics/hello_triangle/source/main.c
 create mode 100644 examples/graphics/hello_triangle/source/mmath.c
 create mode 100644 examples/graphics/hello_triangle/source/mmath.h

diff --git a/examples/graphics/hello_triangle/Makefile b/examples/graphics/hello_triangle/Makefile
new file mode 100644
index 0000000..150cce9
--- /dev/null
+++ b/examples/graphics/hello_triangle/Makefile
@@ -0,0 +1,170 @@
+#---------------------------------------------------------------------------------
+.SUFFIXES:
+#---------------------------------------------------------------------------------
+
+ifeq ($(strip $(DEVKITARM)),)
+$(error "Please set DEVKITARM in your environment. export DEVKITARM=<path to>devkitARM")
+endif
+
+TOPDIR ?= $(CURDIR)
+include $(DEVKITARM)/3ds_rules
+
+#---------------------------------------------------------------------------------
+# TARGET is the name of the output
+# BUILD is the directory where object files & intermediate files will be placed
+# SOURCES is a list of directories containing source code
+# DATA is a list of directories containing data files
+# INCLUDES is a list of directories containing header files
+#
+# NO_SMDH: if set to anything, no SMDH file is generated.
+# APP_TITLE is the name of the app stored in the SMDH file (Optional)
+# APP_DESCRIPTION is the description of the app stored in the SMDH file (Optional)
+# APP_AUTHOR is the author of the app stored in the SMDH file (Optional)
+# ICON is the filename of the icon (.png), relative to the project folder.
+#   If not set, it attempts to use one of the following (in this order):
+#     - <Project name>.png
+#     - icon.png
+#     - <libctru folder>/default_icon.png
+#---------------------------------------------------------------------------------
+TARGET		:=	$(notdir $(CURDIR))
+BUILD		:=	build
+SOURCES		:=	source
+DATA		:=	data
+INCLUDES	:=	include
+
+#---------------------------------------------------------------------------------
+# options for code generation
+#---------------------------------------------------------------------------------
+ARCH	:=	-march=armv6k -mtune=mpcore -mfloat-abi=hard
+
+CFLAGS	:=	-g -Wall -Wfatal-errors -O2 -mword-relocations \
+			-fomit-frame-pointer -ffast-math \
+			$(ARCH)
+
+CFLAGS	+=	$(INCLUDE) -DARM11 -D_3DS
+
+CXXFLAGS	:= $(CFLAGS) -fno-rtti -fno-exceptions -std=gnu++11
+
+ASFLAGS	:=	-g $(ARCH)
+LDFLAGS	=	-specs=3dsx.specs -g $(ARCH) -Wl,-Map,$(notdir $*.map)
+
+LIBS	:= -lctru -lm
+
+#---------------------------------------------------------------------------------
+# list of directories containing libraries, this must be the top level containing
+# include and lib
+#---------------------------------------------------------------------------------
+LIBDIRS	:= $(CTRULIB)
+
+
+#---------------------------------------------------------------------------------
+# no real need to edit anything past this point unless you need to add additional
+# rules for different file extensions
+#---------------------------------------------------------------------------------
+ifneq ($(BUILD),$(notdir $(CURDIR)))
+#---------------------------------------------------------------------------------
+
+export OUTPUT	:=	$(CURDIR)/$(TARGET)
+export TOPDIR	:=	$(CURDIR)
+
+export VPATH	:=	$(foreach dir,$(SOURCES),$(CURDIR)/$(dir)) \
+			$(foreach dir,$(DATA),$(CURDIR)/$(dir))
+
+export DEPSDIR	:=	$(CURDIR)/$(BUILD)
+
+CFILES		:=	$(foreach dir,$(SOURCES),$(notdir $(wildcard $(dir)/*.c)))
+CPPFILES	:=	$(foreach dir,$(SOURCES),$(notdir $(wildcard $(dir)/*.cpp)))
+SFILES		:=	$(foreach dir,$(SOURCES),$(notdir $(wildcard $(dir)/*.s)))
+BINFILES	:=	$(foreach dir,$(DATA),$(notdir $(wildcard $(dir)/*.*)))
+
+#---------------------------------------------------------------------------------
+# use CXX for linking C++ projects, CC for standard C
+#---------------------------------------------------------------------------------
+ifeq ($(strip $(CPPFILES)),)
+#---------------------------------------------------------------------------------
+	export LD	:=	$(CC)
+#---------------------------------------------------------------------------------
+else
+#---------------------------------------------------------------------------------
+	export LD	:=	$(CXX)
+#---------------------------------------------------------------------------------
+endif
+#---------------------------------------------------------------------------------
+
+export OFILES	:=	$(addsuffix .o,$(BINFILES)) \
+			$(CPPFILES:.cpp=.o) $(CFILES:.c=.o) $(SFILES:.s=.o)
+
+export INCLUDE	:=	$(foreach dir,$(INCLUDES),-I$(CURDIR)/$(dir)) \
+			$(foreach dir,$(LIBDIRS),-I$(dir)/include) \
+			-I$(CURDIR)/$(BUILD)
+
+export LIBPATHS	:=	$(foreach dir,$(LIBDIRS),-L$(dir)/lib)
+
+ifeq ($(strip $(ICON)),)
+	icons := $(wildcard *.png)
+	ifneq (,$(findstring $(TARGET).png,$(icons)))
+		export APP_ICON := $(TOPDIR)/$(TARGET).png
+	else
+		ifneq (,$(findstring icon.png,$(icons)))
+			export APP_ICON := $(TOPDIR)/icon.png
+		endif
+	endif
+else
+	export APP_ICON := $(TOPDIR)/$(ICON)
+endif
+
+.PHONY: $(BUILD) clean all
+
+#---------------------------------------------------------------------------------
+all: $(BUILD)
+
+$(BUILD):
+	@[ -d $@ ] || mkdir -p $@
+	@make --no-print-directory -C $(BUILD) -f $(CURDIR)/Makefile
+
+#---------------------------------------------------------------------------------
+clean:
+	@echo clean ...
+	@rm -fr $(BUILD) $(TARGET).3dsx $(OUTPUT).smdh $(TARGET).elf
+
+
+#---------------------------------------------------------------------------------
+else
+
+DEPENDS	:=	$(OFILES:.o=.d)
+
+#---------------------------------------------------------------------------------
+# main targets
+#---------------------------------------------------------------------------------
+ifeq ($(strip $(NO_SMDH)),)
+.PHONY: all
+all	:	$(OUTPUT).3dsx $(OUTPUT).smdh
+endif
+$(OUTPUT).3dsx	:	$(OUTPUT).elf
+$(OUTPUT).elf	:	$(OFILES)
+
+#---------------------------------------------------------------------------------
+# you need a rule like this for each extension you use as binary data
+#---------------------------------------------------------------------------------
+%.bin.o	:	%.bin
+#---------------------------------------------------------------------------------
+	@echo $(notdir $<)
+	@$(bin2o)
+
+# WARNING: This is not the right way to do this! TODO: Do it right!
+#---------------------------------------------------------------------------------
+%.vsh.o	:	%.vsh
+#---------------------------------------------------------------------------------
+	@echo $(notdir $<)
+	picasso ../$(notdir $<).shbin $< 
+	@bin2s ../$(notdir $<).shbin | $(PREFIX)as -o $@
+	@echo "extern const u8" `(echo $(notdir $<).shbin | sed -e 's/^\([0-9]\)/_\1/' | tr . _)`"_end[];" > `(echo $(notdir $<).shbin | tr . _)`.h
+	@echo "extern const u8" `(echo $(notdir $<).shbin | sed -e 's/^\([0-9]\)/_\1/' | tr . _)`"[];" >> `(echo $(notdir $<).shbin | tr . _)`.h
+	@echo "extern const u32" `(echo $(notdir $<).shbin | sed -e 's/^\([0-9]\)/_\1/' | tr . _)`_size";" >> `(echo $(notdir $<).shbin | tr . _)`.h
+	@rm ../$(notdir $<).shbin
+
+-include $(DEPENDS)
+
+#---------------------------------------------------------------------------------------
+endif
+#---------------------------------------------------------------------------------------
diff --git a/examples/graphics/hello_triangle/README.md b/examples/graphics/hello_triangle/README.md
new file mode 100644
index 0000000..00535b6
--- /dev/null
+++ b/examples/graphics/hello_triangle/README.md
@@ -0,0 +1,4 @@
+Hello Triangle
+
+A simple GPU demo to display a white triangle.
+Requires the [picasso](https://github.com/fincs/picasso) shader assembler.
\ No newline at end of file
diff --git a/examples/graphics/hello_triangle/data/shader.vsh b/examples/graphics/hello_triangle/data/shader.vsh
new file mode 100644
index 0000000..d86c35a
--- /dev/null
+++ b/examples/graphics/hello_triangle/data/shader.vsh
@@ -0,0 +1,32 @@
+; Really simple & stupid PICA200 shader
+; Taken from picasso example
+
+; Uniforms
+.fvec projection[4]
+
+; Constants
+.constf myconst(0.0, 1.0, -1.0, 0.0)
+.alias ones myconst.yyyy ; (1.0,1.0,1.0,1.0)
+
+; Outputs : here only position and color
+.out outpos position
+.out outclr color
+
+; Inputs : here we have only vertices
+.alias inpos v0
+
+.proc main
+	; r0 = (inpos.x, inpos.y, inpos.z, 1.0)
+	mov r0.xyz, inpos
+	mov r0.w, ones
+	
+	; outpos = projection * r1
+	dp4 outpos.x, projection[0], r0
+	dp4 outpos.y, projection[1], r0
+	dp4 outpos.z, projection[2], r0
+	dp4 outpos.w, projection[3], r0
+	
+	; Set vertex color to white
+	mov outclr, ones
+	end
+.end
\ No newline at end of file
diff --git a/examples/graphics/hello_triangle/source/3dutils.c b/examples/graphics/hello_triangle/source/3dutils.c
new file mode 100644
index 0000000..45215b8
--- /dev/null
+++ b/examples/graphics/hello_triangle/source/3dutils.c
@@ -0,0 +1,31 @@
+//
+// Created by Lectem on 22/03/2015.
+//
+
+#include "3dutils.h"
+
+void SetUniformMatrix(u32 startreg, float* m) {
+    float param[16];
+
+    param[0x0]=m[3]; //w
+    param[0x1]=m[2]; //z
+    param[0x2]=m[1]; //y
+    param[0x3]=m[0]; //x
+
+    param[0x4]=m[7];
+    param[0x5]=m[6];
+    param[0x6]=m[5];
+    param[0x7]=m[4];
+
+    param[0x8]=m[11];
+    param[0x9]=m[10];
+    param[0xa]=m[9];
+    param[0xb]=m[8];
+
+    param[0xc]=m[15];
+    param[0xd]=m[14];
+    param[0xe]=m[13];
+    param[0xf]=m[12];
+
+    GPU_SetFloatUniform(GPU_VERTEX_SHADER, startreg, (u32*)param, 4);
+}
diff --git a/examples/graphics/hello_triangle/source/3dutils.h b/examples/graphics/hello_triangle/source/3dutils.h
new file mode 100644
index 0000000..9e3f859
--- /dev/null
+++ b/examples/graphics/hello_triangle/source/3dutils.h
@@ -0,0 +1,10 @@
+//
+// Created by Lectem on 22/03/2015.
+//
+
+#ifndef _2DGPU_3DUTILS_H_
+#define _2DGPU_3DUTILS_H_
+#include <3ds.h>
+void SetUniformMatrix(u32 startreg, float* m);
+
+#endif //_2DGPU_3DUTILS_H_
diff --git a/examples/graphics/hello_triangle/source/main.c b/examples/graphics/hello_triangle/source/main.c
new file mode 100644
index 0000000..fe6f25a
--- /dev/null
+++ b/examples/graphics/hello_triangle/source/main.c
@@ -0,0 +1,246 @@
+#include <3ds.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include "shader_vsh_shbin.h"
+#include "3dutils.h"
+#include "mmath.h"
+
+
+#define STRINGIZE(x) STRINGIZE2(x)
+#define STRINGIZE2(x) #x
+#define LINE_STRING STRINGIZE(__LINE__)
+#define my_assert(e) ((e) ? (void)0 : _my_assert("assert failed at " __FILE__ ":" LINE_STRING " (" #e ")\n"))
+void _my_assert(char * text)
+{
+    printf("%s\n",text);
+    do{
+        hidScanInput();
+        if(keysDown()&KEY_START)break;
+        gfxFlushBuffers();
+        gfxSwapBuffers();
+        gspWaitForVBlank();
+    }while(aptMainLoop());
+    exit(0);
+}
+
+
+
+
+typedef struct {
+    float x, y, z;
+} vector_3f;
+
+
+typedef struct {
+    float r, g, b, a;
+} vector_4f;
+
+typedef struct {
+    vector_3f position;
+    vector_4f color;
+} vertex_pos_col;
+
+#define GPU_CMD_SIZE 0x40000
+
+//GPU framebuffer address
+u32* gpuFBuffer =(u32*)0x1F119400;
+//GPU depth buffer address
+u32* gpuDBuffer =(u32*)0x1F370800;
+
+//GPU command buffers
+u32* gpuCmd = NULL;
+
+//shader structure
+DVLB_s* shader_dvlb;    //the header
+shaderProgram_s shader; //the program
+
+
+Result projUniformRegister      =-1;
+Result modelviewUniformRegister =-1;
+
+#define RGBA8(r,g,b,a) ((((r)&0xFF)<<24) | (((g)&0xFF)<<16) | (((b)&0xFF)<<8) | (((a)&0xFF)<<0))
+
+//The color used to clear the screen
+u32 clearColor=RGBA8(0x68, 0xB0, 0xD8, 0xFF);
+
+//The projection matrix
+static float ortho_matrix[4*4];
+
+void GPU_SetDummyTexEnv(u8 num);
+void gpuUIEndFrame();
+
+void gpuUIInit()
+{
+
+    GPU_Init(NULL);//initialize GPU
+
+    gfxSet3D(false);//We will not be using the 3D mode in this example
+    Result res=0;
+
+    /**
+    * Load our vertex shader and its uniforms
+    * Check http://3dbrew.org/wiki/SHBIN for more informations about the shader binaries
+    */
+    shader_dvlb = DVLB_ParseFile((u32 *)shader_vsh_shbin, shader_vsh_shbin_size);//load our vertex shader binary
+    my_assert(shader_dvlb != NULL);
+    shaderProgramInit(&shader);
+    res = shaderProgramSetVsh(&shader, &shader_dvlb->DVLE[0]);
+    my_assert(res >=0); // check for errors
+
+    //In this example we are only rendering in "2D mode", so we don't need one command buffer per eye
+    gpuCmd=(u32*)linearAlloc(GPU_CMD_SIZE * (sizeof *gpuCmd) ); //Don't forget that commands size is 4 (hence the sizeof)
+    my_assert(gpuCmd != NULL);
+
+    //Reset the gpu
+    //This actually needs a command buffer to work, and will then use it as default
+    GPU_Reset(NULL, gpuCmd, GPU_CMD_SIZE);
+
+    projUniformRegister = shaderInstanceGetUniformLocation(shader.vertexShader, "projection");
+    my_assert(projUniformRegister != -1); // make sure we did get the uniform
+
+
+    shaderProgramUse(&shader); // Select the shader to use
+
+
+
+    initOrthographicMatrix(ortho_matrix, 0.0f, 400.0f, 0.0f, 240.0f, 0.0f, 1.0f); // A basic projection for 2D drawings
+    SetUniformMatrix(projUniformRegister, ortho_matrix); // Upload the matrix to the GPU
+
+    //Flush buffers and setup the environment for the next frame
+    gpuUIEndFrame();
+
+}
+
+void gpuUIExit()
+{
+    //do things properly
+    linearFree(gpuCmd);
+    shaderProgramFree(&shader);
+    DVLB_Free(shader_dvlb);
+    GPU_Reset(NULL, gpuCmd, GPU_CMD_SIZE); // Not really needed, but safer for the next applications ?
+}
+
+void gpuUIEndFrame()
+{
+    //Ask the GPU to draw everything (execute the commands)
+    GPU_FinishDrawing();
+    GPUCMD_Finalize();
+    GPUCMD_FlushAndRun(NULL);
+    gspWaitForP3D();
+    //Draw the screen
+    GX_SetDisplayTransfer(NULL, gpuFBuffer, 0x019001E0, (u32*)gfxGetFramebuffer(GFX_TOP, GFX_LEFT, NULL, NULL), 0x019001E0, 0x01001000);
+    gspWaitForPPF();
+    //Clear the screen
+    GX_SetMemoryFill(NULL, gpuFBuffer, clearColor, &gpuFBuffer[0x2EE00],
+            0x201, gpuDBuffer, 0x00000000, &gpuDBuffer[0x2EE00], 0x201);
+    gspWaitForPSC0();
+    gfxSwapBuffersGpu();
+
+    //Wait for the screen to be updated
+    gspWaitForVBlank();
+
+    //Get ready to start a new frame
+    GPUCMD_SetBufferOffset(0);
+
+    //Viewport (http://3dbrew.org/wiki/GPU_Commands#Command_0x0041)
+    GPU_SetViewport((u32 *)osConvertVirtToPhys((u32)gpuDBuffer),
+            (u32 *)osConvertVirtToPhys((u32)gpuFBuffer),
+            0, 0, 240*2, 400);    //Our screen is 400*240, and we actually have 2 framebuffers, even without 3D mode activated
+
+
+    GPU_DepthMap(-1.0f, 0.0f);  //Be careful, standard OpenGL clipping is [-1;1], but it is [-1;0] on the pica200
+    // Note : this is corrected by our projection matrix !
+
+    //Sets the texture environment parameters not to modify our pixels at fragment stage
+    //See https://www.opengl.org/sdk/docs/man2/xhtml/glTexEnv.xml for more insight
+    GPU_SetTexEnv(
+            0,
+            GPU_TEVSOURCES(GPU_PRIMARY_COLOR, GPU_PRIMARY_COLOR, GPU_PRIMARY_COLOR),
+            GPU_TEVSOURCES(GPU_PRIMARY_COLOR, GPU_PRIMARY_COLOR, GPU_PRIMARY_COLOR),
+            GPU_TEVOPERANDS(0,0,0),
+            GPU_TEVOPERANDS(0,0,0),
+            GPU_REPLACE, GPU_REPLACE,
+            0xFFFFFFFF
+    );
+    GPU_SetDummyTexEnv(1);
+    GPU_SetDummyTexEnv(2);
+    GPU_SetDummyTexEnv(3);
+    GPU_SetDummyTexEnv(4);
+    GPU_SetDummyTexEnv(5);
+}
+
+
+
+//Our data
+static const vector_3f triangle_mesh[] =
+    {
+            {240.0f+60.0f, 120.0f,       0.5f},
+            {240.0f-60.0f, 120.0f+60.0f, 0.5f},
+            {240.0f-60.0f, 120.0f-60.0f, 0.5f}
+    };
+
+static void* triangle_data = NULL;
+
+int main(int argc, char** argv)
+{
+
+    srvInit();
+    aptInit();
+    hidInit(NULL);
+
+    gfxInitDefault();
+    consoleInit(GFX_BOTTOM, NULL);
+
+
+    gpuUIInit();
+    printf("hello triangle !\n");
+    triangle_data = linearAlloc(sizeof(triangle_mesh));     //allocate our vbo on the linear heap
+    memcpy(triangle_data, triangle_mesh, sizeof(triangle_mesh)); //Copy our data
+
+    do{
+        hidScanInput();
+        if(keysDown()&KEY_START)break; //Stop the program when Start is pressed
+
+        //Setup the buffers data
+        GPU_SetAttributeBuffers(
+                1, // number of attributes
+                (u32 *) osConvertVirtToPhys((u32) triangle_data),
+                GPU_ATTRIBFMT(0, 3, GPU_FLOAT),//We only have vertices
+                0xFFFE,//Attribute mask, in our case 0b1110
+                0x0,//Attribute permutations (here it is the identity)
+                1, //number of buffers
+                (u32[]) {0x0}, // buffer offsets (placeholders)
+                (u64[]) {0x0}, // attribute permutations for each buffer (identity again)
+                (u8[]) {1} // number of attributes for each buffer
+            );
+        //Display the buffers data
+        GPU_DrawArray(GPU_TRIANGLES, sizeof(triangle_mesh) / sizeof(triangle_mesh[0]));
+
+        gpuUIEndFrame();
+
+    }while(aptMainLoop());
+    gpuUIExit();
+
+
+    gfxExit();
+    hidExit();
+    aptExit();
+    srvExit();
+
+	return 0;
+}
+
+
+void GPU_SetDummyTexEnv(u8 num)
+{
+    //Don't touch the colors of the previous stages
+    GPU_SetTexEnv(num,
+            GPU_TEVSOURCES(GPU_PREVIOUS, 0, 0),
+            GPU_TEVSOURCES(GPU_PREVIOUS, 0, 0),
+            GPU_TEVOPERANDS(0,0,0),
+            GPU_TEVOPERANDS(0,0,0),
+            GPU_REPLACE,
+            GPU_REPLACE,
+            0xFFFFFFFF);
+}
\ No newline at end of file
diff --git a/examples/graphics/hello_triangle/source/mmath.c b/examples/graphics/hello_triangle/source/mmath.c
new file mode 100644
index 0000000..e7715d1
--- /dev/null
+++ b/examples/graphics/hello_triangle/source/mmath.c
@@ -0,0 +1,203 @@
+#include <math.h>
+#include <string.h>
+#include <stdio.h>
+#include <stdbool.h>
+#include <3ds.h>
+#include "mmath.h"
+
+void loadIdentity44(float* m)
+{
+	if(!m)return;
+
+	memset(m, 0x00, 16*4);
+	m[0]=m[5]=m[10]=m[15]=1.0f;
+}
+
+void multMatrix44(float* m1, float* m2, float* m) //4x4
+{
+	int i, j;
+	for(i=0;i<4;i++)for(j=0;j<4;j++)m[i+j*4]=(m1[0+j*4]*m2[i+0*4])+(m1[1+j*4]*m2[i+1*4])+(m1[2+j*4]*m2[i+2*4])+(m1[3+j*4]*m2[i+3*4]);
+
+}
+
+void translateMatrix(float* tm, float x, float y, float z)
+{
+	float rm[16], m[16];
+
+	loadIdentity44(rm);
+	rm[3]=x;
+	rm[7]=y;
+	rm[11]=z;
+	
+	multMatrix44(tm,rm,m);
+	memcpy(tm,m,16*sizeof(float));
+}
+
+// 00 01 02 03
+// 04 05 06 07
+// 08 09 10 11
+// 12 13 14 15
+
+void rotateMatrixX(float* tm, float x, bool r)
+{
+	float rm[16], m[16];
+	memset(rm, 0x00, 16*4);
+	rm[0]=1.0f;
+	rm[5]=cos(x);
+	rm[6]=sin(x);
+	rm[9]=-sin(x);
+	rm[10]=cos(x);
+	rm[15]=1.0f;
+	if(!r)multMatrix44(tm,rm,m);
+	else multMatrix44(rm,tm,m);
+	memcpy(tm,m,16*sizeof(float));
+}
+
+void rotateMatrixY(float* tm, float x, bool r)
+{
+	float rm[16], m[16];
+	memset(rm, 0x00, 16*4);
+	rm[0]=cos(x);
+	rm[2]=sin(x);
+	rm[5]=1.0f;
+	rm[8]=-sin(x);
+	rm[10]=cos(x);
+	rm[15]=1.0f;
+	if(!r)multMatrix44(tm,rm,m);
+	else multMatrix44(rm,tm,m);
+	memcpy(tm,m,16*sizeof(float));
+}
+
+void rotateMatrixZ(float* tm, float x, bool r)
+{
+	float rm[16], m[16];
+	memset(rm, 0x00, 16*4);
+	rm[0]=cos(x);
+	rm[1]=sin(x);
+	rm[4]=-sin(x);
+	rm[5]=cos(x);
+	rm[10]=1.0f;
+	rm[15]=1.0f;
+	if(!r)multMatrix44(tm,rm,m);
+	else multMatrix44(rm,tm,m);
+	memcpy(tm,m,16*sizeof(float));
+}
+
+void scaleMatrix(float* tm, float x, float y, float z)
+{
+	tm[0]*=x; tm[4]*=x; tm[8]*=x; tm[12]*=x;
+	tm[1]*=y; tm[5]*=y; tm[9]*=y; tm[13]*=y;
+	tm[2]*=z; tm[6]*=z; tm[10]*=z; tm[14]*=z;
+}
+
+void initProjectionMatrix(float* m, float fovy, float aspect, float near, float far)
+{
+	float top = near*tan(fovy/2);
+	float right = (top*aspect);
+
+	float mp[4*4];
+	
+	mp[0x0] = near/right;
+	mp[0x1] = 0.0f;
+	mp[0x2] = 0.0f;
+	mp[0x3] = 0.0f;
+
+	mp[0x4] = 0.0f;
+	mp[0x5] = near/top;
+	mp[0x6] = 0.0f;
+	mp[0x7] = 0.0f;
+
+	mp[0x8] = 0.0f;
+	mp[0x9] = 0.0f;
+	mp[0xA] = -(far+near)/(far-near);
+	mp[0xB] = -2.0f*(far*near)/(far-near);
+
+	mp[0xC] = 0.0f;
+	mp[0xD] = 0.0f;
+	mp[0xE] = -1.0f;
+	mp[0xF] = 0.0f;
+
+	float mp2[4*4];
+	loadIdentity44(mp2);
+	mp2[0xA]=0.5;
+	mp2[0xB]=-0.5;
+
+	multMatrix44(mp2, mp, m);
+}
+
+void initOrthographicMatrix(float *m, float left, float right, float bottom, float top, float near, float far)
+{
+	/*  ______________________
+       |                      |
+       |                      |
+       |                      |
+       |                      |
+       |                      |
+       |______________________| ^
+                                | x
+                           <-----
+                             y
+    */
+
+	//Mirror
+	//right = 400-right;
+	//left = 400-left;
+	//top = 240-top;
+	//bottom = 240-bottom;
+
+	float mp[4*4];
+
+	mp[0x0] = 2.0f/(right-left);
+	mp[0x1] = 0.0f;
+	mp[0x2] = 0.0f;
+	mp[0x3] = -(right+left)/(right-left);
+
+	mp[0x4] = 0.0f;
+	mp[0x5] = 2.0f/(top-bottom);
+	mp[0x6] = 0.0f;
+	mp[0x7] = -(top+bottom)/(top-bottom);
+
+	mp[0x8] = 0.0f;
+	mp[0x9] = 0.0f;
+	mp[0xA] = -2.0f/(far-near);
+	mp[0xB] = (far+near)/(far-near);
+
+	mp[0xC] = 0.0f;
+	mp[0xD] = 0.0f;
+	mp[0xE] = 0.0f;
+	mp[0xF] = 1.0f;
+
+	float mp2[4*4];
+	loadIdentity44(mp2);
+	mp2[0xA] = 0.5;
+	mp2[0xB] = -0.5;
+
+	//Convert Z [-1, 1] to [-1, 0] (PICA shiz)
+	multMatrix44(mp2, mp, m);
+
+	//rotateMatrixZ(m, M_PI/2, false);
+}
+
+vect3Df_s getMatrixColumn(float* m, u8 i)
+{
+	if(!m || i>=4)return vect3Df(0,0,0);
+	return vect3Df(m[0+i*4],m[1+i*4],m[2+i*4]);
+}
+
+vect3Df_s getMatrixRow(float* m, u8 i)
+{
+	if(!m || i>=4)return vect3Df(0,0,0);
+	return vect3Df(m[i+0*4],m[i+1*4],m[i+2*4]);
+}
+
+vect4Df_s getMatrixColumn4(float* m, u8 i)
+{
+	if(!m || i>=4)return vect4Df(0,0,0,0);
+	return vect4Df(m[0+i*4],m[1+i*4],m[2+i*4],m[3+i*4]);
+}
+
+vect4Df_s getMatrixRow4(float* m, u8 i)
+{
+	if(!m || i>=4)return vect4Df(0,0,0,0);
+	return vect4Df(m[i+0*4],m[i+1*4],m[i+2*4],m[i+3*4]);
+}
diff --git a/examples/graphics/hello_triangle/source/mmath.h b/examples/graphics/hello_triangle/source/mmath.h
new file mode 100644
index 0000000..370b3c2
--- /dev/null
+++ b/examples/graphics/hello_triangle/source/mmath.h
@@ -0,0 +1,152 @@
+#ifndef MATH_H
+#define MATH_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+#include <3ds/types.h>
+#include <math.h>
+#pragma GCC diagnostic ignored "-Wnarrowing"
+
+
+typedef float mtx44[4][4];
+typedef float mtx33[3][3];
+
+typedef struct
+{
+	s32 x, y, z;
+}vect3Di_s;
+
+static inline vect3Di_s vect3Di(s32 x, s32 y, s32 z)
+{
+	return (vect3Di_s){x,y,z};
+}
+
+static inline vect3Di_s vaddi(vect3Di_s u, vect3Di_s v)
+{
+	return (vect3Di_s){u.x+v.x,u.y+v.y,u.z+v.z};
+}
+
+static inline vect3Di_s vsubi(vect3Di_s u, vect3Di_s v)
+{
+	return (vect3Di_s){u.x-v.x,u.y-v.y,u.z-v.z};
+}
+
+static inline vect3Di_s vmuli(vect3Di_s v, s32 f)
+{
+	return (vect3Di_s){v.x*f,v.y*f,v.z*f};
+}
+
+typedef struct
+{
+	float x, y, z;
+}vect3Df_s;
+
+static inline vect3Df_s vect3Df(float x, float y, float z)
+{
+	return (vect3Df_s){x,y,z};
+}
+
+static inline vect3Df_s vaddf(vect3Df_s u, vect3Df_s v)
+{
+	return (vect3Df_s){u.x+v.x,u.y+v.y,u.z+v.z};
+}
+
+static inline vect3Df_s vsubf(vect3Df_s u, vect3Df_s v)
+{
+	return (vect3Df_s){u.x-v.x,u.y-v.y,u.z-v.z};
+}
+
+static inline vect3Df_s vmulf(vect3Df_s v, float f)
+{
+	return (vect3Df_s){v.x*f,v.y*f,v.z*f};
+}
+
+static inline vect3Df_s vscalef(vect3Df_s v1, vect3Df_s v2)
+{
+	return (vect3Df_s){v1.x*v2.x,v1.y*v2.y,v1.z*v2.z};
+}
+
+static inline float vmagf(vect3Df_s v)
+{
+	return sqrtf(v.x*v.x+v.y*v.y+v.z*v.z);
+}
+
+static inline float vdistf(vect3Df_s v1, vect3Df_s v2)
+{
+	return sqrtf((v1.x-v2.x)*(v1.x-v2.x)+(v1.y-v2.y)*(v1.y-v2.y)+(v1.z-v2.z)*(v1.z-v2.z));
+}
+
+static inline vect3Df_s vnormf(vect3Df_s v)
+{
+	const float l=sqrtf(v.x*v.x+v.y*v.y+v.z*v.z);
+	return (vect3Df_s){v.x/l,v.y/l,v.z/l};
+}
+
+typedef struct
+{
+	float x, y, z, w;
+}vect4Df_s;
+
+static inline vect4Df_s vect4Df(float x, float y, float z, float w)
+{
+	return (vect4Df_s){x,y,z,w};
+}
+
+static inline vect4Df_s vaddf4(vect4Df_s u, vect4Df_s v)
+{
+	return (vect4Df_s){u.x+v.x,u.y+v.y,u.z+v.z,u.w+v.w};
+}
+
+static inline vect4Df_s vsubf4(vect4Df_s u, vect4Df_s v)
+{
+	return (vect4Df_s){u.x-v.x,u.y-v.y,u.z-v.z,u.w-v.w};
+}
+
+static inline vect4Df_s vmulf4(vect4Df_s v, float f)
+{
+	return (vect4Df_s){v.x*f,v.y*f,v.z*f,v.w*f};
+}
+
+static inline float vdotf4(vect4Df_s v1, vect4Df_s v2)
+{
+	return v1.x*v2.x+v1.y*v2.y+v1.z*v2.z+v1.w*v2.w;
+}
+
+static inline vect4Df_s vnormf4(vect4Df_s v)
+{
+	const float l=sqrtf(v.x*v.x+v.y*v.y+v.z*v.z+v.w*v.w);
+	return (vect4Df_s){v.x/l,v.y/l,v.z/l,v.w/l};
+}
+
+//interstuff
+static inline vect3Di_s vf2i(vect3Df_s v)
+{
+	return (vect3Di_s){floorf(v.x),floorf(v.y),floorf(v.z)};
+}
+
+static inline vect3Df_s vi2f(vect3Di_s v)
+{
+	return (vect3Df_s){(float)v.x,(float)v.y,(float)v.z};
+}
+
+void loadIdentity44(float* m);
+void multMatrix44(float* m1, float* m2, float* m);
+
+void translateMatrix(float* tm, float x, float y, float z);
+void rotateMatrixX(float* tm, float x, bool r);
+void rotateMatrixY(float* tm, float x, bool r);
+void rotateMatrixZ(float* tm, float x, bool r);
+void scaleMatrix(float* tm, float x, float y, float z);
+
+void initProjectionMatrix(float* m, float fovy, float aspect, float near, float far);
+void initOrthographicMatrix(float *m, float left, float right, float bottom, float top, float near, float far);
+
+
+vect3Df_s getMatrixColumn(float* m, u8 i);
+vect3Df_s getMatrixRow(float* m, u8 i);
+vect4Df_s getMatrixColumn4(float* m, u8 i);
+vect4Df_s getMatrixRow4(float* m, u8 i);
+#ifdef __cplusplus
+}
+#endif
+#endif

From 80a41c8e20b8893f9a3671f00066e7126938dd81 Mon Sep 17 00:00:00 2001
From: Lectem <lectem@gmail.com>
Date: Sun, 22 Mar 2015 15:48:25 +0100
Subject: [PATCH 14/16] hello triangle picasso

---
 examples/graphics/hello_triangle/Makefile     | 170 ++++++++++++
 examples/graphics/hello_triangle/README.md    |   4 +
 .../graphics/hello_triangle/data/shader.vsh   |  32 +++
 .../graphics/hello_triangle/source/3dutils.c  |  31 +++
 .../graphics/hello_triangle/source/3dutils.h  |  10 +
 .../graphics/hello_triangle/source/main.c     | 246 ++++++++++++++++++
 .../graphics/hello_triangle/source/mmath.c    | 203 +++++++++++++++
 .../graphics/hello_triangle/source/mmath.h    | 152 +++++++++++
 8 files changed, 848 insertions(+)
 create mode 100644 examples/graphics/hello_triangle/Makefile
 create mode 100644 examples/graphics/hello_triangle/README.md
 create mode 100644 examples/graphics/hello_triangle/data/shader.vsh
 create mode 100644 examples/graphics/hello_triangle/source/3dutils.c
 create mode 100644 examples/graphics/hello_triangle/source/3dutils.h
 create mode 100644 examples/graphics/hello_triangle/source/main.c
 create mode 100644 examples/graphics/hello_triangle/source/mmath.c
 create mode 100644 examples/graphics/hello_triangle/source/mmath.h

diff --git a/examples/graphics/hello_triangle/Makefile b/examples/graphics/hello_triangle/Makefile
new file mode 100644
index 0000000..150cce9
--- /dev/null
+++ b/examples/graphics/hello_triangle/Makefile
@@ -0,0 +1,170 @@
+#---------------------------------------------------------------------------------
+.SUFFIXES:
+#---------------------------------------------------------------------------------
+
+ifeq ($(strip $(DEVKITARM)),)
+$(error "Please set DEVKITARM in your environment. export DEVKITARM=<path to>devkitARM")
+endif
+
+TOPDIR ?= $(CURDIR)
+include $(DEVKITARM)/3ds_rules
+
+#---------------------------------------------------------------------------------
+# TARGET is the name of the output
+# BUILD is the directory where object files & intermediate files will be placed
+# SOURCES is a list of directories containing source code
+# DATA is a list of directories containing data files
+# INCLUDES is a list of directories containing header files
+#
+# NO_SMDH: if set to anything, no SMDH file is generated.
+# APP_TITLE is the name of the app stored in the SMDH file (Optional)
+# APP_DESCRIPTION is the description of the app stored in the SMDH file (Optional)
+# APP_AUTHOR is the author of the app stored in the SMDH file (Optional)
+# ICON is the filename of the icon (.png), relative to the project folder.
+#   If not set, it attempts to use one of the following (in this order):
+#     - <Project name>.png
+#     - icon.png
+#     - <libctru folder>/default_icon.png
+#---------------------------------------------------------------------------------
+TARGET		:=	$(notdir $(CURDIR))
+BUILD		:=	build
+SOURCES		:=	source
+DATA		:=	data
+INCLUDES	:=	include
+
+#---------------------------------------------------------------------------------
+# options for code generation
+#---------------------------------------------------------------------------------
+ARCH	:=	-march=armv6k -mtune=mpcore -mfloat-abi=hard
+
+CFLAGS	:=	-g -Wall -Wfatal-errors -O2 -mword-relocations \
+			-fomit-frame-pointer -ffast-math \
+			$(ARCH)
+
+CFLAGS	+=	$(INCLUDE) -DARM11 -D_3DS
+
+CXXFLAGS	:= $(CFLAGS) -fno-rtti -fno-exceptions -std=gnu++11
+
+ASFLAGS	:=	-g $(ARCH)
+LDFLAGS	=	-specs=3dsx.specs -g $(ARCH) -Wl,-Map,$(notdir $*.map)
+
+LIBS	:= -lctru -lm
+
+#---------------------------------------------------------------------------------
+# list of directories containing libraries, this must be the top level containing
+# include and lib
+#---------------------------------------------------------------------------------
+LIBDIRS	:= $(CTRULIB)
+
+
+#---------------------------------------------------------------------------------
+# no real need to edit anything past this point unless you need to add additional
+# rules for different file extensions
+#---------------------------------------------------------------------------------
+ifneq ($(BUILD),$(notdir $(CURDIR)))
+#---------------------------------------------------------------------------------
+
+export OUTPUT	:=	$(CURDIR)/$(TARGET)
+export TOPDIR	:=	$(CURDIR)
+
+export VPATH	:=	$(foreach dir,$(SOURCES),$(CURDIR)/$(dir)) \
+			$(foreach dir,$(DATA),$(CURDIR)/$(dir))
+
+export DEPSDIR	:=	$(CURDIR)/$(BUILD)
+
+CFILES		:=	$(foreach dir,$(SOURCES),$(notdir $(wildcard $(dir)/*.c)))
+CPPFILES	:=	$(foreach dir,$(SOURCES),$(notdir $(wildcard $(dir)/*.cpp)))
+SFILES		:=	$(foreach dir,$(SOURCES),$(notdir $(wildcard $(dir)/*.s)))
+BINFILES	:=	$(foreach dir,$(DATA),$(notdir $(wildcard $(dir)/*.*)))
+
+#---------------------------------------------------------------------------------
+# use CXX for linking C++ projects, CC for standard C
+#---------------------------------------------------------------------------------
+ifeq ($(strip $(CPPFILES)),)
+#---------------------------------------------------------------------------------
+	export LD	:=	$(CC)
+#---------------------------------------------------------------------------------
+else
+#---------------------------------------------------------------------------------
+	export LD	:=	$(CXX)
+#---------------------------------------------------------------------------------
+endif
+#---------------------------------------------------------------------------------
+
+export OFILES	:=	$(addsuffix .o,$(BINFILES)) \
+			$(CPPFILES:.cpp=.o) $(CFILES:.c=.o) $(SFILES:.s=.o)
+
+export INCLUDE	:=	$(foreach dir,$(INCLUDES),-I$(CURDIR)/$(dir)) \
+			$(foreach dir,$(LIBDIRS),-I$(dir)/include) \
+			-I$(CURDIR)/$(BUILD)
+
+export LIBPATHS	:=	$(foreach dir,$(LIBDIRS),-L$(dir)/lib)
+
+ifeq ($(strip $(ICON)),)
+	icons := $(wildcard *.png)
+	ifneq (,$(findstring $(TARGET).png,$(icons)))
+		export APP_ICON := $(TOPDIR)/$(TARGET).png
+	else
+		ifneq (,$(findstring icon.png,$(icons)))
+			export APP_ICON := $(TOPDIR)/icon.png
+		endif
+	endif
+else
+	export APP_ICON := $(TOPDIR)/$(ICON)
+endif
+
+.PHONY: $(BUILD) clean all
+
+#---------------------------------------------------------------------------------
+all: $(BUILD)
+
+$(BUILD):
+	@[ -d $@ ] || mkdir -p $@
+	@make --no-print-directory -C $(BUILD) -f $(CURDIR)/Makefile
+
+#---------------------------------------------------------------------------------
+clean:
+	@echo clean ...
+	@rm -fr $(BUILD) $(TARGET).3dsx $(OUTPUT).smdh $(TARGET).elf
+
+
+#---------------------------------------------------------------------------------
+else
+
+DEPENDS	:=	$(OFILES:.o=.d)
+
+#---------------------------------------------------------------------------------
+# main targets
+#---------------------------------------------------------------------------------
+ifeq ($(strip $(NO_SMDH)),)
+.PHONY: all
+all	:	$(OUTPUT).3dsx $(OUTPUT).smdh
+endif
+$(OUTPUT).3dsx	:	$(OUTPUT).elf
+$(OUTPUT).elf	:	$(OFILES)
+
+#---------------------------------------------------------------------------------
+# you need a rule like this for each extension you use as binary data
+#---------------------------------------------------------------------------------
+%.bin.o	:	%.bin
+#---------------------------------------------------------------------------------
+	@echo $(notdir $<)
+	@$(bin2o)
+
+# WARNING: This is not the right way to do this! TODO: Do it right!
+#---------------------------------------------------------------------------------
+%.vsh.o	:	%.vsh
+#---------------------------------------------------------------------------------
+	@echo $(notdir $<)
+	picasso ../$(notdir $<).shbin $< 
+	@bin2s ../$(notdir $<).shbin | $(PREFIX)as -o $@
+	@echo "extern const u8" `(echo $(notdir $<).shbin | sed -e 's/^\([0-9]\)/_\1/' | tr . _)`"_end[];" > `(echo $(notdir $<).shbin | tr . _)`.h
+	@echo "extern const u8" `(echo $(notdir $<).shbin | sed -e 's/^\([0-9]\)/_\1/' | tr . _)`"[];" >> `(echo $(notdir $<).shbin | tr . _)`.h
+	@echo "extern const u32" `(echo $(notdir $<).shbin | sed -e 's/^\([0-9]\)/_\1/' | tr . _)`_size";" >> `(echo $(notdir $<).shbin | tr . _)`.h
+	@rm ../$(notdir $<).shbin
+
+-include $(DEPENDS)
+
+#---------------------------------------------------------------------------------------
+endif
+#---------------------------------------------------------------------------------------
diff --git a/examples/graphics/hello_triangle/README.md b/examples/graphics/hello_triangle/README.md
new file mode 100644
index 0000000..00535b6
--- /dev/null
+++ b/examples/graphics/hello_triangle/README.md
@@ -0,0 +1,4 @@
+Hello Triangle
+
+A simple GPU demo to display a white triangle.
+Requires the [picasso](https://github.com/fincs/picasso) shader assembler.
\ No newline at end of file
diff --git a/examples/graphics/hello_triangle/data/shader.vsh b/examples/graphics/hello_triangle/data/shader.vsh
new file mode 100644
index 0000000..d86c35a
--- /dev/null
+++ b/examples/graphics/hello_triangle/data/shader.vsh
@@ -0,0 +1,32 @@
+; Really simple & stupid PICA200 shader
+; Taken from picasso example
+
+; Uniforms
+.fvec projection[4]
+
+; Constants
+.constf myconst(0.0, 1.0, -1.0, 0.0)
+.alias ones myconst.yyyy ; (1.0,1.0,1.0,1.0)
+
+; Outputs : here only position and color
+.out outpos position
+.out outclr color
+
+; Inputs : here we have only vertices
+.alias inpos v0
+
+.proc main
+	; r0 = (inpos.x, inpos.y, inpos.z, 1.0)
+	mov r0.xyz, inpos
+	mov r0.w, ones
+	
+	; outpos = projection * r1
+	dp4 outpos.x, projection[0], r0
+	dp4 outpos.y, projection[1], r0
+	dp4 outpos.z, projection[2], r0
+	dp4 outpos.w, projection[3], r0
+	
+	; Set vertex color to white
+	mov outclr, ones
+	end
+.end
\ No newline at end of file
diff --git a/examples/graphics/hello_triangle/source/3dutils.c b/examples/graphics/hello_triangle/source/3dutils.c
new file mode 100644
index 0000000..45215b8
--- /dev/null
+++ b/examples/graphics/hello_triangle/source/3dutils.c
@@ -0,0 +1,31 @@
+//
+// Created by Lectem on 22/03/2015.
+//
+
+#include "3dutils.h"
+
+void SetUniformMatrix(u32 startreg, float* m) {
+    float param[16];
+
+    param[0x0]=m[3]; //w
+    param[0x1]=m[2]; //z
+    param[0x2]=m[1]; //y
+    param[0x3]=m[0]; //x
+
+    param[0x4]=m[7];
+    param[0x5]=m[6];
+    param[0x6]=m[5];
+    param[0x7]=m[4];
+
+    param[0x8]=m[11];
+    param[0x9]=m[10];
+    param[0xa]=m[9];
+    param[0xb]=m[8];
+
+    param[0xc]=m[15];
+    param[0xd]=m[14];
+    param[0xe]=m[13];
+    param[0xf]=m[12];
+
+    GPU_SetFloatUniform(GPU_VERTEX_SHADER, startreg, (u32*)param, 4);
+}
diff --git a/examples/graphics/hello_triangle/source/3dutils.h b/examples/graphics/hello_triangle/source/3dutils.h
new file mode 100644
index 0000000..9e3f859
--- /dev/null
+++ b/examples/graphics/hello_triangle/source/3dutils.h
@@ -0,0 +1,10 @@
+//
+// Created by Lectem on 22/03/2015.
+//
+
+#ifndef _2DGPU_3DUTILS_H_
+#define _2DGPU_3DUTILS_H_
+#include <3ds.h>
+void SetUniformMatrix(u32 startreg, float* m);
+
+#endif //_2DGPU_3DUTILS_H_
diff --git a/examples/graphics/hello_triangle/source/main.c b/examples/graphics/hello_triangle/source/main.c
new file mode 100644
index 0000000..fe6f25a
--- /dev/null
+++ b/examples/graphics/hello_triangle/source/main.c
@@ -0,0 +1,246 @@
+#include <3ds.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include "shader_vsh_shbin.h"
+#include "3dutils.h"
+#include "mmath.h"
+
+
+#define STRINGIZE(x) STRINGIZE2(x)
+#define STRINGIZE2(x) #x
+#define LINE_STRING STRINGIZE(__LINE__)
+#define my_assert(e) ((e) ? (void)0 : _my_assert("assert failed at " __FILE__ ":" LINE_STRING " (" #e ")\n"))
+void _my_assert(char * text)
+{
+    printf("%s\n",text);
+    do{
+        hidScanInput();
+        if(keysDown()&KEY_START)break;
+        gfxFlushBuffers();
+        gfxSwapBuffers();
+        gspWaitForVBlank();
+    }while(aptMainLoop());
+    exit(0);
+}
+
+
+
+
+typedef struct {
+    float x, y, z;
+} vector_3f;
+
+
+typedef struct {
+    float r, g, b, a;
+} vector_4f;
+
+typedef struct {
+    vector_3f position;
+    vector_4f color;
+} vertex_pos_col;
+
+#define GPU_CMD_SIZE 0x40000
+
+//GPU framebuffer address
+u32* gpuFBuffer =(u32*)0x1F119400;
+//GPU depth buffer address
+u32* gpuDBuffer =(u32*)0x1F370800;
+
+//GPU command buffers
+u32* gpuCmd = NULL;
+
+//shader structure
+DVLB_s* shader_dvlb;    //the header
+shaderProgram_s shader; //the program
+
+
+Result projUniformRegister      =-1;
+Result modelviewUniformRegister =-1;
+
+#define RGBA8(r,g,b,a) ((((r)&0xFF)<<24) | (((g)&0xFF)<<16) | (((b)&0xFF)<<8) | (((a)&0xFF)<<0))
+
+//The color used to clear the screen
+u32 clearColor=RGBA8(0x68, 0xB0, 0xD8, 0xFF);
+
+//The projection matrix
+static float ortho_matrix[4*4];
+
+void GPU_SetDummyTexEnv(u8 num);
+void gpuUIEndFrame();
+
+void gpuUIInit()
+{
+
+    GPU_Init(NULL);//initialize GPU
+
+    gfxSet3D(false);//We will not be using the 3D mode in this example
+    Result res=0;
+
+    /**
+    * Load our vertex shader and its uniforms
+    * Check http://3dbrew.org/wiki/SHBIN for more informations about the shader binaries
+    */
+    shader_dvlb = DVLB_ParseFile((u32 *)shader_vsh_shbin, shader_vsh_shbin_size);//load our vertex shader binary
+    my_assert(shader_dvlb != NULL);
+    shaderProgramInit(&shader);
+    res = shaderProgramSetVsh(&shader, &shader_dvlb->DVLE[0]);
+    my_assert(res >=0); // check for errors
+
+    //In this example we are only rendering in "2D mode", so we don't need one command buffer per eye
+    gpuCmd=(u32*)linearAlloc(GPU_CMD_SIZE * (sizeof *gpuCmd) ); //Don't forget that commands size is 4 (hence the sizeof)
+    my_assert(gpuCmd != NULL);
+
+    //Reset the gpu
+    //This actually needs a command buffer to work, and will then use it as default
+    GPU_Reset(NULL, gpuCmd, GPU_CMD_SIZE);
+
+    projUniformRegister = shaderInstanceGetUniformLocation(shader.vertexShader, "projection");
+    my_assert(projUniformRegister != -1); // make sure we did get the uniform
+
+
+    shaderProgramUse(&shader); // Select the shader to use
+
+
+
+    initOrthographicMatrix(ortho_matrix, 0.0f, 400.0f, 0.0f, 240.0f, 0.0f, 1.0f); // A basic projection for 2D drawings
+    SetUniformMatrix(projUniformRegister, ortho_matrix); // Upload the matrix to the GPU
+
+    //Flush buffers and setup the environment for the next frame
+    gpuUIEndFrame();
+
+}
+
+void gpuUIExit()
+{
+    //do things properly
+    linearFree(gpuCmd);
+    shaderProgramFree(&shader);
+    DVLB_Free(shader_dvlb);
+    GPU_Reset(NULL, gpuCmd, GPU_CMD_SIZE); // Not really needed, but safer for the next applications ?
+}
+
+void gpuUIEndFrame()
+{
+    //Ask the GPU to draw everything (execute the commands)
+    GPU_FinishDrawing();
+    GPUCMD_Finalize();
+    GPUCMD_FlushAndRun(NULL);
+    gspWaitForP3D();
+    //Draw the screen
+    GX_SetDisplayTransfer(NULL, gpuFBuffer, 0x019001E0, (u32*)gfxGetFramebuffer(GFX_TOP, GFX_LEFT, NULL, NULL), 0x019001E0, 0x01001000);
+    gspWaitForPPF();
+    //Clear the screen
+    GX_SetMemoryFill(NULL, gpuFBuffer, clearColor, &gpuFBuffer[0x2EE00],
+            0x201, gpuDBuffer, 0x00000000, &gpuDBuffer[0x2EE00], 0x201);
+    gspWaitForPSC0();
+    gfxSwapBuffersGpu();
+
+    //Wait for the screen to be updated
+    gspWaitForVBlank();
+
+    //Get ready to start a new frame
+    GPUCMD_SetBufferOffset(0);
+
+    //Viewport (http://3dbrew.org/wiki/GPU_Commands#Command_0x0041)
+    GPU_SetViewport((u32 *)osConvertVirtToPhys((u32)gpuDBuffer),
+            (u32 *)osConvertVirtToPhys((u32)gpuFBuffer),
+            0, 0, 240*2, 400);    //Our screen is 400*240, and we actually have 2 framebuffers, even without 3D mode activated
+
+
+    GPU_DepthMap(-1.0f, 0.0f);  //Be careful, standard OpenGL clipping is [-1;1], but it is [-1;0] on the pica200
+    // Note : this is corrected by our projection matrix !
+
+    //Sets the texture environment parameters not to modify our pixels at fragment stage
+    //See https://www.opengl.org/sdk/docs/man2/xhtml/glTexEnv.xml for more insight
+    GPU_SetTexEnv(
+            0,
+            GPU_TEVSOURCES(GPU_PRIMARY_COLOR, GPU_PRIMARY_COLOR, GPU_PRIMARY_COLOR),
+            GPU_TEVSOURCES(GPU_PRIMARY_COLOR, GPU_PRIMARY_COLOR, GPU_PRIMARY_COLOR),
+            GPU_TEVOPERANDS(0,0,0),
+            GPU_TEVOPERANDS(0,0,0),
+            GPU_REPLACE, GPU_REPLACE,
+            0xFFFFFFFF
+    );
+    GPU_SetDummyTexEnv(1);
+    GPU_SetDummyTexEnv(2);
+    GPU_SetDummyTexEnv(3);
+    GPU_SetDummyTexEnv(4);
+    GPU_SetDummyTexEnv(5);
+}
+
+
+
+//Our data
+static const vector_3f triangle_mesh[] =
+    {
+            {240.0f+60.0f, 120.0f,       0.5f},
+            {240.0f-60.0f, 120.0f+60.0f, 0.5f},
+            {240.0f-60.0f, 120.0f-60.0f, 0.5f}
+    };
+
+static void* triangle_data = NULL;
+
+int main(int argc, char** argv)
+{
+
+    srvInit();
+    aptInit();
+    hidInit(NULL);
+
+    gfxInitDefault();
+    consoleInit(GFX_BOTTOM, NULL);
+
+
+    gpuUIInit();
+    printf("hello triangle !\n");
+    triangle_data = linearAlloc(sizeof(triangle_mesh));     //allocate our vbo on the linear heap
+    memcpy(triangle_data, triangle_mesh, sizeof(triangle_mesh)); //Copy our data
+
+    do{
+        hidScanInput();
+        if(keysDown()&KEY_START)break; //Stop the program when Start is pressed
+
+        //Setup the buffers data
+        GPU_SetAttributeBuffers(
+                1, // number of attributes
+                (u32 *) osConvertVirtToPhys((u32) triangle_data),
+                GPU_ATTRIBFMT(0, 3, GPU_FLOAT),//We only have vertices
+                0xFFFE,//Attribute mask, in our case 0b1110
+                0x0,//Attribute permutations (here it is the identity)
+                1, //number of buffers
+                (u32[]) {0x0}, // buffer offsets (placeholders)
+                (u64[]) {0x0}, // attribute permutations for each buffer (identity again)
+                (u8[]) {1} // number of attributes for each buffer
+            );
+        //Display the buffers data
+        GPU_DrawArray(GPU_TRIANGLES, sizeof(triangle_mesh) / sizeof(triangle_mesh[0]));
+
+        gpuUIEndFrame();
+
+    }while(aptMainLoop());
+    gpuUIExit();
+
+
+    gfxExit();
+    hidExit();
+    aptExit();
+    srvExit();
+
+	return 0;
+}
+
+
+void GPU_SetDummyTexEnv(u8 num)
+{
+    //Don't touch the colors of the previous stages
+    GPU_SetTexEnv(num,
+            GPU_TEVSOURCES(GPU_PREVIOUS, 0, 0),
+            GPU_TEVSOURCES(GPU_PREVIOUS, 0, 0),
+            GPU_TEVOPERANDS(0,0,0),
+            GPU_TEVOPERANDS(0,0,0),
+            GPU_REPLACE,
+            GPU_REPLACE,
+            0xFFFFFFFF);
+}
\ No newline at end of file
diff --git a/examples/graphics/hello_triangle/source/mmath.c b/examples/graphics/hello_triangle/source/mmath.c
new file mode 100644
index 0000000..e7715d1
--- /dev/null
+++ b/examples/graphics/hello_triangle/source/mmath.c
@@ -0,0 +1,203 @@
+#include <math.h>
+#include <string.h>
+#include <stdio.h>
+#include <stdbool.h>
+#include <3ds.h>
+#include "mmath.h"
+
+void loadIdentity44(float* m)
+{
+	if(!m)return;
+
+	memset(m, 0x00, 16*4);
+	m[0]=m[5]=m[10]=m[15]=1.0f;
+}
+
+void multMatrix44(float* m1, float* m2, float* m) //4x4
+{
+	int i, j;
+	for(i=0;i<4;i++)for(j=0;j<4;j++)m[i+j*4]=(m1[0+j*4]*m2[i+0*4])+(m1[1+j*4]*m2[i+1*4])+(m1[2+j*4]*m2[i+2*4])+(m1[3+j*4]*m2[i+3*4]);
+
+}
+
+void translateMatrix(float* tm, float x, float y, float z)
+{
+	float rm[16], m[16];
+
+	loadIdentity44(rm);
+	rm[3]=x;
+	rm[7]=y;
+	rm[11]=z;
+	
+	multMatrix44(tm,rm,m);
+	memcpy(tm,m,16*sizeof(float));
+}
+
+// 00 01 02 03
+// 04 05 06 07
+// 08 09 10 11
+// 12 13 14 15
+
+void rotateMatrixX(float* tm, float x, bool r)
+{
+	float rm[16], m[16];
+	memset(rm, 0x00, 16*4);
+	rm[0]=1.0f;
+	rm[5]=cos(x);
+	rm[6]=sin(x);
+	rm[9]=-sin(x);
+	rm[10]=cos(x);
+	rm[15]=1.0f;
+	if(!r)multMatrix44(tm,rm,m);
+	else multMatrix44(rm,tm,m);
+	memcpy(tm,m,16*sizeof(float));
+}
+
+void rotateMatrixY(float* tm, float x, bool r)
+{
+	float rm[16], m[16];
+	memset(rm, 0x00, 16*4);
+	rm[0]=cos(x);
+	rm[2]=sin(x);
+	rm[5]=1.0f;
+	rm[8]=-sin(x);
+	rm[10]=cos(x);
+	rm[15]=1.0f;
+	if(!r)multMatrix44(tm,rm,m);
+	else multMatrix44(rm,tm,m);
+	memcpy(tm,m,16*sizeof(float));
+}
+
+void rotateMatrixZ(float* tm, float x, bool r)
+{
+	float rm[16], m[16];
+	memset(rm, 0x00, 16*4);
+	rm[0]=cos(x);
+	rm[1]=sin(x);
+	rm[4]=-sin(x);
+	rm[5]=cos(x);
+	rm[10]=1.0f;
+	rm[15]=1.0f;
+	if(!r)multMatrix44(tm,rm,m);
+	else multMatrix44(rm,tm,m);
+	memcpy(tm,m,16*sizeof(float));
+}
+
+void scaleMatrix(float* tm, float x, float y, float z)
+{
+	tm[0]*=x; tm[4]*=x; tm[8]*=x; tm[12]*=x;
+	tm[1]*=y; tm[5]*=y; tm[9]*=y; tm[13]*=y;
+	tm[2]*=z; tm[6]*=z; tm[10]*=z; tm[14]*=z;
+}
+
+void initProjectionMatrix(float* m, float fovy, float aspect, float near, float far)
+{
+	float top = near*tan(fovy/2);
+	float right = (top*aspect);
+
+	float mp[4*4];
+	
+	mp[0x0] = near/right;
+	mp[0x1] = 0.0f;
+	mp[0x2] = 0.0f;
+	mp[0x3] = 0.0f;
+
+	mp[0x4] = 0.0f;
+	mp[0x5] = near/top;
+	mp[0x6] = 0.0f;
+	mp[0x7] = 0.0f;
+
+	mp[0x8] = 0.0f;
+	mp[0x9] = 0.0f;
+	mp[0xA] = -(far+near)/(far-near);
+	mp[0xB] = -2.0f*(far*near)/(far-near);
+
+	mp[0xC] = 0.0f;
+	mp[0xD] = 0.0f;
+	mp[0xE] = -1.0f;
+	mp[0xF] = 0.0f;
+
+	float mp2[4*4];
+	loadIdentity44(mp2);
+	mp2[0xA]=0.5;
+	mp2[0xB]=-0.5;
+
+	multMatrix44(mp2, mp, m);
+}
+
+void initOrthographicMatrix(float *m, float left, float right, float bottom, float top, float near, float far)
+{
+	/*  ______________________
+       |                      |
+       |                      |
+       |                      |
+       |                      |
+       |                      |
+       |______________________| ^
+                                | x
+                           <-----
+                             y
+    */
+
+	//Mirror
+	//right = 400-right;
+	//left = 400-left;
+	//top = 240-top;
+	//bottom = 240-bottom;
+
+	float mp[4*4];
+
+	mp[0x0] = 2.0f/(right-left);
+	mp[0x1] = 0.0f;
+	mp[0x2] = 0.0f;
+	mp[0x3] = -(right+left)/(right-left);
+
+	mp[0x4] = 0.0f;
+	mp[0x5] = 2.0f/(top-bottom);
+	mp[0x6] = 0.0f;
+	mp[0x7] = -(top+bottom)/(top-bottom);
+
+	mp[0x8] = 0.0f;
+	mp[0x9] = 0.0f;
+	mp[0xA] = -2.0f/(far-near);
+	mp[0xB] = (far+near)/(far-near);
+
+	mp[0xC] = 0.0f;
+	mp[0xD] = 0.0f;
+	mp[0xE] = 0.0f;
+	mp[0xF] = 1.0f;
+
+	float mp2[4*4];
+	loadIdentity44(mp2);
+	mp2[0xA] = 0.5;
+	mp2[0xB] = -0.5;
+
+	//Convert Z [-1, 1] to [-1, 0] (PICA shiz)
+	multMatrix44(mp2, mp, m);
+
+	//rotateMatrixZ(m, M_PI/2, false);
+}
+
+vect3Df_s getMatrixColumn(float* m, u8 i)
+{
+	if(!m || i>=4)return vect3Df(0,0,0);
+	return vect3Df(m[0+i*4],m[1+i*4],m[2+i*4]);
+}
+
+vect3Df_s getMatrixRow(float* m, u8 i)
+{
+	if(!m || i>=4)return vect3Df(0,0,0);
+	return vect3Df(m[i+0*4],m[i+1*4],m[i+2*4]);
+}
+
+vect4Df_s getMatrixColumn4(float* m, u8 i)
+{
+	if(!m || i>=4)return vect4Df(0,0,0,0);
+	return vect4Df(m[0+i*4],m[1+i*4],m[2+i*4],m[3+i*4]);
+}
+
+vect4Df_s getMatrixRow4(float* m, u8 i)
+{
+	if(!m || i>=4)return vect4Df(0,0,0,0);
+	return vect4Df(m[i+0*4],m[i+1*4],m[i+2*4],m[i+3*4]);
+}
diff --git a/examples/graphics/hello_triangle/source/mmath.h b/examples/graphics/hello_triangle/source/mmath.h
new file mode 100644
index 0000000..370b3c2
--- /dev/null
+++ b/examples/graphics/hello_triangle/source/mmath.h
@@ -0,0 +1,152 @@
+#ifndef MATH_H
+#define MATH_H
+#ifdef __cplusplus
+extern "C" {
+#endif
+#include <3ds/types.h>
+#include <math.h>
+#pragma GCC diagnostic ignored "-Wnarrowing"
+
+
+typedef float mtx44[4][4];
+typedef float mtx33[3][3];
+
+typedef struct
+{
+	s32 x, y, z;
+}vect3Di_s;
+
+static inline vect3Di_s vect3Di(s32 x, s32 y, s32 z)
+{
+	return (vect3Di_s){x,y,z};
+}
+
+static inline vect3Di_s vaddi(vect3Di_s u, vect3Di_s v)
+{
+	return (vect3Di_s){u.x+v.x,u.y+v.y,u.z+v.z};
+}
+
+static inline vect3Di_s vsubi(vect3Di_s u, vect3Di_s v)
+{
+	return (vect3Di_s){u.x-v.x,u.y-v.y,u.z-v.z};
+}
+
+static inline vect3Di_s vmuli(vect3Di_s v, s32 f)
+{
+	return (vect3Di_s){v.x*f,v.y*f,v.z*f};
+}
+
+typedef struct
+{
+	float x, y, z;
+}vect3Df_s;
+
+static inline vect3Df_s vect3Df(float x, float y, float z)
+{
+	return (vect3Df_s){x,y,z};
+}
+
+static inline vect3Df_s vaddf(vect3Df_s u, vect3Df_s v)
+{
+	return (vect3Df_s){u.x+v.x,u.y+v.y,u.z+v.z};
+}
+
+static inline vect3Df_s vsubf(vect3Df_s u, vect3Df_s v)
+{
+	return (vect3Df_s){u.x-v.x,u.y-v.y,u.z-v.z};
+}
+
+static inline vect3Df_s vmulf(vect3Df_s v, float f)
+{
+	return (vect3Df_s){v.x*f,v.y*f,v.z*f};
+}
+
+static inline vect3Df_s vscalef(vect3Df_s v1, vect3Df_s v2)
+{
+	return (vect3Df_s){v1.x*v2.x,v1.y*v2.y,v1.z*v2.z};
+}
+
+static inline float vmagf(vect3Df_s v)
+{
+	return sqrtf(v.x*v.x+v.y*v.y+v.z*v.z);
+}
+
+static inline float vdistf(vect3Df_s v1, vect3Df_s v2)
+{
+	return sqrtf((v1.x-v2.x)*(v1.x-v2.x)+(v1.y-v2.y)*(v1.y-v2.y)+(v1.z-v2.z)*(v1.z-v2.z));
+}
+
+static inline vect3Df_s vnormf(vect3Df_s v)
+{
+	const float l=sqrtf(v.x*v.x+v.y*v.y+v.z*v.z);
+	return (vect3Df_s){v.x/l,v.y/l,v.z/l};
+}
+
+typedef struct
+{
+	float x, y, z, w;
+}vect4Df_s;
+
+static inline vect4Df_s vect4Df(float x, float y, float z, float w)
+{
+	return (vect4Df_s){x,y,z,w};
+}
+
+static inline vect4Df_s vaddf4(vect4Df_s u, vect4Df_s v)
+{
+	return (vect4Df_s){u.x+v.x,u.y+v.y,u.z+v.z,u.w+v.w};
+}
+
+static inline vect4Df_s vsubf4(vect4Df_s u, vect4Df_s v)
+{
+	return (vect4Df_s){u.x-v.x,u.y-v.y,u.z-v.z,u.w-v.w};
+}
+
+static inline vect4Df_s vmulf4(vect4Df_s v, float f)
+{
+	return (vect4Df_s){v.x*f,v.y*f,v.z*f,v.w*f};
+}
+
+static inline float vdotf4(vect4Df_s v1, vect4Df_s v2)
+{
+	return v1.x*v2.x+v1.y*v2.y+v1.z*v2.z+v1.w*v2.w;
+}
+
+static inline vect4Df_s vnormf4(vect4Df_s v)
+{
+	const float l=sqrtf(v.x*v.x+v.y*v.y+v.z*v.z+v.w*v.w);
+	return (vect4Df_s){v.x/l,v.y/l,v.z/l,v.w/l};
+}
+
+//interstuff
+static inline vect3Di_s vf2i(vect3Df_s v)
+{
+	return (vect3Di_s){floorf(v.x),floorf(v.y),floorf(v.z)};
+}
+
+static inline vect3Df_s vi2f(vect3Di_s v)
+{
+	return (vect3Df_s){(float)v.x,(float)v.y,(float)v.z};
+}
+
+void loadIdentity44(float* m);
+void multMatrix44(float* m1, float* m2, float* m);
+
+void translateMatrix(float* tm, float x, float y, float z);
+void rotateMatrixX(float* tm, float x, bool r);
+void rotateMatrixY(float* tm, float x, bool r);
+void rotateMatrixZ(float* tm, float x, bool r);
+void scaleMatrix(float* tm, float x, float y, float z);
+
+void initProjectionMatrix(float* m, float fovy, float aspect, float near, float far);
+void initOrthographicMatrix(float *m, float left, float right, float bottom, float top, float near, float far);
+
+
+vect3Df_s getMatrixColumn(float* m, u8 i);
+vect3Df_s getMatrixRow(float* m, u8 i);
+vect4Df_s getMatrixColumn4(float* m, u8 i);
+vect4Df_s getMatrixRow4(float* m, u8 i);
+#ifdef __cplusplus
+}
+#endif
+#endif

From 56556baaa7b39f3000a08ff03569ca355f8c365c Mon Sep 17 00:00:00 2001
From: Lectem <lectem@gmail.com>
Date: Mon, 23 Mar 2015 23:54:46 +0100
Subject: [PATCH 15/16] bit more comments

---
 .../graphics/hello_triangle/source/main.c     | 19 ++++++++++++++-----
 1 file changed, 14 insertions(+), 5 deletions(-)

diff --git a/examples/graphics/hello_triangle/source/main.c b/examples/graphics/hello_triangle/source/main.c
index fe6f25a..872a5de 100644
--- a/examples/graphics/hello_triangle/source/main.c
+++ b/examples/graphics/hello_triangle/source/main.c
@@ -7,6 +7,10 @@
 #include "mmath.h"
 
 
+
+/**
+* Crappy assert stuff that lets you go back to hbmenu by pressing start. 
+*/
 #define STRINGIZE(x) STRINGIZE2(x)
 #define STRINGIZE2(x) #x
 #define LINE_STRING STRINGIZE(__LINE__)
@@ -21,7 +25,7 @@ void _my_assert(char * text)
         gfxSwapBuffers();
         gspWaitForVBlank();
     }while(aptMainLoop());
-    exit(0);
+    //should stop the program and clean up our mess
 }
 
 
@@ -127,10 +131,12 @@ void gpuUIEndFrame()
     GPU_FinishDrawing();
     GPUCMD_Finalize();
     GPUCMD_FlushAndRun(NULL);
-    gspWaitForP3D();
-    //Draw the screen
+    gspWaitForP3D();//Wait for the gpu 3d processing to be done
+    //Copy the GPU output buffer to the screen framebuffer
+	//See http://3dbrew.org/wiki/GPU#Transfer_Engine for more details about the transfer engine 
     GX_SetDisplayTransfer(NULL, gpuFBuffer, 0x019001E0, (u32*)gfxGetFramebuffer(GFX_TOP, GFX_LEFT, NULL, NULL), 0x019001E0, 0x01001000);
     gspWaitForPPF();
+	
     //Clear the screen
     GX_SetMemoryFill(NULL, gpuFBuffer, clearColor, &gpuFBuffer[0x2EE00],
             0x201, gpuDBuffer, 0x00000000, &gpuDBuffer[0x2EE00], 0x201);
@@ -146,7 +152,10 @@ void gpuUIEndFrame()
     //Viewport (http://3dbrew.org/wiki/GPU_Commands#Command_0x0041)
     GPU_SetViewport((u32 *)osConvertVirtToPhys((u32)gpuDBuffer),
             (u32 *)osConvertVirtToPhys((u32)gpuFBuffer),
-            0, 0, 240*2, 400);    //Our screen is 400*240, and we actually have 2 framebuffers, even without 3D mode activated
+            0, 0, 
+			//Our screen is 400*240, but the GPU actually renders to 400*480 and then downscales it SetDisplayTransfer bit 24 is set 
+			//This is the case here (See http://3dbrew.org/wiki/GPU#0x1EF00C10 for more details)
+			240*2, 400);    
 
 
     GPU_DepthMap(-1.0f, 0.0f);  //Be careful, standard OpenGL clipping is [-1;1], but it is [-1;0] on the pica200
@@ -207,7 +216,7 @@ int main(int argc, char** argv)
                 1, // number of attributes
                 (u32 *) osConvertVirtToPhys((u32) triangle_data),
                 GPU_ATTRIBFMT(0, 3, GPU_FLOAT),//We only have vertices
-                0xFFFE,//Attribute mask, in our case 0b1110
+                0xFFFE,//Attribute mask, in our case 0b1110 since we use only the first one
                 0x0,//Attribute permutations (here it is the identity)
                 1, //number of buffers
                 (u32[]) {0x0}, // buffer offsets (placeholders)

From 134f27f520805f08942c967ea24e1937354b119d Mon Sep 17 00:00:00 2001
From: Lectem <lectem@gmail.com>
Date: Tue, 24 Mar 2015 00:11:52 +0100
Subject: [PATCH 16/16] last bit of modif

---
 .../graphics/hello_triangle/data/shader.vsh   |  2 +-
 .../graphics/hello_triangle/source/main.c     | 37 ++++++++++++-------
 2 files changed, 25 insertions(+), 14 deletions(-)

diff --git a/examples/graphics/hello_triangle/data/shader.vsh b/examples/graphics/hello_triangle/data/shader.vsh
index d86c35a..57a694c 100644
--- a/examples/graphics/hello_triangle/data/shader.vsh
+++ b/examples/graphics/hello_triangle/data/shader.vsh
@@ -26,7 +26,7 @@
 	dp4 outpos.z, projection[2], r0
 	dp4 outpos.w, projection[3], r0
 	
-	; Set vertex color to white
+	; Set vertex color to white rgba => (1.0,1.0,1.0,1.0)
 	mov outclr, ones
 	end
 .end
\ No newline at end of file
diff --git a/examples/graphics/hello_triangle/source/main.c b/examples/graphics/hello_triangle/source/main.c
index 872a5de..551048e 100644
--- a/examples/graphics/hello_triangle/source/main.c
+++ b/examples/graphics/hello_triangle/source/main.c
@@ -1,3 +1,14 @@
+/**
+* Hello Triangle example, made by Lectem
+*
+* Draws a white triangle using the 3DS GPU.
+* This example should give you enough hints and links on how to use the GPU for basic non-textured rendering.
+* Another version of this example will be made with colors.
+*
+* Thanks to smea, fincs, neobrain, xerpi and all those who helped me understand how the 3DS GPU works
+*/
+
+
 #include <3ds.h>
 #include <stdio.h>
 #include <stdlib.h>
@@ -133,10 +144,10 @@ void gpuUIEndFrame()
     GPUCMD_FlushAndRun(NULL);
     gspWaitForP3D();//Wait for the gpu 3d processing to be done
     //Copy the GPU output buffer to the screen framebuffer
-	//See http://3dbrew.org/wiki/GPU#Transfer_Engine for more details about the transfer engine 
+    //See http://3dbrew.org/wiki/GPU#Transfer_Engine for more details about the transfer engine
     GX_SetDisplayTransfer(NULL, gpuFBuffer, 0x019001E0, (u32*)gfxGetFramebuffer(GFX_TOP, GFX_LEFT, NULL, NULL), 0x019001E0, 0x01001000);
     gspWaitForPPF();
-	
+
     //Clear the screen
     GX_SetMemoryFill(NULL, gpuFBuffer, clearColor, &gpuFBuffer[0x2EE00],
             0x201, gpuDBuffer, 0x00000000, &gpuDBuffer[0x2EE00], 0x201);
@@ -152,10 +163,10 @@ void gpuUIEndFrame()
     //Viewport (http://3dbrew.org/wiki/GPU_Commands#Command_0x0041)
     GPU_SetViewport((u32 *)osConvertVirtToPhys((u32)gpuDBuffer),
             (u32 *)osConvertVirtToPhys((u32)gpuFBuffer),
-            0, 0, 
-			//Our screen is 400*240, but the GPU actually renders to 400*480 and then downscales it SetDisplayTransfer bit 24 is set 
-			//This is the case here (See http://3dbrew.org/wiki/GPU#0x1EF00C10 for more details)
-			240*2, 400);    
+            0, 0,
+            //Our screen is 400*240, but the GPU actually renders to 400*480 and then downscales it SetDisplayTransfer bit 24 is set
+            //This is the case here (See http://3dbrew.org/wiki/GPU#0x1EF00C10 for more details)
+            240*2, 400);
 
 
     GPU_DepthMap(-1.0f, 0.0f);  //Be careful, standard OpenGL clipping is [-1;1], but it is [-1;0] on the pica200
@@ -183,11 +194,11 @@ void gpuUIEndFrame()
 
 //Our data
 static const vector_3f triangle_mesh[] =
-    {
-            {240.0f+60.0f, 120.0f,       0.5f},
-            {240.0f-60.0f, 120.0f+60.0f, 0.5f},
-            {240.0f-60.0f, 120.0f-60.0f, 0.5f}
-    };
+        {
+                {240.0f+60.0f, 120.0f,       0.5f},
+                {240.0f-60.0f, 120.0f+60.0f, 0.5f},
+                {240.0f-60.0f, 120.0f-60.0f, 0.5f}
+        };
 
 static void* triangle_data = NULL;
 
@@ -222,7 +233,7 @@ int main(int argc, char** argv)
                 (u32[]) {0x0}, // buffer offsets (placeholders)
                 (u64[]) {0x0}, // attribute permutations for each buffer (identity again)
                 (u8[]) {1} // number of attributes for each buffer
-            );
+        );
         //Display the buffers data
         GPU_DrawArray(GPU_TRIANGLES, sizeof(triangle_mesh) / sizeof(triangle_mesh[0]));
 
@@ -237,7 +248,7 @@ int main(int argc, char** argv)
     aptExit();
     srvExit();
 
-	return 0;
+    return 0;
 }