Added preliminary generated API documentation

2 files changed, 184 insertions, 52 deletions

diff --git a/scripts/generator/generator.py b/scripts/generator/generator.py
index 75c0a093..47972714 100644
--- a/scripts/generator/generator.py
+++ b/scripts/generator/generator.py
@@ -18,6 +18,7 @@
 # It also generates the main functions for the correctness and performance tests as found in
 #    test/correctness/routines/levelX/xYYYY.cc
 #    test/performance/routines/levelX/xYYYY.cc
+# It also produces the API documentation found in doc/clblast.md
 #
 # ==================================================================================================
 
@@ -59,62 +60,62 @@ TU = DataType("TU", "typename T, typename U", "T,U", ["T", "U", "T", "U"], "T")
 # Populates a list of routines
 routines = [
 [ # Level 1: vector-vector
-  Routine(False, True,  "1", "rotg",  T,  [S,D],     [], [], [], ["sa","sb","sc","ss"], [], "", "Generate givens plane rotation"),
-  Routine(False, True,  "1", "rotmg", T,  [S,D],     [], [], ["sy1"], ["sd1","sd2","sx1","sparam"], [], "", "Generate modified givens plane rotation"),
-  Routine(False, True,  "1", "rot",   T,  [S,D],     ["n"], [], [], ["x","y"], ["cos","sin"], "", "Apply givens plane rotation"),
-  Routine(False, True,  "1", "rotm",  T,  [S,D],     ["n"], [], [], ["x","y","sparam"], [], "", "Apply modified givens plane rotation"),
-  Routine(True,  True,  "1", "swap",  T,  [S,D,C,Z], ["n"], [], [], ["x","y"], [], "", "Swap two vectors"),
-  Routine(True,  True,  "1", "scal",  T,  [S,D,C,Z], ["n"], [], [], ["x"], ["alpha"], "", "Vector scaling"),
-  Routine(True,  True,  "1", "copy",  T,  [S,D,C,Z], ["n"], [], ["x"], ["y"], [], "", "Vector copy"),
-  Routine(True,  True,  "1", "axpy",  T,  [S,D,C,Z], ["n"], [], ["x"], ["y"], ["alpha"], "", "Vector-times-constant plus vector"),
-  Routine(True,  True,  "1", "dot",   T,  [S,D],     ["n"], [], ["x","y"], ["dot"], [], "n", "Dot product of two vectors"),
-  Routine(True,  True,  "1", "dotu",  T,  [C,Z],     ["n"], [], ["x","y"], ["dot"], [], "n", "Dot product of two complex vectors"),
-  Routine(True,  True,  "1", "dotc",  T,  [C,Z],     ["n"], [], ["x","y"], ["dot"], [], "n", "Dot product of two complex vectors, one conjugated"),
-  Routine(True,  True,  "1", "nrm2",  T, [S,D,Sc,Dz],["n"], [], ["x"], ["nrm2"], [], "2*n", "Euclidian norm of a vector"),
-  Routine(True,  True,  "1", "asum",  T, [S,D,Sc,Dz],["n"], [], ["x"], ["asum"], [], "n", "Absolute sum of values in a vector"),
-  Routine(True,  False, "1", "sum",   T, [S,D,Sc,Dz],["n"], [], ["x"], ["sum"], [], "n", "Sum of values in a vector (non-BLAS function)"),
-  Routine(True,  True,  "1", "amax",  T, [iS,iD,iC,iZ],["n"], [], ["x"], ["imax"], [], "2*n", "Index of absolute maximum value in a vector"),
-  Routine(True,  False, "1", "max",   T, [iS,iD,iC,iZ],["n"], [], ["x"], ["imax"], [], "2*n", "Index of maximum value in a vector (non-BLAS function)"),
-  Routine(True,  False, "1", "min",   T, [iS,iD,iC,iZ],["n"], [], ["x"], ["imin"], [], "2*n", "Index of minimum value in a vector (non-BLAS function)"),
+  Routine(False, True,  "1", "rotg",  T,  [S,D],     [], [], [], ["sa","sb","sc","ss"], [], "", "Generate givens plane rotation", "", []),
+  Routine(False, True,  "1", "rotmg", T,  [S,D],     [], [], ["sy1"], ["sd1","sd2","sx1","sparam"], [], "", "Generate modified givens plane rotation", "", []),
+  Routine(False, True,  "1", "rot",   T,  [S,D],     ["n"], [], [], ["x","y"], ["cos","sin"], "", "Apply givens plane rotation", "", []),
+  Routine(False, True,  "1", "rotm",  T,  [S,D],     ["n"], [], [], ["x","y","sparam"], [], "", "Apply modified givens plane rotation", "", []),
+  Routine(True,  True,  "1", "swap",  T,  [S,D,C,Z], ["n"], [], [], ["x","y"], [], "", "Swap two vectors", "Interchanges the contents of vectors x and y.", []),
+  Routine(True,  True,  "1", "scal",  T,  [S,D,C,Z], ["n"], [], [], ["x"], ["alpha"], "", "Vector scaling", "Multiplies all elements of vector x by a scalar constant alpha.", []),
+  Routine(True,  True,  "1", "copy",  T,  [S,D,C,Z], ["n"], [], ["x"], ["y"], [], "", "Vector copy", "Copies the contents of vector x into vector y.", []),
+  Routine(True,  True,  "1", "axpy",  T,  [S,D,C,Z], ["n"], [], ["x"], ["y"], ["alpha"], "", "Vector-times-constant plus vector", "Performs the operation y = alpha * x + y, in which x and y are vectors and alpha is a scalar constant.", []),
+  Routine(True,  True,  "1", "dot",   T,  [S,D],     ["n"], [], ["x","y"], ["dot"], [], "n", "Dot product of two vectors", "Multiplies the vectors x and y element-wise and accumulates the results. The sum is stored in the dot buffer.", []),
+  Routine(True,  True,  "1", "dotu",  T,  [C,Z],     ["n"], [], ["x","y"], ["dot"], [], "n", "Dot product of two complex vectors", "See the regular xDOT routine.", []),
+  Routine(True,  True,  "1", "dotc",  T,  [C,Z],     ["n"], [], ["x","y"], ["dot"], [], "n", "Dot product of two complex vectors, one conjugated", "See the regular xDOT routine.", []),
+  Routine(True,  True,  "1", "nrm2",  T, [S,D,Sc,Dz],["n"], [], ["x"], ["nrm2"], [], "2*n", "Euclidian norm of a vector", "Accumulates the square of each element in the x vector and takes the square root. The resulting L2 norm is stored in the nrm2 buffer.", []),
+  Routine(True,  True,  "1", "asum",  T, [S,D,Sc,Dz],["n"], [], ["x"], ["asum"], [], "n", "Absolute sum of values in a vector", "Accumulates the absolute value of each element in the x vector. The results are stored in the asum buffer.", []),
+  Routine(True,  False, "1", "sum",   T, [S,D,Sc,Dz],["n"], [], ["x"], ["sum"], [], "n", "Sum of values in a vector (non-BLAS function)", "Accumulates the values of each element in the x vector. The results are stored in the sum buffer. This routine is the non-absolute version of the xASUM BLAS routine.", []),
+  Routine(True,  True,  "1", "amax",  T, [iS,iD,iC,iZ],["n"], [], ["x"], ["imax"], [], "2*n", "Index of absolute maximum value in a vector", "Finds the index of the maximum of the absolute values in the x vector. The resulting integer index is stored in the imax buffer.", []),
+  Routine(True,  False, "1", "max",   T, [iS,iD,iC,iZ],["n"], [], ["x"], ["imax"], [], "2*n", "Index of maximum value in a vector (non-BLAS function)", "Finds the index of the maximum of the values in the x vector. The resulting integer index is stored in the imax buffer. This routine is the non-absolute version of the IxAMAX BLAS routine.", []),
+  Routine(True,  False, "1", "min",   T, [iS,iD,iC,iZ],["n"], [], ["x"], ["imin"], [], "2*n", "Index of minimum value in a vector (non-BLAS function)", "Finds the index of the minimum of the values in the x vector. The resulting integer index is stored in the imin buffer. This routine is the non-absolute minimum version of the IxAMAX BLAS routine.", []),
 ],
 [ # Level 2: matrix-vector
-  Routine(True,  True,  "2a", "gemv",  T,  [S,D,C,Z], ["m","n"], ["layout","a_transpose"], ["a","x"], ["y"], ["alpha","beta"], "", "General matrix-vector multiplication"),
-  Routine(True,  True,  "2a", "gbmv",  T,  [S,D,C,Z], ["m","n","kl","ku"], ["layout","a_transpose"], ["a","x"], ["y"], ["alpha","beta"], "", "General banded matrix-vector multiplication"),
-  Routine(True,  True,  "2a", "hemv",  T,  [C,Z],     ["n"], ["layout","triangle"], ["a","x"], ["y"], ["alpha","beta"], "", "Hermitian matrix-vector multiplication"),
-  Routine(True,  True,  "2a", "hbmv",  T,  [C,Z],     ["n","k"], ["layout","triangle"], ["a","x"], ["y"], ["alpha","beta"], "", "Hermitian banded matrix-vector multiplication"),
-  Routine(True,  True,  "2a", "hpmv",  T,  [C,Z],     ["n"], ["layout","triangle"], ["ap","x"], ["y"], ["alpha","beta"], "", "Hermitian packed matrix-vector multiplication"),
-  Routine(True,  True,  "2a", "symv",  T,  [S,D],     ["n"], ["layout","triangle"], ["a","x"], ["y"], ["alpha","beta"], "", "Symmetric matrix-vector multiplication"),
-  Routine(True,  True,  "2a", "sbmv",  T,  [S,D],     ["n","k"], ["layout","triangle"], ["a","x"], ["y"], ["alpha","beta"], "", "Symmetric banded matrix-vector multiplication"),
-  Routine(True,  True,  "2a", "spmv",  T,  [S,D],     ["n"], ["layout","triangle"], ["ap","x"], ["y"], ["alpha","beta"], "", "Symmetric packed matrix-vector multiplication"),
-  Routine(True,  True,  "2a", "trmv",  T,  [S,D,C,Z], ["n"], ["layout","triangle","a_transpose","diagonal"], ["a"], ["x"], [], "n", "Triangular matrix-vector multiplication"),
-  Routine(True,  True,  "2a", "tbmv",  T,  [S,D,C,Z], ["n","k"], ["layout","triangle","a_transpose","diagonal"], ["a"], ["x"], [], "n", "Triangular banded matrix-vector multiplication"),
-  Routine(True,  True,  "2a", "tpmv",  T,  [S,D,C,Z], ["n"], ["layout","triangle","a_transpose","diagonal"], ["ap"], ["x"], [], "n", "Triangular packed matrix-vector multiplication"),
-  Routine(False, True,  "2a", "trsv",  T,  [S,D,C,Z], ["n"], ["layout","triangle","a_transpose","diagonal"], ["a"], ["x"], [], "", "Solves a triangular system of equations"),
-  Routine(False, True,  "2a", "tbsv",  T,  [S,D,C,Z], ["n","k"], ["layout","triangle","a_transpose","diagonal"], ["a"], ["x"], [], "", "Solves a banded triangular system of equations"),
-  Routine(False, True,  "2a", "tpsv",  T,  [S,D,C,Z], ["n"], ["layout","triangle","a_transpose","diagonal"], ["ap"], ["x"], [], "", "Solves a packed triangular system of equations"),
+  Routine(True,  True,  "2a", "gemv",  T,  [S,D,C,Z], ["m","n"], ["layout","a_transpose"], ["a","x"], ["y"], ["alpha","beta"], "", "General matrix-vector multiplication", "Performs the operation y = alpha * A * x + beta * y, in which x is an input vector, y is an input and output vector, A is an input matrix, and alpha and beta are scalars. The matrix A can optionally be transposed before performing the operation.", []),
+  Routine(True,  True,  "2a", "gbmv",  T,  [S,D,C,Z], ["m","n","kl","ku"], ["layout","a_transpose"], ["a","x"], ["y"], ["alpha","beta"], "", "General banded matrix-vector multiplication", "Same operation as xGEMV, but matrix A is banded instead.", []),
+  Routine(True,  True,  "2a", "hemv",  T,  [C,Z],     ["n"], ["layout","triangle"], ["a","x"], ["y"], ["alpha","beta"], "", "Hermitian matrix-vector multiplication", "Same operation as xGEMV, but matrix A is an Hermitian matrix instead.", []),
+  Routine(True,  True,  "2a", "hbmv",  T,  [C,Z],     ["n","k"], ["layout","triangle"], ["a","x"], ["y"], ["alpha","beta"], "", "Hermitian banded matrix-vector multiplication", "Same operation as xGEMV, but matrix A is an Hermitian banded matrix instead.", []),
+  Routine(True,  True,  "2a", "hpmv",  T,  [C,Z],     ["n"], ["layout","triangle"], ["ap","x"], ["y"], ["alpha","beta"], "", "Hermitian packed matrix-vector multiplication", "Same operation as xGEMV, but matrix A is an Hermitian packed matrix instead and represented as AP.", []),
+  Routine(True,  True,  "2a", "symv",  T,  [S,D],     ["n"], ["layout","triangle"], ["a","x"], ["y"], ["alpha","beta"], "", "Symmetric matrix-vector multiplication", "Same operation as xGEMV, but matrix A is symmetric instead.", []),
+  Routine(True,  True,  "2a", "sbmv",  T,  [S,D],     ["n","k"], ["layout","triangle"], ["a","x"], ["y"], ["alpha","beta"], "", "Symmetric banded matrix-vector multiplication", "Same operation as xGEMV, but matrix A is symmetric and banded instead.", []),
+  Routine(True,  True,  "2a", "spmv",  T,  [S,D],     ["n"], ["layout","triangle"], ["ap","x"], ["y"], ["alpha","beta"], "", "Symmetric packed matrix-vector multiplication", "Same operation as xGEMV, but matrix A is a symmetric packed matrix instead and represented as AP.", []),
+  Routine(True,  True,  "2a", "trmv",  T,  [S,D,C,Z], ["n"], ["layout","triangle","a_transpose","diagonal"], ["a"], ["x"], [], "n", "Triangular matrix-vector multiplication", "Same operation as xGEMV, but matrix A is triangular instead.", []),
+  Routine(True,  True,  "2a", "tbmv",  T,  [S,D,C,Z], ["n","k"], ["layout","triangle","a_transpose","diagonal"], ["a"], ["x"], [], "n", "Triangular banded matrix-vector multiplication", "Same operation as xGEMV, but matrix A is triangular and banded instead.", []),
+  Routine(True,  True,  "2a", "tpmv",  T,  [S,D,C,Z], ["n"], ["layout","triangle","a_transpose","diagonal"], ["ap"], ["x"], [], "n", "Triangular packed matrix-vector multiplication", "Same operation as xGEMV, but matrix A is a triangular packed matrix instead and repreented as AP.", []),
+  Routine(False, True,  "2a", "trsv",  T,  [S,D,C,Z], ["n"], ["layout","triangle","a_transpose","diagonal"], ["a"], ["x"], [], "", "Solves a triangular system of equations", "", []),
+  Routine(False, True,  "2a", "tbsv",  T,  [S,D,C,Z], ["n","k"], ["layout","triangle","a_transpose","diagonal"], ["a"], ["x"], [], "", "Solves a banded triangular system of equations", "", []),
+  Routine(False, True,  "2a", "tpsv",  T,  [S,D,C,Z], ["n"], ["layout","triangle","a_transpose","diagonal"], ["ap"], ["x"], [], "", "Solves a packed triangular system of equations", "", []),
   # Level 2: matrix update
-  Routine(True,  True,  "2b", "ger",   T,  [S,D],     ["m","n"], ["layout"], ["x","y"], ["a"], ["alpha"], "", "General rank-1 matrix update"),
-  Routine(True,  True,  "2b", "geru",  T,  [C,Z],     ["m","n"], ["layout"], ["x","y"], ["a"], ["alpha"], "", "General rank-1 complex matrix update"),
-  Routine(True,  True,  "2b", "gerc",  T,  [C,Z],     ["m","n"], ["layout"], ["x","y"], ["a"], ["alpha"], "", "General rank-1 complex conjugated matrix update"),
-  Routine(True,  True,  "2b", "her",   Tc, [Css,Zdd], ["n"], ["layout","triangle"], ["x"], ["a"], ["alpha"], "", "Hermitian rank-1 matrix update"),
-  Routine(True,  True,  "2b", "hpr",   Tc, [Css,Zdd], ["n"], ["layout","triangle"], ["x"], ["ap"], ["alpha"], "", "Hermitian packed rank-1 matrix update"),
-  Routine(True,  True,  "2b", "her2",  T,  [C,Z],     ["n"], ["layout","triangle"], ["x","y"], ["a"], ["alpha"], "", "Hermitian rank-2 matrix update"),
-  Routine(True,  True,  "2b", "hpr2",  T,  [C,Z],     ["n"], ["layout","triangle"], ["x","y"], ["ap"], ["alpha"], "", "Hermitian packed rank-2 matrix update"),
-  Routine(True,  True,  "2b", "syr",   T,  [S,D],     ["n"], ["layout","triangle"], ["x"], ["a"], ["alpha"], "", "Symmetric rank-1 matrix update"),
-  Routine(True,  True,  "2b", "spr",   T,  [S,D],     ["n"], ["layout","triangle"], ["x"], ["ap"], ["alpha"], "", "Symmetric packed rank-1 matrix update"),
-  Routine(True,  True,  "2b", "syr2",  T,  [S,D],     ["n"], ["layout","triangle"], ["x","y"], ["a"], ["alpha"], "", "Symmetric rank-2 matrix update"),
-  Routine(True,  True,  "2b", "spr2",  T,  [S,D],     ["n"], ["layout","triangle"], ["x","y"], ["ap"], ["alpha"], "", "Symmetric packed rank-2 matrix update"),
+  Routine(True,  True,  "2b", "ger",   T,  [S,D],     ["m","n"], ["layout"], ["x","y"], ["a"], ["alpha"], "", "General rank-1 matrix update", "", []),
+  Routine(True,  True,  "2b", "geru",  T,  [C,Z],     ["m","n"], ["layout"], ["x","y"], ["a"], ["alpha"], "", "General rank-1 complex matrix update", "", []),
+  Routine(True,  True,  "2b", "gerc",  T,  [C,Z],     ["m","n"], ["layout"], ["x","y"], ["a"], ["alpha"], "", "General rank-1 complex conjugated matrix update", "", []),
+  Routine(True,  True,  "2b", "her",   Tc, [Css,Zdd], ["n"], ["layout","triangle"], ["x"], ["a"], ["alpha"], "", "Hermitian rank-1 matrix update", "", []),
+  Routine(True,  True,  "2b", "hpr",   Tc, [Css,Zdd], ["n"], ["layout","triangle"], ["x"], ["ap"], ["alpha"], "", "Hermitian packed rank-1 matrix update", "", []),
+  Routine(True,  True,  "2b", "her2",  T,  [C,Z],     ["n"], ["layout","triangle"], ["x","y"], ["a"], ["alpha"], "", "Hermitian rank-2 matrix update", "", []),
+  Routine(True,  True,  "2b", "hpr2",  T,  [C,Z],     ["n"], ["layout","triangle"], ["x","y"], ["ap"], ["alpha"], "", "Hermitian packed rank-2 matrix update", "", []),
+  Routine(True,  True,  "2b", "syr",   T,  [S,D],     ["n"], ["layout","triangle"], ["x"], ["a"], ["alpha"], "", "Symmetric rank-1 matrix update", "", []),
+  Routine(True,  True,  "2b", "spr",   T,  [S,D],     ["n"], ["layout","triangle"], ["x"], ["ap"], ["alpha"], "", "Symmetric packed rank-1 matrix update", "", []),
+  Routine(True,  True,  "2b", "syr2",  T,  [S,D],     ["n"], ["layout","triangle"], ["x","y"], ["a"], ["alpha"], "", "Symmetric rank-2 matrix update", "", []),
+  Routine(True,  True,  "2b", "spr2",  T,  [S,D],     ["n"], ["layout","triangle"], ["x","y"], ["ap"], ["alpha"], "", "Symmetric packed rank-2 matrix update", "", []),
 ],
 [ # Level 3: matrix-matrix
-  Routine(True,  True,  "3", "gemm",  T,  [S,D,C,Z], ["m","n","k"], ["layout","a_transpose","b_transpose"], ["a","b"], ["c"], ["alpha","beta"], "", "General matrix-matrix multiplication"),
-  Routine(True,  True,  "3", "symm",  T,  [S,D,C,Z], ["m","n"], ["layout","side","triangle"], ["a","b"], ["c"], ["alpha","beta"], "", "Symmetric matrix-matrix multiplication"),
-  Routine(True,  True,  "3", "hemm",  T,  [C,Z],     ["m","n"], ["layout","side","triangle"], ["a","b"], ["c"], ["alpha","beta"], "", "Hermitian matrix-matrix multiplication"),
-  Routine(True,  True,  "3", "syrk",  T,  [S,D,C,Z], ["n","k"], ["layout","triangle","a_transpose"], ["a"], ["c"], ["alpha","beta"], "", "Rank-K update of a symmetric matrix"),
-  Routine(True,  True,  "3", "herk",  Tc, [Css,Zdd], ["n","k"], ["layout","triangle","a_transpose"], ["a"], ["c"], ["alpha","beta"], "", "Rank-K update of a hermitian matrix"),
-  Routine(True,  True,  "3", "syr2k", T,  [S,D,C,Z], ["n","k"], ["layout","triangle","ab_transpose"], ["a","b"], ["c"], ["alpha","beta"], "", "Rank-2K update of a symmetric matrix"),
-  Routine(True,  True,  "3", "her2k", TU, [Ccs,Zzd], ["n","k"], ["layout","triangle","ab_transpose"], ["a","b"], ["c"], ["alpha","beta"], "", "Rank-2K update of a hermitian matrix"),
-  Routine(True,  True,  "3", "trmm",  T,  [S,D,C,Z], ["m","n"], ["layout","side","triangle","a_transpose","diagonal"], ["a"], ["b"], ["alpha"], "", "Triangular matrix-matrix multiplication"),
-  Routine(False, True,  "3", "trsm",  T,  [S,D,C,Z], ["m","n"], ["layout","side","triangle","a_transpose","diagonal"], ["a"], ["b"], ["alpha"], "", "Solves a triangular system of equations"),
+  Routine(True,  True,  "3", "gemm",  T,  [S,D,C,Z], ["m","n","k"], ["layout","a_transpose","b_transpose"], ["a","b"], ["c"], ["alpha","beta"], "", "General matrix-matrix multiplication", "", []),
+  Routine(True,  True,  "3", "symm",  T,  [S,D,C,Z], ["m","n"], ["layout","side","triangle"], ["a","b"], ["c"], ["alpha","beta"], "", "Symmetric matrix-matrix multiplication", "", []),
+  Routine(True,  True,  "3", "hemm",  T,  [C,Z],     ["m","n"], ["layout","side","triangle"], ["a","b"], ["c"], ["alpha","beta"], "", "Hermitian matrix-matrix multiplication", "", []),
+  Routine(True,  True,  "3", "syrk",  T,  [S,D,C,Z], ["n","k"], ["layout","triangle","a_transpose"], ["a"], ["c"], ["alpha","beta"], "", "Rank-K update of a symmetric matrix", "", []),
+  Routine(True,  True,  "3", "herk",  Tc, [Css,Zdd], ["n","k"], ["layout","triangle","a_transpose"], ["a"], ["c"], ["alpha","beta"], "", "Rank-K update of a hermitian matrix", "", []),
+  Routine(True,  True,  "3", "syr2k", T,  [S,D,C,Z], ["n","k"], ["layout","triangle","ab_transpose"], ["a","b"], ["c"], ["alpha","beta"], "", "Rank-2K update of a symmetric matrix", "", []),
+  Routine(True,  True,  "3", "her2k", TU, [Ccs,Zzd], ["n","k"], ["layout","triangle","ab_transpose"], ["a","b"], ["c"], ["alpha","beta"], "", "Rank-2K update of a hermitian matrix", "", []),
+  Routine(True,  True,  "3", "trmm",  T,  [S,D,C,Z], ["m","n"], ["layout","side","triangle","a_transpose","diagonal"], ["a"], ["b"], ["alpha"], "", "Triangular matrix-matrix multiplication", "", []),
+  Routine(False, True,  "3", "trsm",  T,  [S,D,C,Z], ["m","n"], ["layout","side","triangle","a_transpose","diagonal"], ["a"], ["b"], ["alpha"], "", "Solves a triangular system of equations", "", []),
 ]]
 
 # ==================================================================================================
@@ -401,3 +402,61 @@ for level in [1,2,3]:
 				f.write(footer)
 
 # ==================================================================================================
+
+# Outputs the API documentation
+filename = path_clblast+"/doc/clblast.md"
+with open(filename, "w") as f:
+
+	# Outputs the header
+	f.write("CLBlast: API reference\n")
+	f.write("================\n")
+	f.write("\n\n")
+
+	# Loops over the routines
+	for level in [1,2,3]:
+		for routine in routines[level-1]:
+			if routine.implemented:
+
+				# Routine header
+				f.write("x"+routine.name.upper()+": "+routine.description+"\n")
+				f.write("-------------\n")
+				f.write("\n")
+				f.write(routine.details+"\n")
+				f.write("\n")
+
+				# Routine API
+				f.write("C++ API:\n")
+				f.write("```\n")
+				f.write(routine.RoutineHeaderCPP(12, "")+"\n")
+				f.write("```\n")
+				f.write("\n")
+				f.write("C API:\n")
+				f.write("```\n")
+				for flavour in routine.flavours:
+					f.write(routine.RoutineHeaderC(flavour, 20, "")+"\n")
+				f.write("```\n")
+				f.write("\n")
+
+				# Routine arguments
+				f.write("Arguments to "+routine.name.upper()+":\n")
+				f.write("\n")
+				for argument in routine.ArgumentsDoc():
+					f.write("* "+argument+"\n")
+				f.write("* `cl_command_queue* queue`: Pointer to an OpenCL command queue associated with a context and device to execute the routine on.\n")
+				f.write("* `cl_event* event`: Pointer to an OpenCL event to be able to wait for completion of the routine's OpenCL kernel(s). This is an optional argument.\n")
+				f.write("\n")
+
+				# Routine requirements
+				if len(routine.RequirementsDoc()) > 0:
+					f.write("Requirements for "+routine.name.upper()+":\n")
+					f.write("\n")
+					for requirement in routine.RequirementsDoc():
+						f.write("* "+requirement+"\n")
+					f.write("\n")
+
+
+				# Routine footer
+				f.write("\n\n")
+
+
+# ==================================================================================================
diff --git a/scripts/generator/routine.py b/scripts/generator/routine.py
index 95681da6..e5059c61 100644
--- a/scripts/generator/routine.py
+++ b/scripts/generator/routine.py
@@ -51,12 +51,24 @@ def OptionToWrapperC(x):
 	    'diagonal': "CBLAS_DIAG",
 	}[x]
 
+# Translates an option name to a documentation string
+def OptionToDoc(x):
+	return {
+	    'layout': "Data-layout of the matrices, either `Layout::kRowMajor` (101) for row-major layout or `Layout::kColMajor` (102) for column-major data-layout.",
+	    'a_transpose': "Transposing the input matrix A, either `Transpose::kNo` (111), `Transpose::kYes` (112), or `Transpose::kConjugate` (113) for a complex-conjugate transpose.",
+	    'b_transpose': "Transposing the input matrix B, either `Transpose::kNo` (111), `Transpose::kYes` (112), or `Transpose::kConjugate` (113) for a complex-conjugate transpose.",
+	    'ab_transpose': "Transposing the packed input matrix AP, either `Transpose::kNo` (111), `Transpose::kYes` (112), or `Transpose::kConjugate` (113) for a complex-conjugate transpose.",
+	    'side': "The horizontal position of the triangular matrix, either `Side::kLeft` (141) or `Side::kRight` (142).",
+	    'triangle': "The vertical position of the triangular matrix, either `Triangle::kUpper` (121) or `Triangle::kLower` (122).",
+	    'diagonal': "The property of the diagonal matrix, either `Diagonal::kNonUnit` (131) for a non-unit values on the diagonal or `Diagonal::kUnit` (132) for a unit values on the diagonal.",
+	}[x]
+
 # ==================================================================================================
 
 # Class holding routine-specific information (e.g. name, which arguments, which precisions)
 class Routine():
 	def __init__(self, implemented, has_tests, level, name, template, flavours, sizes, options,
-	             inputs, outputs, scalars, scratch, description):
+	             inputs, outputs, scalars, scratch, description, details, requirements):
 		self.implemented = implemented
 		self.has_tests = has_tests
 		self.level = level
@@ -70,6 +82,8 @@ class Routine():
 		self.scalars = scalars
 		self.scratch = scratch # Scratch buffer (e.g. for xDOT)
 		self.description = description
+		self.details = details
+		self.requirements = requirements
 
 	# List of scalar buffers
 	def ScalarBuffersFirst(self):
@@ -115,6 +129,12 @@ class Routine():
 			return ["ap","a","b","c"]
 		return ["y","c"]
 
+	# Distinguish between vectors and matrices
+	def BuffersVector(self):
+		return ["x","y"]
+	def BuffersMatrix(self):
+		return ["a","b","c","ap"]
+
 	# ==============================================================================================
 
 	# Retrieves a variable name for a specific input/output vector/matrix (e.g. 'x')
@@ -197,6 +217,19 @@ class Routine():
 			return [", ".join(a+b+c)]
 		return []
 
+	# Retrieves the documentation of the buffers
+	def BufferDoc(self, name):
+		prefix = "const " if (name in self.inputs) else ""
+		inout = "input" if (name in self.inputs) else "output"
+		if (name in self.inputs) or (name in self.outputs):
+			math_name = name.upper()+" matrix" if (name in self.BuffersMatrix()) else name+" vector"
+			incld_description = "Leading dimension " if (name in self.BuffersMatrix()) else "Stride/increment "
+			a = ["`"+prefix+"cl_mem "+name+"_buffer`: OpenCL buffer to store the "+inout+" "+math_name+"."]
+			b = ["`const size_t "+name+"_offset`: The offset in elements from the start of the "+inout+" "+math_name+"."]
+			c = ["`const size_t "+name+"_"+self.Postfix(name)+"`: "+incld_description+"of the "+inout+" "+math_name+"."] if (name not in self.BuffersWithoutLdInc()) else []
+			return a+b+c
+		return []
+
 	# ==============================================================================================
 
 	# Retrieves the name of a scalar (alpha/beta)
@@ -257,6 +290,14 @@ class Routine():
 			return ["const "+flavour.beta_cpp]
 		return []
 
+	# Retrieves the documentation of a scalar
+	def ScalarDoc(self, name):
+		if name in self.scalars:
+			if name == "alpha":
+				return ["`const "+self.template.alpha_cpp+" "+name+"`: Input scalar constant."]
+			return ["`const "+self.template.beta_cpp+" "+name+"`: Input scalar constant."]
+		return []
+
 	# ==============================================================================================
 
 	# Retrieves a list of comma-separated sizes (m, n, k)
@@ -277,6 +318,13 @@ class Routine():
 			return [", ".join(["const size_t" for s in self.sizes])]
 		return []
 
+	# Retrieves the documentation of the sizes
+	def SizesDoc(self):
+		if self.sizes:
+			definitions = ["`const size_t "+s+"`: Integer size argument." for s in self.sizes]
+			return definitions
+		return []
+
 	# ==============================================================================================
 
 	# Retrieves a list of options
@@ -320,6 +368,13 @@ class Routine():
 			return [", ".join(definitions)]
 		return []
 
+	# Retrieves the documentation of the options
+	def OptionsDoc(self):
+		if self.options:
+			definitions = ["`const "+OptionToCLBlast(o)+"`: "+OptionToDoc(o) for o in self.options]
+			return definitions
+		return []
+
 	# ==============================================================================================
 
 	# Retrieves a combination of all the argument names, with Claduc casts
@@ -408,6 +463,24 @@ class Routine():
 		        list(chain(*[self.BufferType(b) for b in self.BuffersSecond()])) +
 		        list(chain(*[self.BufferType(b) for b in self.ScalarBuffersSecond()])) +
 		        list(chain(*[self.ScalarType(s, flavour) for s in self.OtherScalars()])))
+	
+	# Retrieves a combination of all the argument types
+	def ArgumentsDoc(self):
+		return (self.OptionsDoc() + self.SizesDoc() +
+		        list(chain(*[self.BufferDoc(b) for b in self.ScalarBuffersFirst()])) +
+		        list(chain(*[self.BufferDoc(b) for b in self.ScalarBuffersFirst()])) +
+		        self.ScalarDoc("alpha") +
+		        list(chain(*[self.BufferDoc(b) for b in self.BuffersFirst()])) +
+		        self.ScalarDoc("beta") +
+		        list(chain(*[self.BufferDoc(b) for b in self.BuffersSecond()])) +
+		        list(chain(*[self.BufferDoc(b) for b in self.ScalarBuffersSecond()])) +
+		        list(chain(*[self.ScalarDoc(s) for s in self.OtherScalars()])))
+
+	# ==============================================================================================
+
+	# Retrieves a list of routine requirements for documentation
+	def RequirementsDoc(self):
+		return []
 
 	# ==============================================================================================